From b058aae1b690ad2a1a8dddc9b9421b51266c7859 Mon Sep 17 00:00:00 2001 From: ojwb Date: Fri, 29 Sep 2023 05:04:13 +0000 Subject: [PATCH] =?UTF-8?q?Deploying=20to=20gh-pages=20from=20@=20snowball?= =?UTF-8?q?stem/snowball-website@49453106689db279f61acb80f61da99deb9cdc27?= =?UTF-8?q?=20=F0=9F=9A=80?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- algorithms/armenian/stemmer.tt | 54 - algorithms/basque/stemmer.tt | 24 - algorithms/catalan/stemmer.tt | 33 - algorithms/czech/stemmer.tt | 16 - algorithms/danish/stemmer.tt | 132 - algorithms/dutch/stemmer.tt | 103 - algorithms/english/stemmer.tt | 583 ---- algorithms/estonian/stemmer.tt | 485 --- algorithms/finnish/stemmer.tt | 212 -- algorithms/french/stemmer.tt | 301 -- algorithms/german/stemmer.tt | 146 - algorithms/german2/stemmer.tt | 22 - algorithms/germanic.tt | 113 - algorithms/greek/stemmer.tt | 27 - algorithms/hindi/stemmer.tt | 83 - algorithms/hungarian/stemmer.tt | 243 -- algorithms/index.tt | 92 - algorithms/indonesian/stemmer.tt | 124 - algorithms/irish/stemmer.tt | 52 - algorithms/italian/stemmer.tt | 185 - algorithms/kraaij_pohlmann/stemmer.tt | 69 - algorithms/lithuanian/stemmer.tt | 22 - algorithms/lovins/festschrift.tt | 1740 ---------- algorithms/lovins/stemmer.tt | 332 -- algorithms/norwegian/stemmer.tt | 109 - algorithms/porter/stemmer.tt | 656 ---- algorithms/portuguese/stemmer.tt | 175 - algorithms/romance.tt | 106 - algorithms/romanian/stemmer.tt | 224 -- algorithms/russian/stemmer.tt | 327 -- algorithms/scandinavian.tt | 34 - algorithms/serbian/stemmer.tt | 273 -- algorithms/spanish/stemmer.tt | 205 -- algorithms/swedish/stemmer.tt | 107 - algorithms/turkish/stemmer.tt | 47 - algorithms/yiddish/stemmer.tt | 202 -- codesets/guide.tt | 93 - compiler/snowman.tt | 1558 --------- js/arabic-stemmer.js | 1613 --------- js/armenian-stemmer.js | 391 --- js/base-stemmer.js | 296 -- js/basque-stemmer.js | 849 ----- js/catalan-stemmer.js | 927 ----- js/danish-stemmer.js | 312 -- js/dutch-stemmer.js | 671 ---- js/english-stemmer.js | 1086 ------ js/estonian-stemmer.js | 1112 ------ js/finnish-stemmer.js | 788 ----- js/french-stemmer.js | 1311 ------- js/german-stemmer.js | 591 ---- js/greek-stemmer.js | 2870 ---------------- js/hindi-stemmer.js | 183 - js/hungarian-stemmer.js | 709 ---- js/indonesian-stemmer.js | 422 --- js/irish-stemmer.js | 419 --- js/italian-stemmer.js | 1008 ------ js/lithuanian-stemmer.js | 558 --- js/nepali-stemmer.js | 319 -- js/norwegian-stemmer.js | 263 -- js/porter-stemmer.js | 739 ---- js/portuguese-stemmer.js | 896 ----- js/romanian-stemmer.js | 918 ----- js/russian-stemmer.js | 622 ---- js/serbian-stemmer.js | 4557 ------------------------- js/spanish-stemmer.js | 976 ------ js/swedish-stemmer.js | 267 -- js/tamil-stemmer.js | 1190 ------- js/turkish-stemmer.js | 2361 ------------- js/yiddish-stemmer.js | 1173 ------- otherapps/romanian/index.tt | 180 - otherapps/schinke/index.tt | 168 - runtime/use.tt | 381 --- texts/apostrophe.tt | 75 - texts/earlyenglish.tt | 135 - texts/glossary.tt | 106 - texts/howtohelp.tt | 65 - texts/introduction.tt | 923 ----- texts/r1r2.tt | 78 - texts/vowelmarking.tt | 74 - 79 files changed, 41891 deletions(-) delete mode 100644 algorithms/armenian/stemmer.tt delete mode 100644 algorithms/basque/stemmer.tt delete mode 100644 algorithms/catalan/stemmer.tt delete mode 100644 algorithms/czech/stemmer.tt delete mode 100644 algorithms/danish/stemmer.tt delete mode 100644 algorithms/dutch/stemmer.tt delete mode 100644 algorithms/english/stemmer.tt delete mode 100644 algorithms/estonian/stemmer.tt delete mode 100644 algorithms/finnish/stemmer.tt delete mode 100644 algorithms/french/stemmer.tt delete mode 100644 algorithms/german/stemmer.tt delete mode 100644 algorithms/german2/stemmer.tt delete mode 100644 algorithms/germanic.tt delete mode 100644 algorithms/greek/stemmer.tt delete mode 100644 algorithms/hindi/stemmer.tt delete mode 100644 algorithms/hungarian/stemmer.tt delete mode 100644 algorithms/index.tt delete mode 100644 algorithms/indonesian/stemmer.tt delete mode 100644 algorithms/irish/stemmer.tt delete mode 100644 algorithms/italian/stemmer.tt delete mode 100644 algorithms/kraaij_pohlmann/stemmer.tt delete mode 100644 algorithms/lithuanian/stemmer.tt delete mode 100644 algorithms/lovins/festschrift.tt delete mode 100644 algorithms/lovins/stemmer.tt delete mode 100644 algorithms/norwegian/stemmer.tt delete mode 100644 algorithms/porter/stemmer.tt delete mode 100644 algorithms/portuguese/stemmer.tt delete mode 100644 algorithms/romance.tt delete mode 100644 algorithms/romanian/stemmer.tt delete mode 100644 algorithms/russian/stemmer.tt delete mode 100644 algorithms/scandinavian.tt delete mode 100644 algorithms/serbian/stemmer.tt delete mode 100644 algorithms/spanish/stemmer.tt delete mode 100644 algorithms/swedish/stemmer.tt delete mode 100644 algorithms/turkish/stemmer.tt delete mode 100644 algorithms/yiddish/stemmer.tt delete mode 100644 codesets/guide.tt delete mode 100644 compiler/snowman.tt delete mode 100644 js/arabic-stemmer.js delete mode 100644 js/armenian-stemmer.js delete mode 100644 js/base-stemmer.js delete mode 100644 js/basque-stemmer.js delete mode 100644 js/catalan-stemmer.js delete mode 100644 js/danish-stemmer.js delete mode 100644 js/dutch-stemmer.js delete mode 100644 js/english-stemmer.js delete mode 100644 js/estonian-stemmer.js delete mode 100644 js/finnish-stemmer.js delete mode 100644 js/french-stemmer.js delete mode 100644 js/german-stemmer.js delete mode 100644 js/greek-stemmer.js delete mode 100644 js/hindi-stemmer.js delete mode 100644 js/hungarian-stemmer.js delete mode 100644 js/indonesian-stemmer.js delete mode 100644 js/irish-stemmer.js delete mode 100644 js/italian-stemmer.js delete mode 100644 js/lithuanian-stemmer.js delete mode 100644 js/nepali-stemmer.js delete mode 100644 js/norwegian-stemmer.js delete mode 100644 js/porter-stemmer.js delete mode 100644 js/portuguese-stemmer.js delete mode 100644 js/romanian-stemmer.js delete mode 100644 js/russian-stemmer.js delete mode 100644 js/serbian-stemmer.js delete mode 100644 js/spanish-stemmer.js delete mode 100644 js/swedish-stemmer.js delete mode 100644 js/tamil-stemmer.js delete mode 100644 js/turkish-stemmer.js delete mode 100644 js/yiddish-stemmer.js delete mode 100644 otherapps/romanian/index.tt delete mode 100644 otherapps/schinke/index.tt delete mode 100644 runtime/use.tt delete mode 100644 texts/apostrophe.tt delete mode 100644 texts/earlyenglish.tt delete mode 100644 texts/glossary.tt delete mode 100644 texts/howtohelp.tt delete mode 100644 texts/introduction.tt delete mode 100644 texts/r1r2.tt delete mode 100644 texts/vowelmarking.tt diff --git a/algorithms/armenian/stemmer.tt b/algorithms/armenian/stemmer.tt deleted file mode 100644 index b57a5d2..0000000 --- a/algorithms/armenian/stemmer.tt +++ /dev/null @@ -1,54 +0,0 @@ -[% header('Armenian stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([11, 'աղոթում', 'բանաձևեր']) %] - -

-This stemmer for Armenian was developed and contributed by Astghik Mkrtchyan. -

- -

-The following characters are vowels for the purposes of this algorithm: - -

- ա է ի օ ւ ե ո ը -
- -

-R2 is the region after the first non-vowel following a vowel after the -first non-vowel following a vowel, or the end of the word if there is no such -non-vowel. -

- -

-RV has the same definition as in the - Spanish stemmer. -

- -

-The algorithm has a fairly simple structure which only removes suffixes. There -are four steps, applied in turn: -

- - - -

-See the Snowball implementation of the stemmer below for the lists of suffixes -each step checks for. -

- -

The full algorithm in Snowball

- -[% highlight_file('armenian') %] - -[% footer %] diff --git a/algorithms/basque/stemmer.tt b/algorithms/basque/stemmer.tt deleted file mode 100644 index 171932c..0000000 --- a/algorithms/basque/stemmer.tt +++ /dev/null @@ -1,24 +0,0 @@ -[% header('Basque stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([12, 'barrutiaren', 'museoak']) %] - -

-The following letters are vowels: -

- -
- a   e   i   o   u -
- - -

The stemming algorithm

- -[% highlight_file('basque') %] - -[% footer %] diff --git a/algorithms/catalan/stemmer.tt b/algorithms/catalan/stemmer.tt deleted file mode 100644 index d38f8e4..0000000 --- a/algorithms/catalan/stemmer.tt +++ /dev/null @@ -1,33 +0,0 @@ -[% header('Catalan stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([12, 'abatuda', 'gore']) %] - -

-Letters in Catalan include the following accented forms, -

- -
- á   é   í   ó   ú   à   è   ì   ò   ù   ü   ï -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u   á   é   í   ó   ú   ü   ï -
- - -

The stemming algorithm

- -[% highlight_file('catalan') %] - -[% footer %] diff --git a/algorithms/czech/stemmer.tt b/algorithms/czech/stemmer.tt deleted file mode 100644 index 92d050e..0000000 --- a/algorithms/czech/stemmer.tt +++ /dev/null @@ -1,16 +0,0 @@ -[% header('Czech stemming algorithm') %] - -

Links to resources

- - - -

-In March 2012 Jim O’Regan sent us an implementation of Ljiljana -Dolamic's Czech stemmer. -

- -[% highlight_file('czech') %] - -[% footer %] diff --git a/algorithms/danish/stemmer.tt b/algorithms/danish/stemmer.tt deleted file mode 100644 index 3491cb1..0000000 --- a/algorithms/danish/stemmer.tt +++ /dev/null @@ -1,132 +0,0 @@ -[% header('Danish stemming algorithm') %] -

Links to resources

- - - -[% algorithm_vocab([40, 'indtage', 'underste']) %] - -

The stemming algorithm

- -

-The Danish alphabet includes the following additional letters, -

- -
- æ   å   ø -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u   y   æ   å   ø -
- -

-A consonant is defined as a character from ASCII a-z which isn't a vowel -(originally this was "A consonant is defined as a non-vowel" but since -2018-11-15 we've changed this definition to avoid the stemmer altering -alphanumeric codes which end with a repeated digit). -

- -

-R2 is not used: R1 is defined in the same way as in the -German stemmer. -(See the note on R1 and R2.) -

- -

-Define a valid s-ending as one of -

- -
-a   b   c   d   f   g   h   j   k   l   m   n   o   p   r -   t   v   y   z   å -
- -

-Do each of steps 1, 2, 3 and 4. -

- -

-Step 1: -

-
-

- Search for the longest among the following suffixes in R1, and - perform the action indicated. -

-
-
(a) - hed   ethed   ered   e   erede   ende   erende   ene -   erne   ere   en   heden   eren   er   heder   erer -   heds   es   endes   erendes   enes   ernes   eres   - ens   hedens   erens   ers   ets   erets   et   eret -
delete -
(b) - s -
delete if preceded by a valid s-ending -
-

- (Of course the letter of the valid s-ending is - not necessarily in R1) -

-
- -

-Step 2: -

-
-

- Search for one of the following suffixes in R1, and if found - delete the last letter. -

-
- gd   dt   gt   kt -
- (For example, friskt → frisk) -
- -Step 3: -
-

- If the word ends igst, remove the final st. -

- -

- Search for the longest among the following suffixes in R1, and - perform the action indicated. -

-
-
(a) - ig   lig   elig   els -
delete, and then repeat step 2 -
(b) - løst -
replace with løs -
-
- -Step 4: undouble -
-

- If the word ends with double consonant in R1, remove one of the - consonants. -

- -

- (For example, bestemmelse → bestemmels (step 1) - → bestemm (step 3a) - → bestem in this step.) -

-
- -

The same algorithm in Snowball

- -[% highlight_file('danish') %] - -[% footer %] diff --git a/algorithms/dutch/stemmer.tt b/algorithms/dutch/stemmer.tt deleted file mode 100644 index 76d9f33..0000000 --- a/algorithms/dutch/stemmer.tt +++ /dev/null @@ -1,103 +0,0 @@ -[% header('Dutch stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'lichaamsziek', 'opgingen']) %] - -

The stemming algorithm

- -Dutch includes the following accented forms -
- ä   ë   ï   ö   ü   á   é   í   ó   ú   è -
-First, remove all umlaut and acute accents. A vowel is then one of, -
- a   e   i   o   u   y   è -
-Put initial y, y after a vowel, and -i between vowels into upper case. R1 and -R2 -(see the note on R1 and R2) -are then defined as in German. -

-Define a valid s-ending as a non-vowel other than j. -

-Define a valid en-ending as a non-vowel, and not gem. -

-Define undoubling the ending as removing the last letter if the word ends -kk, dd or tt. -

-Do each of steps 1, 2 3 and 4. -

-Step 1: -
- Search for the longest among the following suffixes, and perform the - action indicated -

-
-
(a) heden -
replace with heid if in R1 -

-
(b) en   ene -
delete if in R1 and preceded by a valid en-ending, and then - undouble the ending -

-
(c) s   se -
delete if in R1 and preceded by a valid s-ending -
-
-Step 2: -
- Delete suffix e if in R1 and preceded by a non-vowel, and then undouble - the ending -
-Step 3a: heid -
- delete heid if in R2 and not preceded by c, and treat a preceding - en as in step 1(b) -
-Step 3b: d-suffixes (*) -
- Search for the longest among the following suffixes, and perform the - action indicated. -

-
-
end   ing -
delete if in R2 -
if preceded by ig, delete if in R2 and not preceded by e, otherwise - undouble the ending -

-
ig -
delete if in R2 and not preceded by e -

-
lijk -
delete if in R2, and then repeat step 2 -

-
baar -
delete if in R2 -

-
bar -
delete if in R2 and if step 2 actually removed an e -
-
-Step 4: undouble vowel -
- If the words ends CVD, where C is a non-vowel, D is a non-vowel other - than I, and V is double a, e, o or u, remove one of the vowels from - V (for example, maan → man, brood → brod). -
-Finally, -
- Turn I and Y back into lower case. -
- -

The same algorithm in Snowball

- -[% highlight_file('dutch') %] - -[% footer %] diff --git a/algorithms/english/stemmer.tt b/algorithms/english/stemmer.tt deleted file mode 100644 index 8b35c7a..0000000 --- a/algorithms/english/stemmer.tt +++ /dev/null @@ -1,583 +0,0 @@ -[% header('The English (Porter2) stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'consign', 'knack']) %] - -

Developing the English stemmer

- -

-(Revised slightly, December 2001)
-(Further revised, September 2002) -

- -

-I have made more than one attempt to improve the structure of the Porter -algorithm by making it follow the pattern of ending removal of the Romance -language stemmers. It is not hard to see why one should want to do this: -step 1b of the Porter stemmer removes ed and ing, which are -i-suffixes (*) attached to verbs. If these suffixes are removed, there -should be no need to remove d-suffixes which are not verbal, although -it will try to do so. This seems to be a deficiency in the Porter stemmer, -not shared by the Romance stemmers. Again, the divisions between steps -2, 3 and 4 seem rather arbitrary, and are not found in the Romance stemmers. -

- -

-Nevertheless, these attempts at improvement have been abandoned. They seem -to lead to a more complicated algorithm with no very obvious improvements. -A reason for not taking note of the outcome of step 1b may be that -English endings do not determine word categories quite as strongly as -endings in the Romance languages. For example, condition and -position in French have to be nouns, but in English they can be verbs -as well as nouns, -

- We are all conditioned by advertising
- They are positioning themselves differently today -
-A possible reason for having separate steps 2, 3 and 4 is that -d-suffix combinations in English are quite complex, a point which has -been made -elsewhere. -

- -

-But it is hardly surprising that after twenty years of use of the Porter -stemmer, certain improvements did suggest themselves, and a new algorithm -for English is therefore offered here. (It could be called the ‘Porter2’ -stemmer to distinguish it from the Porter stemmer, from which it derives.) -The changes are not so very extensive: (1) terminating y is changed to -i rather less often, (2) suffix us does not lose its s, (3) a -few additional suffixes are included for removal, including (4) suffix -ly. In addition, a small list of exceptional forms is included. In -December 2001 there were two further adjustments: (5) Steps 5a and 5b -of the old Porter stemmer were combined into a single step. This means -that undoubling final ll is not done with removal of final e. (6) -In Step 3 ative is removed only when in region R2. -(7) -In July -2005 a small adjustment was made (including a new step 0) to handle -apostrophe. -

- -

-To begin with, here is the basic algorithm without reference to the -exceptional forms. An exact comparison with the Porter algorithm needs to -be done quite carefully if done at all. Here we indicate by * points -of departure, and by + additional features. In the sample vocabulary, -Porter and Porter2 stem slightly under 5% of words to different forms. -

- -

Definition of the English stemmer

- -

-Define a vowel as one of -

- a   e   i   o   u   y -
-Define a double as one of -
- bb   dd   ff   gg   mm   nn   pp   rr   tt -
-Define a valid li-ending as one of -
- c   d   e   g   h   k   m   n   r   t -
- -R1 is the region after the first non-vowel following a vowel, or the end of -the word if there is no such non-vowel. (This definition may be modified for certain exceptional -words — see below.) -

- -

-R2 is the region after the first non-vowel following a vowel in R1, or the -end of the word if there is no such non-vowel. -(See note on R1 and R2.) -

- -

-Define a short syllable in a word as either (a) a vowel followed by a -non-vowel other than w, x or Y and preceded by a non-vowel, or -* -(b) a vowel at the beginning of the word followed by a non-vowel. -

- -

-So rap, -trap, entrap end with a short syllable, and ow, on, at are -classed as short syllables. But uproot, bestow, disturb do not end with a -short syllable. -

- -

-A word is called short if it ends in a short syllable, and if R1 is null. -

- -

-So bed, shed and shred are short words, bead, embed, beds are -not short words. -

- -

-An apostrophe (') may be regarded as a letter. -(See note on apostrophes in English.) -

- -

-If the word has two letters or less, leave it as it is. -

- -

-Otherwise, do each of the following operations, -

- -

-Remove initial ', if present. + Then, -

- -

-Set initial y, or y after a vowel, to Y, and then establish the regions -R1 and R2. -(See note on vowel marking.) -

- -

-Step 0: + -

-

- Search for the longest among the suffixes, -

-
-
' -
's -
's' -
and remove if found. -
-
-Step 1a: -
-

- Search for the longest among the following suffixes, and perform the - action indicated. -

-
-
sses -
replace by ss -
ied+   ies* -
replace by i if preceded by more than one letter, otherwise by ie - (so ties → tie, cries → cri) -
s -
delete if the preceding word part contains a vowel not immediately before the -s (so gas and this retain the s, gaps and kiwis lose it) -
us+   ss -
do nothing -
-
- -Step 1b: -
-

- Search for the longest among the following suffixes, and perform the - action indicated. -

-
-
eed   eedly+ -
replace by ee if in R1 -
ed   edly+   ing   ingly+ -
delete if the preceding word part contains a vowel, and after the deletion: -
if the word ends at, bl or iz add e (so luxuriat → luxuriate), or -
if the word ends with a double - remove the last letter (so hopp → hop), or -
if the word is short, add e (so hop → hope) -
-
- -Step 1c: * -
- replace suffix y or Y by i if preceded by a non-vowel which is not the - first letter of the word (so cry → cri, by → by, say → say) -
- -Step 2: -
-

- Search for the longest among the following suffixes, and, if - found and in R1, perform the action indicated. -

-
-
tional:   replace by tion -
enci:   replace by ence -
anci:   replace by ance -
abli:   replace by able -
entli:   replace by ent -
izer   ization:   replace by ize -
ational   ation   ator:   replace by ate -
alism   aliti   alli:   replace by al -
fulness:   replace by ful -
ousli   ousness:   replace by ous -
iveness   iviti:   replace by ive -
biliti   bli+:   replace by ble -
ogi+:   replace by og if preceded by l -
fulli+:   replace by ful -
lessli+:   replace by less -
li+:   delete if preceded by a valid li-ending -
-
- -Step 3: -
-

- Search for the longest among the following suffixes, and, if - found and in R1, perform the action indicated. -

-
-
tional+:   replace by tion -
ational+:   replace by ate -
alize:   replace by al -
icate   iciti   ical:   replace by ic -
ful   ness:   delete -
ative*:   delete if in R2 -
-
- -Step 4: -
-

- Search for the longest among the following suffixes, and, if - found and in R2, perform the action indicated. -

-
-
al   ance   ence   er   ic   able   ible   ant   ement   - ment   ent   ism   ate   iti   ous   ive   ize -
delete -
ion -
delete if preceded by s or t -
-
- -Step 5: * -
-

- Search for the following suffixes, and, if - found, perform the action indicated. -

-
-
e -
delete if in R2, or in R1 and not preceded by a short - syllable -
l -
delete if in R2 and preceded by l -
-
-

-Finally, turn any remaining Y letters in the word back into lower case. -

- -

Exceptional forms in general

- -

-It is quite easy to expand a Snowball script so that certain exceptional -word forms get special treatment. The standard case is that certain words -W1,  W2  ..., instead of passing through the stemming process, are -mapped to the forms  X1,  X2  ... respectively. If the script does -the stemming by means of the call -

-[% highlight(" - define stem as C -") %] -

-where  C  is a command, the exceptional cases can be dealt with by extending this to -

-[% highlight(" - define stem as ( exception or C ) -") %] -

-and putting in a routine  exception: -

-
-    define exception as (
-        [substring] atlimit among(
-            'W1'  ( <- 'X1' )
-            'W2'  ( <- 'X2' )
-            ...
-        )
-    )
-
-

-atlimit  causes the whole string to be tested for equality with one of -the  Wi, and if a match is found, the string is replaced with -Xi. -

- -

-More precisely we might have a group of words  W11,  W12  ... -that need to be mapped to  X1, another group  W21,  W22 -... that need to be mapped to  X2, and so on, and a list of words -V1,  V2  ...  Vk  that are to remain invariant. The -exception  routine may then be written as follows: - -

-    among( 'W11' 'W12' ... (<- 'X1')
-           'W21' 'W22' ... (<- 'X2')
-           ...
-           'Wn1' 'Wn2' ... (<- 'Xn')
-           'V1' 'V2' ... 'Vk'
-         )
-
-

-And indeed the  exception1  routine for the English stemmer has just that -shape: -

-[% highlight(" - define exception1 as ( - - [substring] atlimit among( - - /* special changes: */ - - 'skis' (<-'ski') - 'skies' (<-'sky') - 'dying' (<-'die') - 'lying' (<-'lie') - 'tying' (<-'tie') - - /* special -LY cases */ - - 'idly' (<-'idl') - 'gently' (<-'gentl') - 'ugly' (<-'ugli') - 'early' (<-'earli') - 'only' (<-'onli') - 'singly' (<-'singl') - - // ... extensions possible here ... - - /* invariant forms: */ - - 'sky' - 'news' - 'howe' - - 'atlas' 'cosmos' 'bias' 'andes' // not plural forms - - // ... extensions possible here ... - ) - ) -") %] - -

-(More will be said about the words that appear here shortly.) -

- -

-Here we see words being treated exceptionally before stemming is done, but equally we could -treat stems exceptionally after stemming is done, and so, if we wish, map absorpt to -absorb, reduct to reduc etc., as in the -Lovins stemmer. -But more generally, throughout the algorithm, each significant step may have recognised -exceptions, and a suitably placed  among  will take care of them. For example, a point made -at least twice in the literature is that words beginning gener are overstemmed by the -Porter stemmer: -

- -
-
generate
- generates
- generated
- generating
- general
- generally
- generic
- generically
- generous
- generously 		  →   gener - -
- -

-To fix this over-stemming, we make an exception to the usual setting of p1, -the left point of R1, and therefore replace -

- -[% highlight(" - gopast v gopast non-v setmark p1 -") %] - -

-with -

- -[% highlight(" - among ( - 'gener' - // ... and other stems may be included here ... - ) or (gopast v gopast non-v) - setmark p -") %] - -

-after which the words beginning gener stem as follows: -

- -
-
generate
- generates
- generated
- generating - 		  →   generat - -
general
- generally - 		  →   general -
generic
- generically - 		  →   generic -
generous
- generously - 		  →   generous -
- -

-Another example is given by the  exception2  routine, which is similar to  exception1, -but placed after the call of  Step_1a, which may have removed terminal s, -

- -[% highlight(" - define exception2 as ( - - [substring] atlimit among( - 'inning' 'outing' 'canning' 'herring' - 'proceed' 'exceed' 'succeed' - - // ... extensions possible here ... - - ) - ) -") %] - -

-Snowball makes it easy therefore to add in lists of exceptions. But deciding what the lists of -exceptions should be is far from easy. Essentially there are two lines of attack, the -systematic and the piecemeal. One might systematically treat as exceptions the stem changes of -irregular verbs, for example. The piecemeal approach is to add in exceptions as people notice -them — like gener above. The problem with the systematic approach is that it should be -done by investigating the entire language vocabulary, and that is more than most people are -prepared to do. The problem with the piecemeal approach is that it is arbitrary, and usually -yields little. -

- -

-The exception lists in the English stemmer are meant to be illustrative (‘this is how it is done if you -want to do it’), and were derived piecemeal. -

- -

-a) -The new stemmer improves on the Porter stemmer in handling short words ending e and -y. There is however a mishandling of the four forms sky, skies, ski, -skis, which is easily corrected by treating three of these words as -special cases. -

- -

-b) -Similarly there is a problem with the ing form of three letter verbs ending ie. There -are only three such verbs: die, lie and tie, so a special case is made for -dying, lying and tying. -

- -

-c) -One has to be a little careful of certain ing forms. -inning, outing, canning, which one does not wish -to be stemmed to -in, out, can. -

- -

-d) -The removal of suffix ly, which is not in the Porter stemmer, has a number of exceptions. -Certain short-word exceptions are idly, gently, ugly, early, only, singly. -Rarer words (bristly, burly, curly, surly ...) are not included. -

- -

-e) -The remaining words were included following complaints from users of the Porter algorithm. -news is not the plural of new (noticed when IR systems were being set up for -Reuters). Howe is a surname, and needs to be separated from how (noticed when -doing a search for ‘Sir Geoffrey Howe’ in a demonstration at the House of Commons). -succeed etc are not past participles, so the ed should not be removed (pointed out -to me in an email from India). herring should not stem to her (another email from -Russia). -

- -

-f) -Finally, a few non-plural words ending s have been added. -

- -

-Incidentally, this illustrates how much feedback to expect from the real users of a stemming -algorithm: seven or eight words in twenty years! -

- -

-The definition of the English stemmer above is therefore supplemented by the following: -

- -

Exceptional forms in the English stemmer

- -
-

- If the words begins gener, commun or arsen, set R1 to be the remainder of the - word. -

- -

- Stem certain special words as follows, -

- -
-
skis   →   ski -
skies   →   sky - -
dying
lying
tying - 		→ - die
lie
tie - - -
idly
gently
ugly
early
only
singly - 		→ - idl
gentl
ugli
earli
onli
singl - -
- -

- If one of the following is found, leave it invariant, -

- -
-
sky
news
howe -
atlas     cosmos     bias     andes -
- -

- Following step 1a, leave the following invariant, -

- -
-
inning     outing     canning     herring     earring -
proceed     exceed     succeed -
-
- -

The full algorithm in Snowball

- -[% highlight_file('english') %] - -[% footer %] diff --git a/algorithms/estonian/stemmer.tt b/algorithms/estonian/stemmer.tt deleted file mode 100644 index dec4b74..0000000 --- a/algorithms/estonian/stemmer.tt +++ /dev/null @@ -1,485 +0,0 @@ -[% header('Estonian stemming algorithm') %] - -

Links to resources

- - - -
- -

-Here is a sample of vocabulary, with the stemmed forms that will -be generated with the algorithm. -

- -[% algorithm_vocab([ -'raamat', -'raamatu', -'raamatut', -'raamatule', -'raamatud', -'raamatute', -'raamatuid', -'raamatutele', -'raamatutestki', -'hele', -'heleda', -'heledat', -'heledale', -'heledad', -'heledate', -'heledaid', -'heledatele', -'heledam', -'heledama', -'heledamat', -'heledamad', -'heledamate', -'heledamaid', -'heledamatelegi', -'heledaim', -'heledaima', -'heledaimat', -'heledaimale', -'heledaimad', -'heledaimate', -'heledaimaid', -'heledaimatelt', -'hobune', -'hobuse', -'hobust', -'hobusele', -'hobused', -'hobuste', -'hobuseid', -'hobustele', -], [ -'hüpata', -'hüppa', -'hüppaksin', -'hüppaksid', -'hüppaks', -'hüppaksime', -'hüppaksite', -'hüppan', -'hüppad', -'hüppab', -'hüppame', -'hüppate', -'hüppavad', -'hüppasin', -'hüppasid', -'hüppas', -'hüppasime', -'hüppasite', -'hüpanuksite', -'hüpatakse', -'hüpati', -'hüpanud', -'hüpanutest', -'hüpates', -'hüppavat', -'hüppavatele', -'hüppamata', -'hüppamast', -'hüljes', -'hülge', -'hüljest', -'hülgesse', -'hüljeste', -'hülgeid', -'hüljestesse', -'hülgeisse', -'ohutule', -'ohutud', -'ohutuid', -'ohututele', -]) %] -
- -

-This algorithm is written in collaboration with Estonian text analytics enterprise Texta. -

- -

-Letters in Estonian include the following accented forms, -

- -
- ä   ö   õ   ü   š   ž -
- -

-The following letters are vowels (V1): -

- -
- a   e   i   o   u   õ   ä   ö   ü -
- -

-RV is defined as one of the following: -

- -
- a   e   i   u   o -
- -

-KI is defined as one of the following (letters possible before -ki emphasis): -

- -
- k   p   t   g   b   d   s   h   f   š   z   ž -
- -

-GI is defined as one of the following (letters possible before -gi emphasis): -

- -
- c   j   l   m   n   q   r   v   w   x   a   e   i   o   u   õ   ä   ö   ü -
- -

-R1 in this algorithm is defined as a region after the first consonant preceded by a vowel (laul[nud], mõt[teid], kar[tuleid], saab[as]). If there’s no such region, then R1 is empty (laul[Ø], saun[Ø]). Limitations in steps (such as "if preceded by RV") are not restricted to the R1 region. -

- -

-LONGV is defined as one of the following: -

- -
- aa   ee   ii   oo   uu   ää   öö   üü   õõ -
- -

-Do step 0. If nothing was changed in step 0, continue with the steps, otherwise stop. Do step 1 and step 2. If nothing was changed in step 2, do steps 3, 4, 5, 6, 7, 8 and 9. If something was changed in step 2, do step 9. -

- -

-Step 0: verb_exceptions -

- -
- Search for some frequent irregular short verbs which wouldn’t have been found otherwise and give them a chosen stem. -

-
-
joon   jood   joob   joote   joome   joovad -
replace by joo -
jõin   jõid   jõi   jõime   jõite -
replace by joo -
joomata   juuakse   joodakse   juua   jooma -
replace by joo -
saan   saad   saab   saate   saame   saavad -
replace by saa -
saaksin   saaksid   saaks   saaksite   saaksime -
replace by saa -
sain   said   sai   saite   saime -
replace by saa -
saamata   saadakse   saadi   saama   saada -
replace by saa -
viin   viid   viib   viite   viime   viivad -
replace by viima -
viiksin   viiksid   viiks   viiksite   viiksime -
replace by viima -
viisin   viisite   viisime -
replace by viima -
viimata   viiakse   viidi   viima   viia -
replace by viima -
keen   keeb   keed   kees   keeme   keete   keevad -
replace by keesi -
keeksin   keeks   keeksid   keeksime   keeksite -
replace by keesi -
keemata   keema   keeta   keedakse -
replace by keesi -
löön   lööd   lööb   lööme   lööte   löövad -
replace by löö -
lööksin   lööksid   lööks   lööksime   lööksite -
replace by löö -
löömata   lüüakse   löödakse   löödi   lööma   lüüa -
replace by löö -
lõin   lõid   lõi   lõime   lõite -
replace by lõi -
loon   lood   loob   loome   loote   loovad -
replace by loo -
looksin   looksid   looks   looksime   looksite -
replace by loo -
loomata   luuakse   loodi   luua   looma -
replace by loo -
käin   käib   käid   käis   käime   käite   käivad -
replace by käisi -
käiksin   käiks   käiksid   käiksime   käiksite -
replace by käisi -
käimata   käiakse   käidi   käia   käima -
replace by käisi -
söön   sööb   sööd   sööme   sööte   söövad -
replace by söö -
sööksin   sööks   sööksid   sööksime   sööksite -
replace by söö -
sõin   sõi   sõid   sõime   sõite -
replace by söö -
söömata   süüakse   söödakse   söödi   sööma   süüa -
replace by söö -
toon   tood   toob   toote   toome   toovad -
replace by too -
tooksin   tooksid   tooks   tooksite   tooksime -
replace by too -
tõin   tõid   tõi   tõime   tõite -
replace by too -
toomata   tuuakse   toodi   tooma   tuua -
replace by too -
võin   võid   võib   võime   võis   võite   võivad -
replace by võisi -
võiksin   võiksid   võiks   võiksime   võiksite -
replace by võisi -
võimata   võidakse   võidi   võida   võima -
replace by võisi -
jään   jääd   jääb   jääme   jääte   jäävad -
replace by jääma -
jääksin   jääksid   jääks   jääksime   jääksite -
replace by jääma -
jäime   jäite   jäin   jäid   jäi -
replace by jääma -
jäämata   jäädakse   jääda   jääma   jäädi -
replace by jääma -
müün   müüd   müüb   müüs   müüme   müüte   müüvad -
replace by müüsi -
müüksin   müüksid   müüks   müüksime   müüksite -
replace by müüsi -
müümata   müüakse   müüdi   müüa   müüma -
replace by müüsi -
loeb   loen   loed   loeme   loete   loevad -
replace by luge -
loeks   loeksin   loeksid   loeksime   loeksite -
replace by luge -
põen   põeb   põed   põeme   põete   põevad -
replace by põde -
põeksin   põeks   põeksid   põeksime   põeksite -
replace by põde -
laon   laob   laod   laome   laote   laovad -
replace by ladu -
laoksin   laoks   laoksid   laoksime   laoksite -
replace by ladu -
teeksin   teeks   teeksid   teeksime   teeksite -
replace by tegi -
teen   teeb   teed   teeme   teete   teevad -
replace by tegi -
tegemata   tehakse   tehti   tegema   teha -
replace by tegi -
näen   näeb   näed   näeme   näete   näevad -
replace by nägi -
näeksin   näeks   näeksid   näeksime   näeksite -
replace by nägi -
nägemata   nähakse   nähti   näha   nägema -
replace by nägi -
-
- - -

-Step 1: emphasis -

- -
- Search for the longest among the following suffixes in R1, and perform the action indicated -

-
-
Test if there’s at least 4 characters before R1 region. If so, continue this step -
gi -
if preceded by a character from GI which is not the second character of a long vowel as defined by LONGV, delete -
ki -
if preceded by KI, delete -
-
- -

-Step 2: verb -

-
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

- -
-
nuksin   nuksime   nuksid   nuksite -
delete -
ksin   ksid   ksime   ksite -
delete -
mata -
delete -
takse   dakse -
delete -
taks   daks -
delete -
akse -
replace with a -
sime -
delete -
site -
delete -
sin -
delete -
me -
if preceded by V1, delete -
da -
if preceded by V1, delete -
n -
if preceded by V1, delete -
b -
if preceded by V1, delete -
-
- -

-Step 3: special_noun_endings -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
lasse -
replace by lase -
last -
replace by lase -
lane -
replace by lase -
lasi -
replace by lase -
misse -
replace by mise -
mist -
replace by mise -
mine -
replace by mise -
misi -
replace by mise -
lisse -
replace by lise -
list -
replace by lise -
line -
replace by lise -
lisi -
replace by lise -
-
- -

-Step 4: case_ending -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
sse if preceded by RV or LONGV -
st if preceded by RV or LONGV -
le if preceded by RV or LONGV -
lt if preceded by RV or LONGV -
ga if preceded by RV or LONGV -
ks if preceded by RV or LONGV -
ta if preceded by RV or LONGV -
t if preceded by at least 4 characters -
s if preceded by RV or LONGV -
l if preceded by RV or LONGV -
delete -
-
- -

-Step 5: plural_three_first_cases -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
ikkude -
replace by iku -
ikke -
replace by iku -
ike -
replace by iku -
sid -
if it is not preceded by LONGV, delete -
te -
if it doesn't have at least 4 characters before it, replace by t. -
Otherwise: -
a) if it is preceded by mis, replace with e, -
b) if it is preceded by las, replace with e, -
c) if it is preceded by lis, replace with e, -
if it wasn't replaced with e in steps a)-c) and it isn't preceded by t, delete -
de if preceded by RV or LONGV -
delete -
d if preceded by RV or LONGV -
delete -
-
- -

-Step 6: degrees -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
mai if preceded by RV -
ma -
m if preceded by RV -
delete -
-
- -

-Step 7: i_plural -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
i if preceded by RV -
delete -
-
- -

-Step 8: nu -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
nu -
tu -
du -
va -
delete -
-
- -

-Step 9: undouble_kpt -

- -
- Undouble consonant if word ending is kk+V1, tt+V1, pp+V1, - provided the vowel is in R1. -
- -

The full algorithm in Snowball

- -[% highlight_file('estonian') %] - -[% footer %] diff --git a/algorithms/finnish/stemmer.tt b/algorithms/finnish/stemmer.tt deleted file mode 100644 index dd2c0bf..0000000 --- a/algorithms/finnish/stemmer.tt +++ /dev/null @@ -1,212 +0,0 @@ -[% header('Finnish stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'edeltäjien', 'innostu']) %] - -

-Finnish is not an Indo-European language, but belongs to the Finno-Ugric -group, which again belongs to the Uralic group (*). Distinctions between -a-, i- and d-suffixes can be made in Finnish, but they are much -less sharply separated than in an Indo-European language. The system of -endings is extremely elaborate, but strictly defined, and applies equally to -all nominals, that is, to nouns, adjectives and pronouns. Verb endings have a -close similarity to nominal endings, which again makes Finnish very different -from any Indo-European language. -

- -

-More problematical than the endings themselves is the change that can be -effected in a stem as a result of taking a particular ending. A stem typically -has two forms, strong and weak, where one class of ending follows the -strong form and the complementary class the weak. Normalising strong and weak -forms after ending removal is not generally possible, although the common case -where strong and weak forms only differ in the single or double form of a -final consonant can be dealt with. -

- -

-Finnish includes the following accented forms, -

- -
- ä   ö -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u   y   ä   ö -
- -

-R1 and -R2 are then defined in the usual way -(see the note on R1 and R2). -

- -

-Do each of steps 1, 2, 3, 4, 5 and 6. -

- -

-Step 1: particles etc -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
(a) kin   kaan   kään   ko   kö   han   hän   pa   pä -
delete if preceded by n, t or a vowel -
(b) sti -
delete if in R2 -
-
- -

-(Of course, the n, t or vowel of 1(a) need not be in R1: only -the suffix removed must be in R1. And similarly below. -

- -

-Step 2: possessives -

- -
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

-
-
si -
delete if not preceded by k -
ni -
delete -
if preceded by kse, replace with ksi -
nsa   nsä   mme   nne -
delete -
an -
delete if preceded by one of   ta   ssa   sta   lla   lta   na -
än -
delete if preceded by one of   tä   ssä   stä   llä   ltä   nä -
en -
delete if preceded by one of   lle   ine -
-
- -

-The remaining steps require a few definitions. -

- -

-Define a v (vowel) as one of   a   e   i   o   u   y   ä   ö. -
-Define a V (restricted vowel) as one of   a   e   i   o   u   ä   ö. -
-So Vi means a V followed by letter i. -
-Define LV (long vowel) as one of   aa   ee   ii   oo   uu   ää   öö. -
-Define a c (consonant) as a character from ASCII a-z which isn't in -v (originally this was "a character other than a v but since -2018-04-11 we've changed this definition to avoid the stemmer from altering -sequences of digits). -
-So cv means a c followed by a v. -

- -

-Step 3: cases -

-
- Search for the longest among the following suffixes in R1, and perform the - action indicated -

- -
-
hXn   preceded by X, where X is a V other than u (a/han, e/hen etc) -
siin   den   tten   preceded by Vi -
seen   preceded by LV -
a   ä   preceded by cv -
tta   ttä   preceded by e -
ta   tä   ssa   ssä   sta   stä   lla   llä   lta   ltä   lle   na   nä   ksi   ine -
delete -
n -
delete, and if preceded by LV or ie, delete the last vowel -
-
- -

-So aarteisiin → aartei, the longest matching suffix being siin, -preceded as it is by Vi. But adressiin → adressi. The longest -matching suffix is not siin, because there is no preceding Vi, but n, -and then the last vowel of the preceding LV is removed. -

- -

-Step 4: other endings -

- -
- Search for the longest among the following suffixes in R2, and perform the - action indicated -

-
-
mpi   mpa   mpä   mmi   mma   mmä -
delete if not preceded by po -
impi   impa   impä   immi   imma   immä   eja   ejä -
delete -
-
- -

-Step 5: plurals -

- -
-If an ending was removed in step 3, delete a final i or j if in R1; -otherwise, if an ending was not removed in step 3, delete a final t in -R1 if it follows a vowel, and, if a t is removed, delete a final mma or -imma in R2, unless the mma is preceded by po. -
- -

-Step 6: tidying up -

- -
-Do in turn steps (a), (b), (c), (d), restricting all tests to the region -R1. -

- -

-a) If R1 ends LV delete the last letter
-b) If R1 ends cX, c a consonant and X one of   a   ä   e   i, delete the last -letter
-c) If R1 ends oj or uj delete the last letter
-d) If R1 ends jo delete the last letter -

- -

-Do step (e), which is not restricted to R1. -

- -

-e) If the word ends with a double consonant followed by zero or more vowels, -remove the last consonant (so eläkk → eläk, aatonaatto → -aatonaato) -

-
- -

The full algorithm in Snowball

- -[% highlight_file('finnish') %] - -[% footer %] diff --git a/algorithms/french/stemmer.tt b/algorithms/french/stemmer.tt deleted file mode 100644 index 4b23e44..0000000 --- a/algorithms/french/stemmer.tt +++ /dev/null @@ -1,301 +0,0 @@ -[% header('French stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'continu', 'main']) %] - -

The stemming algorithm

- -

-Letters in French include the following accented forms, -

- -
- â   à   ç   ë   é   ê   è   ï   î   ô   û   ù -
-The following letters are vowels: -
- a   e   i   o   u   y   â   à   ë   é   ê   è   ï   î   ô   û   ù -
-Assume the word is in lower case. Then, taking the letters in turn from the -beginning to end of the word, put u or i into upper -case when it is both preceded and followed by a vowel; put y into -upper case when it is either preceded or followed by a vowel; and put u into upper case when it follows q. For example, -
-
jouer → joUer -
ennuie → ennuIe -
yeux → Yeux -
quand → qUand -
croyiez → croYiez -
- -

-In the last example, y becomes Y because it is -between two vowels, but i does not become I because -it is between Y and e, and Y is not -defined as a vowel above. -

- -

-(The upper case forms are not then classed as vowels — see note on vowel -marking.) -

- -

-Replace ë and ï with He and Hi. The H -marks the vowel as having originally had a diaeresis, while the vowel itself, lacking an accent, is able to -match suffixes beginning in e or i. -

- -

-If the word begins with two vowels, RV is the region after the third -letter, otherwise the region after the first vowel not at the beginning of -the word, or the end of the word if these positions cannot be found. (Exceptionally, -par, col or tap, at the beginning of a word is also taken to define -RV as the region to their right.) -

- -

-For example, -

- -
-    a i m e r     a d o r e r     v o l e r    t a p i s
-         |...|         |.....|       |.....|        |...|
-
- -

-R1 is the region after the first non-vowel following a vowel, or the end of -the word if there is no such non-vowel. -

- -

-R2 is the region after the first non-vowel following a vowel in R1, or the -end of the word if there is no such non-vowel. -(See note on R1 and R2.) -

- -

-For example: -

- -
-    f a m e u s e m e n t
-         |......R1.......|
-               |...R2....|
-
- -

-Note that R1 can contain RV (adorer), and RV can contain R1 (voler). -

- -

-Below, ‘delete if in R2’ means that a found suffix should be removed if it -lies entirely in R2, but not if it overlaps R2 and the rest of the word. -‘delete if in R1 and preceded by X’ means that X itself does not have to -come in R1, while ‘delete if preceded by X in R1’ means that X, like the -suffix, must be entirely in R1. -

- -

-Start with step 1 -

- -

-Step 1: Standard suffix removal -

- Search for the longest among the following suffixes, and perform the - action indicated. -
-
ance   iqUe   isme   able   iste   eux   ances   iqUes   ismes   ables   istes -
delete if in R2 -
atrice   ateur   ation   atrices   ateurs   ations -
delete if in R2 -
if preceded by ic, delete if in R2, else replace by iqU -
logie   logies -
replace with log if in R2 -
usion   ution   usions   utions -
replace with u if in R2 -
ence   ences -
replace with ent if in R2 -
ement   ements -
delete if in RV -
if preceded by iv, delete if in R2 (and if further preceded by at, - delete if in R2), otherwise, -
if preceded by eus, delete if in R2, else replace by eux - if in R1, otherwise, -
if preceded by abl or iqU, delete if in R2, otherwise, -
if preceded by ièr or Ièr, replace by i if in RV -
ité   ités -
delete if in R2 -
if preceded by abil, delete if in R2, else replace by abl, - otherwise, -
if preceded by ic, delete if in R2, else replace by iqU, otherwise, -
if preceded by iv, delete if in R2 -
if   ive   ifs   ives -
delete if in R2 -
if preceded by at, delete if in R2 (and if further preceded by ic, - delete if in R2, else replace by iqU) -
eaux -
replace with eau -
aux -
replace with al if in R1 -
euse   euses -
delete if in R2, else replace by eux if in R1 -
issement   issements -
delete if in R1 and preceded by a non-vowel -
amment -
replace with ant if in RV -
emment -
replace with ent if in RV -
ment   ments -
delete if preceded by a vowel in RV -
-
- -

-In steps 2a and 2b all tests are confined to the RV region. -

- -

-Do step 2a if either no ending was removed by step 1, or if one of endings -amment, emment, ment, ments was found. -

- -

-Step 2a: Verb suffixes beginning i -

- -
- Search for the longest among the following suffixes and if found, - delete if the preceding character is neither a vowel nor H. -
- îmes   ît   îtes   i   ie   ies   ir   ira   irai   iraIent   irais   irait   iras -   irent   irez   iriez   irions   irons   iront   is   issaIent   issais   issait -   issant   issante   issantes   issants   isse   issent   isses   issez   issiez -   issions   issons   it -
-
- (Note that the preceding character itself must also be in RV.) -
- -

-Do step 2b if step 2a was done, but failed to remove a suffix. -

- -

-Step 2b: Other verb suffixes -

- -
- Search for the longest among the following suffixes, and perform the - action indicated. -
-
ions -
delete if in R2 -
é   ée   ées   és   èrent   er   era   erai   eraIent   erais   erait   eras   erez -   eriez   erions   erons   eront   ez   iez -
delete -
âmes   ât   âtes   a   ai   aIent   ais   ait   ant   ante   antes   ants   as   asse -   assent   asses   assiez   assions -
delete -
if preceded by e, delete -
-
- (Note that the e that may be deleted in this last step must also be in - RV.) -
- -

-If the last step to be obeyed — either step 1, 2a or 2b — altered the word, -do step 3 -

- -

-Step 3 -

-
- Replace final Y with i or final ç with c -
-

-Alternatively, if the last step to be obeyed did not alter the word, do -step 4 -

- -

-Step 4: Residual suffix -

- -
-

- If the word ends s, not preceded by a, i (unless itself preceded by H), o, u, è or s, delete it. -

- -

- In the rest of step 4, all tests are confined to the RV region. -

- -

- Search for the longest among the following suffixes, and perform the - action indicated. -

- -
-
ion -
delete if in R2 and preceded by s or t -
ier   ière   Ier   Ière -
replace with i -
e -
delete -
-
- (So note that ion is removed only when it is in R2 — as well as being - in RV — and preceded by s or t which must be in RV.) -
- -

-Always do steps 5 and 6. -

- -

-Step 5: Undouble -

- -
- If the word ends enn, onn, ett, ell or eill, delete the last letter -
- -

-Step 6: Un-accent -

- -
- If the words ends é or è followed by at least one non-vowel, remove - the accent from the e. -
- -

-And finally: -

- -
-

- Turn any remaining I, U and Y letters in the word back into lower case. -

- -

- Turn He and Hi back into ë and ï, and remove any - remaining H. -

-
- -

The same algorithm in Snowball

- -[% highlight_file('french') %] - -[% footer %] diff --git a/algorithms/german/stemmer.tt b/algorithms/german/stemmer.tt deleted file mode 100644 index 7220e24..0000000 --- a/algorithms/german/stemmer.tt +++ /dev/null @@ -1,146 +0,0 @@ -[% header('German stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'aufeinander', 'kategorie']) %] - -

The stemming algorithm

- -

-German includes the following accented forms, -

- -
- ä   ö   ü -
- -

-and a special letter, ß, equivalent to double s. -

- -

-The following letters are vowels: -

- -
- a   e   i   o   u   y   ä   ö   ü -
- -

-First put u and y between vowels into -upper case, and then do the following mappings, -

-
- (a) replace ß with ss,
- (a) replace ae with ä,
- (a) replace oe with ö,
- (a) replace ue with ü unless preceded by q. -
- -

-(The rules here for ae, oe and ue were -added in Snowball 2.3.0, but were previously present as a variant of the -algorithm termed "german2"). The condition -on the replacement of ue prevents the unwanted changing of -quelle. Also note that feuer is not modified because the first -part of the rule changes it to feUer, so ue is not -found.) -

- -

-R1 and R2 are first set up in the standard way -(see the note on R1 and R2), -but then R1 is adjusted so that the region before it contains at least 3 letters. -

- -

-Define a valid s-ending as one of b, d, f, g, h, k, l, m, n, r or t. -

- -

-Define a valid st-ending as the same list, excluding letter r. -

- -

-Do each of steps 1, 2 and 3. -

- -

-Step 1: -

- Search for the longest among the following suffixes, -
- (a) em   ern   er
- (b) e   en   es
- (c) s (preceded by a valid s-ending) -
-

- and delete if in R1. (Of course the letter of the valid s-ending is - not necessarily in R1.) If an ending of group (b) is deleted, and the ending - is preceded by niss, delete the final s. -

- -

- (For example, äckern → äck, ackers → acker, - armes → arm, bedürfnissen → bedürfnis) -

-
-Step 2: -
-

- Search for the longest among the following suffixes, -

-
- (a) en   er   est
- (b) st (preceded by a valid st-ending, itself preceded by at least 3 - letters) -
-

- and delete if in R1. -

- -

- (For example, derbsten → derbst by step 1, and derbst → derb by step - 2, since b is a valid st-ending, and is preceded by just 3 letters) -

-
-Step 3: d-suffixes (*) -
-

- Search for the longest among the following suffixes, and perform the - action indicated. -

-
-
end   ung -
delete if in R2 -
if preceded by ig, delete if in R2 and not preceded by e -
ig   ik   isch -
delete if in R2 and not preceded by e -
lich   heit -
delete if in R2 -
if preceded by er or en, delete if in R1 -
keit -
delete if in R2 -
if preceded by lich or ig, delete if in R2 -
-
- -

-Finally, -

- -
- turn U and Y back into lower case, and remove the umlaut accent from a, - o and u. -
- -

The same algorithm in Snowball

- -[% highlight_file('german') %] - -[% footer %] diff --git a/algorithms/german2/stemmer.tt b/algorithms/german2/stemmer.tt deleted file mode 100644 index 6751bd6..0000000 --- a/algorithms/german2/stemmer.tt +++ /dev/null @@ -1,22 +0,0 @@ -[% header('German stemming algorithm variant') %] - -

Links to resources

- - - -

-We used to present a variant of the main German stemmer, termed "german2" which -was the same as the German stemmer but adjusted the first step to improve -handling of input text where the German letters ä, -ö and ü, were written as ae, -oe and ue respectively. -

- -

-Snowball 2.3.0 added these adjustments to the main German stemmer, so there -is no longer a "german2" variant - just used the "german" stemmer. -

- -[% footer %] diff --git a/algorithms/germanic.tt b/algorithms/germanic.tt deleted file mode 100644 index eb52a74..0000000 --- a/algorithms/germanic.tt +++ /dev/null @@ -1,113 +0,0 @@ -[% header('Germanic language stemmers') %] - -

Links to resources

- - - -

-Despite its inflexional complexities, German has quite a simple suffix -structure, so that, if one ignores the almost intractable problems of -compound words, separable verb prefixes, and prefixed and infixed ge, an -algorithmic stemmer can be made quite short. (Infixed zu can be removed -algorithmically, but this minor feature is not shown here.) The umlaut in -German is a regular feature of plural formation, so its removal is a -natural feature of stemming, but this leads to certain false conflations -(for example, schön, beautiful; schon, already). -

- -

-By contrast, Dutch is inflexionally simple, but even so, this does not make -for any great difference between the stemmers. A feature of Dutch that -makes it markedly different from German is that the grammar of the written -language has changed, and continues to change, relatively rapidly, and that -it has assimilated a large and mixed foreign vocabulary with some of the -accompanying foreign suffixes. Foreign words may, or may not, be -transliterated into a Dutch style. Naturally these create problems in -stemming. The stemmer here is intended for native words of contemporary -Dutch. -

- -

-In a Dutch noun, a vowel may double in the singular form (manen = moons, maan -= moon). We attempt to solve this by undoubling the double vowel (Kraaij -Pohlman by contrast attempt to double the single vowel). The endings je, -tje, pje etc., although extremely common, are not stemmed. They are -diminutives and can significantly alter word meaning. -

- -

A note on compound words

- -

-Famously, German allows for the formation of long compound words, written -without spaces. For retrieval purposes, it is useful to be able to search -on the parts of such words, as well as the on the complete words -themselves. This is not just peculiar to German: Dutch, Danish, Norwegian, -Swedish, Icelandic and Finnish have the same property. To split up -compound words cannot be done without a dictionary, and the purely -algorithmic stemmers presented here do not attempt it. -

- -

-We would suggest, however, that the need for compound word splitting in -these languages has been somewhat overstated. In the case of German: -

- -

-1) There are many English compounds one would see no advantage in -splitting, -

- -
-
blackberry blackboard rainbow coastguard .... -
- -

-Many German compounds are like this, -

- -
-
Bleistift (pencil) = Blei (lead) + Stift (stick) -
Eisenbahn (railway) = Eisen (iron) + Bahn (road) -
Unterseeboot (submarine) = under + sea + boat -
- -

-2) Other compounds correspond to what in English one would want to do by -phrase searching, so they are ready made for that purpose, -

- -
-
Gesundheitspflege = ‘health care’ -
Fachhochschule = ‘technical college’ -
Kunstmuseum = ‘museum of fine art’ -
- -

-3) In any case, longer compounds, especially involving personal names, are -frequently hyphenated, -

- -
Heinrich-Heine-Universität -
- -

-4) It is possible to construct participial adjectives of almost any -length, but they are little used in contemporary German, and regarded now -as poor style. As in English, very long words are not always to be taken -too seriously. On the author's last visit to Germany, the longest word he -had to struggle with was -

- -
Nasenspitzenwurzelentzündung -
- -

-It means ‘inflammation of the root of the tip of the nose’, and comes from -a cautionary tale for children. -

- -[% footer %] diff --git a/algorithms/greek/stemmer.tt b/algorithms/greek/stemmer.tt deleted file mode 100644 index 2327149..0000000 --- a/algorithms/greek/stemmer.tt +++ /dev/null @@ -1,27 +0,0 @@ -[% header('Greek stemming algorithm') %] - -

Links to resources

- - - -

This is an implementation of the stemmer described in:

- -
- Ntais, Georgios. Development of a Stemmer for the Greek Language. Diss. Royal Institute of Technology, 2006. -
- -

with additional improvements from:

- -
- Saroukos, Spyridon. Enhancing a Greek language stemmer. University of Tampere, 2008. -
- -

The full algorithm in Snowball

- -[% highlight_file('greek') %] - -[% footer %] diff --git a/algorithms/hindi/stemmer.tt b/algorithms/hindi/stemmer.tt deleted file mode 100644 index 8300a82..0000000 --- a/algorithms/hindi/stemmer.tt +++ /dev/null @@ -1,83 +0,0 @@ -[% header('Hindi stemming algorithm') %] - -

Links to resources

- - - -

-This is an implementation of the "Lightweight Stemmer for Hindi" described in: -

- -
- A. Ramanathan and D. Rao (2003) A Lightweight Stemmer for Hindi -
- -

-The major difference in our implementation is that rather than transliterating -to the Latin alphabet we instead work in the original Devanagari script. We -have modified the suffixes in the list by converting them back to Devanagari -like so: -

- - - -

-The transliterations of our stems would end with "a" when our -stems end in a consonant, so we also include the character virama in the -list of suffixes to remove (this affects 222 words from our sample vocabulary). -

- -

-Aside from this, our implementation attempts to be faithful to the algorithm -described in the paper, though in a few places we've had to resolve ambiguities -in the paper: -

- - - -

The full algorithm in Snowball

- -[% highlight_file('hindi') %] - -[% footer %] diff --git a/algorithms/hungarian/stemmer.tt b/algorithms/hungarian/stemmer.tt deleted file mode 100644 index 18e64e4..0000000 --- a/algorithms/hungarian/stemmer.tt +++ /dev/null @@ -1,243 +0,0 @@ -[% header('Hungarian stemming algorithm') %] - -

Contributed by Anna Tordai University of Amsterdam -

- -

Links to resources

- - - -[% algorithm_vocab([40, 'babaháznak', 'muattta']) %] - -

-This stemming algorithm removes the inflectional suffixes of nouns. Nouns are -inflected for case, person/possession and number. -

- -

-Letters in Hungarian include the following accented forms, -

- -
- á   é   í   ó   ö   ő   ú   ü   ű -
- -

-The following letters are vowels: -

- -
- a   á   e   é   i   í   o   ó   ö   ő   u   ú   - ü   ű -
- -

-The following letters are digraphs: -

- -
- cs   dz   dzs   gy   ly   ny   ty   zs -
- -

-A double consonant is defined as: -

- -
- bb   cc   ccs   dd   ff   gg   ggy   jj   kk   ll   lly   mm -   nn   nny   pp   rr   ss   ssz   tt   tty   vv   zz   zzs -
- -

-If the word begins with a vowel, R1 is defined as the region after the -first consonant or digraph in the word. If the word begins with a consonant, it -is defined as the region after the first vowel in the word. If the word does -not contain both a vowel and consonant, R1 is the null region at the end of -the word. -

- -

-For example: -

- -
-    t ó b a n           consonant-vowel
-       |.....|          R1 is 'a b a n'
-
-    a b l a k a n       vowel-consonant
-       |.........|      R1 is 'l a k a n'
-
-    a c s o n y         vowel-digraph
-         |.....|        R1 is 'o n y'
-
-    c v s
-     --->|<---          null R1 region
-
- -

-‘Delete if in R1’ means that the suffix should be removed if it is in -region R1 but not if it is outside. -

- -

-Do steps 1 to 9 in turn -

- -

-Step 1: Remove instrumental case -

- -
- Search for one of the following suffixes and perform the action indicated. -
-
al   el -
delete if in R1 and preceded by a double consonant, and - remove one of the double consonants. (In the case of consonant plus digraph, such as ccs, remove a c). -
-
- -

-Step 2: Remove frequent cases -

- -
- Search for the longest among the following suffixes and perform the action indicated. -
-
ban   ben   ba   be   ra   re   nak   nek   val   vel   tól -   től   ról   ről   ból   ből   hoz   hez   höz   - nál   nél   ig   at   et   ot   öt   ért   képp   - képpen   kor   ul   ül   vá   vé   onként   enként   - anként   ként   en   on   an   ön   n   t - - -
delete if in R1 -
if the remaining word ends á replace by a -
if the remaining word ends é replace by e -
-
- -

-Step 3: Remove special cases: -

- -
- Search for the longest among the following suffixes and perform the action - indicated. -
-
án   ánként -
replace by a if in R1 -
én -
replace by e if in R1 -
-
- -

-Step 4: Remove other cases: -

- -
- Search for the longest among the following suffixes and perform the action indicated -
-
astul   estül   stul   stül -
delete if in R1 -
ástul -
replace with a if in R1 -
éstül -
replace with e if in R1 -
-
- -

-Step 5: Remove factive case -

- -
- Search for one of the following suffixes and perform the action indicated. -
-
á   é -
delete if in R1 and preceded by a double consonant, and - remove one of the double consonants (as in step 1). -
-
- -

-Step 6: Remove owned -

- -
- Search for the longest among the following suffixes and perform the action - indicated. -
-
oké   öké   aké   eké   ké   éi   é -
delete if in R1 -
áké   áéi -
replace with a if in R1 -
éké   ééi   éé -
replace with e if in R1 -
-
- -

-Step 7: Remove singular owner suffixes -

- -
- Search for the longest among the following suffixes and perform the action - indicated. -
-
ünk   unk   nk   juk   jük   uk   ük   em   om   am   m -   od   ed   ad   öd   d   ja   je   a   e o -
delete if in R1 -
ánk ájuk ám ád á -
replace with a if in R1 -
énk éjük ém éd é -
replace with e if in R1 -
-
- -

-Step 8: Remove plural owner suffixes -

- -
- Search for the longest among the following suffixes and perform the action - indicated. -
-
jaim   jeim   aim   eim   im   jaid   jeid   aid   eid   id   - jai   jei   ai   ei   i   jaink   jeink   eink   aink   ink   - jaitok   jeitek   aitok   eitek   itek   jeik   jaik   aik   eik   - ik - -
delete if in R1 -
áim   áid   ái   áink   áitok   áik -
replace with a if in R1 -
éim   éid     éi   éink   éitek   éik -
replace with e if in R1 -
-
- -

-Step 9: Remove plural suffixes -

- -
- Search for the longest among the following suffixes and perform the action - indicated. -
-
ák -
replace with a if in R1 -
replace with e if in R1 -
ök   ok   ek   ak   k -
delete if in R1 -
-
- -

The full algorithm in Snowball

- -[% highlight_file('hungarian') %] - -[% footer %] diff --git a/algorithms/index.tt b/algorithms/index.tt deleted file mode 100644 index 58c622e..0000000 --- a/algorithms/index.tt +++ /dev/null @@ -1,92 +0,0 @@ -[% header('Stemming algorithms') %] - -

Stemming for various European languages

- -

-We present stemming algorithms (with implementations in Snowball) for the -following languages: -

- - - -

-There are two English stemmers, the original Porter stemmer, -and an improved stemmer which has been called Porter2. Read the accounts of them to -learn a bit more about using Snowball. -

- -

-Each formal algorithm should be compared with the corresponding Snowball program. -

- -

-Surprisingly, among the Indo-European languages (*), the French stemmer turns out to be the most complicated, whereas -the Russian stemmer, despite its large number of suffixes, is very simple. In -fact it is interesting that English, with its minimal use of i-suffixes, -has such a complex stemmer. This is partly due to the delicate nature of -i-suffix removal (undoubling the p after removing ing from hopping etc), -and partly to the wealth of forms of d-suffixes, deriving as they do from -the mixed Romance and Germanic ancestry of the language. -

- -

-Note that by i-suffix we mean inflexional suffix, and by d-suffix, -derivational suffix (*). -

- -

Other Stemming Algorithms

- -

-We also provide Snowball implementations of some algorithms developed by other parties: -

- - - -[% footer %] diff --git a/algorithms/indonesian/stemmer.tt b/algorithms/indonesian/stemmer.tt deleted file mode 100644 index ffffe04..0000000 --- a/algorithms/indonesian/stemmer.tt +++ /dev/null @@ -1,124 +0,0 @@ -[% header('Indonesian stemming algorithm') %] - -

Links to resources

- - - -

-This is an implementation of the "Porter Stemmer for Bahasa Indonesia" described -in: -

- -
- Tala F Z (2003) A Study of Stemming Effects on Information Retrieval in Bahasa Indonesia. M.S. thesis, University of Amsterdam. -
- -

-It would be more accurately described as "Porter-style" or "Porter-inspired" -since Martin Porter wasn't directly involved in its development. -

- -

-Our implementation attempts to be faithful to the algorithm described in the -paper, but we have had to address some places in the paper which are unclear, -and a case where an example doesn't match the described algorithm. -

- - - -

The full algorithm in Snowball

- -[% highlight_file('indonesian') %] - -[% footer %] diff --git a/algorithms/irish/stemmer.tt b/algorithms/irish/stemmer.tt deleted file mode 100644 index 1293bc2..0000000 --- a/algorithms/irish/stemmer.tt +++ /dev/null @@ -1,52 +0,0 @@ -[% header('Irish Gaelic stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([30, 'ábharú', 'pábháil']) %] - -

-This basic stemmer for Irish was developed and contributed by Jim -O’Regan. -

- -

-One thing that should be taken into account with Irish is the initial -mutation (n-eclipsis and h-prothesis) which causes problems if words -are simply folded to lowercase before stemming in the way that is -usually assumed by Snowball stemmers. A Snowball version of an algorithm to -fold to lowercase while taking this into account would look something like: -

- -[% highlight_file('tolower_irish') %] - -

-The following characters are vowels for the purposes of this algorithm: - -

- a e i o u á é í ó ú -
- -

-The algorithm first addresses the initial mutation, then regions are determined -based on the word after this first step: -

- - - -

The full algorithm in Snowball

- -[% highlight_file('irish') %] - -[% footer %] diff --git a/algorithms/italian/stemmer.tt b/algorithms/italian/stemmer.tt deleted file mode 100644 index de88f5c..0000000 --- a/algorithms/italian/stemmer.tt +++ /dev/null @@ -1,185 +0,0 @@ -[% header('Italian stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'abbandonata', 'pronto']) %] - -

The stemming algorithm

- -

-Italian can include the following accented forms: -

- -
- á   é   í   ó   ú   à   è   ì   ò   ù -
- -

-First, replace all acute accents by grave accents. And, as in French, put u after -q, and u, i between vowels into upper case. -(See note on vowel marking.) -

- -

-The vowels are then -

- -
- a   e   i   o   u   à   è   ì   ò   ù -
- -

-R2 -(see the note on R1 and R2) -and RV have the same definition as in the - Spanish stemmer. -

- -

-First exceptional cases are checked for. These need to match the whole word, and currently are: -

- - - -

-If found then handle as described and that's it. -

- -

-Otherwise always do steps 0 and 1. -

- -

-Step 0: Attached pronoun -

- -
- Search for the longest among the following suffixes -
- ci   gli   la   le   li   lo   mi   ne   si   ti   vi -   sene   gliela   gliele   glieli   glielo   gliene -   mela   mele   meli   melo   mene -   tela   tele   teli   telo   tene -   cela   cele   celi   celo   cene -   vela   vele   veli   velo   vene -
-

- following one of -

-
- (a) ando   endo
- (b) ar   er   ir -
-

- in RV. In case of (a) the suffix is deleted, in case (b) it is replace - by e (guardandogli → guardando, accomodarci → accomodare) -

-
- -

-Step 1: Standard suffix removal -

- -
- Search for the longest among the following suffixes, and perform the - action indicated. -
-
anza   anze   ico   ici   ica   ice   iche   ichi   ismo   ismi   abile   abili   ibile   ibili -   ista   iste   isti   istà   istè   istì   oso   osi   osa   ose   mente -   atrice   atrici   ante   anti -
delete if in R2 -
azione   azioni   atore   atori - delete if in R2 -
if preceded by ic, delete if in R2 -
logia   logie -
replace with log if in R2 -
uzione   uzioni   usione   usioni -
replace with u if in R2 -
enza   enze -
replace with ente if in R2 -
amento   amenti   imento   imenti -
delete if in RV -
amente -
delete if in R1 -
if preceded by iv, delete if in R2 (and if further preceded by at, - delete if in R2), otherwise, -
if preceded by os, ic or abil, delete if in R2 -
ità -
delete if in R2 -
if preceded by abil, ic or iv, delete if in R2 -
ivo   ivi   iva   ive -
delete if in R2 -
if preceded by at, delete if in R2 (and if further preceded by ic, - delete if in R2) -
-
- -

-Do step 2 if no ending was removed by step 1. -

- -

-Step 2: Verb suffixes -

- -
- Search for the longest among the following suffixes in RV, and if found, - delete. -
- ammo   ando   ano   are   arono   - asse   assero   assi   assimo   ata   ate   - ati   ato   ava   avamo   avano   avate   avi   avo   emmo -   enda   ende   endi   endo   erà   erai   eranno   ere -   erebbe   erebbero   erei   eremmo   eremo   ereste   - eresti   erete   erò   erono   essero   ete   eva   evamo -   evano   evate   evi   evo   Yamo   iamo   immo   irà -   irai   iranno   ire   irebbe   irebbero   irei   iremmo -   iremo   ireste   iresti   irete   irò   irono   isca   - iscano   isce   isci   isco   iscono   issero   ita   ite -   iti   ito   iva   ivamo   ivano   ivate   ivi   ivo   - ono   uta   ute   uti   uto   ar   ir -
- -

-Always do steps 3a and 3b. -

- -
- -

-Step 3a -

- -
- Delete a final a, e, i, o, à, è, ì or ò if it is in RV, and a - preceding i if it is in RV (crocchi → crocch, crocchio → crocch) -
- -

-Step 3b -

- -
- Replace final ch (or gh) with c (or g) if in RV (crocch → crocc) -
- -

-Finally, -

- -
- turn I and U back into lower case -
- -

The same algorithm in Snowball

- -[% highlight_file('italian') %] - -[% footer %] diff --git a/algorithms/kraaij_pohlmann/stemmer.tt b/algorithms/kraaij_pohlmann/stemmer.tt deleted file mode 100644 index 4fad378..0000000 --- a/algorithms/kraaij_pohlmann/stemmer.tt +++ /dev/null @@ -1,69 +0,0 @@ -[% header('The Kraaij-Pohlmann stemming algorithm') %] - -

Links to resources

- - - -

-The Kraaij-Pohlmann stemming algorithm is an ANSI C program for stemming in Dutch. Although -advertised as an algorithm, it is in fact a program without an accompanying -algorithmic description. It is possible to produce a fairly clean Snowball -version, but only by sacrificing exact functional equivalence. But that does not -matter too much, since in the demonstration vocabulary only 32 words out of over -45,000 stem differently. Here they are: -

- -
-
-source ANSI C stemmer Snowball stemmer -
airways airways airway -
algerije algerije alrije -
assays assays assay -
bruys bruys bruy -
cleanaways cleanaways cleanaway -
creys creys crey -
croyden croyd croy -
edele edel edeel -
essays essays essay -
gedijen gedij dij -
geoff of off -
gevrey gevrey vrey -
geysels ysel gey -
grootmeesteres grootmee grootmeest -
gròotmeesteres gròotmee gròotmeest -
hectares hectaar hect -
huys huys huy -
kayen kayen kaay -
lagerwey lagerwey larwey -
mayen mayen maay -
meesteres meester meest -
oppasseres oppasser oppas -
pays pays pay -
royale royale royaal -
schilderes schilder schild -
summerhayes summerhayes summerhaye -
tyumen tyuum tyum -
verheyen verheyen verheey -
verleideres verleider verleid -
ytsen yts ytsen -
yves yve yves -
zangeres zanger zang -
- -

-The Kraaij-Pohmann stemmer can make fairly drastic reductions to a word. For -example, infixed ge is removed, so geluidgevoelige stems to -luidvoel. Often, therefore, the original word cannot be easily guessed from -the stemmed form. -

- -

-Here then is the Snowball equivalent of the Kraaij-Pohlmann algorithm. -

- -[% highlight_file('kraaij_pohlmann') %] - -[% footer %] diff --git a/algorithms/lithuanian/stemmer.tt b/algorithms/lithuanian/stemmer.tt deleted file mode 100644 index 8db874a..0000000 --- a/algorithms/lithuanian/stemmer.tt +++ /dev/null @@ -1,22 +0,0 @@ -[% header('Lithuanian stemming algorithm') %] - -

Links to resources

- - - -

-This algorithm was contributed by Dainius Jocas. -

- -

-Its intended domain of use is information retrieval, and so handling of nouns -is considered more important than that of verbs, adjectives, etc. -

- -

The full algorithm in Snowball

- -[% highlight_file('lithuanian') %] - -[% footer %] diff --git a/algorithms/lovins/festschrift.tt b/algorithms/lovins/festschrift.tt deleted file mode 100644 index b461436..0000000 --- a/algorithms/lovins/festschrift.tt +++ /dev/null @@ -1,1740 +0,0 @@ -[% header('Lovins revisited') %] - -

-This is a revised version of Martin Porter’s paper which was published as part -of the Karen Sparck Jones Festschrift of 2005. -

- -

-Charting a New Course: Progress in Natural Language Processing and -Information Retrieval: A Festschrift for Professor Karen Sparck Jones, edited -by John Tait, Amsterdam: Kluwer, 2005. -

- -

Lovins Revisited

- -

-Martin Porter, December 2001 (revised November 2008). -

- -

Abstract

-
- The Lovins stemming algorithm for English is analysed, and compared - with the Porter stemming algorithm, using Snowball, a language designed - specifically for the development of stemming algorithms. It is shown - how the algorithms manage to function in a similar way, while appearing - to be quite different. The Porter algorithm is recoded in the style of - the Lovins algorithm, which leads to the discovery of a few possible - improvements. -
- -

Preamble

- -

-This is a festschrift paper, so I am allowed to begin on a personal note. -In 1979 I was working with Keith van Rijsbergen and Stephen Robertson on a -British Library funded IR project to investigate the selection of good -index terms, and one of the things we found ourselves having to do was to -establish a document test collection from some raw data that had been sent -to us on a magnetic tape by Peter Vaswani of the National Physical -Laboratory. I was the tame programmer in the project, so it was my job to -set up the test collection. -

- -

-On the whole it did not prove too difficult. The data we received was a -collection of about 11,000 documents (titles and short abstracts), 93 -queries — in a free text form, and relevance judgements. All the text was -in upper case without punctuation, and there were one or two marker -characters to act as field terminators. By modern standards the data was -really very small indeed, but at the time it was considerably larger than -any of the other test collections we had. What you had to do was to cast it -into a standard form -for experimental work. You represented terms and documents by numbers, and -created flat files in text form corresponding to the queries, relevance -assessments, and term to document index. One process however was less -straightforward. On their way to becoming numeric terms, the words of the -source text were put through a process of linguistic normalisation called -suffix stripping, in which certain derivational and inflectional suffixes -attached to the words were removed. There was a standard piece of software -used in Cambridge at that time to do this, written in 1971 by Keith -Andrews (Andrews, 1971) as part of a Diploma Project. -One of the courses in -Cambridge is the one year post-graduate Diploma in Computer Science. Each -student on the course is required to do a special project, which includes -writing a significant piece of software — significant in the sense of being -both useful and substantial. -Keith's piece of software was more useful than most, and it continued to be -used as a suffix stripping program, or stemmer, for many years after it was -written. -

- -

-Now by an odd chance I was privy to much of Keith Andrews’ original -thinking at the time that he was doing the work. The reason for this was -that in 1971 I was looking for a house in Cambridge, and the base I was -operating from was a sleeping bag on the living room floor of an old friend -called John Dawson, who was Keith’s diploma supervisor. Keith used to come round -and discuss stemming algorithms with him, while I formed a mute audience. I -learnt about the Lovins stemming algorithm of 1968 (Lovins, 1968), -and must I think have -at least looked at her paper then, since I know it was not new to me when I -saw it again in 1979. Their view of Lovins’ work was that it did not go far -enough. There needed to be many more suffixes, and more complex rules to -determine the criteria for their removal. Much of their discussion was -about new suffixes to add to the list, and removal rules. It was interesting -therefore to find myself needing to use Andrews’ work eight years later, -and questioning some of its assumptions. Did you need that many suffixes? -Did the rules need to be so complicated? Perhaps one would do better to -break composite suffixes into smaller units and remove them piecemeal. -And perhaps syllables would be a better count of stem length than letters. -So I wrote my own stemmer, which became known as the Porter stemmer, and -which was published in 1980 (Porter, 1980). -

- -

-I must explain where Karen Sparck Jones fits into all of this. Keith -Andrews’ piece of work was originally suggested by Karen as a Diploma -student project, and she was able to use the Andrews stemmer in her IR -experiments throughout the seventies. In 1979 however Karen had moved much -more into the field of Natural Language Processing and Artificial -Intelligence, and by then had two or three research students in that field -just writing up their PhDs (only one of whom I really got to know — John -Tait, the editor of this volume). So we were in contact, but not working -together. That again was an odd chance: that Karen had been my research -supervisor in a topic other than IR, and that when later I was doing IR -research at Cambridge I was not working with Karen. While I was engaged on -writing the stemmer, Karen showed some justifiable irritation that I had -become interested in a topic so very remote from the one for which we had -received the British Library funding. Nevertheless, she came into my room -one day, said, ‘Look, if you're getting interested in stemming, you’d -better read this,’ and handed me the 1968 issue of Mechanical -Translation that contains the Lovins paper. I still have this issue with -Karen’s name across the top. (And I hope she didn't expect it back!) -

- -

-Another 20 years have gone by, and I have been studying the Lovins stemmer -again, really because I was looking for examples to code up in Snowball, a -small string processing language I devised in the latter half of 2001 -particularly adapted for writing stemming algorithms. Lovins’ stemmer -strikes me now as a fine piece of work, for which she never quite received -the credit she deserved. It was the first stemmer for English set out as -an algorithm that described the stemming process exactly. She explained -how it was intended to be used to improve IR performance, in just the way -in which stemmers are used today. It is not seriously short of suffixes: -the outstanding omissions are the plural forms ements and ents -corresponding to her ement and ent, and it is easy enough to add -them into the definition. It performs well in practice. In fact it is -still in use, and can be downloaded in various languages from the net (1). -The tendency since 1980 has been to attach the name ‘Porter’ to any -language stemming process that does not use a dictionary, even when it is -quite dissimilar to the original Porter stemmer (witness the Dutch Porter -stemmer of Kraaij and Pohlmann (2) (Kraaij, 1994 and Kraaij, 1995), but -the priority really belongs to Lovins. It also has one clear advantage -over the Porter algorithm, in that it involves fewer steps. Coded up well, -it should run a lot faster. -

- -

-A number of things intrigued me. Why are the Lovins and Porter stemmers so -different, when what they do looks so similar? Could the stemmer, in some -sense, be brought up-to-date? Could the Porter stemmer be cast into the -Lovins form, and so run faster? -

- -

-This paper is about the answers for these questions. In discovering them, I -have learned a lot more about my own stemmer. -

- -

Why stem?

- -

-It may be worth saying a little on what stemming is all about. We can imagine -a document with the title, -

- -
- Pre-raphaelitism: A Study of Four Critical Approaches -
- -

-and a query, containing the words -

- -
- PRE-RAPHAELITE CRITICISM -
- -

-We want to match query against title so that ‘Pre-raphaelitism’ matches -‘PRE-RAPHAELITE’ and ‘Critical’ matches ‘CRITICISM’. This leads to the -idea of removing endings from words as part of the process of extracting index -terms from documents, a similar process of ending removal being applied to -queries prior to the match. For example, we would like to remove the endings -from -

- -
-critical
-critically
-criticism
-criticisms
-critics
-
- -

-so that each word is reduced to ‘critic’. This is the stem, from which the -other words are formed, so the process as a whole is called stemming. It is -a feature of English morphology that the part of the word we want to remove is -at the end — the suffix. But the same is broadly true of French, German and other -languages of the Indo-European group. It is also true of numerous languages -outside Indo-European, Finnish for example, although there is a -boundary beyond which it is not true. So Chinese, where words are simple -units without affixes, and Arabic, where the stem is modified by -prefixes and infixes as well as suffixes, lie outside the -boundary. As an IR technique it therefore has wide applicability. In developing -stemmers two points were recognised quite early on. One is that the -morphological regularities that you find in English (or other languages) mean -that you can attempt to do stemming by a purely algorithmic process. Endings -al, ally, ism etc. occur throughout English vocabulary, and are -easy to detect and remove: you don’t need access to an on-line dictionary. The -other is that the morphological irregularities of English set a limit to the -success of an algorithmic approach. Syntactically, what look like endings may -not be endings (offspring is not offspr + ing), and the list of -endings seems to extend indefinitely (trapez-oid, likeli-hood, -guardian-ship, Tibet-an, juven-ilia, Roman-esque, ox-en -...) It is difficult to gauge where to set the cut-off for these rarer forms. -Semantically, the addition of a suffix may alter the meaning of a word a -little, a lot, or completely, and morphology alone cannot measure the degree of -change (prove and provable have closely related meanings; probe and -probable do not.) This meant that stemming, if employed at all, became the -most challenging, and the most difficult part of the indexing process. -

- -

-In the seventies, stemming might be applied as part of the process of -establishing a test collection, and when it was there would not usually be any -attempt to make the stemming process well-defined, or easily repeatable by -another researcher. This was really because the basis for experiment replication -was the normalised data that came out of the stemming process, rather than the -source data plus a description of stemming procedures. Stemming tended to be -applied, and then forgotten about. But by the 1980s, stemming itself was being -investigated. Lennon and others (Lennon, 1981) found no substantial differences -between the use of different stemmers for English. Harman (Harman, 1991) -challenged the effectiveness of stemming altogether, when she reported no -substantial differences between using and not using stemming in a series of -experiments. But later work has been more positive. Krovetz (Krovetz, 1995), for example, -reported small but significant improvements with stemming over a range of test -collections. -

- -

-Of course, all these experiments assume some IR model which will use stemming in -a particular way, and will measure just those features that tests collections -are, notoriously, able to measure. We might imagine an IR system where the users -have been educated in the advantages and disadvantages to be expected from -stemming, and are able to flag individual search terms to say whether or not -they are to be used stemmed or unstemmed. Stemming sometimes improves, -occasionally degrades, search performance, and this would be the best way of -using it as an IR facility. Again stemming helps regularise the IR vocabulary, -which is very useful when preparing a list of terms to present to a user as -candidates for query expansion. But this advantage too is difficult to quantify. -

- -

-An evaluative comparison between the Lovins and later stemmers lies in any case -outside the scope of this paper, but it is important to -bear in mind that it is not a straightforward undertaking. -

- -

The Lovins Stemmer

- -

-Structurally, the Lovins stemmer is in four parts, collected together in -four Appendices A, B, C and D in her paper. Part A is a list of 294 -endings, each with a letter which identifies a condition for whether or -not the ending should be removed. (I will follow Lovins in using ‘ending’ -rather than ‘suffix’ as a name for the items on the list.) -Part A therefore looks like this: -

- -
- .11.
- alistically   B
- arizability   A
- izationally   B
- .10.
- antialness   A
- arisations   A
- arizations   A
- entialness   A
- .09.
- allically   C
- antaneous   A
- antiality   A
- . . .
-
- .01.
- a   A
- e   A
- i   A
- o   A
- s   W
- y   B -
- -

-Endings are banked by length, from 11 letters down to 1. Each bank is tried -in turn until an ending is found which matches the end of the word to be -stemmed and leaves a stem which satisfies the given condition, when the -ending is removed. For example condition C says that the stem must have at -least 4 letters, so bimetallically would lose allically leaving a -stem bimet of length 5, but metallically would not reduce to -met, since its length is only 3. -

- -

-There are 29 such conditions, called A to Z, AA, BB and CC, and they -constitute part B of the stemmer. Here they are (* stands for any letter): -

- -
- -
A No restrictions on stem -
B Minimum stem length = 3 -
C Minimum stem length = 4 -
D Minimum stem length = 5 -
E Do not remove ending after e -
F Minimum stem length = 3 and do not remove ending after e -
G Minimum stem length = 3 and remove ending only after f -
H Remove ending only after t or ll -
I Do not remove ending after o or e -
J Do not remove ending after a or e -
K Minimum stem length = 3 and remove ending only after l, i or -u*e -
L Do not remove ending after u, x or s, unless s follows -o -
M Do not remove ending after a, c, e or m -
N Minimum stem length = 4 after s**, elsewhere = 3 -
O Remove ending only after l or i -
P Do not remove ending after c -
Q Minimum stem length = 3 and do not remove ending after l or -n -
R Remove ending only after n or r -
S Remove ending only after dr or t, unless t follows t -
T Remove ending only after s or t, unless t follows o -
U Remove ending only after l, m, n or r -
V Remove ending only after c -
W Do not remove ending after s or u -
X Remove ending only after l, i or u*e -
Y Remove ending only after in -
Z Do not remove ending after f -
AA Remove ending only after d, f, ph, th, l, er, or, es or t -
BB Minimum stem length = 3 and do not remove ending after met or -ryst -
CC Remove ending only after l -
-
- -

-There is an implicit assumption in each condition, A included, that the minimum -stem length is 2. -

- -

-This is much less complicated than it seems at first. Conditions A to D -depend on a simple measure of minimum stem length, and E and F are slight -variants of A and B. Out of the 294 endings, 259 use one of these -6 conditions. The remaining 35 endings use the other 23 conditions, so -conditions G, H ... CC have less than 2 suffixes each, on average. What is -happening here is that Lovins is trying to capture a rule which gives a -good removal criterion for one ending, or a small number of similar -endings. She does not explain the thinking behind the conditions, but it is -often not too difficult to reconstruct. Here for example are the last few -conditions with their endings, -

- -
- -Y (early,   ealy,   eal,   ear). collinearly, multilinear are -stemmed.
- -Z (eature). misfeature does not lose eature.
- -AA (ite). acolouthite, hemimorphite lose ite, ignite and -requite retain it.
- -BB (allic,   als,   al). Words ending metal, crystal retain -al.
- -CC (inity). crystallinity → crystall, but affinity, -infinity are unaltered. - -
- -

-Part C of the Lovins stemmer is a set of 35 transformation rules used to -adjust the letters at the end of the stem. These rules are invoked after the -stemming step proper, irrespective of whether an ending was actually -removed. Here are about half of them, with examples to show the type of -transformation intended (letters in square brackets indicate the full form -of the words), -

- -
- -
1) bb →     b rubb[ing] → rub -
ll → l controll[ed] → control -
mm → m trimm[ed] → trim -
rr → r abhorr[ing] → abhor -
2) iev → ief believ[e] → belief -
3) uct → uc induct[ion] → induc[e] -
4) umpt → um consumpt[ion] → consum[e] -
5) rpt → rb absorpt[ion] → absorb -
6) urs → ur recurs[ive] → recur -
7a) metr → meter     parametr[ic] → paramet[er] -
8) olv → olut dissolv[ed] → dissolut[ion] -
11) dex → dic index → indic[es] -
16) ix → ic matrix → matric[es] -
18) uad → uas persuad[e] → persuas[ion] -
19) vad → vas evad[e] → evas[ion] -
20) cid → cis decid[e] → decis[ion] -
21) lid → lis elid[e] → elis[ion] -
31) ert → ers convert[ed] → convers[ion] -
33) yt → ys analytic → analysis -
34) yz → ys analyzed → analysed -
-
- -

-Finally, part D suggests certain relaxed matching rules between query terms -and index terms when the stemmer has been used to set up an IR system, but -we can regard that as not being part of the stemmer proper. -

- -

The Lovins stemmer in Snowball

- -

-Snowball is a string processing language designed with the idea of making -the definition of stemming algorithms much more rigorous. The Snowball -compiler translates a Snowball script into a thread-safe ANSI C module, -where speed of execution is a major design consideration. The resulting -stemmers are pleasantly fast, and will process one million or so words a -second on a high-performance modern PC. The Snowball website (3) gives a -full description of the language, and also presents stemmers for a range of -natural languages. Each stemmer is written out as a formal algorithm, with -the corresponding Snowball script following. The algorithm definition acts -as program comment for the Snowball script, and the Snowball script gives a -precise definition to the algorithm. The ANSI C code with the -same functionality can also be inspected, and sample vocabularies in source -and stemmed form can be used for test purposes. -An essential function of -the Snowball script is therefore comprehensibility — it should be fully understood -by the reader of the script, and Snowball has been designed with this in mind. -It contrasts interestingly in this respect with a system like Perl. -Perl has a very big definition. Writing your own scripts in Perl is easy, -after the initial learning hurdle, but understanding other scripts can be -quite hard. The size of the language means that there are many different -ways of doing the same thing, which gives programmers the opportunity of -developing highly idiosyncratic styles. Snowball has a small, tight -definition. Writing Snowball is much less easy than writing Perl, but on -the other hand once it is written it is fairly easy to understand -(or at least one hopes that it is). This is -illustrated by the Lovins stemmer in Snowball, which is given in Appendix -1. There is a very easy and natural correspondence -between the different parts of the stemmer definition in Lovins' original -paper and their Snowball equivalents. -For example, the Lovins conditions A, B ... CC code up very neatly -into routines with the same name. Taking condition L, -

- -
- L   Do not remove ending after u, x or s, unless s follows - o -
- -

-corresponds to -

- -[% highlight(" - define L as ( test hop 2 not 'u' not 'x' not ('s' not 'o') ) -") %] - -

-When  L  is called, we are the right end of the stem, moving left towards the -front of the word. Each Lovins condition has an implicit test for a stem of -length 2, and this is done by [% highlight_inline('test hop 2') %], which sees if it is possible to -hop two places left. If it is not, the routine immediately returns with a -false signal, otherwise it carries on. It tests that the character at the -right hand end is not u, and also not x, and also not s following a letter -which is not o. This is equivalent to the Lovins condition. Here is not of -course the place to give the exact semantics, but the you can quickly get -the feel of the language by comparing the 29 Lovins conditions with their -Snowball definitions. -

- -

-Something must be said about the [% highlight_inline('among') %] feature of Snowball however, -since this is central to the efficient implementation of stemmers. It is -also the one part of Snowball that requires just a little effort to -understand. -

- -

-At its simplest, [% highlight_inline('among') %] can be used to test for alternative strings. The -[% highlight_inline('among') %]s used in the definition of condition AA and the  undouble -routine have this form. In Snowball you can write -

- -[% highlight(" - 'sh' or 's' or 't' 'o' or 'i' 'p' -") %] - -

-which will match the various forms shop, ship, sop, sip, top, tip. The -order is important, because if [% highlight_inline("'sh'") %] and [% highlight_inline("'s'") %] are swapped over, the -[% highlight_inline("'s'") %] would match the first letter of ship, while [% highlight_inline("'o'") %] or [% highlight_inline("'i'") %] -would fail to match with the following [% highlight_inline("'h'") %] — in other words the pattern -matching has no backtracking. But it can also be written as -

- -[% highlight(" - among('sh' 's' 't') among('i' 'o') 'p' -") %] - -

-The order of the strings in each [% highlight_inline('among') %] is not important, because the -match will be with the longest of all the strings that can match. In -Snowball the implementation of [% highlight_inline('among') %] is based on the binary-chop idea, -but has been carefully optimised. For example, in the Lovins stemmer, the -main [% highlight_inline('among') %] in the  endings  routine has 294 different strings of average -length 5.2 characters. A search for an ending involves accessing a number -of characters within these 294 strings. The order is going to be -Klog2294, or 8.2K, where K is a number that one hopes will -be small, although one must certainly expect it to be greater than 1. It -turns out that, for the successive words of a standard test vocabulary, -K averages to 1.6, so for each word there are about 13 character -comparisons needed to determine whether it has one of the Lovins endings. -

- -

-Each string in an [% highlight_inline('among') %] construction can be followed by a routine name. The -routine returns a true/false signal, and then the [% highlight_inline('among') %] searches for the -longest substring whose associated routine gives a true signal. A string not -followed by a routine name can be thought of as a string which is associated -with a routine that does nothing except give a true signal. This is the way -that the [% highlight_inline('among') %] in the  endings  routine works, where indeed every string is -followed by a routine name. -

- -

-More generally, lists of strings in the [% highlight_inline('among') %] construction can be followed -by bracketed commands, which are obeyed if one of the strings in the list is -picked out for the longest match. The syntax is then -

- -
-    among( S11 S12 ... (C1)
-           S21 S22 ... (C2)
-           ...
-
-           Sn1 Sn2 ... (Cn)
-         )
-
- -

-where the  Sij  are strings, optionally followed by their routine names, -and the  Ci  are Snowball command sequences. The semantics is a bit -like a switch in C, where the switch is on a string rather than a numerical -value: -

- -
-    switch(...) {
-        case S11: case S12: ... C1; break;
-        case S21: case S22: ... C2; break;
-        ...
-
-        case Sn1: case Sn2: ... Cn; break;
-    }
-
- -

-The [% highlight_inline('among') %] in the  respell  routine has this form. -

- -

-The full form however is to use [% highlight_inline('among') %] with a preceding [% highlight_inline('substring') %], with -[% highlight_inline('substring') %] and [% highlight_inline('among') %] possibly separated by further commands. -[% highlight_inline('substring') %] -triggers the test for the longest matching substring, and the [% highlight_inline('among') %] then -causes the corresponding bracketed command to be obeyed. At a simple -level this can be used to cut down the size of the code, in that -

- -
-    substring C among( S11 S12 ... (C1)
-                       S21 S22 ... (C2)
-                       ...
-
-                       Sn1 Sn2 ... (Cn)
-                     )
-
- -

-is a shorter form of -

- -
-    among( S11 S12 ... (C C1)
-           S21 S22 ... (C C2)
-           ...
-
-           Sn1 Sn2 ... (C Cn)
-         )
-
- -

-More importantly, [% highlight_inline('substring') %] and [% highlight_inline('among') %] can work in different contexts. For -example, [% highlight_inline('substring') %] could be used to test for the longest string, matching from -right to left, while the commands in the [% highlight_inline('among') %] could operate in a left to -right direction. In the Lovins stemmer, [% highlight_inline('substring') %] is used in this style: -

- -[% highlight(" - [substring] among ( ... ) -") %] - -

-The two square brackets are in fact individual commands, so before the [% highlight_inline('among') %] -come three commands. [% highlight_inline('[') %] sets a lower marker, [% highlight_inline('substring') %] is obeyed, searching -for the strings in the following among, and then [% highlight_inline(']') %] sets an upper marker. -The region between the lower and upper markers is called the slice, and this -may subsequently be copied, replaced or deleted. -

- -

-It was possible to get the Lovins stemmer working in Snowball very quickly. -The Sourceforge versions (1) could be used to get the long list of endings and -to help with the debugging. There was however one problem, that rules 24 and -30 of part C conflicted. They are given as -

- -
- 24) end → ens except following s
- ...
- 30) end → ens except following m -
- -

-This had not been noticed in the Sourceforge implementations, but -immediately gave rise to a compilation error in Snowball. Experience -suggested that I was very unlikely to get this problem resolved. Only a few -months before, I had hit a point in a stemming algorithm where -something did not quite make sense. The algorithm had been published just a -few years ago, and contacting one at least of the authors was quite easy. -But I never sorted it out. The author I traced was not au fait -with the linguistic background, and the language expert had been swallowed -up in the wilds of America. So what chance would I have here? Even if I was -able to contact Lovins, it seemed to me inconceivable that she would have -any memory of, or even interest in, a tiny problem in a paper which she -published 33 years ago. But the spirit of academic enquiry forced me to -venture the attempt. After pursuing a number of red-herrings, email contact -was finally made. -

- -

-Her reply was a most pleasant surprise. - -

-

- ... The explanation is both mundane and exciting. You have just found - a typo in the MT article, which I was unaware of all these years, and I - suspect has puzzled a lot of other people too. The original paper, an - MIT-published memorandum from June 1968, has rule 30 as -

- -

-       ent → ens except following m -

- -

- and that is undoubtedly what it should be ... -

-
- -

An analysis of the Lovins stemmer

- -

-It is very important in understanding the Lovins stemmer to know something -of the IR background of the late sixties. In the first place there was an -assumption that IR was all, or mainly, about the retrieval of -technical scientific papers, and research projects were set up accordingly. -I remember being shown, in about 1968, a graph illustrating the -‘information explosion’, as it was understood at the time, which showed -just the rate of growth of publications of scientific papers in various -different domains over the previous 10 or 20 years. Computing resources -were very precious, and they could not be wasted by setting up IR systems -for information that was, by comparison, merely frivolous (articles in -popular magazines, say). And even in 1980, when I was working in IR, the -data I was using came from the familiar, and narrow, scientific domain. -Lovins was working with Project Intrex (Overhage, 1966), where the data came from -papers in materials science and engineering. -

- -

-Secondly, the idea of indexing on every word in a document, or even looking -at every word before deciding whether or not to put it into an index, would -have seemed quite impractical, even though it might have been recognised as -theoretically best. In the first place, the computing resources necessary to -store and analyse complete documents in machine readable form were absent, and in the -second, the rigidities of the printing industry almost guaranteed that one -would never get access to them. -A stemmer, therefore, would be seen as something not -applied to general text but to certain special words, and in the case of the -Lovins stemmer, the plan was to apply it to the subject terms that were used -to categorize each document. Subsequently it would be used with each word -in a query, where it -was hoped that the vocabulary of the queries would match the vocabulary of -the catalogue of subject terms. -

- -

-This accounts for: — -

- -
    -
  1. The emphasis on the scientific vocabulary. This can be seen in the -endings, which include oidal, on, oid, ide, for words like colloidal, -proton, spheroid, nucleotide. It can be seen in the transformation rules, -with their concern for Greek sis and Latin ix suffixes. And also it can be -seen in in the word samples of the paper (magnesia, magnesite, magnesian, -magnesium, magnet, magnetic, magneto etc. of Fig. 2). -
    2. - -
  2. The slight shortage of plural forms. The subject terms would naturally -have been mainly in the singular, and one might also expect the same of -query terms. -
    3. - -
  3. The surprising shortness of the allowed minimum stems — usually 2 -letters. A controlled technical vocabulary will contain longish words, and -the problem of minimum stem lengths only shows up with shorter words. -
    4. -
- -

-If we take a fairly ordinary vocabulary of modern English, derived from -non-scientific writing, it is interesting to see how much of the Lovins -stemmer does not actually get used. We use vocabulary V, derived from a -sample of modern texts from Project Gutenberg (4). V can be inspected -at (5). It contains 29,401 words, and begins -

- a   aback   abandon   abandoned   abandoning   abandonment   - abandons   abasement   abashed   abate   abated ... -
-We find that 22,311, or about 76%, of the words in V have one of the -294 endings removed if passed through the Lovins stemmer. Of this 76%, over a -half (55%) of the removals are done by just five of the endings, the breakdown -being, -
- s (13%)   ed (12%)   e (10%)   ing (10%)   es (6%)   y (4%) -
-If, on the other hand, you look at the least frequent endings, 51% of them -do only 1.4% of the removals. So of the ones removed, half the endings in -V -correspond to 2% of the endings in the stemmer, and 1.4% of the endings in -V -correspond to half the endings in the stemmer. In fact 62 of the endings -(about a fifth) do not lead to any ending removals in V at all. These are -made up of the rarer ‘scientific’ endings, such as aroid and oidal, and -long endings, such as alistically and entiality. -

- -

-This helps explain why the Porter and Lovins stemmers behave in a fairly -similar way despite the fact that they look completely different — it is -because most of the work is being done in just a small part of the stemmer, -and in that part there is a lot of overlap. Porter and Lovins stem 64% of -the words in V identically, which is quite high. (By contrast, an -erroneous but plausibly written Perl script -advertised on the Web as an implementation of the Porter stemmer -still proves to stem only 86% of the words in V -to the same forms that are produced by the Porter stemmer.) -

- -

-A feature of the Lovins stemmer that is worth looking at in some detail is -the transformation rules. People who come to the problem of stemming for -the first time usually devote a lot of mental energy to the issue of -morphological irregularity which they are trying to address. -

- -

-A good starting point is the verbs of English. Although grammatically -complex, the morphological forms of the English verb are few, and are -illustrated by the pattern harm, harms, harming, harmed, where the basic -verb form adds s, ing and ed to make the other three forms. There are -certain special rules: to add s to a verb ending ss an e is inserted, -so pass becomes passes, and adding e and ing replaces a final e of -the verb (love to loves), and can cause consonant doubling (hop to -hopped), but -apart from this all verbs in the language follow the basic pattern with the -exception of a finite class of irregular verbs. -In a regular verb, the addition of ed to the basic verb creates both the -past form (‘I harmed’) and the p.p. (past participle) form (‘I have -harmed’). An irregular verb, such as ring, forms its past in some other -way (‘I rang’), and may have a distinct p.p. (‘I have rung’). -The irregular verbs have a -different past form, and sometimes a separate p.p. form. -It is easy to think up more examples, - -

-
stem past p.p. -
-
ring rang rung -
rise rose risen -
sleep slept slept -
fight       fought       fought -
come came come -
go went gone -
hit hit hit -
- -How many of these verbs are there altogether? On 20 Jan 2000, in order to -test the hypothesis that the number is consistently over-estimated, I asked -this question in a carefully worded email to a mixed group of -about 50 -well-educated -work colleagues (business rather than academic people). Ten of them replied, -and here are the -guesses they made: - -
- 20,   25,   25,   50,   180,   200,   426,   25000,   10%,   20% -
- -The last two numbers mean 10% and 20% of all English verbs. -My hypothesis was of course wrong. The truth is that most people have no -idea at all how many irregular verbs there are in English. -In -fact there are around 135 (see section 3.3 of Palmer, 1965). -If a stemming algorithm handles suffix removal -of all regular verbs correctly, the question arises as to whether it is -worth making it do the same for the irregular forms. Conflating fought and -fight, for example, could be useful in IR queries about boxing. It seems -easy: you make a list of the irregular verbs and create a mapping of the -past and p.p. forms to the main form. We can call the process -English verb respelling. But when you try it, numerous problems arise. Are -forsake, beseech, cleave really verbs of contemporary English? If so, what -is the p.p. of cleave? -Or take the verb stride, which is common enough. What is its p.p.? My -Concise Oxford English Dictionary says it is stridden (6), but have we ever -heard this word used? (‘I have stridden across the paving.’) -

- -

-To compose a realistic list for English verb respelling we therefore need to -judge word rarity. But among the commoner verb forms even greater problems -arise because of their use as homonyms. A rose is a type of flower, so -is it wise -to conflate rose and rise? Is it wise to conflate -saw and see when saw can mean a cutting instrument? -

- -

-We suddenly get to -the edge of what it is useful to include in a stemming algorithm. So long as -a stemming algorithm is built around general rules, the full impact of the -stemmer on a vocabulary need not be studied too closely. It is sufficient to -know that the stemmer, judiciously used, improves retrieval performance. But -when we look at its effect on individual words these issues can no longer be -ignored. To build even a short list of words into a stemmer for special -treatment takes us into the area of the dictionary-based stemmer, and the -problem of determining, for a pair of related words in the dictionary, a -measure of semantic similarity which tells us whether or not the words -should be conflated together. -

- -

-About half the transformation rules in the Lovins stemmer deal with a -problem which is similar to that posed by the irregular verbs of English, -and which ultimately goes back to the irregular forms of second conjugation -verbs in Latin. We can call it Latin verb respelling. Verbs like -induce, consume, commit are perfectly regular in modern English, but -the adjectival and noun forms induction, consumptive, commission that -derive from them correspond to p.p. forms in Latin. -You can see the descendants of these Latin irregularities -in modern Italian, which has commettere with p.p. -commesso, like our commit and commission, and scendere with -p.p. sceso like our ascend and ascension (although scendere -means ‘to go down’ rather than ‘to go up’). -

- -

-Latin verb respelling often seems to be more the territory of a stemmer than -English verb respelling, presumably because Latin verb irregularities -correspond to consonantal changes at the end of the stem, where the -stemmer naturally operates, while English verb irregularities more often -correspond to vowel changes in the middle. Lovins was no doubt -particularly interested in Latin verb respelling because so many of the -words affected have scientific usages. -

- -

-We can judge that Latin verb respellings constitute a small set because the -number of second conjugation verbs of Latin form a small, fixed set. Again, -looking at Italian, a modern list of irregular verbs contains 150 basic forms -(nearly all of them second conjugation), not unlike the number of forms in -English. Extra verbs are formed with prefixes. Corresponding English words -that exhibit the Latin verb respelling problem -will be a subset of this system. In fact we -can offer a Snowball script that does the Latin verb respelling with more -care. It should be invoked, in the Porter stemmer, after removal of ive or -ion endings only, - -[% highlight(" -define prefix as ( - - among ( - - 'a' 'ab' 'ad' 'al' 'ap' 'col' 'com' 'con' 'cor' 'de' - 'di' 'dis' 'e' 'ex' 'in' 'inter' 'o' 'ob' 'oc' 'of' - 'per' 'pre' 'pro' 're' 'se' 'sub' 'suc' 'trans' - ) atlimit -) - -define second_conjugation_form as ( - - [substring] prefix among ( - - 'cept' (<-'ceiv') //-e con de re - 'cess' (<-'ced') //-e con ex inter pre re se suc - 'cis' (<-'cid') //-e de (20) - 'clus' (<-'clud') //-e con ex in oc (26) - 'curs' (<-'cur') // re (6) - 'dempt' (<-'deem') // re - 'duct' (<-'duc') //-e de in re pro (3) - 'fens' (<-'fend') // de of - 'hes' (<-'her') //-e ad (28) - 'lis' (<-'lid') //-e e col (21) - 'lus' (<-'lud') //-e al de e - 'miss' (<-'mit') // ad com o per re sub trans (29) - 'pans' (<-'pand') // ex (23) - 'plos' (<-'plod') //-e ex - 'prehens' (<-'prehend') // ap com - 'ris' (<-'rid') //-e de (22) - 'ros' (<-'rod') //-e cor e - 'scens' (<-'scend') // a - 'script' (<-'scrib') //-e de in pro - 'solut' (<-'solv') //-e dis re (8) - 'sorpt' (<-'sorb') // ab (5) - 'spons' (<-'spond') // re (25) - 'sumpt' (<-'sum') // con pre re (4) - 'suas' (<-'suad') //-e dis per (18) - 'tens' (<-'tend') // ex in pre (24) - 'trus' (<-'trud') //-e ob (27) - 'vas' (<-'vad') //-e e (19) - 'vers' (<-'vert') // con in re (31) - 'vis' (<-'vid') //-e di pro - ) -) -") %] - -This means that if suas, for example, is preceded by one of the strings -in [% highlight_inline('prefix') %], and there is nothing more before the prefix string (which is -what the -[% highlight_inline('atlimit') %] -command tests), it is replaced by suad. So dissuas(ion) goes to -dissuad(e) -and persuas(ive) to persuad(e). Of course, asuas(ion), absuas(ion), -adsuas(ion) and so on would get the same treatment, but not being words of -English that does not really matter. The corresponding Lovins rules are -shown in brackets. -This is not quite the end -of the story, however, because the Latin forms ex + cedere (‘go -beyond’) pro + cedere (‘go forth’), and sub + cedere -(‘go after’) give rise to verbs which, -by an oddity of English orthography, have an extra letter e: exceed, proceed, -succeed. They can be sorted out in a final respelling step: -

- -[% highlight(" -define final_respell as ( - - [substring] atlimit among( - - 'exced' (<-'exceed') - 'proced' (<-'proceed') - 'succed' (<-'succeed') - /* extra forms here perhaps */ - ) -) -") %] - -

-As you might expect, close inspection of this process creates doubts in -the same way as for English verb respelling. (Should we really conflate -commission and commit? etc.) -

- -

-The other transformation rules are concerned with unusual plurals, mainly -of Latin or Greek origin, er and re differences, as in parameter and -parametric, and the sis/tic connection of certain words of Greek origin: -analysis/analytic, paralysis/paralytic ... (rule 33), and -hypothesis/hypothetic, kinesis/kinetic ... (rule 32). Again, these -irregularities might be tackled by forming explicit word lists. Certainly -rule 30, given as, -

- -
- ent → ens except following m, -
- -

-goes somewhat wild when given a general English vocabulary (dent becomes -dens for example), although it is the only rule that might be said to -have a damaging effect. -

- -

A Lovins shape for the Porter stemmer

- -

-The 1980 paper (Porter, 1980) may be said to define the ‘pure’ Porter stemmer. -The stemmer distributed at (7) can be called the ‘real’ Porter -stemmer, and differs from the pure stemmer in three small respects, which -are carefully explained. This disparity does not require much excuse, -since the oldest traceable encodings of the stemmer have always contained -these differences. There is also a revised stemmer for English, called -‘Porter2’ and still subject to slight changes. Unless otherwise stated, -it is the real Porter stemmer which is being studied below. -

- -

-The Porter stemmer differs from the Lovins stemmer in a number of -respects. In the first place, it only takes account of fairly common -features of English. So rare suffixes are not included, and there is no -equivalent of Lovins’ transformation rules, other than her rule (1), the -undoubling of terminal double letters. Secondly, it removes suffixes only -when the residual stem is fairly substantial. Some suffixes are removed -only when at least one syllable is left, and most are removed only when at least two -syllables are left. (One might say that this is based on a guess about the -way in which the meanings of a stem is related to its length in syllables (8).) -The Porter stemmer is therefore ‘conservative’ in its removal -of suffixes, or at least that is how it has often been described. Thirdly, -it removes suffixes in a series of steps, often reducing a compound suffix -to its first part, so a step might reduce ibility to ible, where -ibility is thought of as being ible + ity. Although the -description of the whole stemmer is a bit complicated, the total number of -suffixes is quite small — about 60. -

- -

-The Porter stemmer has five basic steps. Step 1 removes an -inflectional suffix. There are only three of these: ed and ing, which are -verbal, and s, which is verbal (he sings), plural (the songs) or possessive -(the horses’ hooves), although the rule for s removal is the same in all -three cases. Step 1 may also restore an e (hoping → hope), undouble a -double letter pair (hopping → hop), or change y to i (poppy → -poppi, to match with poppies → poppi.) Steps 2 to 4 remove derivational -suffixes. So -ibility may reduce to ible in step 2, and ible itself may be removed in step -4. Step 5 is for removing final e, and undoubling ll. -

- -

-A clear advantage of the Lovins stemmer over the Porter stemmer is speed. -The Porter stemmer has five steps of suffix removal to the Lovins stemmer’s -one. It is instructive therefore to try and cast the Porter stemmer into -the shape of the Lovins stemmer, if only for the promise of certain speed -advantages. As we will see, we learn a few other things from the exercise -as well. -

- -

-First we need a list of endings. The Lovins endings were built up by hand, -but we can construct a set of endings for the Porter stemmer by writing an -ending generator that follows the algorithm definition. From an analysis of -the suffixes in steps 2 to 4 of the Porter stemmer we can construct -the following diagram: -

- -Diagram showing ending combinations for the Porter stemmer - -

-This is not meant to be a linguistic analysis of the suffix structure of -English, but is merely intended to show how the system of endings works in -the stemming algorithm. Suffixes combine if their boxes are connected by -an arrow. So ful combines with ness to make fulness. - -

- ful + ness → fulness -
- -The combination is not always a concatenation of the strings -however, for we have, - -
- able + ity → ability
- able + ly → ably
- ate + ion → ation
- ible + ity → ibility
- ible + ly → ibly
- ize + ate + ion → ization -
- -The path from ize to ion goes via ate, so we can form ization, but there is -no suffix izate. Three of the suffixes, ator, ance and ence, do not connect -into the rest of the diagram, and ance, ence also appear in the forms -ancy, ency. The letter to the left of the box is going to be the -condition for the -removal of the suffix in the box, so - -
-      B +-------+ n
-        |  ism  |
-        +-------+
-
- -means that ism will be removed if it follows a stem that satisfies -condition B. On the right of the box is either n, v or hyphen. n means the -suffix is of noun type. So if a word ends ism it is a noun. v means verb -type. hyphen means neither: ly (adverbial) and ful, ous (adjectival) are of -this type. If a suffix is a noun type it can have a plural form (criticism, -criticisms), so we have to generate isms as well as ism. Again, the -combining is not just concatenation, - -
- ity + s → ities
- ness + s → nesses -
- -If a suffix has v type, it has s, ed and ing forms, - -
- ize + s → izes
- ize + ed → ized
- ize + ing → izing -
- -Type v therefore includes type n, and we should read this type as ‘verb or -noun’, rather than just ‘verb’. For example, condition, with suffix ion, is -both verb (‘They have been conditioned to behave like that’) and noun -(‘It is subject to certain conditions’). -

- -

-The diagram is therefore a scheme for generating combined derivational -suffixes, each combination possibly terminated with an inflectional suffix. -A problem is that it contains a loop in - -

- ize → ate → ion → al → ize → ... -
- -suggesting suffixes of the form izationalizational... We break the loop by -limiting the number of joined derivational suffixes of diagram 1 to four. -(Behaviour of the Porter stemmer shows that removal of five combined -derivation suffixes is never desirable, even supposing five ever combine.) -We can then generate 181 endings, with their removal codes. But 75 of these -suffixes do not occur as endings in V, and they can be eliminated as rare -forms, leaving 106. Alphabetically, the endings begin, - -
- abilities   ability   able   ables   ably   al   alism   - (alisms)   alities   ality   alization   (alizationed)   - (alizationing)   (alizations)   alize   alized   (alizer)   - (alizered)   (alizering)   (alizers)   (alizes)   (alizing)   - ally   alness   (alnesses)   als   ance   ances   ancies   - ancy ... -
- -The eliminated rare forms are shown bracketed. -

- -

-The 106 endings are arranged in a file as a list of strings followed by -condition letter, - -

-    'abilities'     B
-    'ability'       B
-    'able'          B
-    'ables'         B
-    'ably'          B
-    'al'            B
-    ....
-
- -This ending list is generated by running the ANSI C program shown in -Appendix 4, and line-sorting the result into a file, -and this file is called in by the [% highlight_inline('get') %] directive in the Snowball script of -Appendix 2, which is the Porter stemming algorithm laid out in the style of -the Lovins algorithm. In fact, precise equivalence cannot be achieved, but -in V only 137 words stem differently, which is 0.4% of V. There are 10 -removal conditions, compared with Lovins’ 29, and 11 transformation or -respelling rules, compared with Lovins’ 35. We can describe the process in -Lovins style, once we have got over a few preliminaries. -

- -

-We have to distinguish y as a vowel from y as a consonant. We treat initial -y, and y before vowel, as a consonant, and make it upper case. Thereafter -a, e, i, o, u and y are vowels, and the other lower case letters and Y are -consonants. If [C] stands for zero or more consonants, C for one or more -consonants, and V for one or more vowels, then a stem of shape [C]VC has -length 1s (1 syllable), of shape [C]VCVC length 2s, and so on. -

- -

-A stem ends with a short vowel if the ending has the form cvx, where c is a -consonant, v a vowel, and x a consonant other than w, x or Y. -(Short vowel endings with ed and ing imply loss of an e from -the stem, as in removing = remove + ing.) -

- -

-Here are the removal conditions, -

- -
- -
A   Minimum stem length = 1s -
B Minimum stem length = 2s -
C Minimum stem length = 2s and remove ending only after s or t -
D Minimum stem length = 2s and do not remove ending after m -
E Remove ending only after e or ous after minimum stem length 1s -
F Remove ending only after ss or i -
G Do not remove ending after s -
H Remove ending only if stem contains a vowel -
I Remove ending only if stem contains a vowel and does not end in e -
J Remove ending only after ee after minimum stem length 1s -
-
- -

-In condition J the stem must end ee, and the part of the stem before the -ee must have minimum length 1s. Condition E is similar. -

- -

-Here are the respelling rules, defined with the help of the removal -conditions. In each case, the stem being tested does not include the string -at the end which has been identified for respelling. - -

-
1)   Remove e if A, or if B and the stem does not end with a short vowel -
2) Remove l if B and the stem ends with l -
3) enci/ency → enc if A, otherwise → enci -
4) anci/ancy → anc if A, otherwise → anci -
5) ally → al if A, otherwise → alli -
6) ently → ent if A, otherwise → entli -
7) ator → at if A -
8) logi/logy → log if A, otherwise → log -
9) bli/bly → bl if A, otherwise → bli -
10) bil → bl if stem ends vowel after A -
11) y/Y → i if stem contains a vowel -
- -The 106 endings are distributed among conditions A to E as A(5), B(87), -C(8), D(3) and E(1). F to J deal with the purely inflectional endings: F -with es, G with s, H with ing and ings, I with ed and J with d. -There is however one point at which the Lovins structure breaks down, in that -removal of ed and ing(s) after conditions I and H requires a special -adjustment that cannot be left to a separate transformation rule. It is to -undouble the last letter, and to restore a final e if the stem has length 1s -and ends with a short vowel (so shopping loses a p and becomes shop, -sloping gains an e and becomes slope.) -

- -

-The Porter stemmer cast into this form runs significantly faster than the -multi-stage stemmer — about twice as fast in tests with Snowball. -

- -

-We will call the Porter stemmer P, the Lovins stemmer L, and this Lovins -version of the Porter stemmer LP. As we have said, P and LP are not identical, -but stem 137 of the 29,401 words of V differently. -

- -

-A major cause of difference is unexpected suffix combinations. These can be -subdivided into combinations of what seem to be suffixes but are not, and -rare combinations of valid suffixes. -

- -

-The first case is illustrated by the word disenchanted. P stems this to -disench, first taking off suffix ed, and then removing ant, which is -a suffix in English, although not a suffix in this word. P also stems -disenchant to disench, so the two words disenchant and -disenchanted are conflated by P, even though they make an error in the -stemming process. But ant is a noun type suffix, and so does not combine -with ed. anted is therefore omitted from the suffix list of LP, so LP -stems disenchanted to disenchant, but disenchant to disench. -

- -

-This illustrates a frequently encountered problem in stemming. S1 -and S2 are suffixes of a language, but the combination -S1S2 is -not. A word has the form xS1, where x is some string, but in -xS1, S1 is not actually a suffix, but part of the stem. -S2 is a valid suffix for this word, so xS1S2 is -another word in the language. An algorithmic stemmer stems xS1 to -x in error. If presented with xS1S2 it can either -(a) stem it to xS1, knowing S1 cannot be a suffix in -this context, or (b) stem it to x, ignoring the knowledge to be -derived from the presence of S2. (a) gives the correct stemming -of at least xS1S2, although the stemming of xS1 -will be wrong, while (b) overstems both words, but at least achieves -their conflation. In other words (a) fails to conflate the two forms, but -may achieve correct conflations of xS1S2 with similar forms -xS1S3, xS1S4 etc., while (b) conflates -the two forms, but at the risk of additional false conflations. Often a study -of the results of a stemming strategy on a sample vocabulary leads one to -prefer approach (b) to (a) for certain classes of ending. This is -true in particular of the inflectional endings of English, which is why the -removals in step 1 of P are not remembered in some state variable, which -records whether the ending just removed is verb-type, noun-or-verb-type etc. -On balance you get better results by throwing that information away, and then -the many word pairs on the pattern of disenchant / disenchanted will -conflate together. -

- -

-Other examples from V can be given: in misrepresenting, ent is -not a suffix, and enting not a valid suffix combination); in -witnessed, ness is not a suffix, and nessed not a valid -suffix combination. -

- -

-This highlights a disadvantage of stemmers that work with a fixed list of -endings. To get the flexibility of context-free ending removal, we need to -build in extra endings which are not grammatically correct (like anted = -ant + ed), and this adds considerably to the burden of constructing -the list. In fact L does not include anted, but it does include for -example antic (ant + ic), which may be serving a similar -purpose. -

- -

-For the second case, the rare combinations of valid suffixes, one may instance -ableness. Here again the multi-step stemmer makes life easier. P removes -ness in step 3 and able in step 4, but without making any necessary -connection. L has ableness as an ending, dictionaries contain many -ableness words, and it is an easy matter to make the connection across from -able to ness in diagram 1 and generate extra endings. Nevertheless the -ending is very rare in actual use. For example, Dickens’ Nicholas Nickleby -contains no examples, Bleak House contains two, in the same sentence: -

- -
- I was sure you would feel it yourself and would excuse the - reasonableness of MY feelings when coupled with the known - excitableness of my little woman. -
- -

-reasonableness is perhaps the commonest word in English of this form, and -excitableness (instead of excitability) is there for contrast. Thackeray’s -Vanity Fair, a major source in testing out P and Porter2, contains one -word of this form, charitableness. One may say of this word that it is -inevitably rare, because it has no really distinct -meaning from the simpler charity, but that it has to be formed by adding -ableness rather than ability, because the repeated ity in charity + -ability is morphologically unacceptable. Other rare combinations are -ateness, entness -and eds (as in intendeds and beloveds). -fuls is another interesting case. The ful suffix, usually adjectival, -can sometimes create nouns, giving plurals such as mouthfuls and -spoonfuls. But in longer words sful is a more ‘elegant’ plural -(handbagsful, dessertspoonsful). -

- -

-These account for most of the differences, but there are a few others. -

- -

-One is in forms like bricklayers → bricklai (P), bricklay (LP). -Terminal y is usefully turned to i to help conflate words where y is changed -to i and es added to form the plural, but this does not happen when -y -follows a vowel. LP improves on P here, but the Porter2 algorithm makes the -same improvement, so we have nothing to learn. -There is also a difference in words endings lle or lles, -quadrille → quadril (P), quadrill (LP). This is because e and -l -removal are successive in step 5 of P, and done as alternatives in the -respelling rules -of LP. In LP this is not quite correct, since -Lovins makes it clear that her transformation rules should be -applied in succession. Even so, LP seems better than P, suggesting -that step 5b of P (undouble l) should not have been attempted after e removal -in step 5a. So here is a possible small improvement to Porter2. Another -small, but quite interesting difference, is the condition attached to the -ative ending. The ending generator makes B the removal condition by a -natural process, but in P its removal condition is A. This goes back to step -3 as originally presented in the paper of 1980: - -

- (m>0) ICATE → IC
- (m>0) ATIVE →
- (m>0) ALIZE → AL
- (m>0) ICITI → IC
- (m>0) ICAL → IC
- (m>0) FUL →
- (m>0) NESS → -
-(m>0) corresponds to A. With removal condition B, the second line would be - -
- (m>1) ATIVE → -
- -which looks slightly incongruous. Nevertheless it is probably correct, because we -remove a half suffix from icate, alize, icity and ical when the stem -length is at least s1, and so we should remove the full ate + ive suffix when the stem -length is at least s2. We should not be influenced by ful and ness. -They are ‘native English’ stems, unlike the other five, which -have a ‘Romance’ origin, and for these two condition A has been found to -be more appropriate. In fact putting in this adjustment to Porter2 results in an -improvement in the small class of words thereby affected. -

- -

Conclusion

- -

-You never learn all there is to know about a computer program, unless the -program is really very simple. So even after 20 years of regular use, -we can learn something new about P by creating LP and comparing the -two. And in the process we learn a lot about L, the Lovins stemmer itself. -

- -

-The truth is that the main motivation for studying L was to see how well the -Snowball system could be used for implementing and analyzing Lovins’ -original work, and the interest in what she had actually achieved in 1968 -only came later. I hope that this short account helps clarify her work, and -place it the context of the development of stemmers since then. -

- -

Notes

- -

-The http addresses below have a ‘last visited’ date of December 2001. -

- -
    -
  1. The Lovins stemmer is available at -

    - -
      -
    • http://www.cs.waikato.ac.nz/~eibe/stemmers
      • -
    • http://sourceforge.net/projects/stemmers
      • -
    -
    2. - -
  2. See  http://www-uilots.let.uu.nl/~uplift/
    3. - -
  3. See  http://snowball.sourceforge.net
    4. - -
  4. See  http://promo.net/pg/
    5. - -
  5. See  http://snowball.sourceforge.net/english/voc.txt
    6. - -
  6. In looking at verbs with the pattern ride, rode, ridden, Palmer, -1965, notes that ‘we should perhaps add STRIDE, with past tense strode, -but without a past participle (there is no *stridden).’
    7. - -
  7. See  https://tartarus.org/~martin/PorterStemmer/
    8. - -
  8. Lovins (1968), p. 25, mentions that a stemming algorithm developed by - James L. Dolby in California used a two-syllable minimum stem length as a - condition for most of the stemming.
    9. -
- -

Bibiliography

- -

-Andrews K (1971) The development of a fast conflation algorithm for English. -Dissertation for the Diploma in Computer Science, Computer Laboratory, -University of Cambridge. -

- -

-Harman D (1991) How effective is suffixing? Journal of the American -Society for Information Science, 42: 7-15. -

- -

-Kraaij W and Pohlmann R (1994) Porter’s stemming algorithm for Dutch. In -Noordman LGM and de Vroomen WAM, eds. Informatiewetenschap 1994: -Wetenschappelijke bijdragen aan de derde STINFON Conferentie, Tilburg, -1994. pp. 167-180. -

- -

-Kraaij W and Pohlmann R (1995) Evaluation of a Dutch stemming algorithm. -Rowley J, ed. The New Review of Document and Text Management, volume 1, -Taylor Graham, London, 1995. pp. 25-43, -

- -

-Krovetz B (1995) Word sense disambiguation for large text databases. PhD -Thesis. Department of Computer Science, University of Massachusetts -Amherst. -

- -

-Lennon M, Pierce DS, Tarry BD and Willett P (1981) An evaluation of some -conflation algorithms for information retrieval. Journal of Information -Science, 3: 177-183. -

- -

-Lovins JB (1968) Development of a stemming algorithm. Mechanical -Translation and Computational Linguistics, 11: 22-31. -

- -

-Overhage, CFJ (1966) Plans for project Intrex. Science, 152: -1032-1037. -

- -

-Palmer FR (1965) A linguistic study of the English verb. London, -Longmans. -

- -

-Porter MF (1980) An algorithm for suffix stripping. Program, 14: -130-137. -

- -

Appendix 1

- -

-The Lovins stemmer in Snowball. -

- -[% highlight_file('lovins') %] - -

Appendix 2

- -

-The Porter stemmer, cast, as far as is possible, into Lovins form. -

- -[% highlight_file('porter_recast_as_lovins') %] - -

Appendix 3

- -

-The list of 181 endings included by the [% highlight_inline('get') %] directive in the program -of Appendix 2. The numbers to the right show their frequency of occurrence -in the sample vocabulary. The 75 rare endings are shown commented out. -

- -[% highlight(" - 'abilities' B /* (3) */ - 'ability' B /* (14) */ - 'able' B /* (293) */ - 'ables' B /* (4) */ - 'ably' B /* (68) */ - 'al' B /* (285) */ - 'alism' B /* (5) */ -// 'alisms' B /* (-) */ - 'alities' B /* (7) */ - 'ality' B /* (24) */ - 'alization' B /* (1) */ -// 'alizationed' B /* (-) */ -// 'alizationing' B /* (-) */ -// 'alizations' B /* (-) */ - 'alize' B /* (2) */ - 'alized' B /* (4) */ -// 'alizer' B /* (-) */ -// 'alizered' B /* (-) */ -// 'alizering' B /* (-) */ -// 'alizers' B /* (-) */ -// 'alizes' B /* (-) */ -// 'alizing' B /* (-) */ - 'ally' B /* (78) */ - 'alness' B /* (2) */ -// 'alnesses' B /* (-) */ - 'als' B /* (46) */ - 'ance' B /* (93) */ - 'ances' B /* (30) */ - 'ancies' B /* (2) */ - 'ancy' B /* (18) */ - 'ant' B /* (92) */ - 'ants' B /* (29) */ - 'ate' B /* (261) */ - 'ated' B /* (208) */ - 'ately' B /* (38) */ - 'ates' B /* (73) */ - 'ating' B /* (119) */ - 'ation' B /* (356) */ - 'ational' B /* (4) */ -// 'ationalism' B /* (-) */ -// 'ationalisms' B /* (-) */ -// 'ationalities' B /* (-) */ -// 'ationality' B /* (-) */ -// 'ationalize' B /* (-) */ -// 'ationalized' B /* (-) */ -// 'ationalizes' B /* (-) */ -// 'ationalizing' B /* (-) */ - 'ationally' B /* (2) */ -// 'ationalness' B /* (-) */ -// 'ationalnesses' B /* (-) */ -// 'ationals' B /* (-) */ -// 'ationed' B /* (-) */ -// 'ationing' B /* (-) */ - 'ations' B /* (139) */ - 'ative' B /* (40) */ - 'atively' B /* (4) */ -// 'ativeness' B /* (-) */ -// 'ativenesses' B /* (-) */ - 'atives' B /* (7) */ -// 'ativities' B /* (-) */ -// 'ativity' B /* (-) */ - 'ator' B /* (25) */ - 'ators' B /* (10) */ - 'ement' B /* (70) */ -// 'emently' B /* (-) */ - 'ements' B /* (31) */ - 'ence' B /* (100) */ - 'ences' B /* (25) */ - 'encies' B /* (9) */ - 'ency' B /* (41) */ - 'ent' D /* (154) */ - 'ently' D /* (53) */ - 'ents' D /* (25) */ - 'er' B /* (613) */ - 'ered' B /* (44) */ - 'ering' B /* (31) */ - 'ers' B /* (281) */ - 'ful' A /* (163) */ - 'fulness' A /* (31) */ -// 'fulnesses' A /* (-) */ - 'fuls' A /* (5) */ - 'ibilities' B /* (2) */ - 'ibility' B /* (10) */ - 'ible' B /* (53) */ - 'ibles' B /* (2) */ - 'ibly' B /* (14) */ - 'ic' B /* (142) */ - 'ical' B /* (91) */ -// 'icalism' B /* (-) */ -// 'icalisms' B /* (-) */ -// 'icalities' B /* (-) */ - 'icality' B /* (1) */ -// 'icalize' B /* (-) */ -// 'icalized' B /* (-) */ -// 'icalizer' B /* (-) */ -// 'icalizered' B /* (-) */ -// 'icalizering' B /* (-) */ -// 'icalizers' B /* (-) */ -// 'icalizes' B /* (-) */ -// 'icalizing' B /* (-) */ - 'ically' B /* (59) */ -// 'icalness' B /* (-) */ -// 'icalnesses' B /* (-) */ - 'icals' B /* (2) */ - 'icate' B /* (9) */ - 'icated' B /* (7) */ -// 'icately' B /* (-) */ - 'icates' B /* (4) */ - 'icating' B /* (3) */ - 'ication' B /* (23) */ -// 'icational' B /* (-) */ -// 'icationals' B /* (-) */ -// 'icationed' B /* (-) */ -// 'icationing' B /* (-) */ - 'ications' B /* (8) */ - 'icative' B /* (2) */ -// 'icatively' B /* (-) */ -// 'icativeness' B /* (-) */ -// 'icativenesses' B /* (-) */ -// 'icatives' B /* (-) */ -// 'icativities' B /* (-) */ -// 'icativity' B /* (-) */ - 'icities' B /* (1) */ - 'icity' B /* (5) */ - 'ics' B /* (21) */ - 'ion' C /* (383) */ - 'ional' C /* (18) */ -// 'ionalism' C /* (-) */ -// 'ionalisms' C /* (-) */ - 'ionalities' C /* (1) */ - 'ionality' C /* (1) */ -// 'ionalize' C /* (-) */ -// 'ionalized' C /* (-) */ -// 'ionalizer' C /* (-) */ -// 'ionalizered' C /* (-) */ -// 'ionalizering' C /* (-) */ -// 'ionalizers' C /* (-) */ -// 'ionalizes' C /* (-) */ -// 'ionalizing' C /* (-) */ - 'ionally' C /* (12) */ - 'ionalness' C /* (1) */ -// 'ionalnesses' C /* (-) */ - 'ionals' C /* (1) */ - 'ioned' C /* (13) */ - 'ioning' C /* (3) */ - 'ions' C /* (192) */ - 'ism' B /* (33) */ - 'isms' B /* (5) */ - 'ities' B /* (62) */ - 'ity' B /* (236) */ - 'ive' B /* (132) */ - 'ively' B /* (34) */ - 'iveness' B /* (14) */ -// 'ivenesses' B /* (-) */ - 'ives' B /* (12) */ -// 'ivities' B /* (-) */ - 'ivity' B /* (1) */ - 'ization' B /* (4) */ -// 'izational' B /* (-) */ -// 'izationals' B /* (-) */ -// 'izationed' B /* (-) */ -// 'izationing' B /* (-) */ - 'izations' B /* (1) */ - 'ize' B /* (32) */ - 'ized' B /* (32) */ - 'izer' B /* (3) */ -// 'izered' B /* (-) */ -// 'izering' B /* (-) */ - 'izers' B /* (1) */ - 'izes' B /* (6) */ - 'izing' B /* (30) */ - 'ly' E /* (135) */ - 'ment' B /* (105) */ -// 'mently' B /* (-) */ - 'ments' B /* (50) */ - 'ness' A /* (428) */ - 'nesses' A /* (21) */ - 'ous' B /* (340) */ - 'ously' B /* (130) */ - 'ousness' B /* (22) */ -// 'ousnesses' B /* (-) */ -") %] - -

Appendix 4

- -

-An ANSI C program which will generate on  stdout  the raw ending list -(endings with condition letters) from which the list of Appendix 3 is -constructed. -

- -[% highlight_file('porter_recast_as_lovins_generator.c') %] - -[% footer %] diff --git a/algorithms/lovins/stemmer.tt b/algorithms/lovins/stemmer.tt deleted file mode 100644 index 9de41fb..0000000 --- a/algorithms/lovins/stemmer.tt +++ /dev/null @@ -1,332 +0,0 @@ -[% header('The Lovins stemming algorithm') %] - -

Links to resources

- - - -

-The first ever published stemming algorithm was: Lovins JB (1968) Development of -a stemming algorithm. Mechanical Translation and Computational Linguistics, -11: 22-31. Julie Beth Lovins’ paper was remarkable for the early date at which -it was done, and for its seminal influence on later work in -this area. -

- -

-The design of the algorithm was much influenced by the technical vocabulary -with which Lovins found herself working (subject term keywords attached to -documents in the materials science and engineering field). The subject term -list may also have been slightly limiting in that certain common endings -are not represented (ements and ents for example, corresponding to -the singular forms ement and ent), and also in that the algorithm's -treatment of short words, or words with short stems, can be rather -destructive. -

- -

-The Lovins algorithm is noticeably bigger than the Porter algorithm, -because of its very extensive endings list. But in one way that is used to -advantage: it is faster. It has effectively traded space for time, and with -its large suffix set it needs just two major steps to remove a suffix, -compared with the eight of the Porter algorithm. -

- -

-transformation rules. Each ending is associated with one of the -conditions. In the first step the longest ending is found which satisfies -its associated condition, and is removed. In the second step the 35 rules -are applied to transform the ending. The second step is done whether or not -an ending is removed in the first step. -

- -

-For example, nationally has the ending ationally, with associated -condition, B, ‘minimum stem length = 3’. Since removing ationally -would leave a stem of length 1 this is rejected. But it also has ending -ionally with associated condition A. Condition A is ‘no restriction on -stem length’, so ionally is removed, leaving nat. -

- -

-The transformation rules handle features like letter undoubling (sitting -→ sitt → sit), irregular plurals (matrix and matrices), -and English morphological oddities ultimately caused by the behaviour of -Latin verbs of the second conjugation (assume / assumption, -commit / commission etc). Although they are described as being -applied in turn, they can be broken into two stages, rule 1 being done in -stage 1, and either zero or one of rules 2 to 35 being done in stage 2. -

- -

-Here is the list of endings as given in Appendix A of Lovins’ paper. They -are grouped by length, from 11 characters down to 1. Each ending is -followed by its condition code. -

- -
-

Appendix A. The list of endings

- -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
.11.
alistically B arizability A izationally B
.10.
antialness A arisations A arizations A entialness A
.09.
allically C antaneous A antiality A arisation A
arization A ationally B ativeness A eableness E
entations A entiality A entialize A entiation A
ionalness A istically A itousness A izability A
izational A
.08.
ableness A arizable A entation A entially A
eousness A ibleness A icalness A ionalism A
ionality A ionalize A iousness A izations A
lessness A
.07.
ability A aically A alistic B alities A
ariness E aristic A arizing A ateness A
atingly A ational B atively A ativism A
elihood E encible A entally A entials A
entiate A entness A fulness A ibility A
icalism A icalist A icality A icalize A
ication G icianry A ination A ingness A
ionally A isation A ishness A istical A
iteness A iveness A ivistic A ivities A
ization F izement A oidally A ousness A
.06.
aceous A acious B action G alness A
ancial A ancies A ancing B ariser A
arized A arizer A atable A ations B
atives A eature Z efully A encies A
encing A ential A enting C entist A
eously A ialist A iality A ialize A
ically A icance A icians A icists A
ifully A ionals A ionate D ioning A
ionist A iously A istics A izable E
lessly A nesses A oidism A
.05.
acies A acity A aging B aical A
alist A alism B ality A alize A
allic BB anced B ances B antic C
arial A aries A arily A arity B
arize A aroid A ately A ating I
ation B ative A ators A atory A
ature E early Y ehood A eless A
elity A ement A enced A ences A
eness E ening E ental A ented C
ently A fully A ially A icant A
ician A icide A icism A icist A
icity A idine I iedly A ihood A
inate A iness A ingly B inism J
inity CC ional A ioned A ished A
istic A ities A itous A ively A
ivity A izers F izing F oidal A
oides A otide A ously A
.04.
able A ably A ages B ally B
ance B ancy B ants B aric A
arly K ated I ates A atic B
ator A ealy Y edly E eful A
eity A ence A ency A ened E
enly E eous A hood A ials A
ians A ible A ibly A ical A
ides L iers A iful A ines M
ings N ions B ious A isms B
ists A itic H ized F izer F
less A lily A ness A ogen A
ward A wise A ying B yish A
.03.
acy A age B aic A als BB
ant B ars O ary F ata A
ate A eal Y ear Y ely E
ene E ent C ery E ese A
ful A ial A ian A ics A
ide L ied A ier A ies P
ily A ine M ing N ion Q
ish C ism B ist A ite AA
ity A ium A ive A ize F
oid A one R ous A
.02.
ae A al BB ar X as B
ed E en F es E ia A
ic A is A ly B on S
or T um U us V yl R
s' A 's A
.01.
a A e A i A o A
s W y B
-
- -

-Here are the 29 conditions, called A to Z, AA, BB and CC (* stands for any letter): -

- -
-

Appendix B. Codes for context-sensitive rules associated with -certain endings

- -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
A No restrictions on stem
B Minimum stem length = 3
C Minimum stem length = 4
D Minimum stem length = 5
E Do not remove ending after e
F Minimum stem length = 3 and do not remove ending after e
G Minimum stem length = 3 and remove ending only after f
H Remove ending only after t or ll
I Do not remove ending after o or e
J Do not remove ending after a or e
K Minimum stem length = 3 and remove ending only after l, i or u*e
L Do not remove ending after u, x or s, unless s follows o
M Do not remove ending after a, c, e or m
N Minimum stem length = 4 after s**, elsewhere = 3
O Remove ending only after l or i
P Do not remove ending after c
Q Minimum stem length = 3 and do not remove ending after l or n
R Remove ending only after n or r
S Remove ending only after dr or t, unless t follows t
T Remove ending only after s or t, unless t follows o
U Remove ending only after l, m, n or r
V Remove ending only after c
W Do not remove ending after s or u
X Remove ending only after l, i or u*e
Y Remove ending only after in
Z Do not remove ending after f
AA Remove ending only after d, f, ph, th, l, er, or, es or t
BB Minimum stem length = 3 and do not remove ending after met or ryst
CC Remove ending only after l
-
- -

-There is an implicit assumption in each condition, A included, that the minimum -stem length is 2. -

- -

-Finally, here are the 35 transformation rules. -

- -
-

Appendix C. Transformation rules used in recoding stem terminations

- -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
1       remove one of double b, d, g, l, m, n, p, r, s, t
2 iev   →   ief
3 uct   →   uc
4 umpt   →   um
5 rpt   →   rb
6 urs   →   ur
7 istr   →   ister
7a metr   →   meter
8 olv   →   olut
9 ul   →   l except following a, o, i
10 bex   →   bic
11 dex   →   dic
12 pex   →   pic
13 tex   →   tic
14 ax   →   ac
15 ex   →   ec
16 ix   →   ic
17 lux   →   luc
18 uad   →   uas
19 vad   →   vas
20 cid   →   cis
21 lid   →   lis
22 erid   →   eris
23 pand   →   pans
24 end   →   ens except following s
25 ond   →   ons
26 lud   →   lus
27 rud   →   rus
28 her   →   hes except following p, t
29 mit   →   mis
30 ent   →   ens except following m
31 ert   →   ers
32 et   →   es except following n
33 yt   →   ys
34 yz   →   ys
-
- -

-(Rule 30 as given here corrects a typographical error in the published -paper of 1968.) -

- -

-The following examples show the intentions behind these rules. -

- -
-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
1       rubb[ing] → rub, embedd[ed] → embed etc
2 believ[e] → belief
3 induct[ion] → induc[e]
4 consumpt[ion] → consum[e]
5 absorpt[ion] → absorb
6 recurs[ive] → recur
7 administr[ate] → administ[er]
7a parametr[ic] → paramet[er]
8 dissolv[ed] → dissolut[ion]
9 angul[ar] → angl[e]
10 vibex → vibic[es]
11 index → indic[es]
12 apex → apic[es]
13 cortex → cortic[al]
14 anthrax → anthrac[ite]
15 ?
16 matrix → matric[es]
17 ?
18 persuad[e] → persuas[ion]
19 evad[e] → evas[ion]
20 decid[e] → decis[ion]
21 elid[e] → elis[ion]
22 derid[e] → deris[ion]
23 expand → expans[ion]
24 defend → defens[ive]
25 respond → respons[ive]
26 collud[e] → collus[ion]
27 obtrud[e] → obtrus[ion]
28 adher[e] → adhes[ion]
29 remit → remis[s][ion]
30 extent → extens[ion]
31 convert[ed] → convers[ion]
32 parenthet[ic] → parenthes[is]
33 analyt[ic] → analys[is]
34 analyz[ed] → analys[ed]
-
- -

The Lovins algorithm in Snowball

- -

-And here is the Lovins algorithm in Snowball. The natural representation -of the Lovins endings, conditions and rules in Snowball, is, I believe, a -vindication of the appropriateness of Snowball for stemming work. Once the -tables had been established, getting the Snowball version running was the -work of a few minutes. -

- -[% highlight_file('lovins') %] - -[% footer %] diff --git a/algorithms/norwegian/stemmer.tt b/algorithms/norwegian/stemmer.tt deleted file mode 100644 index 30578d1..0000000 --- a/algorithms/norwegian/stemmer.tt +++ /dev/null @@ -1,109 +0,0 @@ -[% header('Norwegian stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'havnedistrikt', 'opning']) %] - -

The stemming algorithm

- -

-The Norwegian alphabet includes the following additional letters, -

- -
- æ   å   ø -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u   y   æ   å   ø -
- -

-R2 is not used: R1 is defined in the same way as in the -German stemmer. -(See the note on R1 and R2.) -

- -

-Define a valid s-ending as one of -

- -
-b   c   d   f   g   h   j   -l   m   n   o   p   r   t   v   -y   z, -
or k not preceded by a vowel. -
- -

-Do each of steps 1, 2 and 3. -

- -

-Step 1: -

- -
- Search for the longest among the following suffixes in R1, and - perform the action indicated. -
-
(a) - a   e   ede   ande   ende   ane   ene   hetene   en -   heten   ar   er   heter   as   es   edes   endes   - enes   hetenes   ens   hetens   ers   ets   et   het   - ast -
delete -
(b) - s -
delete if preceded by a valid s-ending -
(c) - erte   ert -
replace with er -
-

- (Of course the letter of the valid s-ending is - not necessarily in R1) -

-
- -

-Step 2: -

- -
-

- If the word ends dt or vt in R1, delete the t. -

- -

- (For example, meldt → meld, operativt → operativ) -

-
- -

-Step 3: -

- -
- Search for the longest among the following suffixes in R1, and if found, - delete. -
- leg   eleg   ig   eig   lig   elig   els -   lov   elov   slov   hetslov -
-
- -

The same algorithm in Snowball

- -[% highlight_file('norwegian') %] - -[% footer %] diff --git a/algorithms/porter/stemmer.tt b/algorithms/porter/stemmer.tt deleted file mode 100644 index c345a88..0000000 --- a/algorithms/porter/stemmer.tt +++ /dev/null @@ -1,656 +0,0 @@ -[% header('The Porter stemming algorithm') %] - -

Links to resources

- - - -

-Here is a case study on how to code up a stemming algorithm in Snowball. First, -the definition of the Porter stemmer, as it appeared in Program, Vol 14 no. 3 pp -130-137, July 1980. -

- -
-

THE ALGORITHM

- -

-A consonant in a word is a letter other than A, E, I, O or U, and other -than Y preceded by a consonant. (The fact that the term ‘consonant’ is -defined to some extent in terms of itself does not make it ambiguous.) So in -TOY the consonants are T and Y, and in SYZYGY they are S, Z and G. If a -letter is not a consonant it is a vowel. -

- -

-A consonant will be denoted by c, a vowel by v. A list ccc... of length -greater than 0 will be denoted by C, and a list vvv... of length greater -than 0 will be denoted by V. Any word, or part of a word, therefore has one -of the four forms: -

- -
-
CVCV ... C -
CVCV ... V -
VCVC ... C -
VCVC ... V -
- -

-These may all be represented by the single form -

- -
- [C]VCVC ... [V] -
- -

-where the square brackets denote arbitrary presence of their contents. -Using (VC)m to denote VC repeated m times, this may again be written as -

- -
- [C](VC)m[V]. -
- -

-m will be called the measure of any word or word part when represented in -this form. The case m = 0 covers the null word. Here are some examples: -

- -
-
m=0 TR,   EE,   TREE,   Y,   BY. -
m=1 TROUBLE,   OATS,   TREES,   IVY. -
m=2 TROUBLES,   PRIVATE,   OATEN,   ORRERY. -
- -

-The rules for removing a suffix will be given in the form -

- -
- (condition) S1 → S2 -
- -

-This means that if a word ends with the suffix S1, and the stem before S1 -satisfies the given condition, S1 is replaced by S2. The condition is -usually given in terms of m, e.g. -

- -
- (m > 1) EMENT → -
- -

-Here S1 is ‘EMENT’ and S2 is null. This would map REPLACEMENT to REPLAC, -since REPLAC is a word part for which m = 2. -

- -

-The ‘condition’ part may also contain the following: -

- -
-
*S - the stem ends with S (and similarly for the other letters). - -
*v* - the stem contains a vowel. - -
*d - the stem ends with a double consonant (e.g. -TT, -SS). - -
*o - the stem ends cvc, where the second c is not W, X or Y (e.g. - -WIL, -HOP). -
- -

-And the condition part may also contain expressions with and, or and -not, so that -

- -
- (m>1 and (*S or *T)) -
- -

-tests for a stem with m>1 ending in S or T, while -

- -
- (*d and not (*L or *S or *Z)) -
- -

-tests for a stem ending with a double consonant other than L, S or Z. -Elaborate conditions like this are required only rarely. -

- -

-In a set of rules written beneath each other, only one is obeyed, and this -will be the one with the longest matching S1 for the given word. For -example, with -

- -
-
SSES → SS -
IES → I -
SS → SS -
S → -
- -

-(here the conditions are all null) CARESSES maps to CARESS since SSES is -the longest match for S1. Equally CARESS maps to CARESS (S1=‘SS’) and CARES -to CARE (S1=‘S’). -

- -

-In the rules below, examples of their application, successful or otherwise, -are given on the right in lower case. The algorithm now follows: -

- -

-Step 1a -

- -
-
SSES → SS      caresses → caress -
IES → I      ponies → poni -
     ties → ti -
SS → SS      caress → caress -
S →      cats → cat -
- -

-Step 1b -

- -
-
(m>0) EED → EE      feed → feed -
     agreed → agree -
(*v*) ED →      plastered → plaster -
     bled → bled -
(*v*) ING →      motoring → motor -
sing → sing -
- -

-If the second or third of the rules in Step 1b is successful, the following -is done: -

- -
-
AT → ATE      conflat(ed) → conflate -
BL → BLE      troubl(ed) → trouble -
IZ → IZE      siz(ed) → size -
(*d and not (*L or *S or *Z)) - → single letter      hopp(ing) → hop -
     tann(ed) → tan -
     fall(ing) → fall -
     hiss(ing) → hiss -
     fizz(ed) → fizz -
(m=1 and *o) - → E      fail(ing) → fail -
     fil(ing) → file -
- -

-The rule to map to a single letter causes the removal of one of the double -letter pair. The -E is put back on -AT, -BL and -IZ, so that the suffixes --ATE, -BLE and -IZE can be recognised later. This E may be removed in step -4. -

- -

-Step 1c -

- -
-
(*v*) Y → I      happy → happi -
     sky → sky -
- -

-Step 1 deals with plurals and past participles. The subsequent steps are -much more straightforward. -

- -

-Step 2 -

- -
-
(m>0) ATIONAL → ATE      relational → relate -
(m>0) TIONAL → TION      conditional → condition -
     rational → rational -
(m>0) ENCI → ENCE      valenci → valence -
(m>0) ANCI → ANCE      hesitanci → hesitance -
(m>0) IZER → IZE      digitizer → digitize -
(m>0) ABLI → ABLE      conformabli → conformable -
(m>0) ALLI → AL      radicalli → radical -
(m>0) ENTLI → ENT      differentli → different -
(m>0) ELI → E      vileli → vile -
(m>0) OUSLI → OUS      analogousli → analogous -
(m>0) IZATION → IZE      vietnamization → vietnamize -
(m>0) ATION → ATE      predication → predicate -
(m>0) ATOR → ATE      operator → operate -
(m>0) ALISM → AL      feudalism → feudal -
(m>0) IVENESS → IVE      decisiveness → decisive -
(m>0) FULNESS → FUL      hopefulness → hopeful -
(m>0) OUSNESS → OUS      callousness → callous -
(m>0) ALITI → AL      formaliti → formal -
(m>0) IVITI → IVE      sensitiviti → sensitive -
(m>0) BILITI → BLE      sensibiliti → sensible -
- -

-The test for the string S1 can be made fast by doing a program switch on -the penultimate letter of the word being tested. This gives a fairly even -breakdown of the possible values of the string S1. It will be seen in fact -that the S1-strings in step 2 are presented here in the alphabetical order -of their penultimate letter. Similar techniques may be applied in the other -steps. -

- -

-Step 3 -

- -
-
(m>0) ICATE → IC      triplicate → triplic -
(m>0) ATIVE →      formative → form -
(m>0) ALIZE → AL      formalize → formal -
(m>0) ICITI → IC      electriciti → electric -
(m>0) ICAL → IC      electrical → electric -
(m>0) FUL →      hopeful → hope -
(m>0) NESS →      goodness → good -
- -

-Step 4 -

- -
-
(m>1) AL →      revival → reviv -
(m>1) ANCE →      allowance → allow -
(m>1) ENCE →      inference → infer -
(m>1) ER →      airliner → airlin -
(m>1) IC →      gyroscopic → gyroscop -
(m>1) ABLE →      adjustable → adjust -
(m>1) IBLE →      defensible → defens -
(m>1) ANT →      irritant → irrit -
(m>1) EMENT →      replacement → replac -
(m>1) MENT →      adjustment → adjust -
(m>1) ENT →      dependent → depend -
(m>1 and (*S or *T)) ION - →      adoption → adopt -
(m>1) OU →      homologou → homolog -
(m>1) ISM →      communism → commun -
(m>1) ATE →      activate → activ -
(m>1) ITI →      angulariti → angular -
(m>1) OUS →      homologous → homolog -
(m>1) IVE →      effective → effect -
(m>1) IZE →      bowdlerize → bowdler -
- -

-The suffixes are now removed. All that remains is a little tidying up. -

- -

-Step 5a -

- -
-
(m>1) E →      probate → probat -
     rate → rate -
(m=1 and not *o) E - →      cease → ceas -
- -

-Step 5b -

- -
-
(m > 1 and *d and *L) - → single letter      controll → control -
     roll → roll -
-
- -

-Now, turning it into Snowball. -

- -

-The Porter stemmer makes a use of a measure, m, of the length of a word or -word part. If C is a sequence of one or more consonants, and V a sequence -of one or more vowels, any word part has the form -

- -
- [C](VC)m[V], -
- -

-which is to be read as an optional C, followed by m repetitions of VC, -followed by an optional V. This defines m. So for crepuscular the -measure would be 4. -

- -
-    c r e p u s c u l a r
-       |   |     |   |   |
-    [C] V C  V C  V C V C
-         1    2    3   4
-
- -

-Most of the rules for suffix removal involve leaving behind a stem whose -measure exceeds some value, for example, -

- -
- (m > 0) eed → ee -
- -

-means ‘replace eed with ee if the stem before eed has measure -m > 0’. Implementations of the Porter stemmer usually have a routine that -computes m each time there is a possible candidate for removal. -

- -

-In fact the only tests on m in the Porter stemmer are m > 0, m > 1, and, -at two interesting points, m = 1. This suggests that there are two -critical positions in a word: the point at which, going from left to -right, m > 0 becomes true, and then the point at which m > 1 becomes true. -It turns out that m > 0 becomes true at the point after the first consonant -following a vowel, and m > 1 becomes true at the point after the first -consonant following a vowel following a consonant following a vowel. -Calling these positions p1 and p2, we can determine them quite simply in -Snowball: -

- -[% highlight(" - define v 'aeiouy' - - /* ... */ - - do( - gopast v gopast non-v setmark p1 - gopast v gopast non-v setmark p2 - ) -") %] - -

-The region to the right of p1 will be denoted by R1, the region to the -right of p2 by R2: -

- -
-    c r e p u s c u l a r
-           |   |
-           p1  p2
-           <---  R1  --->
-               <-- R2 -->
-
- -

-We can test for being in these regions with calls to  R1  and  R2, defined by, -

- -[% highlight(" - define R1 as $p1 <= cursor - define R2 as $p2 <= cursor -") %] - -

-and using these tests instead of computing m is acceptable, so long as the -stemming process never alters the p1 and p2 positions, which is indeed true -in the Porter stemmer. -

- -

-A particularly interesting feature of the stemmers presented here is the -common use they make of the positions p1 and p2. The details of marking -p1 -and p2 vary between the languages because the definitions of vowel and -consonant vary. For example, French i preceded and followed by vowel -should be treated as a consonant (inquiétude); Portuguese (ã and õ -should be treated as a vowel-consonant pair (São João). A third -important position is pV, which tries to mark the position of the shortest -acceptable verb stem. Its definition varies somewhat between languages. -The Porter stemmer does not use a pV explicitly, but the idea appears when -the verb endings ing and ed are removed only when preceded by a vowel. -In English therefore pV would be defined as the position after the first -vowel. -

- -

-The Porter stemmer is divided into five steps, step 1 is divided further -into steps 1a, 1b and 1c, and step 5 into steps 5a and 5b. Step 1 removes -the i-suffixes, and steps 2 to 4 the d-suffixes (*). Composite d-suffixes are -reduced to single d-suffixes one at a time. So for example if a word ends -icational, step 2 reduces it to icate and step 3 to ic. Three steps are -sufficient for this process in English. Step 5 does some tidying up. -

- -

-One can see how easily the stemming rules translate into Snowball by -comparing the definition of Step 1a from the 1980 paper, -

- -
-    Step 1a:
-        SSES → SS                         caresses  →  caress
-        IES  → I                          ponies    →  poni
-                                           ties      →  ti
-        SS   → SS                         caress    →  caress
-        S    →                            cats      →  cat
-
- -

-with its Snowball equivalent, -

- -[% highlight(" - define Step_1a as ( - [substring] among ( - 'sses' (<-'ss') - 'ies' (<-'i') - 'ss' () - 's' (delete) - ) - ) -") %] - -

-The word to be stemmed is being scanned right to left from the end. The -longest of  'sses',  'ies',  'ss'  or  's'  is searched for and defined as the -slice. (If none are found, Step_1a signals f.) If  'sses'  is found, it is -replaced by  'ss', and so on. Of course, replacing  'ss'  by  'ss'  is a dummy -action, so we can write -

- -[% highlight(" - 'ss' () -") %] - -

-instead of -

- -[% highlight(" - 'ss' (<-'ss') -") %] - -

-Remember that  delete  just means  <- ''. -

- -

-The really tricky part of the whole algorithm is step 1b, -which may be worth looking at in detail. Here it is, without the -example words on the far right, -

- -
-    Step 1b:
-        (m > 0) EED → EE
-        (*v*)   ED  →
-        (*v*)   ING →
-
-    If the second or third of the rules in Step 1b is successful, the
-    following is done:
-
-        AT → ATE
-        BL → BLE
-        IZ → IZE
-        (*d and not (*L or *S or *Z)) → single letter
-        (m = 1 and *o) → E
-
- -

-The first part of the rule means that eed maps to ee if eed is in R1 -(which is equivalent to m > 0), or ed and ing are removed if they are -preceded by a vowel. In Snowball this is simply, -

- -[% highlight(" - define Step_1b as ( - [substring] among ( - 'eed' (R1 <-'ee') - 'ed' - 'ing' (test gopast v delete) - ) - ) -") %] - -

-But this must be modified by the second part of the rule. *d indicates a -test for double letter consonant — bb, dd etc. *L, *S, *Z are tests -for l, s, z. *o is a short vowel test — it is matched by -consonant-vowel-consonant, where the consonant on the right is not w, x -or y. If the short vowel test is satisfied, m = 1 is equivalent to the -cursor being at p1. So the second part of the rule means, map at, bl, iz -to ate, ble, ize; map certain double letters to single letters; and -add e after a short vowel in words of one syllable. -

- -

-We first need two extra groupings, -

- -[% highlight(" - define v 'aeiouy' - define v_WXY v + 'wxY' // v with 'w', 'x' and 'y'-consonant - define v_LSZ v + 'lsz' // v with 'l', 's', 'z' -") %] - -

-and a test for a short vowel, -

- -[% highlight(" - define shortv as ( non-v_WXY v non-v ) -") %] - -

-(The  v_WXY  test comes first because we are scanning backwards, from right to -left.) -

- -

-The double to single letter map can be done as follows: first define the -slice as the next  non-v_LSZ  and copy it to a string,  ch, as a single -character, -

- -[% highlight(" - strings ( ch ) - - /* ... */ - - [non-v_LSZ] ->ch -") %] - -

-A further test,  ch, tests that the next letter of the string is the same -as the one in  ch, and if this gives signal t,  delete  deletes the slice, -

- -[% highlight(" - [non-v_LSZ] ->ch ch delete -") %] - -

-Step_1b  can then be written like this, -

- -[% highlight(" - define Step_1b as ( - [substring] among ( - 'eed' (R1 <-'ee') - 'ed' - 'ing' ( - test gopast v delete - (test among('at' 'bl' 'iz') <+ 'e') - or - ([non-v_LSZ]->ch ch delete) - or - (atmark p1 test shortv <+ 'e') - ) - ) - ) -") %] - -

-But we can improve the appearance, and speed, of this by turning the -second part of the rule into another  among  command, noting that the only -letters that need undoubling are b, d, f, g, m, n, p, r -and t, -

- -[% highlight(" - define Step_1b as ( - [substring] among ( - 'eed' (R1 <-'ee') - 'ed' - 'ing' ( - test gopast v delete - test substring among( - 'at' 'bl' 'iz' - (<+ 'e') - 'bb' 'dd' 'ff' 'gg' 'mm' 'nn' 'pp' 'rr' 'tt' - // ignoring double c, h, j, k, q, v, w, and x - ([next] delete) - '' (atmark p1 test shortv <+ 'e') - ) - ) - ) - ) -") %] - -

-Note the null string in the second  among, which acts as a default case. -

- -

-The Porter stemmer in Snowball is given below. This is an exact -implementation of the algorithm described in the 1980 paper, unlike the -other implementations distributed by the author, which have, and have -always had, three small points of difference (clearly indicated) from the -original algorithm. Since all other implementations of the algorithm seen -by the author are in some degree inexact, this may well be the first ever -correct implementation. -

- -

The full algorithm in Snowball

- -[% highlight_file('porter') %] - -[% footer %] diff --git a/algorithms/portuguese/stemmer.tt b/algorithms/portuguese/stemmer.tt deleted file mode 100644 index 945a37e..0000000 --- a/algorithms/portuguese/stemmer.tt +++ /dev/null @@ -1,175 +0,0 @@ -[% header('Portuguese stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'boa', 'quiabo']) %] - -

The stemming algorithm

- -

-Letters in Portuguese include the following accented forms, -

- -
- á   é   í   ó   ú   â   ê   ô   ç   ã   õ   ü -
-The following letters are vowels: -
- a   e   i   o   u   á   é   í   ó   ú   â   ê   ô -
-And the two nasalised vowel forms, -
- ã   õ -
- -

-should be treated as a vowel followed by a consonant. -

- -

-ã and õ are therefore replaced by a~ and o~ in the word, where ~ is a -separate character to be treated as a consonant. And then — -

- -

-R2 -(see the note on R1 and R2) -and RV have the same definition as in the - Spanish stemmer. -

- -

-Always do step 1. -

- -

-Step 1: Standard suffix removal -

- -
- Search for the longest among the following suffixes, and perform the - action indicated. -
-
eza   ezas   ico   ica   icos   icas   ismo   ismos   - ável   ível   ista   istas   oso   osa   - osos   osas   amento   amentos   imento   imentos   - adora   ador   aça~o   adoras   adores   aço~es   - ante   antes   ância -
delete if in R2 -
logia   logias -
replace with log if in R2 -
ução   uções -
replace with u if in R2 -
ência   ências -
replace with ente if in R2 -
amente -
delete if in R1 -
if preceded by iv, delete if in R2 (and if further preceded by at, - delete if in R2), otherwise, -
if preceded by os, ic or ad, delete if in R2 -
mente -
delete if in R2 -
if preceded by ante, avel or ível, delete if in R2 -
idade   idades -
delete if in R2 -
if preceded by abil, ic or iv, delete if in R2 -
iva   ivo   ivas   ivos -
delete if in R2 -
if preceded by at, delete if in R2 -
ira   iras -
replace with ir if in RV and preceded by e -
-
- -

-Do step 2 if no ending was removed by step 1. -

- -

-Step 2: Verb suffixes -

- -
- Search for the longest among the following suffixes in RV, and if found, - delete. -
- ada   ida   ia   aria   eria   iria   ará   ara   erá   era   irá   ava   asse   esse -   isse   aste   este   iste   ei   arei   erei   irei   am   iam   ariam   eriam   iriam -   aram   eram   iram   avam   em   arem   erem   irem   assem   essem   issem   ado   ido -   ando   endo   indo   ara~o   era~o   ira~o   ar   er   ir   as   adas   idas   ias   arias -   erias   irias   arás   aras   erás   eras   irás   avas   es   ardes   erdes -   irdes   ares   eres   ires   asses   esses   isses   astes   estes   istes   is   ais -   eis   íeis   aríeis   eríeis   iríeis   áreis   areis   éreis   ereis -   íreis   ireis   ásseis   ésseis   ísseis   áveis   ados   idos   ámos -   amos   íamos   aríamos   eríamos   iríamos   áramos   éramos -   íramos   ávamos   emos   aremos   eremos   iremos   ássemos   êssemos -   íssemos   imos   armos   ermos   irmos   eu   iu   ou   ira   - iras -

-If the last step to be obeyed — either step 1 or 2 — altered the word, -do step 3 -
-Step 3 -
- Delete suffix i if in RV and preceded by c -
- -

-Alternatively, if neither steps 1 nor 2 altered the word, do step 4 -

- -

-Step 4: Residual suffix -

- -
- If the word ends with one of the suffixes -
- os   a   i   o   á   í   ó -

- in RV, delete it -
- -

-Always do step 5 -

- -

-Step 5: -

- -
-

- If the word ends with one of -

-
- e   é   ê -
-

- in RV, delete it, and if preceded by gu (or ci) with the u (or i) in RV, - delete the u (or i). -

- -

- Or if the word ends ç remove the cedilla -

-
- -

-And finally: -

- -
- Turn a~, o~ back into ã, õ -
- -

The same algorithm in Snowball

- -[% highlight_file('portuguese') %] - -[% footer %] diff --git a/algorithms/romance.tt b/algorithms/romance.tt deleted file mode 100644 index 2c1d703..0000000 --- a/algorithms/romance.tt +++ /dev/null @@ -1,106 +0,0 @@ -[% header('Romance language stemmers') %] - -

Links to resources

- - - -

-The Romance languages have a wealth of different i-suffixes (*) among the verb -forms, and relatively few for the other parts of speech. In addition to -this, many verbs exhibit irregularities. Many also have short stems, -leading to dangers of over-stemming. The verb, therefore, tends to -dominate initial thinking about stemming in these languages. -

- -

-An algorithmic stemmer can usually reduce the multiple forms of a verb to at -most two or three, and often just one. This is probably -adequate for standard IR use, where the verb is used rather less than other -parts of speech in short queries. -

- -

-In French the verb endings ent and ons cannot be removed without -unacceptable overstemming. The ons form is rarer, but ent forms -are quite common, and will appear regularly throughout a stemmed vocabulary. -

- -

-In Italian, the final vowel of nouns and adjectives indicates number and -gender (amico is male friend, amica is female friend) and its removal is a -necessary part of stemming, but the final vowel sometimes separates words -of different meanings (banco is bench, banca is bank), which leads to some -over-stemming. -

- -

-The d-suffixes of all four languages follow a similar pattern. They can be -tabulated as follows, -

- -
- -
French Spanish Portug. Italian -
-
noun ANCE ance anza eza anza -
adjective IC ique ico ico ico -
noun ISM isme ismo ismo ismo -
adjective ABLE able able ável abile -
adjective IBLE - ible ível ibile -
noun IST iste ista ista ista -
adjective OUS eux oso oso oso -
noun MENT ment amiento amento mente -
noun ATOR ateur ador ador attore -
noun ATRESS atrice - - atrice -
noun ATION ation ación ação azione -
noun LOGY logie logía logía logia -
noun USION usion ución ución uzione -
noun ENCE ence encia ência enza -
adjective ENT ent ente ente ente - -
noun ANCE ance ancia ância anza -
noun ANT ant ante ante ante - -
adverb LY (e)ment (a)mente (a)mente -(a)mente -
noun ITY ité idad idade ità -
adjective IVE if ive ivo ivo -
verb ATE at at at at -
- -

-Equivalent English forms are shown in upper case. In English, ATE is a valid ending, but -in the Romance languages it only exists in combinations. The endings can appear in a -number of styles. In Italian, oso can also be osa, osi or ose, French -ique becomes ic in combinations. -

- -

-The important combining forms are summarised in the following picture: -

- -Graph showing important combining forms in English - -

-In English, ABLE combines with LY to form ABLY. So in French, for example, -able combines with (e)ment to form ablement. -In some languages particular combinations are rare. In Italian, for example, -ANT + LY, which would be the ending antemente, is so rare that it does not -figure in the stemming algorithm. -According to the picture, we -should encounter the forms ICATIVELY and ICATIVITY, and dictionaries -instance a few English words with these endings (communicatively for -example). -But in practice three is the maximum number of derivational -suffixes that one need consider in combination. -

- -[% footer %] diff --git a/algorithms/romanian/stemmer.tt b/algorithms/romanian/stemmer.tt deleted file mode 100644 index 3e70031..0000000 --- a/algorithms/romanian/stemmer.tt +++ /dev/null @@ -1,224 +0,0 @@ -[% header('Romanian stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'abruptă', 'ocol']) %] - -

-(For the background to this work, see the -credits page. Following earlier misgivings on the wisdom -of removing IST/ISM endings, in this stemmer they are now conflated to a single -form. It can easily be modified it to bring it in line with the other Romance -stemmers: see the internal comments marked ‘IST’. -

- -

-It is assumed that hyphenated forms are split into separate words prior to -stemming.) -

- -

The stemming algorithm

- -

-Letters in Romanian include the following accented forms, -

- -
- ă   â   î   ș   ț -
- -

-The following letters are vowels: -

- -
- a   ă   â   e   i   î   o   u -
- -

-Before full Unicode support was widespread it was common to use ş and -ţ (cedilla instead of comma-below) in Romanian text as these characters -were more readily available in 8-bit character sets. The original version of -this algorithm only recognised the cedilla forms, but the current version -instead normalises the old forms as a first step: replace ş by -ș and ţ by ț. -

- -

-Then, i and u between vowels are put into upper case -(so that they are treated as consonants). -

- -

-R1, R2 -(see the note on R1 and R2) -and RV then have the same definition as in the - Spanish stemmer. -

- -

-Always do steps 0, 1, 2 and 4. (Step 3 is conditional on steps 1 and 2.) -

- -

-Step 0: Removal of plurals (and other simplifications) -

- -
- Search for the longest among the following suffixes, and, if - it is in R1, perform the - action indicated. -
-
ul   ului -
delete -
aua -
replace with a -
ea   ele   elor -
replace with e -
ii   iua   iei   iile   iilor   ilor -
replace with i -
ile -
replace with i if not preceded by ab -
atei -
replace with at -
ație   ația -
replace with ați -
-
- -

-Step 1: Reduction of combining suffixes -

- -
- Search for the longest among the following suffixes, and, if - it is in R1, preform the replacement action indicated. - Then repeat this step until no replacement occurs. -
-
abilitate   abilitati   abilităi   abilități -
replace with abil -
ibilitate -
replace with ibil -
ivitate   ivitati   ivităi   ivități -
replace with iv -
icitate   icitati   icităi   icități   - icator   icatori   - iciv   iciva   icive   icivi   icivă   - ical   icala   icale   icali   icală -
replace with ic -
ativ   ativa   ative   ativi   ativă   ațiune   - atoare   ator   atori   - ătoare   ător   ători -
replace with at -
itiv   itiva   itive   itivi   itivă   ițiune   - itoare   itor   itori -
replace with it -
-
- -

-Step 2: Removal of ‘standard’ suffixes -

- -
- Search for the longest among the following suffixes, and, if - it is in R2, perform the action indicated. -
-
at   ata   ată   ati   ate   - ut   uta   ută   uti   ute   - it   ita   ită   iti   ite   - ic   ica   ice   ici   ică   - abil   abila   abile   abili   abilă   - ibil   ibila   ibile   ibili   ibilă   - oasa   oasă   oase   os   osi   oși   - ant   anta   ante   anti   antă   - ator   atori   - itate   itati   ităi   ități   - iv   iva   ive   ivi   ivă -
delete -
iune   iuni -
delete if preceded by ț, and replace the ț by t. -
ism   isme   - ist   ista   iste   isti   istă   iști -
replace with ist -
-
- -

-Do step 3 if no suffix was removed either by step 1 or step 2. -

- -

-Step 3: Removal of verb suffixes -

- -
- Search for the longest suffix in region RV among the following, - and perform the action indicated. -
-
are   ere   ire   âre   - ind   ând   - indu   ându   - eze   - ească   - ez   ezi   ează   esc   ești   - ește   - ăsc   ăști   - ăște   - am   ai   au   - eam   eai   ea   eați   eau   - iam   iai   ia   iați   iau   - ui   - ași   arăm   arăți   ară   - uși   urăm   urăți   ură   - iși   irăm   irăți   iră   - âi   âși   ârăm   ârăți   âră   - asem   aseși   ase   aserăm   aserăți   aseră   - isem   iseși   ise   iserăm   iserăți   iseră   - âsem   âseși   âse   âserăm   âserăți   âseră   - usem   useși   use   userăm   userăți   useră - -
delete if preceded in RV by a consonant or u -
ăm   ați   - em   eți   - im   iți   - âm   âți   - seși   serăm   serăți   seră   - sei   se   - sesem   seseși   sese   seserăm   seserăți   seseră -
delete -
-
- -

-Step 4: Removal of final vowel -

- -
-Search for the longest among the suffixes -
- a   e   i   ie   ă -
-and, if it is in RV, delete it. -
- -

-And finally: -

- -
- Turn I, U back into i, u. -
- -

The same algorithm in Snowball

- -[% highlight_file('romanian') %] - -[% footer %] diff --git a/algorithms/russian/stemmer.tt b/algorithms/russian/stemmer.tt deleted file mode 100644 index 9e7b408..0000000 --- a/algorithms/russian/stemmer.tt +++ /dev/null @@ -1,327 +0,0 @@ -[% header('Russian stemming algorithm') %] - -

Links to resources

- - - -

-The Snowball stemmer represents the Cyrillic alphabet with ASCII characters, -following the standard Library of Congress transliteration scheme. - -

- -[% algorithm_vocab([60, 'в', 'п']) %] - -

The stemming algorithm

- -

-i-suffixes (*) of Russian tend to be quite regular, with irregularities of -declension involving a change to the stem. Irregular forms therefore -usually just generate two or more possible stems. Stems in Russian can -be very short, and many of the suffixes are also particle words that make -‘natural stopwords’, so a tempting way of running the stemmer is to set a -minimum stem length of zero, and thereby reduce to null all words which -are made up entirely of suffix parts. We have been a little more cautious, -and have insisted that a minimum stem contains one vowel. -

- -

-The 32 letters of the Russian alphabet are as follows, with the -transliterated forms that we will use here shown in brackets: -

- -
-
а (a) - б (b) - в (v) - г (g) - д (d) - е (e) - ж (zh) - з (z) - -
и (i) - й (ì) - к (k) - л (l) - м (m) - н (n) - о (o) - п (p) - -
р (r) - с (s) - т (t) - у (u) - ф (f) - х (kh) - ц (ts) - ч (ch) - -
ш (sh) - щ (shch) - ъ (") - ы (y) - ь (') - э (è) - ю (iu) - я (ia) - -
- -

-There is a 33rd letter, ё (e"), but it is rarely used and often -replaced by е in informal writing. The original algorithm here assumed it -had already been mapped to е (e); since 2018-03-16 the Snowball -implementation we provide performs this mapping for you. -

- -

-The following are vowels: -

- -
- а (a)   е (e)   и (i)   о (o)   у (u)   ы (y)   - э (è)   ю (iu)   я (ia) -
- -

-In any word, RV is the region after the first vowel, or the end of the word -if it contains no vowel. -

- -

-R1 is the region after the first non-vowel following a vowel, or the end of -the word if there is no such non-vowel. -

- -

-R2 is the region after the first non-vowel following a vowel in R1, or the -end of the word if there is no such non-vowel. -

- -

-For example: -

- -
-    p r o t i v o e s t e s t v e n n o m
-         |<------       RV        ------>|
-           |<-----       R1       ------>|
-               |<-----     R2     ------>|
-
- -

-(See note on R1 and R2.) -

- -

-We now define the following classes of ending: -

- -

-PERFECTIVE GERUND: -

- -
-

- group 1:   в (v)   вши (vshi)   вшись (vshis') -

- -

- group 2:   ив (iv)   ивши (ivshi)   ившись (ivshis')   - ыв (yv)   ывши (yvshi)   ывшись (yvshis') -

-
- -

-group 1 endings must follow а (a) or я (ia) -

- -

-ADJECTIVE: -

- -
- ее (ee)   ие (ie)   ые (ye)   ое (oe)   ими (imi)   ыми - (ymi)   ей (eì)   ий (iì)   ый (yì)   ой (oì)   ем - (em)   им (im)   ым (ym)   ом (om)   его (ego)   ого (ogo) -   ему (emu)   ому (omu)   их (ikh)   ых (ykh)   ую (uiu) -   юю (iuiu)   ая (aia)   яя (iaia) -   ою (oiu) -   ею (eiu) -
- -

-PARTICIPLE: -

- -
-

- group 1:   ем (em)   нн (nn)   вш (vsh)   ющ (iushch)   щ (shch) -

- -

- group 2:   ивш (ivsh)   ывш (yvsh)   ующ (uiushch) -

-
- -

-group 1 endings must follow а (a) or я (ia) -

- -

-REFLEXIVE: -

- -
-

- ся (sia)   сь (s') -

-
- -

-VERB: -

- -
-

- group 1: ла (la)   на (na)   ете (ete)   йте (ìte)   ли (li) -   й (ì)   л (l)   ем (em)   н (n)   ло (lo)   но (no)   ет - (et)   ют (iut)   ны (ny)   ть (t')   ешь (esh')   нно (nno) -

- -

- group 2: ила (ila)   ыла (yla)   ена (ena)   ейте (eìte)   - уйте (uìte)   ите (ite)   или (ili)   ыли - (yli)   ей (eì)   уй (uì)   ил (il)   ыл (yl)   им (im)   - ым (ym)   ен (en)   ило (ilo)   ыло (ylo)   ено (eno)   ят - (iat)   ует (uet)   уют (uiut)   ит (it)   ыт (yt)   ены - (eny)   ить (it')   ыть (yt')   ишь (ish')   - ую (uiu)   ю (iu) -

-
- -

-group 1 endings must follow а (a) or я (ia) -

- -

-NOUN: -

- -
-

-а (a)   ев (ev)   ов (ov)   ие (ie)   ье ('e)   е (e)   иями -(iiami)   ями (iami)   ами (ami)   еи (ei)   ии (ii)   и (i)   -ией (ieì)   ей (eì)   ой (oì)   ий (iì)   й (ì)   -иям (iiam)   ям (iam)   ием (iem)   ем (em)   ам (am)   ом -(om)   о (o)   у (u)   ах (akh)   иях (iiakh)   ях (iakh)   ы -(y)   ь (')   ию (iiu)   ью ('iu)   ю (iu)   ия (iia)   ья -('ia)   я (ia) -

-
- -

-SUPERLATIVE: -

- -
-

- ейш (eìsh)   ейше (eìshe) -

-
- -

-These are all i-suffixes. The list of d-suffixes is very short, -

- -

-DERIVATIONAL: -

- -
-

- ост (ost)   ость (ost') -

-
- -

-Define an ADJECTIVAL ending as an ADJECTIVE ending optionally preceded -by a PARTICIPLE ending. -

- -
- For example, in -
-
бегавшая = бега + вш + ая -
(begavshaia = bega + vsh + aia) -
- ая (aia) is an adjective ending, and вш (vsh) a participle ending of group 1 - (preceded by the final а (a) of бега (bega)), so вшая (vshaia) is an - adjectival ending. -
- -

-In searching for an ending in a class, always choose the longest one -from the class. -

- -
- So in seaching for a NOUN ending for величие (velichie), choose ие (ie) rather than - е (e). -
- -

-Undouble н (n) means, if the word ends нн (nn), remove the last letter. -

- -

-Here now are the stemming rules. -

- -

-All tests take place in the RV part of the word. -

- -
- So in the test for perfective gerund, the а (a) or я (ia) which the group 1 - endings must follow must itself be in RV. In other words the letters - before the RV region are never examined in the stemming process. -
- -

-Do each of steps 1, 2, 3 and 4. -

- -

-Step 1: -Search for a PERFECTIVE GERUND ending. If one is found remove it, and that -is then the end of step 1. Otherwise try and remove a REFLEXIVE ending, -and then search in turn for (1) an ADJECTIVAL, (2) a VERB or (3) a -NOUN ending. As soon as one of the endings (1) to (3) is found remove it, -and terminate step 1. -

- -

-Step 2: If the word ends with и (i), remove it. -

- -

-Step 3: Search for a DERIVATIONAL ending in R2 (i.e. the entire ending -must lie in R2), and if one is found, remove it. -

- -

-Step 4: (1) Undouble н (n), or, (2) if the word ends with a SUPERLATIVE ending, -remove it and undouble н (n), or (3) if the word ends ь (') (soft sign) remove it. -

- -

The same algorithm in Snowball

- -[% highlight_file('russian') %] - -[% footer %] diff --git a/algorithms/scandinavian.tt b/algorithms/scandinavian.tt deleted file mode 100644 index 94f6d13..0000000 --- a/algorithms/scandinavian.tt +++ /dev/null @@ -1,34 +0,0 @@ -[% header('Scandinavian language stemmers') %] - -

Links to resources

- - - -

-The stemmers for these three Scandinavian languages are all very simple, -and quite similar to each other. But between the languages there is a difference -in which endings can be removed without difficulty, even though the endings -are very similar. For example, in Norwegian -the ending ede can be removed safely, but not in Danish. -

- -

-To the definite article (the in English, der etc in German) there -corresponds -a noun ending in the Scandinavian languages. This ending cannot always be removed -with certainty. In Swedish, for example, the en form is removed, but not the -t or n form, -

- -
-
husen hus -
flickan   →   flickan -
äpplet äpplet - -
- -[% footer %] diff --git a/algorithms/serbian/stemmer.tt b/algorithms/serbian/stemmer.tt deleted file mode 100644 index c7298ba..0000000 --- a/algorithms/serbian/stemmer.tt +++ /dev/null @@ -1,273 +0,0 @@ -[% header('Serbian stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([ -'ambasade', -'ambasadi', -'abdominalna', -'abdominalno', -'abdominalnih', -'abdominalnim', -'abdominalnog', -'abdominalnoj', -'abdominalnom', -'abdominalnu', -'abeceda', -'abecede', -'abecedi', -'abecedni', -'abecednih', -'abecednim', -'abecedno', -'abecednog', -'abecednom', -'abecedom', -'abecedu', -'abecendom', -'ablendovanje', -'ablenduje', -'ablenduju', -'ablendujući', -'abnormalan', -'abnormalije', -'abnormalijom', -'abnormalna', -'abnormalne', -'abnormalni', -'abnormalnih', -'abnormalnim', -'abnormalno', -'abnormalnog', -'abnormalnom', -'abnormalnost', -'abnormalnosti', -'abnormalnostima', -'abnormalnu', -], [ -'obustavila', -'obustavile', -'obustavili', -'obustavilo', -'obustavio', -'ocenjivala', -'ocenjivali', -'ocenjivan', -'ocenjivana', -'ocenjivane', -'ocenjivani', -'ocenjivano', -'ocenjivanja', -'ocenjivanje', -'ocenjivanju', -'ocenjivao', -'ocenjivati', -'ocenjuje', -'ocenjujem', -'ocenjujemo', -'ocenjuješ', -'ocenjujete', -'ocenjuju', -'ocenjujući', -'očajan', -'očajna', -'očajne', -'očajni', -'očajno', -'padobrana', -'padobranaca', -'padobranci', -'padobrancima', -'padobranom', -'padobranskim', -'padobransku', -'padobranu', -'paganska', -'paganske', -'paganski', -'paganskih', -]) %] - -

The stemming algorithm

- -

-The Serbian language is a Slavic language (Indo-European) of the South Slavic -subgroup. It is highly inflected and uses similar rules for morphological -derivation and flexion as other Slavic languages, especially ones derived from -the Serbo-Croatian language used in the former Yugoslavia. Because of this -highly inflected characteristic a stemmer for Serbian language will have many -more rules than stemmers for less inflected languages. -

- -

-Serbian Stemmer described in this document is based on the Croatian -Stemmer which is published under the GNU Lesser General Public License. -Mark Regions, Morphological Changes (Step_1) and Stemming -(Step_2) routines are based on the Croatian Stemming Algorithm. In -addition, some of the existing rules for Morphological Changes and Stemming -(Step_1 and Step_2 among lists) have been modified and new rules have -been added for the needs of the Serbian Stemmer. -

- -

-Latin alphabet in Serbian includes the following letters with diacritics: -

- -
- č   ć   đ   š   ž -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u -
- -

-There is also letter - r - that isn't a vowel but it is sometimes used for syllabification. -

- -

Main Routines of Serbian Stemming Algorithm are:

- -
    -
  1. Conversion of Cyrillic alphabet to Latin alphabet -

    -The Serbian language uses both Cyrillic and Latin alphabets, but -these days most people use the Latin alphabet on their PCs, Phones, etc. This -algorithm is developed mostly for the purposes of the Information Retrieval, -therefore the first thing it does is to convert Cyrillic letters to -Latin. -

    -
    2. - -
  2. Prelude -

    -In Serbian language there are two dialects: Ekavian and -Ijekavian. For example words: -

      -
    • senka (Ekavian) -
    • sjenka (Ijekavian) -
    -have the same meaning (Shadow), also words: -
      -
    • mleko (Ekavian) -
    • mlijeko (Ijekavian) -
    -have the same meaning (Milk) but are spelled differently and because -mostly used dialect in Serbia is Ekavian the next thing to do is to -replace Ijekavian dialect with it. -

    - -

    -These days it is also common, although not valid, to use combination of letters -"d" and "j" instead of a single letter "đ". For example -people will more often write "Novak Djoković" instead of "Novak -Đoković" and because this algorithm is developed with Information Retrieval -in mind they should be treated as the same terms. -

    -
    3. -
  3. Mark Regions -

    -R1 is either: -

      -
    1. a region after the first vowel if there are at least two letters outside -of it, otherwise it is a region after the first non-vowel following a vowel, -
    2. a region after the first "r" if there are at least two letters -outside of it, otherwise it is a region after the first non-"r" -following an "r". -
    -

    -Note that every suffix which the stemmer can remove contains at least one -vowel, so in the degenerate case of an input which contains no vowels there -is nothing to be done. The Snowball implementation of this stemmer sets -R1 to be a zero length region at the end of the word if the input -contains no vowels and no "r". -

    -

    -In Serbian language there are some words in which "r" letter is used for -syllabification and in such words vowels can appear at the very end - for -example word "grmlje". -

    - -

    -So before algorithm decide what will R1 be, it needs to look if and -where "r" letter occurs and where is the first vowel. If it finds "r" -that occurred before the first vowel and there is at least one letter between -them this means that "r" is used for syllabification and R1 is -2), otherwise R1 is 1). -

    - -

    -For example: -

      -
    • "tr|go|va|čki" - in this word "tr" is the first syllable - which means that "r" is used for syllabification and R1 = - "govački" - -
    • "tre|ne|rka" - in this word there is a letter "r" before the - first vowel but there aren't any letters between them which means that - "r" isn't used for syllabification and R1 = "nerka". - -
    • "r|ta|njski" - in this word "r" is the first syllable but if - we use "tanjski" as R1 it won't left enough letters outside - of it, so we need to shrink it down to a region after the first - non-"r" following an "r" which is in this case = - "anjski". - -
    • "a|vi|on" - similar to the previous case but with a vowel instead - of an "r". -
    - -Inside Mark Regions routine there is a test routine that is used to -check for letters with diacritics and is used later to apply certain rules in -stemming. Result of this test routine is stored inside no_diacritics flag. -This test routine is used because people these days tend to use letters without -diacritics (instead of the proper ones with diacritics) and we need to take -this into account also. -

    -
    4. - -
  4. Morphological Changes -

    -Very last thing to do, before any stemming is done, are morphological changes. -These changes are applied so that we get the same stems for different forms of a -word. -

    - -

    -For example words: -

      -
    • "pravilan" (Masculine, Singular) -
    • "pravilna" (Feminine, Singular) -
    • "pravilno" (Neuter, Singular) -
    -should have the same stem. To get that result the algorithm will first change -word "pravilan" (Masculine, Singular) to "pravilni" (Masculine, -Plural) and after that the word will be stemmed. -

    -
    5. - -
  5. Stemming -

    -There are two steps for stemming. The first contains most of the rules and is -the primary stemming routine and the second one will try to stem the word only -if the first one failed to do so - whether it was because there were no rules -that could be applied or the rule overlapped the R1 region. The second -step contains a few rules that will do proper stemming for most words that -couldn't be stemmed using the rules from the first step. -

    -
    6. -
- -

The full algorithm in Snowball

- -[% highlight_file('serbian') %] - -[% footer %] diff --git a/algorithms/spanish/stemmer.tt b/algorithms/spanish/stemmer.tt deleted file mode 100644 index 2098c3b..0000000 --- a/algorithms/spanish/stemmer.tt +++ /dev/null @@ -1,205 +0,0 @@ -[% header('Spanish stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'che', 'torá']) %] - -

The stemming algorithm

- -

-Letters in Spanish include the following accented forms, -

- -
- á   é   í   ó   ú   ü   ñ -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u   á   é   í   ó   ú   ü -
- -

-R2 is defined in the usual way — -see the note on R1 and R2. -

- -

-RV is defined as follows (and this is not the same as the - French stemmer -definition): -

- -

-If the second letter is a consonant, RV is the region after the next -following vowel, or if the first two letters are vowels, RV is the region -after the next consonant, and otherwise (consonant-vowel case) RV is the -region after the third letter. But RV is the end of the word if these -positions cannot be found. -

- -

-For example, -

- -
-    m a c h o     o l i v a     t r a b a j o     á u r e o
-         |...|         |...|         |.......|         |...|
-
- -

-Always do steps 0 and 1. -

- -

-Step 0: Attached pronoun -

- -
- Search for the longest among the following suffixes -
- me   se   sela   selo   selas   selos   la   le   lo   las   les   los   nos -

- and delete it, if comes after one of -
- (a) iéndo   ándo   ár   ér   ír
- (b) ando   iendo   ar   er   ir
- (c) yendo following u -
-

- in RV. In the case of (c), yendo must lie in RV, but the preceding - u can be outside it. -

- -

- In the case of (a), deletion is followed by removing the acute accent - (for example, haciéndola → haciendo). -

-
- -

-Step 1: Standard suffix removal -

- -
- Search for the longest among the following suffixes, and perform the - action indicated. -
-
anza   anzas   ico   ica   icos   icas   ismo   ismos   able   ables   ible   ibles   ista -   istas   oso   osa   osos   osas   amiento   amientos   imiento   - imientos -
delete if in R2 -
adora   ador   ación   adoras   adores   aciones   ante   antes   ancia   ancias -
delete if in R2 -
if preceded by ic, delete if in R2 -
logía   logías -
replace with log if in R2 -
ución   uciones -
replace with u if in R2 -
encia   encias -
replace with ente if in R2 -
amente -
delete if in R1 -
if preceded by iv, delete if in R2 (and if further preceded by at, - delete if in R2), otherwise, -
if preceded by os, ic or ad, delete if in R2 -
mente -
delete if in R2 -
if preceded by ante, able or ible, delete if in R2 -
idad   idades -
delete if in R2 -
if preceded by abil, ic or iv, delete if in R2 -
iva   ivo   ivas   ivos -
delete if in R2 -
if preceded by at, delete if in R2 -
-
- -

-Do step 2a if no ending was removed by step 1. -

- -

-Step 2a: Verb suffixes beginning y -

- -
- Search for the longest among the following suffixes in RV, and if found, - delete if preceded by u. -
- ya   ye   yan   yen   yeron   yendo   yo   yó   yas   yes   yais   - yamos -
- (Note that the preceding u need not be in RV.) -
- -

-Do Step 2b if step 2a was done, but failed to remove a suffix. -

- -

-Step 2b: Other verb suffixes -

- -
- Search for the longest among the following suffixes in RV, and perform the - action indicated. -
-
en   es   éis   emos -
delete, and if preceded by gu delete the u (the gu need not be in - RV) -
arían   arías   arán   arás   aríais   aría   aréis   aríamos   aremos -   ará   aré -   erían   erías   erán   erás   eríais   ería   eréis   eríamos   eremos -   erá   eré -   irían   irías   irán   irás   iríais   iría   iréis   iríamos   iremos -   irá   iré -   aba   ada   ida   ía   ara   iera   ad   ed   id   ase   iese   aste   iste   an   aban   ían -   aran   ieran   asen   iesen   aron   ieron   ado   ido   ando   iendo   ió   ar   er   ir   as -   abas   adas   idas   ías   aras   ieras   ases   ieses   ís   áis   abais   íais -   arais   ierais     aseis   ieseis   asteis   isteis   ados   idos   amos   ábamos -   íamos   imos   áramos   iéramos   iésemos   ásemos -
delete -
-
- -

-Always do step 3. -

- -

-Step 3: residual suffix -

- -
- Search for the longest among the following suffixes in RV, and perform the - action indicated. -
-
os   a   o   á   í   ó -
delete if in RV -
e   é -
delete if in RV, and if preceded by gu with the u in RV delete the u -
-
- -

-And finally: -

- -
- Remove acute accents -
- -

The same algorithm in Snowball

- -[% highlight_file('spanish') %] - -[% footer %] diff --git a/algorithms/swedish/stemmer.tt b/algorithms/swedish/stemmer.tt deleted file mode 100644 index aaf8c82..0000000 --- a/algorithms/swedish/stemmer.tt +++ /dev/null @@ -1,107 +0,0 @@ -[% header('Swedish stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([40, 'jakt', 'klo']) %] - -

The stemming algorithm

- -

-The Swedish alphabet includes the following additional letters, -

- -
- ä   å   ö -
- -

-The following letters are vowels: -

- -
- a   e   i   o   u   y   ä   å   ö -
- -

-R2 is not used: R1 is defined in the same way as in the -German stemmer. -(See the note on R1 and R2.) -

- -

-Define a valid s-ending as one of -

- -
-b   c   d   f   g   h   j   k   -l   m   n   o   p   r   t   v   -y -
- -

-Do each of steps 1, 2 and 3. -

- -

-Step 1: -

- -
- Search for the longest among the following suffixes in R1, and - perform the action indicated. -
-
(a) - a   arna   erna   heterna   orna   ad   e   ade   - ande   arne   are   aste   en   anden   aren   heten   - ern   ar   er   heter   or   as   arnas   ernas   - ornas   es   ades   andes   ens   arens   hetens   erns -   at   andet   het   ast -
delete -
(b) - s -
delete if preceded by a valid s-ending -
- (Of course the letter of the valid s-ending is - not necessarily in R1) -
- -

-Step 2: -

- -
- Search for one of the following suffixes in R1, and if found - delete the last letter. -
- dd   gd   nn   dt   gt   kt   tt -
- (For example, friskt → frisk, fröknarnn fröknarn) -
- -

-Step 3: -

- -
- Search for the longest among the following suffixes in R1, and - perform the action indicated. -
-
lig   ig   els -
delete -
löst -
replace with lös -
fullt -
replace with full -
-
- -

The same algorithm in Snowball

- -[% highlight_file('swedish') %] - -[% footer %] diff --git a/algorithms/turkish/stemmer.tt b/algorithms/turkish/stemmer.tt deleted file mode 100644 index 3a8c2a4..0000000 --- a/algorithms/turkish/stemmer.tt +++ /dev/null @@ -1,47 +0,0 @@ -[% header('Turkish stemming algorithm') %] - -

Links to resources

- - - -

-The Turkish stemming algorithm was provided by Evren Kapusuz Cilden. It stems -only noun and nominal verb suffixes because noun stems are more important for -information retrieval, and only handling these simplifies the algorithm -significantly. -

- -

-In her paper (linked above) Evren explains -

- -
-

-The stemmer can be enhanced to stem all kinds of verb suffixes. In Turkish, -there are over fifty suffixes that can be affixed to verbs [2]. The -morphological structure of verb suffixes is more complicated than noun -suffixes. Despite this, one can use the methodology presented in this paper to -enhance the stemmer to find stems of all kinds of Turkish words. -

-
- -

where [2] is a reference to the following paper:

- -
-

-Gulsen Eryigit and Esref Adali. -An Affix Stripping Morphological Analyzer for Turkish -Proceedings of the IAESTED International -Conference -ARTIFICIAL INTELLIGENCE AND APPLICATIONS, February 16-18,2004, Innsbruck, Austria. -

-
- -

The algorithm in Snowball

- -[% highlight_file('turkish') %] - -[% footer %] diff --git a/algorithms/yiddish/stemmer.tt b/algorithms/yiddish/stemmer.tt deleted file mode 100644 index 136e9b0..0000000 --- a/algorithms/yiddish/stemmer.tt +++ /dev/null @@ -1,202 +0,0 @@ -[% header('Yiddish stemming algorithm') %] - -

Links to resources

- - - -[% algorithm_vocab([ -'אַװעקבלאָנדזשען', -'אַװעקבלאָנדזשענדיק', -'אַװעקבלאָנדזשענדיקן', -'אַװעקבלאָנדזשענדיקס', -'אַװעקבלאָנדזשענדיקע', -'אַװעקבלאָנדזשענדיקער', -'אַװעקגײן', -'אַװעקגײנדיק', -'אַװעקגײנדיקן', -'אַװעקגײנדיקס', -'אַװעקגײנדיקע', -'אַװעקגײנדיקער', -'אַװעקגנבֿענען', -'אַװעקגנבֿענענדיק', -'אַװעקגנבֿענענדיקן', -'אַװעקגנבֿענענדיקס', -'אַװעקגנבֿענענדיקע', -'אַװעקגנבֿענענדיקער', -'אַװעקגעבלאָנדזשעט', -'אַװעקגעבלאָנדזשעטן', -'אַװעקגעבלאָנדזשעטס', -'אַװעקגעבלאָנדזשעטע', -'אַװעקגעבלאָנדזשעטער', -'אַװעקגעבן', -'אַװעקגעבנדיק', -'אַװעקגעבנדיקן', -'אַװעקגעבנדיקס', -'אַװעקגעבנדיקע', -'אַװעקגעבנדיקער', -'אַװעקגעגאַנגען', -'אַװעקגעגאַנגענס', -'אַװעקגעגאַנגענע', -'אַװעקגעגאַנגענעם', -'אַװעקגעגאַנגענער', -'אַװעקגעגנבֿעט', -], [ -'אַבֿידות', -'אַבסטראַקטסטער', -'אַדורכבײַסנדיקער', -'אַדורכגעביסן', -'אַדורכגעשמועסט', -'אַדורכפֿירנדיק', -'אַװעקגעגאַנגען', -'אַװעקגעגאַנגענעם', -'אַװעקגענומענער', -'אמתדיק', -'אמתדיקן', -'אמתדיקע', -'אמתדיקער', -'באַהאַלטן', -'ביכער', -'געאַכלט', -'געאײַלט', -'געאײַלן', -'געבאָדענעם', -'געבאָטענעם', -'געשדכנטע', -'עראָפּלאַנען', -'פֿאַרגאַנגענהײט', -'פֿאָרױסגעגאַנגענע', -'קינדהײט', -'װילן', -'װילסט', -]) %] - -

The stemming algorithm

- -

Groupings

-

We setup the following groupings:

- -
-
Niked
-
All niked used in Yiddish and Hebrew
-
AlefBeys
-
- All actual letters in the Hebrew alphabet, including: -
    -
  • The alphabet itself: א ב ג ד ה ו ז ח ט י כ ל מ נ ס ע פ צ ק ר ש ת
    • -
  • Final consonants: ך ם ן ף ץ
    • -
  • Ligatures: װ ױ ײ
    • -
-
-
Vowel
-
א ו י ע ױ ײ
-
Consonant
-
AlefBeys - Vowel
-
- -

Pre-processing

- - -

Marking regions

-

- Only a single marker is used: P1. - To begin with, this is set at the end of the word. -

- - - -

We are now at the start of the main portion of the word (past any verbal prefix and past participle marker).

- - - -

Backwards mode

- -

Unless otherwise stated, all deletes ensure we are beyond P1.

-

In each pass, at the first level of bullets, the longest matching suffix always wins.

- -

First pass:

- - -

Second pass - after the first pass, do the following to the remaining stem:

- - -

Third pass - after the second pass, do the following to the remaining stem:

- - -Finally, all remaining GE and TSU are deleted. - -

The same algorithm in Snowball

- -[% highlight_file('yiddish') %] - -[% footer %] diff --git a/codesets/guide.tt b/codesets/guide.tt deleted file mode 100644 index eb02f9f..0000000 --- a/codesets/guide.tt +++ /dev/null @@ -1,93 +0,0 @@ -[% header('Character codes') %] - -

-Snowball (since version 2.0) supports specifying non-ASCII characters using -the standard Unicode notation U+XXXX where XXXX is a string of -hex digits. However, this doesn't make for very readable source code, so the -Snowball scripts on this site define more mnemonic representations of the -non-ASCII characters which they use - for example, the German stemmer includes -the lines -

- -[% highlight(' - /* special characters */ - - stringdef a" ' _ "'{U+00E4}'" _ ' - stringdef o" ' _ "'{U+00F6}'" _ ' - stringdef u" ' _ "'{U+00FC}' - stringdef ss '{U+00DF}' -") %] - -

-(In Unicode, hex values E4, F6, FC and DF are the numeric values -of characters ä, ö, ü and ß respectively.) -

- -

-Then the code which follows uses [% highlight_inline("'{a" _ '"' _ "}'") %] when it wants -ä, etc. -

- -

-Using literal Unicode character in strings in the source file may work in some -cases, but isn't really supported - the snowball compiler doesn't (currently at -least) have the concept of "source character set", so at best you'll limit -which programming languages your stemmer can be used with. -

- -

-If you wish to describe other Latin-alphabet based codesets for use in stemmers -we recommend using the following conventions: -

- -
-
accent ASCII form example -
acute single quote  e' for é -
grave grave  a` for à -
umlaut double quote  u" for ü -
circumflex circumflex  i^ for î -
cedilla letter c  cc for ç -
tilde tilde  n~ for ñ -
ring letter o  ao for å -
line through solidus  o/ for ø - -
breve plus  a+ for ă -
double acute letter q  oq for ő -
comma below ,  t, for ț -
- -

-And, should they ever arise, use  r  for left and right -hook (as in Polish), and  v  for hacek (as in Czech). -

- -

-The ‘line-through’ accent covers a numbers of miscellaneous cases: the -Scandinavian  o/, Icelandic  d/  and Polish  l/. -

- -

-Use  ae  and  ss  for æ ligature and the German -ß, with -upper case forms  AE  and  SS. Use  th  for Icelandic thorn. -

- -

-We used to recommend , for cedilla, but we need a way to -represent comma-below for Romanian, so we've repurposed , -for that and now recommend c for cedilla instead. -

- -

-If you're writing a new stemmer, see below for a file of suitable -stringdef lines you can cut and paste into your code. -

- -

Links

- - - -[% footer %] diff --git a/compiler/snowman.tt b/compiler/snowman.tt deleted file mode 100644 index 442af83..0000000 --- a/compiler/snowman.tt +++ /dev/null @@ -1,1558 +0,0 @@ -[% header('Snowball Manual') %] - -

Links to resources

- - - -

Snowball definition

- -

-Snowball is a small string-handling language, and its name was chosen as a -tribute to SNOBOL (Farber 1964, Griswold 1968 — -see the references at the end of the -introduction), -with which it shares the -concept of string patterns delivering signals that are used to control the -flow of the program. -

- -

1 Data types

- -

-The basic data types handled by Snowball are strings of characters, signed -integers, and boolean truth values, or more simply strings, integers -and booleans. Snowball supports Unicode characters, which may be represented -as UTF-8, 8-bit characters, or 16-bit wide characters (depending on the -programming language code is being generated for - for C, all these options are -supported). -

- -

2 Names

- -

-A name in Snowball starts with an ASCII letter, followed by zero or more ASCII -letters, digits and underscores. A name can be of type string, -integer, boolean, routine, external or -grouping. All names must be declared. A declaration has the form -

- -
-    Ts ( ... )
-
- -

-where symbol  T  is one of  string,  integer  etc, and the region in -brackets contains a list of names separated by whitespace. For example, -

- -[% highlight(" - integers ( p1 p2 ) - booleans ( Y_found ) - - routines ( - shortv - R1 R2 - Step_1a Step_1b Step_1c Step_2 Step_3 Step_4 Step_5a Step_5b - ) - - externals ( stem ) - - groupings ( v v_WXY v_LSZ ) -") %] - -

-p1  and  p2  are integers,  Y_found  is boolean, and so on. Snowball is quite -strict about the declarations, so all the names go in the same name space, -no name may be declared twice, all used names must be declared, no two -routine definitions can have the same name, etc. Names declared and -subsequently not used are merely reported in a warning message.

- -

-A name may not be one of the reserved words of Snowball. Additionally, names -for externals must be valid function/method names in the language being -generated in most cases, which generally means they can't be reserved words -in that language (e.g. [% highlight_inline("externals (null)") %] will generate -invalid Java code containing a method public boolean null().) -For internal symbols we add a prefix to avoid this issue, but an external -has to provide an external interface. When generating C code, the --eprefix option provides a potential solution to this problem. -

- -

-Names in Snowball are case-sensitive, but external names which differ only in -case will cause a problem for languages with case-insensitive identifiers (such -as Pascal). This issue is avoided for internal symbols in such languages by -encoding case difference via an added prefix. -

- -

-So for portability a little care is needed when choosing names for externals. -The convention when using Snowball to implement stemming algorithms is to have -a single external named stem, which should be safe. -

- -

3 Literals

- -

3.1 Integer Literals

- -

-A literal integer is an ASCII digit sequence, and is always interpreted as -decimal. -

- -

3.2 String Literals

- -

-A literal string is written between single quotes, for example, -

- -[% highlight(" - 'aeiouy' -") %] - -

-Two special insert characters for use in literal strings are defined by -the directive [% highlight_inline("stringescapes AB") %], for example, -

- -[% highlight(" - stringescapes {} -") %] - -

-Conventionally { and } are used as the insert -characters, and we would recommend following this convention unless you want to -use these as literal characters in your strings a lot. However, - A  and  B  can be any printing -characters, except that  A  can't be a single quote. -(If A  and  B are the same then - A  itself can never be escaped.) -

- -

-A subsequent occurrence of the stringescapes directive redefines -the insert characters (but any string macros already defined with -stringdef remain defined). -

- -

-Within insert characters, the following sequences are understood: -

- - - -

-For example, -

- -[% highlight(" - stringescapes {} - - /* Spanish diacritics */ - - stringdef a' '{U+00E1}' // a-acute - stringdef e' '{U+00E9}' // e-acute - stringdef i' '{U+00ED}' // i-acute - stringdef o' '{U+00F3}' // o-acute - stringdef u' '{U+00FA}' // u-acute - stringdef u\" '{U+00FC}' // u-diaeresis - stringdef n~ '{U+00F1}' // n-tilde - - /* All the characters in Spanish used to represent vowels */ - - define v 'aeiou{a'}{e'}{i'}{o'}{u'}{u\"}' -") %] - -

4 Routines

- -

-A routine definition has the form -

- -[% highlight(" - define R as C -") %] - -

-where  R  is the routine name and  C  is a command, or bracketed group of -commands. So a routine is defined as a sequence of zero or more commands. -Snowball routines do not (at present) take parameters. For example, -

- -[% highlight(" - define Step_5b as ( // this defines Step_5b - ['l'] // three commands here: [, 'l' and ] - R2 'l' // two commands, R2 and 'l' - delete // delete is one command - ) -" _ ' - define R1 as $p1 <= cursor - /* R1 is defined as the single command "$p1 <= cursor" */ -') %] - -

-A routine is called simply by using its name,  R, as a command. -

- -

5 Commands and signals

- -

-The flow of control in Snowball is arranged by the implicit use of -signals, rather than the explicit use of constructs like the  if, -else,  break  of C. The scheme is designed for handling strings, but is -perhaps easier to introduce using integers. Suppose  x,  y,  z  ... are -integers. The command -

- -[% highlight(' - $x = 1 -') %] - -

-sets  x  to 1. The command -

- -[% highlight(' - $x > 0 -') %] - -

-tests if  x  is greater than zero. Both commands give a signal t or f, -(true or false), but while the second command gives t if  x  is greater -than zero and f otherwise, the first command always gives t. In Snowball, -every command gives a t or f signal. A sequence of commands can be turned -into a single command by putting them in a list surrounded by round -brackets: -

- -
-    ( C1 C2 C3 ... Ci Ci+1 ... )
-
- -

-When this is obeyed,  Ci+1  will be obeyed if each of the preceding  C1  ... -Ci  give t, but as soon as a  Ci  gives f, the subsequent  Ci+1 Ci+2  ... -are ignored, and the whole sequence gives signal f. If all the  Ci  give t, -however, the bracketed command sequence also gives t. So, -

- -[% highlight(' - $x > 0 $y = 1 -') %] - -

-sets  y  to 1 if  x  is greater than zero. If  x  is less than or equal to zero -the two commands give f. -

- -

-If  C1  and  C2  are commands, we can build up the larger commands, -

- -
-
C1 or C2 -
— Do  C1. If it gives t ignore  C2, otherwise do  C2. The resulting - signal is t if and only  C1  or  C2  gave t. -
C1 and C2 -
— Do  C1. If it gives f ignore  C2, otherwise do  C2. The resulting - signal is t if and only  C1  and  C2  gave t. -
not C -
— Do  C. The resulting signal is t if  C  gave f, otherwise f. -
try C -
— Do  C. The resulting signal is t whatever the signal of  C. -
fail C -
— Do  C. The resulting signal is f whatever the signal of  C. -
- -

-So for example, -

- -
-
[% highlight_inline('($x > 0 $y = 1) or ($y = 0)') %] -
— sets  y  to 1 if  x  is greater than zero, otherwise to zero. - -
[% highlight_inline('try( ($x > 0) and ($z > 0) $y = 1)') %] -
— sets  y  to 1 if both  x  and  z  are greater than 0, and gives t. -
- -

-This last example is the same as -

- -[% highlight(' - try($x > 0 $z > 0 $y = 1) -') %] - -

-so that  and  seems unnecessary here. But we will see that  and  has a -particular significance in string commands. -

- -

-When a ‘monadic’ construct like  not,  try  or  fail  is not followed by a -round bracket, the construct applies to the shortest following valid command. -So for example -

- -[% highlight(' - try not $x < 1 $z > 0 -') %] - -

-would mean -

- -[% highlight(' - try ( not ( $x < 1 ) ) $z > 0 -') %] - -

-because [% highlight_inline('$x < 1') %] is the shortest valid command following  not, and then -not $x < 1  is the shortest valid command following  try. -

- -

-The ‘dyadic’ constructs like  and  and  or  must sit in a bracketed list -of commands anyway, for example, -

- -
-    ( C1 C2 and C3 C4 or C5 )
-
- -

-And then in this case  C2  and  C3  are connected by the  and;  C4  and  C5  are -connected by the  or. So -

- -[% highlight(' - $x > 0 not $y > 0 or not $z > 0 $t > 0 -') %] - -

-means -

- -[% highlight(' - $x > 0 ((not ($y > 0)) or (not ($z > 0))) $t > 0 -') %] - -

-and  and  or  are equally binding, and bind from left to right, -so  C1 or C2 and C3  means  (C1 or C2) and C3  etc. -

- -

6 Integer commands

- -

-There are two sorts of integer commands - assignments and comparisons. Both -are built from Arithmetic Expressions (AEs). -

- -

Arithmetic Expressions (AEs)

- -

-An AE consists of integer names, literal numbers and a few other things -connected by dyadic  +,  -,  *  and  /, and monadic  -, with the same -binding powers and semantics as C. As well as integer names and literal -numbers, the following may be used in AEs: -

- -
- -
minint  — the minimum negative number -
maxint  — the maximum positive number -
cursor  — the current value of the string cursor -
limit  — the current value of the string limit -
size  — the size of the string, in "slots" -
sizeof s  — the number of "slots" in  s, where  s  is the name of a string or (since Snowball 2.1) a literal string -
New in Snowball 2.0:
len  — the length of the string, in Unicode characters -
lenof s  — the number of Unicode characters in  s, where  s  is the name of a string or (since Snowball 2.1) a literal string -
- -

-[% highlight_inline('size') %] and [% highlight_inline('sizeof') %] count in -"slots" - see the "Character representation" section below for details. -

- -

-The cursor and limit concepts are explained below. -

- -

Integer assignments

- -

-An integer assignment has the form -

- -
-    $X assign_op AE
-
- -

-where  X  is an integer name and assign_op is one of the five assignments - =,  +=,  -=,  *=, or  /=. -The meanings are the same as in C. -

- -

-For example, -

- -[% highlight(' - $p1 = limit // set p1 to the string limit -') %] - -

-Integer assignments always give the signal t. -

- -

Integer comparisons

- -

-An integer comparison has the form -

- -
-    $X rel_op AE
-
- -

-or (since Snowball 2.0): -

- -
-    $(AE1 rel_op AE2)
-
- -

-where  X  is an integer name and rel_op is one of the six tests - ==,  !=,  >=, - >, <=, or  <. -Again, the meanings are the same as in C. -

- -

-Examples of integer comparisons are, -

- -[% highlight(' - $p1 <= cursor // signal is f if the cursor is before position p1 - $(len >= 3) // signal is f unless the string is at least 3 characters long -') %] - -

-The second form is more general since an integer name is a valid AE, but it -also allows comparisons which don't involve integer variables. Before support -for this was added the second example could only be achieved by assigning -len to a variable and then testing that variable instead. -

- -

7 String commands

- -

-If  s  is a string name, a string command has the form -

- -[% highlight(' - $s C -') %] - -

-where  C  is a command that operate on the string. Strings can be processed -left-to-right or right-to-left, but we will describe only the -left-to-right case for now. The string has a cursor, which we will -denote by c, and a limit point, or limit, which we will denote by l. c -advances towards l in the course of a string command, but the various -constructs  and,  or,  not  etc have side-effects which keep moving it -backwards. Initially c is at the start and l the end of the string. For -example, -

- -
-        'a|n|i|m|a|d|v|e|r|s|i|o|n'
-        |                         |
-        c                         l
-
- -

-c, and l, mark the boundaries between characters, and not -characters themselves. The characters between c and l will be denoted by -c:l. -

- -

-If  C  gives t, the cursor c will have a new, well-defined value. But if  C -gives f, c is undefined. Its later value will in fact be determined by the -outer context of commands in which  C  came to be obeyed, not by  C  itself. -

- -

-Here is a list of the commands that can be used to operate on strings. -

- -

a) Setting a value

- -
-
= S -
where  S  is the name of a string or a literal string. c:l is set equal - to  S, and l is adjusted to point to the end of the copied string. The - signal is t. For example, - -[% highlight(' - $x ' _ " = 'animadversion' /* literal string */" _ ' - $y = x /* string name */ -') %] - -
- -

b) Basic tests

- -
-
S -
here and below,  S  is the name of a string or a literal string. If c:l - begins with the substring  S, c is repositioned to the end of this - substring, and the signal is t. Otherwise the signal is f. For example, - -[% highlight(' - $x ' _ "'anim' /* gives t, assuming the string is 'animadversion' */" _ ' - $x ' _ "('anim' 'ad' 'vers')" _ ' - /* ditto */ - - $t ' _ "= 'anim'" _ ' - $x t /* ditto */ -') %] - -
true,  false -
true  is a dummy command that generates signal t.  false  generates - signal f. They are sometimes useful for emphasis, - -[% highlight(" - define start_off as true // nothing to do - define exception_list as false // put in among(...) list later -") %] - -  true  is equivalent to  () -
C1 or C2 -
This is like the case for integers described above, but the extra - touch is that if  C1  gives f, c is set back to its old position after -  C1  has given f and before  C2  is tried, so that the test takes place on - the same point in the string. So we have - -[% highlight(' - $x ' _ "('anim' /* signal t */ - 'ation' /* signal f */ - ) or - ( 'an' /* signal t - from the beginning */ - ) -") %] - -
C1 and C2 -
And similarly c is set back to its old position after  C1  has given t - and before  C2  is tried. So, - -[% highlight(' - $x ' _ "'anim' and 'an' /* signal t */" _ ' - $x ' _ "('anim' 'an') /* signal f, since 'an' and 'ad' mis-match */ -") %] - -
not C -
try C -
These are like the integer tests, with the added feature that c is set - back to its old position after an f signal is turned into t. So, - -[% highlight(' - $x ' _ "(not 'animation' not 'immersion') - /* both tests are done at the start of the string */ -" _ ' - $x ' _ "(try 'animus' try 'an' - 'imad') - /* - gives t */ -") %] - -
-
 try C  is equivalent to  C or true -
-
test C -
This does command  C  but without advancing c. Its signal is the same as - the signal of  C, but following signal t, c is set back to its old - value. -
-
 test C  is equivalent to  not not C -
 test C1 C2  is equivalent to  C1 and C2 -
-
fail C -
This does  C  and gives signal f. It is equivalent to  C false. Like -  false  it is useful, but only rarely. - -
do C -
This does  C, puts c back to its old value and gives signal t. It is - very useful as a way of suppressing the side effect of f signals and - cursor movement. -
-
 do C  is equivalent to  try test C -
or  test try C -
-
goto C -
c is moved right until obeying  C  gives t. But if c cannot be moved - right because it is at l the signal is f. c is set back to the position - it had before the last obeying of  C, so the effect is to leave c before - the pattern which matched against  C. - -[% highlight(' - $x goto' _ " 'ad' /* positions c after 'anim' */" _ ' - $x goto' _ " 'ax' /* signal f */ -") %] - -
gopast C -
Like goto, but c is not set back, so the effect is to leave c after - the pattern which matched against  C. - -[% highlight(' - $x gopast' _ " 'ad' /* positions c after 'animad' */ -") %] - -
repeat C -
C  is repeated until it gives f. When this happens c is set back to the - position it had before the last repetition of  C, and  repeat C  gives - signal t. For example, - -[% highlight(' - $x repeat gopast' _ " 'a' /* position c after the last 'a' */ -") %] - -
loop AE C -
This is like  C C ... C  written out AE times, where AE is an arithmetic - expression. For example, - -[% highlight(' - $x loop 2 gopast' _ " ('a' or 'e' or 'i' or 'o' or 'u') - /* position c after the second vowel */ -") %] - - The equivalent expression in C has the shape, - -[% highlight(" - { int i; - int limit = AE; - for (i = 0; i < limit; i++) C; - } -", "c") %] - -
atleast AE C -
This is equivalent to  loop AE C repeat C. - -
hop AE -
moves c AE character positions towards l, but if AE is negative, or if - there are less than AE characters between c and l the signal is f. - For example, - -[% highlight(" - test hop 3 -") %] - - tests that c:l contains more than 2 characters. - -
next -
is equivalent to  hop 1. -
- -

c) Moving text about

- -

-We have seen in (a) that  $x = y, when  x  and  y  are strings, sets c:l of  x -to the value of  y. Conversely -

- -[% highlight(' - $x => y -') %] - -

-sets the value of  y  to the c:l region of  x. -

- -

-A more delicate mechanism for pushing text around is to define a substring, -or slice of the string being tested. Then -

- -
-
[% highlight_inline('[') %] -
sets the left-end of the slice to c, -
[% highlight_inline(']') %] -
sets the right-end of the slice to c, -
[% highlight_inline("-> s") %] -
moves the slice to variable  s, -
[% highlight_inline("<- S") %] -
replaces the slice with variable (or literal)  S. -
- -

-For example -

- -[% highlight(" - /* assume x holds 'animadversion' */" _ ' - $x ( [ ' _ " // '[animadversion' - [ set as indicated - loop 2 gopast 'a' - // '[anima|dversion' - c is marked by '|' - ] // '[anima]dversion' - ] set as indicated - -> y // y is 'anima' - ) -") %] - -

-For any string, the slice ends should be assumed to be unset until they are -set with the two commands  [,  ]. Thereafter the slice ends will retain -the same values until altered. -

- -
-
[% highlight_inline("delete") %] -
is equivalent to [% highlight_inline("<- ''") %] -
- -

-This next example deletes all vowels in x, -

- -[% highlight(" - define vowel ('a' or 'e' or 'i' or 'o' or 'u') - /* ... */" _ ' - $ x repeat ( gopast([vowel]) delete ) -') %] - -

-As this example shows, the slice markers  [  and  ]  often appear as -pairs in a bracketed style, which makes for easy reading of the Snowball -scripts. But it must be remembered that, unusually in a computer -programming language, they are not true brackets. -

- -

-More simply, text can be inserted at c. -

- -
-
[% highlight_inline("insert S") %] -
insert variable or literal  S  before c, moving c to the right of the - insert.  <+  is a synonym for  insert. - -
[% highlight_inline("attach S") %] -
the same, but leave c at the left of the insert. -
- -

d) Marks

- -

-The cursor, c, (and the limit, l) can be thought of as having a numeric -value, from zero upwards: -

- -
-         | a | n | i | m | a | d | v | e | r | s | i | o | n |
-         0   1   2   3   4   5   6   7   8   9  10  11  12  13
-
- -

-It is these numeric values of c and l which are accessible through -cursor  and  limit  in arithmetic expressions. -

- -
-
[% highlight_inline("setmark X") %] -
sets  X  to the current value of c, where  X  is an integer variable. - It's equivalent to: [% highlight_inline("$X = cursor") %] - -
[% highlight_inline("tomark AE") %] -
moves c forward to the position given by AE, - -
[% highlight_inline("atmark AE") %] -
tests if c is at position AE (t or f signal). - It's equivalent to: [% highlight_inline("$(cursor == AE)") %] -
- -

-In the case of [% highlight_inline("tomark AE") %], a similar fail condition occurs as with [% highlight_inline("hop AE") %]. -If c is already beyond AE, or if position l is before position AE, the -signal is f. -

- -

-In the stemming algorithms, certain regions of the word are defined by -setting marks, and later the failure condition of [% highlight_inline("tomark") %] is used to see if -c is inside a particular region. -

- -

-Two other commands put c at l, and test if c is at l, -

- -
-
[% highlight_inline("tolimit") %] -
moves c forward to l (signal t always), - -
[% highlight_inline("atlimit") %] -
tests if c is at l (t or f signal). -
- -

e) Changing l

- -

-In this account of string commands we see c moving right towards l, while -l stays fixed at the end. In fact l can be reset to a new position between -c and its old position, to act as a shorter barrier for the movement of c. -

- -
-
setlimit C1 for C2 -
C1  is obeyed, and if it gives f the signal from  setlimit - is f with no further action. -

- -

- Otherwise, the final value of c becomes the new - position of l. c is then set back to its old value before  C1  was - obeyed, and  C2  is obeyed. Finally l is set back to its old position, - and the signal of  C2  becomes the signal of  setlimit. -

- -

- So the signal is f if either  C1  or  C2  gives f, otherwise t. - For example, -

- -[% highlight(' - $x ( setlimit goto' _ " 's' // 'animadver}sion' new l as marked '}' - for // below, '|' marks c after each goto - ( goto 'a' and // '|animadver}sion' - goto 'e' and // 'animadv|er}sion' - goto 'i' and // 'an|imadver}sion' - ) - ) -") %] - -

- This checks that x has characters ‘a’, ‘e’ and ‘i’ before the first - ‘s’. -

- -
- -

f) Backward processing

- -

-String commands have been described with c to the left of l and moving -right. But the process can be reversed. -

- -
-
[% highlight_inline("backwards C") %] -
c and l are swapped over, and c moves left towards l.  C  is obeyed, the - signal given by  C  becomes the signal of  backwards C, and c and l are - swapped back to their old values (except that l may have been adjusted - because of deletions and insertions).  C  cannot contain another - [% highlight_inline("backwards") %] command. - -
[% highlight_inline("reverse C") %] -
A similar idea, but here c simply moves left instead of moving right, - with the beginning of the string as the limit, l.  C  can contain other - [% highlight_inline("reverse") %] commands, but it cannot contain commands to do deletions or - insertions — it must be used for testing only. (Without this - restriction Snowball's semantics would become very untidy.) -
- -

-Forward and backward processing are entirely symmetric, except that forward -processing is the default direction, and literal strings are always -written out forwards, even when they are being tested backwards. So the -following are equivalent, -

- -[% highlight(' - $x (' _ " - 'ani' 'mad' 'version' atlimit - ) -" _ ' - $x backwards (' _ " - 'version' 'mad' 'ani' atlimit - ) -") %] - -

-If a routine is defined for backwards mode processing, it must be included -inside a  backwardmode(...)  declaration. -

- -

g) substring and among

- -

-The use of [% highlight_inline("substring") %] and [% highlight_inline("among") %] is central to the implementation of the -stemming algorithms. It is like a case switch on strings. In its simpler -form, -

- -
-        substring among('S1' 'S2' 'S3' ...)
-
- -

-searches for the longest matching substring  'S1'  or  'S2'  or  'S3'  ... from -position c. (The  'Si'  must all be different.) So this has the same -semantics as -

- -
-        ('S1' or 'S2' or 'S3' ...)
-
- -

-— so long as the  'Si'  are written out in decreasing order of length. -

- -

-substring  may be omitted, in which case it is attached to its following -among, so -

- -[% highlight(" - among(/*...*/) -") %] - -

-without a preceding [% highlight_inline("substring") %] is equivalent to -

- -[% highlight(" - (substring among(/*...*/)) -") %] - -

-[% highlight_inline("substring") %] may also be detached from its [% highlight_inline("among") %], although it must -precede it textually in the same routine in which the [% highlight_inline("among") %] appears. -The more general form of [% highlight_inline("substring /* ... */ among") %] is, -

- -
-    substring
-    C
-    among( 'S11' 'S12' ... (C1)
-           'S21' 'S22' ... (C2)
-           ...
-
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

-Obeying  substring  searches for a longest match among the  'Sij'. The -signal from  substring  is t if a match is found, otherwise f. -Any commands C between the substring and among will be run after this -search and only if the search finds a match (it would be equivalent to remove C and replace each -Ci with C Ci). When the -among  comes to be obeyed, the  Ci  corresponding to the matched  'Sij'  is -obeyed, and its signal becomes the signal of the  among  command. -

- -

-substring/among  pairs must match up textually inside each routine -definition. But there is no problem with an  among  containing other -substring/among  pairs, and  substring  is optional before  among  anyway. -The essential constraint is that two  substrings must be separated by an -among, and each  substring  must be followed by an  among. -

- -

-The effect of obeying  among  when the preceding  substring  is not obeyed -is undefined. This would happen for example here, -

- -[% highlight(' - try($x != 617 substring)' _ " - among(...) // 'substring' is bypassed in the exceptional case where x == 617 -") %] - -

-The significance of separating the  substring  from the  among  is to allow -them to work in different contexts. For example, -

- -
-    setlimit tomark L for substring
-
-    among( 'S11' 'S12' ... (C1)
-           ...
-
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

-Here the test for the longest  'Sij'  is constrained to the region between c -and the mark point given by integer  L. But the commands  Ci  operate outside -this limit. Another example is -

- -
-    reverse substring
-
-    among( 'S11' 'S12' ... (C1)
-           ...
-
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

-The substring test is in the opposite direction in the string to the -direction of the commands  Ci. -

- -

-The last  (Cn)  may be omitted, in which case  (true)  is assumed. -

- -

-Each string  'Sij'  may be optionally followed by a -routine name, -

- -
-    among(
-           'S11' R11 'S12' R12 ... (C1)
-           'S21' R21 'S22' R22 ... (C2)
-           ...
-           'Sn1' Rn1 'Sn2' Rn1 ... (Cn)
-         )
-
- -

-If a routine name is not specified, it is equivalent -to a routine which simply returns signal t, -

- -[% highlight(" - define null as true -") %] - -

-— so we can imagine each  'Sij'  having its associated routine -Rij. Then obeying the  among  causes a search for the longest -'Sij'  whose corresponding routine -Rij  gives t. -

- -

-The routines Rij  should be written without any -side-effects, other than the inevitable cursor movement. (c is in -any case set back to its old value following a call of -Rij.) -

- -

8 Booleans

- -

-[% highlight_inline("set B") %] and [% highlight_inline("unset B") %] set  B  to true and false respectively, where  B  is a -boolean name. [% highlight_inline("B") %] as a command gives a signal t if it is set true, f -otherwise. For example, -

- -[% highlight(" - booleans ( Y_found ) // declare the boolean - - /* ... */ - - unset Y_found // unset it - do ( ['y'] <-'Y' set Y_found ) - /* if c:l begins 'y' replace it by 'Y' and set Y_found */ - - do repeat(goto (v ['y']) <-'Y' set Y_found) - /* repeatedly move down the string looking for v 'y' and - replacing 'y' with 'Y'. Whenever the replacement takes - place set Y_found. v is a test for a vowel, defined as - a grouping (see below). */ - - - /* Y_found means there are some letters Y in the string. - Later we can use this to trigger a conversion back to - lower case y. */ - - /* ... */ - - do (Y_found repeat(goto (['Y']) <- 'y') -") %] - -

9 Groupings

- -

-A grouping brings characters together and enables them to be looked for -with a single test. -

- -

-If  G  is declared as a grouping, it can be defined by -

- -
-    define G G1 op G2 op G3 ...
-
- -

-where op is  +  or  -, and  G1,  G2,  G3  are literal strings, or groupings that -have already been defined. (There can be zero or more of these additional -op components). For example, -

- -[% highlight(" - define capital_letter 'ABDEFGHIJKLMNOPQRSTUVWXYZ' - define small_letter 'abdefghijklmnopqrstuvwxyz' - define letter capital_letter + small_letter - define vowel 'aeiou' + 'AEIOU' - define consonant letter - vowel - define digit '0123456789' - define alphanumeric letter + digit -") %] - -

-Once  G  is defined, it can be used as a command, and is equivalent to a test -

- -
-    'ch1' or 'ch2' or ...
-
- -

-where  ch1,  ch2  ... list all the characters in the grouping. -

- -

-[% highlight_inline("non G") %] is the converse test, and matches any character except the -characters of  G. Note that [% highlight_inline("non G") %] is not the same as [% highlight_inline("not G") %], in fact -

- -

-[% highlight_inline("non G") %] is equivalent to [% highlight_inline("(not G next)") %] -

- -

-[% highlight_inline("non") %] may be optionally followed by hyphen, for example: -

- -[% highlight(" - non-vowel - non-digit -") %] - -

-Bear in mind that [% highlight_inline("non-vowel") %] doesn't only match a -consonant - it'll match any character which isn't in the vowel -grouping. Failing to consider this has lead to bugs in stemming algorithms - -for example, here we intended to undouble a consonant: -

- -[% highlight(" - [non-vowel] -> ch - ch - delete -") %] - -

-The problem with this code is it will also mangle numbers with repeated digits, -for example 1900 would become 190. A good rule of -thumb here seems to be to use an inclusive grouping check if the code goes on -to delete the character matched: -

- -[% highlight(" - [consonant] -> ch - ch - delete -") %] - -

10 A Snowball program

- -

-A complete program consists of a sequence of declarations followed by a -sequence of definitions of groupings and routines. Routines which are -implicitly defined as operating on c:l from right to left must be included -in a  backwardmode(...)  declaration. -

- -

-A Snowball program is called up via a simple -API -through its defined externals. For example, -

- -[% highlight(" - externals ( stem1 stem2 ) - /* ... */ - define stem1 as ( /* stem1 commands */ ) - define stem2 as ( /* stem2 commands */ ) -") %] - -

-The API also allows a current string to be defined, and this becomes the -c:l string for the external routine to work on. Its final value is the -result handed back through the API. -

- -

-The strings, integers and booleans are accessible from any point in the -program, and exist throughout the running of the Snowball program. They are -therefore like static declarations in C. -

- -

11 Comments, and other whitespace fillers

- -

-At a deeper level, a program is a sequence of tokens, interspersed with -whitespace. Names, reserved words, literal numbers and strings are all -tokens. Various symbols, made up of non-alphanumerics, are also tokens. -

- -

-A name, reserved word or number is terminated by the first character that -cannot form part of it. A symbol is recognised as the longest sequence of -characters that forms a valid symbol. So  +=-  is two symbols,  +=  and --, because  +=  is a valid symbol in the language while  +=-  is not. -Whitespace separates tokens but is otherwise ignored. This of course is -like C. -

- -

-Occasionally a newer version of Snowball may add a new token. So as not to -break existing programs, any such tokens declared as a name (via -[% highlight_inline('integers') %], [% highlight_inline('routines') %], etc) -will lose their token status for the rest of the program. This applies -to the tokens -[% highlight_inline('len') %] -and -[% highlight_inline('lenof') %]. -

- -

-Anywhere that whitespace can occur, there may also occur: -

- -

-(a) Comments, in the usual multi-line [% highlight_inline('/* .... */') %] or single line -[% highlight_inline('// ...') %] format. -

- -

-(b) Get directives. These are like  #include  commands in C, and have the form -[% highlight_inline("get 'S'") %], where  'S'  is a literal string. For example, -

- -[% highlight(" - get '/home/martin/snowball/main-hdr' // include the file contents -") %] - -

-(c) [% highlight_inline("stringescapes XY") %] where  X  and  Y  are any two printing characters. -

- -

-(d) [% highlight_inline("stringdef m 'S'") %] where  m  is sequence of characters not including -whitespace and terminated with whitespace, and  'S'  is a literal string. -

- -

12 Character representation

- -

-In this description of Snowball, it is assumed that strings are composed of -characters, and that characters can be defined numerically, but the numeric range -of these characters is not defined. As implemented, three different schemes -are supported. Characters can either be (a) bytes in the range 0 to 255, -as in traditional C strings, or (b) byte pairs in the range 0 to 65535, -as in Java strings, or (c) UTF-8 encoded bytes sequences in the range 0 -to 65535, so that a character may occupy 1, 2 or 3 bytes. -

- -

-For case (c), we need to make a slight separation of the concept of -characters into symbols, the units of text being represented, and -slots, the units of space into which they map. (So in case (a), all -slots are one byte; in case (b) all slots are two bytes.) -c and l have numeric values that can be used in AEs (arithmetic -expressions). These values count the number of slots. Similarly -setmark,  tomark  and  atmark  are remembering and then using slot -counts.  size  and  sizeof  measure string size -in slots, not symbols. However,  hop N  moves c over  N  symbols, -not  N  slots, and  next  is equivalent to  hop 1. -

- -

-Snowball 2.0 adds len and lenof, which measure string length in symbols -(so they're the same as size and sizeof in cases (a) and (b), but -different in case (c)). -

- -

-So long as these simple distinctions are recognised, the same Snowball -script can be compiled to work with any of the three encoding schemes. -

- -

13 Legacy Features

- -

13.1 hex and decimal

- -

-This section documents features of Snowball for which there's a strongly -prefered alternative. They're still support for compatibility with -existing code which uses them, but you shouldn't use them in then code. -We document them here so that their meaning in existing code can be -understood, and especially to aid updated to the preferred alternatives. -

- -

-In a  stringdef , string may be preceded by the word  hex, -or the word  decimal. This was how non-ASCII characters -were specified before support for specifying Unicode codepoints using the -U+ notation was added. -

- -

-hex and decimal mean that the contents of the string -are interpreted as characters values written out in hexadecimal, or decimal, -notation. The characters should be separated by spaces. For example, -

- -[% highlight(" - hex 'DA' /* is character hex DA */ - hex 'D A' /* is the two characters, hex D and A (carriage - return, and line feed) */ - decimal '10' /* character 10 (line feed) */ - decimal '13 10' /* characters 13 and 10 (carriage return, and - line feed) */ -") %] - -

-The following forms are equivalent, -

- -[% highlight(" - hex 'd a' /* lower case also allowed */ - hex '0D 000A' /* leading zeroes ignored */ - hex ' D A ' /* extra spacing is harmless */ -") %] - -

-The interpretation of the values is as Unicode codepoints if command -line option -utf8 or -widechars is specified, and as -character values in an unspecified single byte character set otherwise. For -ASCII and ISO-8859-1 the character values match Unicode codepoints, but to -handle other single byte character sets (e.g. ISO-8859-2 or KOI8-R) you needed -a special version of a Snowball source with different character values -specified via stringdef. The U+ notation allows -you to use a single Snowball source in this situation. -

- -

13.2 among starter command

- -

-The among command supports a "starter" command, C -in this example: -

- -
-    among( (C)
-           'S11' 'S12' ... (C1)
-           'S21' 'S22' ... (C2)
-           ...
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

-This is equivalent to adding C at the start of each -Ci: -

- -
-    among( 'S11' 'S12' ... (C C1)
-           'S21' 'S22' ... (C C2)
-           ...
-           'Sn1' 'Sn2' ... (C Cn)
-         )
-
- -

-However, both are equivalent to: -

- -
-    substring C
-    among( 'S11' 'S12' ... (C1)
-           'S21' 'S22' ... (C2)
-           ...
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

-This requires an explicit substring but seems clearer so -we recommend using this in new code and have designated the use of a starter as -a legacy feature. -

- -

-A starter is also allowed with an explicit substring, for example: -

- -
-    substring
-    Cs
-    among( (Ca)
-           'S11' 'S12' ... (C1)
-           'S21' 'S22' ... (C2)
-           ...
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

-is equivalent to: -

- -
-    substring
-    Cs
-    Ca
-    among( 'S11' 'S12' ... (C1)
-           'S21' 'S22' ... (C2)
-           ...
-           'Sn1' 'Sn2' ... (Cn)
-         )
-
- -

Snowball syntax

- -
-

-In the grammar which follows, ||  is used for alternatives, - [X]  means that X is -optional, and  [X]*  means that X is repeated zero or more -times. meta-symbols are defined on the left.  <char>  means any -character. -

- -

-The definition of  literal string  does not allow for the escaping -conventions established by the  stringescapes  directive. The command -?  is a debugging aid. -

- -
-<letter>        ::= a || b || ... || z || A || B || ... || Z
-<digit>         ::= 0 || 1 || ... || 9
-<name>          ::= <letter> [ <letter> || <digit> || _ ]*
-<s_name>        ::= <name>
-<i_name>        ::= <name>
-<b_name>        ::= <name>
-<r_name>        ::= <name>
-<g_name>        ::= <name>
-<literal string>::= '[<char>]*'
-<number>        ::= <digit> [ <digit> ]*
-
-S               ::= <s_name> || <literal string>
-G               ::= <g_name> || <literal string>
-
-<declaration>   ::= strings ( [<s_name>]* ) ||
-                    integers ( [<i_name>]* ) ||
-                    booleans ( [<b_name>]* ) ||
-                    routines ( [<r_name>]* ) ||
-                    externals ( [<r_name>]* ) ||
-                    groupings ( [<g_name>]* )
-
-<r_definition>  ::= define <r_name> as C
-<plus_or_minus> ::= + || -
-<g_definition>  ::= define <g_name> G [ <plus_or_minus> G ]*
-
-AE              ::= (AE) ||
-                    AE + AE || AE - AE || AE * AE || AE / AE || - AE ||
-                    maxint || minint || cursor || limit ||
-                    size || sizeof S ||
-                    len || lenof S ||
-                    <i_name> || <number>
-
-<i_assign>      ::= $ <i_name> = AE ||
-                    $ <i_name> += AE || $ <i_name> -= AE ||
-                    $ <i_name> *= AE || $ <i_name> /= AE
-
-<i_test_op>     ::= == || != || > || >= || < || <=
-
-<i_test>        ::= $ ( AE <i_test_op> AE ) ||
-                    $ <i_name> <i_test_op> AE
-
-<s_command>     ::= $ <s_name> C
-
-C               ::= ( [C]* ) ||
-                    <i_assign> || <i_test> || <s_command> || C or C || C and C ||
-                    not C || test C || try C || do C || fail C ||
-                    goto C || gopast C || repeat C || loop AE C ||
-                    atleast AE C || S || = S || insert S || attach S ||
-                    <- S || delete ||  hop AE || next ||
-                    => <s_name> || [ || ] || -> <s_name> ||
-                    setmark <i_name> || tomark AE || atmark AE ||
-                    tolimit || atlimit || setlimit C for C ||
-                    backwards C || reverse C || substring ||
-                    among ( [<literal string> [<r_name>] || (C)]* ) ||
-                    set <b_name> || unset <b_name> || <b_name> ||
-                    <r_name> || <g_name> || non [-] <g_name> ||
-                    true || false || ?
-
-P              ::=  [P]* || <declaration> ||
-                    <r_definition> || <g_definition> ||
-                    backwardmode ( P )
-
-<program>      ::=  P
-
-
-
-synonyms:      <+ for insert
-
- -[% footer %] diff --git a/js/arabic-stemmer.js b/js/arabic-stemmer.js deleted file mode 100644 index 7de24c0..0000000 --- a/js/arabic-stemmer.js +++ /dev/null @@ -1,1613 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var ArabicStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0640", -1, 1], - ["\u064B", -1, 1], - ["\u064C", -1, 1], - ["\u064D", -1, 1], - ["\u064E", -1, 1], - ["\u064F", -1, 1], - ["\u0650", -1, 1], - ["\u0651", -1, 1], - ["\u0652", -1, 1], - ["\u0660", -1, 2], - ["\u0661", -1, 3], - ["\u0662", -1, 4], - ["\u0663", -1, 5], - ["\u0664", -1, 6], - ["\u0665", -1, 7], - ["\u0666", -1, 8], - ["\u0667", -1, 9], - ["\u0668", -1, 10], - ["\u0669", -1, 11], - ["\uFE80", -1, 12], - ["\uFE81", -1, 16], - ["\uFE82", -1, 16], - ["\uFE83", -1, 13], - ["\uFE84", -1, 13], - ["\uFE85", -1, 17], - ["\uFE86", -1, 17], - ["\uFE87", -1, 14], - ["\uFE88", -1, 14], - ["\uFE89", -1, 15], - ["\uFE8A", -1, 15], - ["\uFE8B", -1, 15], - ["\uFE8C", -1, 15], - ["\uFE8D", -1, 18], - ["\uFE8E", -1, 18], - ["\uFE8F", -1, 19], - ["\uFE90", -1, 19], - ["\uFE91", -1, 19], - ["\uFE92", -1, 19], - ["\uFE93", -1, 20], - ["\uFE94", -1, 20], - ["\uFE95", -1, 21], - ["\uFE96", -1, 21], - ["\uFE97", -1, 21], - ["\uFE98", -1, 21], - ["\uFE99", -1, 22], - ["\uFE9A", -1, 22], - ["\uFE9B", -1, 22], - ["\uFE9C", -1, 22], - ["\uFE9D", -1, 23], - ["\uFE9E", -1, 23], - ["\uFE9F", -1, 23], - ["\uFEA0", -1, 23], - ["\uFEA1", -1, 24], - ["\uFEA2", -1, 24], - ["\uFEA3", -1, 24], - ["\uFEA4", -1, 24], - ["\uFEA5", -1, 25], - ["\uFEA6", -1, 25], - ["\uFEA7", -1, 25], - ["\uFEA8", -1, 25], - ["\uFEA9", -1, 26], - ["\uFEAA", -1, 26], - ["\uFEAB", -1, 27], - ["\uFEAC", -1, 27], - ["\uFEAD", -1, 28], - ["\uFEAE", -1, 28], - ["\uFEAF", -1, 29], - ["\uFEB0", -1, 29], - ["\uFEB1", -1, 30], - ["\uFEB2", -1, 30], - ["\uFEB3", -1, 30], - ["\uFEB4", -1, 30], - ["\uFEB5", -1, 31], - ["\uFEB6", -1, 31], - ["\uFEB7", -1, 31], - ["\uFEB8", -1, 31], - ["\uFEB9", -1, 32], - ["\uFEBA", -1, 32], - ["\uFEBB", -1, 32], - ["\uFEBC", -1, 32], - ["\uFEBD", -1, 33], - ["\uFEBE", -1, 33], - ["\uFEBF", -1, 33], - ["\uFEC0", -1, 33], - ["\uFEC1", -1, 34], - ["\uFEC2", -1, 34], - ["\uFEC3", -1, 34], - ["\uFEC4", -1, 34], - ["\uFEC5", -1, 35], - ["\uFEC6", -1, 35], - ["\uFEC7", -1, 35], - ["\uFEC8", -1, 35], - ["\uFEC9", -1, 36], - ["\uFECA", -1, 36], - ["\uFECB", -1, 36], - ["\uFECC", -1, 36], - ["\uFECD", -1, 37], - ["\uFECE", -1, 37], - ["\uFECF", -1, 37], - ["\uFED0", -1, 37], - ["\uFED1", -1, 38], - ["\uFED2", -1, 38], - ["\uFED3", -1, 38], - ["\uFED4", -1, 38], - ["\uFED5", -1, 39], - ["\uFED6", -1, 39], - ["\uFED7", -1, 39], - ["\uFED8", -1, 39], - ["\uFED9", -1, 40], - ["\uFEDA", -1, 40], - ["\uFEDB", -1, 40], - ["\uFEDC", -1, 40], - ["\uFEDD", -1, 41], - ["\uFEDE", -1, 41], - ["\uFEDF", -1, 41], - ["\uFEE0", -1, 41], - ["\uFEE1", -1, 42], - ["\uFEE2", -1, 42], - ["\uFEE3", -1, 42], - ["\uFEE4", -1, 42], - ["\uFEE5", -1, 43], - ["\uFEE6", -1, 43], - ["\uFEE7", -1, 43], - ["\uFEE8", -1, 43], - ["\uFEE9", -1, 44], - ["\uFEEA", -1, 44], - ["\uFEEB", -1, 44], - ["\uFEEC", -1, 44], - ["\uFEED", -1, 45], - ["\uFEEE", -1, 45], - ["\uFEEF", -1, 46], - ["\uFEF0", -1, 46], - ["\uFEF1", -1, 47], - ["\uFEF2", -1, 47], - ["\uFEF3", -1, 47], - ["\uFEF4", -1, 47], - ["\uFEF5", -1, 51], - ["\uFEF6", -1, 51], - ["\uFEF7", -1, 49], - ["\uFEF8", -1, 49], - ["\uFEF9", -1, 50], - ["\uFEFA", -1, 50], - ["\uFEFB", -1, 48], - ["\uFEFC", -1, 48] - ]; - - /** @const */ var a_1 = [ - ["\u0622", -1, 1], - ["\u0623", -1, 1], - ["\u0624", -1, 1], - ["\u0625", -1, 1], - ["\u0626", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["\u0622", -1, 1], - ["\u0623", -1, 1], - ["\u0624", -1, 2], - ["\u0625", -1, 1], - ["\u0626", -1, 3] - ]; - - /** @const */ var a_3 = [ - ["\u0627\u0644", -1, 2], - ["\u0628\u0627\u0644", -1, 1], - ["\u0643\u0627\u0644", -1, 1], - ["\u0644\u0644", -1, 2] - ]; - - /** @const */ var a_4 = [ - ["\u0623\u0622", -1, 2], - ["\u0623\u0623", -1, 1], - ["\u0623\u0624", -1, 1], - ["\u0623\u0625", -1, 4], - ["\u0623\u0627", -1, 3] - ]; - - /** @const */ var a_5 = [ - ["\u0641", -1, 1], - ["\u0648", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["\u0627\u0644", -1, 2], - ["\u0628\u0627\u0644", -1, 1], - ["\u0643\u0627\u0644", -1, 1], - ["\u0644\u0644", -1, 2] - ]; - - /** @const */ var a_7 = [ - ["\u0628", -1, 1], - ["\u0628\u0627", 0, -1], - ["\u0628\u0628", 0, 2], - ["\u0643\u0643", -1, 3] - ]; - - /** @const */ var a_8 = [ - ["\u0633\u0623", -1, 4], - ["\u0633\u062A", -1, 2], - ["\u0633\u0646", -1, 3], - ["\u0633\u064A", -1, 1] - ]; - - /** @const */ var a_9 = [ - ["\u062A\u0633\u062A", -1, 1], - ["\u0646\u0633\u062A", -1, 1], - ["\u064A\u0633\u062A", -1, 1] - ]; - - /** @const */ var a_10 = [ - ["\u0643\u0645\u0627", -1, 3], - ["\u0647\u0645\u0627", -1, 3], - ["\u0646\u0627", -1, 2], - ["\u0647\u0627", -1, 2], - ["\u0643", -1, 1], - ["\u0643\u0645", -1, 2], - ["\u0647\u0645", -1, 2], - ["\u0647\u0646", -1, 2], - ["\u0647", -1, 1], - ["\u064A", -1, 1] - ]; - - /** @const */ var a_11 = [ - ["\u0646", -1, 1] - ]; - - /** @const */ var a_12 = [ - ["\u0627", -1, 1], - ["\u0648", -1, 1], - ["\u064A", -1, 1] - ]; - - /** @const */ var a_13 = [ - ["\u0627\u062A", -1, 1] - ]; - - /** @const */ var a_14 = [ - ["\u062A", -1, 1] - ]; - - /** @const */ var a_15 = [ - ["\u0629", -1, 1] - ]; - - /** @const */ var a_16 = [ - ["\u064A", -1, 1] - ]; - - /** @const */ var a_17 = [ - ["\u0643\u0645\u0627", -1, 3], - ["\u0647\u0645\u0627", -1, 3], - ["\u0646\u0627", -1, 2], - ["\u0647\u0627", -1, 2], - ["\u0643", -1, 1], - ["\u0643\u0645", -1, 2], - ["\u0647\u0645", -1, 2], - ["\u0643\u0646", -1, 2], - ["\u0647\u0646", -1, 2], - ["\u0647", -1, 1], - ["\u0643\u0645\u0648", -1, 3], - ["\u0646\u064A", -1, 2] - ]; - - /** @const */ var a_18 = [ - ["\u0627", -1, 1], - ["\u062A\u0627", 0, 2], - ["\u062A\u0645\u0627", 0, 4], - ["\u0646\u0627", 0, 2], - ["\u062A", -1, 1], - ["\u0646", -1, 1], - ["\u0627\u0646", 5, 3], - ["\u062A\u0646", 5, 2], - ["\u0648\u0646", 5, 3], - ["\u064A\u0646", 5, 3], - ["\u064A", -1, 1] - ]; - - /** @const */ var a_19 = [ - ["\u0648\u0627", -1, 1], - ["\u062A\u0645", -1, 1] - ]; - - /** @const */ var a_20 = [ - ["\u0648", -1, 1], - ["\u062A\u0645\u0648", 0, 2] - ]; - - /** @const */ var a_21 = [ - ["\u0649", -1, 1] - ]; - - var /** boolean */ B_is_defined = false; - var /** boolean */ B_is_verb = false; - var /** boolean */ B_is_noun = false; - - - /** @return {boolean} */ - function r_Normalize_pre() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - lab2: { - var /** number */ v_3 = base.cursor; - lab3: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - if (among_var == 0) - { - break lab3; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("0")) - { - return false; - } - break; - case 3: - if (!base.slice_from("1")) - { - return false; - } - break; - case 4: - if (!base.slice_from("2")) - { - return false; - } - break; - case 5: - if (!base.slice_from("3")) - { - return false; - } - break; - case 6: - if (!base.slice_from("4")) - { - return false; - } - break; - case 7: - if (!base.slice_from("5")) - { - return false; - } - break; - case 8: - if (!base.slice_from("6")) - { - return false; - } - break; - case 9: - if (!base.slice_from("7")) - { - return false; - } - break; - case 10: - if (!base.slice_from("8")) - { - return false; - } - break; - case 11: - if (!base.slice_from("9")) - { - return false; - } - break; - case 12: - if (!base.slice_from("\u0621")) - { - return false; - } - break; - case 13: - if (!base.slice_from("\u0623")) - { - return false; - } - break; - case 14: - if (!base.slice_from("\u0625")) - { - return false; - } - break; - case 15: - if (!base.slice_from("\u0626")) - { - return false; - } - break; - case 16: - if (!base.slice_from("\u0622")) - { - return false; - } - break; - case 17: - if (!base.slice_from("\u0624")) - { - return false; - } - break; - case 18: - if (!base.slice_from("\u0627")) - { - return false; - } - break; - case 19: - if (!base.slice_from("\u0628")) - { - return false; - } - break; - case 20: - if (!base.slice_from("\u0629")) - { - return false; - } - break; - case 21: - if (!base.slice_from("\u062A")) - { - return false; - } - break; - case 22: - if (!base.slice_from("\u062B")) - { - return false; - } - break; - case 23: - if (!base.slice_from("\u062C")) - { - return false; - } - break; - case 24: - if (!base.slice_from("\u062D")) - { - return false; - } - break; - case 25: - if (!base.slice_from("\u062E")) - { - return false; - } - break; - case 26: - if (!base.slice_from("\u062F")) - { - return false; - } - break; - case 27: - if (!base.slice_from("\u0630")) - { - return false; - } - break; - case 28: - if (!base.slice_from("\u0631")) - { - return false; - } - break; - case 29: - if (!base.slice_from("\u0632")) - { - return false; - } - break; - case 30: - if (!base.slice_from("\u0633")) - { - return false; - } - break; - case 31: - if (!base.slice_from("\u0634")) - { - return false; - } - break; - case 32: - if (!base.slice_from("\u0635")) - { - return false; - } - break; - case 33: - if (!base.slice_from("\u0636")) - { - return false; - } - break; - case 34: - if (!base.slice_from("\u0637")) - { - return false; - } - break; - case 35: - if (!base.slice_from("\u0638")) - { - return false; - } - break; - case 36: - if (!base.slice_from("\u0639")) - { - return false; - } - break; - case 37: - if (!base.slice_from("\u063A")) - { - return false; - } - break; - case 38: - if (!base.slice_from("\u0641")) - { - return false; - } - break; - case 39: - if (!base.slice_from("\u0642")) - { - return false; - } - break; - case 40: - if (!base.slice_from("\u0643")) - { - return false; - } - break; - case 41: - if (!base.slice_from("\u0644")) - { - return false; - } - break; - case 42: - if (!base.slice_from("\u0645")) - { - return false; - } - break; - case 43: - if (!base.slice_from("\u0646")) - { - return false; - } - break; - case 44: - if (!base.slice_from("\u0647")) - { - return false; - } - break; - case 45: - if (!base.slice_from("\u0648")) - { - return false; - } - break; - case 46: - if (!base.slice_from("\u0649")) - { - return false; - } - break; - case 47: - if (!base.slice_from("\u064A")) - { - return false; - } - break; - case 48: - if (!base.slice_from("\u0644\u0627")) - { - return false; - } - break; - case 49: - if (!base.slice_from("\u0644\u0623")) - { - return false; - } - break; - case 50: - if (!base.slice_from("\u0644\u0625")) - { - return false; - } - break; - case 51: - if (!base.slice_from("\u0644\u0622")) - { - return false; - } - break; - } - break lab2; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_Normalize_post() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - lab0: { - base.limit_backward = base.cursor; base.cursor = base.limit; - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_from("\u0621")) - { - return false; - } - base.cursor = base.limit_backward; - } - base.cursor = v_1; - var /** number */ v_2 = base.cursor; - lab1: { - while(true) - { - var /** number */ v_3 = base.cursor; - lab2: { - lab3: { - var /** number */ v_4 = base.cursor; - lab4: { - base.bra = base.cursor; - among_var = base.find_among(a_2); - if (among_var == 0) - { - break lab4; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u0627")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u0648")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u064A")) - { - return false; - } - break; - } - break lab3; - } - base.cursor = v_4; - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - continue; - } - base.cursor = v_3; - break; - } - } - base.cursor = v_2; - return true; - }; - - /** @return {boolean} */ - function r_Checks1() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_3); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (base.current.length <= 4) - { - return false; - } - B_is_noun = true; - B_is_verb = false; - B_is_defined = true; - break; - case 2: - if (base.current.length <= 3) - { - return false; - } - B_is_noun = true; - B_is_verb = false; - B_is_defined = true; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Prefix_Step1() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_4); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_from("\u0623")) - { - return false; - } - break; - case 2: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_from("\u0622")) - { - return false; - } - break; - case 3: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_from("\u0627")) - { - return false; - } - break; - case 4: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_from("\u0625")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Prefix_Step2() { - base.bra = base.cursor; - if (base.find_among(a_5) == 0) - { - return false; - } - base.ket = base.cursor; - if (base.current.length <= 3) - { - return false; - } - { - var /** number */ v_1 = base.cursor; - lab0: { - if (!(base.eq_s("\u0627"))) - { - break lab0; - } - return false; - } - base.cursor = v_1; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Prefix_Step3a_Noun() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_6); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (base.current.length <= 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (base.current.length <= 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Prefix_Step3b_Noun() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_7); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_from("\u0628")) - { - return false; - } - break; - case 3: - if (base.current.length <= 3) - { - return false; - } - if (!base.slice_from("\u0643")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Prefix_Step3_Verb() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_8); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (base.current.length <= 4) - { - return false; - } - if (!base.slice_from("\u064A")) - { - return false; - } - break; - case 2: - if (base.current.length <= 4) - { - return false; - } - if (!base.slice_from("\u062A")) - { - return false; - } - break; - case 3: - if (base.current.length <= 4) - { - return false; - } - if (!base.slice_from("\u0646")) - { - return false; - } - break; - case 4: - if (base.current.length <= 4) - { - return false; - } - if (!base.slice_from("\u0623")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Prefix_Step4_Verb() { - base.bra = base.cursor; - if (base.find_among(a_9) == 0) - { - return false; - } - base.ket = base.cursor; - if (base.current.length <= 4) - { - return false; - } - B_is_verb = true; - B_is_noun = false; - if (!base.slice_from("\u0627\u0633\u062A")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step1a() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_10); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (base.current.length < 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (base.current.length < 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (base.current.length < 6) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step1b() { - base.ket = base.cursor; - if (base.find_among_b(a_11) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length <= 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step2a() { - base.ket = base.cursor; - if (base.find_among_b(a_12) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length <= 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step2b() { - base.ket = base.cursor; - if (base.find_among_b(a_13) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length < 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step2c1() { - base.ket = base.cursor; - if (base.find_among_b(a_14) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length < 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step2c2() { - base.ket = base.cursor; - if (base.find_among_b(a_15) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length < 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Noun_Step3() { - base.ket = base.cursor; - if (base.find_among_b(a_16) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length < 3) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Verb_Step1() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_17); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (base.current.length < 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (base.current.length < 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (base.current.length < 6) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Verb_Step2a() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_18); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (base.current.length < 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (base.current.length < 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (base.current.length <= 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 4: - if (base.current.length < 6) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Verb_Step2b() { - base.ket = base.cursor; - if (base.find_among_b(a_19) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.current.length < 5) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_Verb_Step2c() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_20); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (base.current.length < 4) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (base.current.length < 6) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Suffix_All_alef_maqsura() { - base.ket = base.cursor; - if (base.find_among_b(a_21) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_from("\u064A")) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - B_is_noun = true; - B_is_verb = true; - B_is_defined = false; - var /** number */ v_1 = base.cursor; - r_Checks1(); - base.cursor = v_1; - r_Normalize_pre(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - if (!B_is_verb) - { - break lab2; - } - lab3: { - var /** number */ v_5 = base.limit - base.cursor; - lab4: { - { - var v_6 = 1; - while(true) - { - var /** number */ v_7 = base.limit - base.cursor; - lab5: { - if (!r_Suffix_Verb_Step1()) - { - break lab5; - } - v_6--; - continue; - } - base.cursor = base.limit - v_7; - break; - } - if (v_6 > 0) - { - break lab4; - } - } - lab6: { - var /** number */ v_8 = base.limit - base.cursor; - lab7: { - if (!r_Suffix_Verb_Step2a()) - { - break lab7; - } - break lab6; - } - base.cursor = base.limit - v_8; - lab8: { - if (!r_Suffix_Verb_Step2c()) - { - break lab8; - } - break lab6; - } - base.cursor = base.limit - v_8; - if (base.cursor <= base.limit_backward) - { - break lab4; - } - base.cursor--; - } - break lab3; - } - base.cursor = base.limit - v_5; - lab9: { - if (!r_Suffix_Verb_Step2b()) - { - break lab9; - } - break lab3; - } - base.cursor = base.limit - v_5; - if (!r_Suffix_Verb_Step2a()) - { - break lab2; - } - } - break lab1; - } - base.cursor = base.limit - v_4; - lab10: { - if (!B_is_noun) - { - break lab10; - } - var /** number */ v_9 = base.limit - base.cursor; - lab11: { - lab12: { - var /** number */ v_10 = base.limit - base.cursor; - lab13: { - if (!r_Suffix_Noun_Step2c2()) - { - break lab13; - } - break lab12; - } - base.cursor = base.limit - v_10; - lab14: { - lab15: { - if (!B_is_defined) - { - break lab15; - } - break lab14; - } - if (!r_Suffix_Noun_Step1a()) - { - break lab14; - } - lab16: { - var /** number */ v_12 = base.limit - base.cursor; - lab17: { - if (!r_Suffix_Noun_Step2a()) - { - break lab17; - } - break lab16; - } - base.cursor = base.limit - v_12; - lab18: { - if (!r_Suffix_Noun_Step2b()) - { - break lab18; - } - break lab16; - } - base.cursor = base.limit - v_12; - lab19: { - if (!r_Suffix_Noun_Step2c1()) - { - break lab19; - } - break lab16; - } - base.cursor = base.limit - v_12; - if (base.cursor <= base.limit_backward) - { - break lab14; - } - base.cursor--; - } - break lab12; - } - base.cursor = base.limit - v_10; - lab20: { - if (!r_Suffix_Noun_Step1b()) - { - break lab20; - } - lab21: { - var /** number */ v_13 = base.limit - base.cursor; - lab22: { - if (!r_Suffix_Noun_Step2a()) - { - break lab22; - } - break lab21; - } - base.cursor = base.limit - v_13; - lab23: { - if (!r_Suffix_Noun_Step2b()) - { - break lab23; - } - break lab21; - } - base.cursor = base.limit - v_13; - if (!r_Suffix_Noun_Step2c1()) - { - break lab20; - } - } - break lab12; - } - base.cursor = base.limit - v_10; - lab24: { - lab25: { - if (!B_is_defined) - { - break lab25; - } - break lab24; - } - if (!r_Suffix_Noun_Step2a()) - { - break lab24; - } - break lab12; - } - base.cursor = base.limit - v_10; - if (!r_Suffix_Noun_Step2b()) - { - base.cursor = base.limit - v_9; - break lab11; - } - } - } - if (!r_Suffix_Noun_Step3()) - { - break lab10; - } - break lab1; - } - base.cursor = base.limit - v_4; - if (!r_Suffix_All_alef_maqsura()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_3; - base.cursor = base.limit_backward; - var /** number */ v_15 = base.cursor; - lab26: { - var /** number */ v_16 = base.cursor; - lab27: { - if (!r_Prefix_Step1()) - { - base.cursor = v_16; - break lab27; - } - } - var /** number */ v_17 = base.cursor; - lab28: { - if (!r_Prefix_Step2()) - { - base.cursor = v_17; - break lab28; - } - } - lab29: { - var /** number */ v_18 = base.cursor; - lab30: { - if (!r_Prefix_Step3a_Noun()) - { - break lab30; - } - break lab29; - } - base.cursor = v_18; - lab31: { - if (!B_is_noun) - { - break lab31; - } - if (!r_Prefix_Step3b_Noun()) - { - break lab31; - } - break lab29; - } - base.cursor = v_18; - if (!B_is_verb) - { - break lab26; - } - var /** number */ v_19 = base.cursor; - lab32: { - if (!r_Prefix_Step3_Verb()) - { - base.cursor = v_19; - break lab32; - } - } - if (!r_Prefix_Step4_Verb()) - { - break lab26; - } - } - } - base.cursor = v_15; - r_Normalize_post(); - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['ArabicStemmer'] = ArabicStemmer; diff --git a/js/armenian-stemmer.js b/js/armenian-stemmer.js deleted file mode 100644 index 669e63c..0000000 --- a/js/armenian-stemmer.js +++ /dev/null @@ -1,391 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var ArmenianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0580\u0578\u0580\u0564", -1, 1], - ["\u0565\u0580\u0578\u0580\u0564", 0, 1], - ["\u0561\u056C\u056B", -1, 1], - ["\u0561\u056F\u056B", -1, 1], - ["\u0578\u0580\u0561\u056F", -1, 1], - ["\u0565\u0572", -1, 1], - ["\u0561\u056F\u0561\u0576", -1, 1], - ["\u0561\u0580\u0561\u0576", -1, 1], - ["\u0565\u0576", -1, 1], - ["\u0565\u056F\u0565\u0576", 8, 1], - ["\u0565\u0580\u0565\u0576", 8, 1], - ["\u0578\u0580\u0567\u0576", -1, 1], - ["\u056B\u0576", -1, 1], - ["\u0563\u056B\u0576", 12, 1], - ["\u0578\u057E\u056B\u0576", 12, 1], - ["\u056C\u0561\u0575\u0576", -1, 1], - ["\u057E\u0578\u0582\u0576", -1, 1], - ["\u057A\u0565\u057D", -1, 1], - ["\u056B\u057E", -1, 1], - ["\u0561\u057F", -1, 1], - ["\u0561\u057E\u0565\u057F", -1, 1], - ["\u056F\u0578\u057F", -1, 1], - ["\u0562\u0561\u0580", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["\u0561", -1, 1], - ["\u0561\u0581\u0561", 0, 1], - ["\u0565\u0581\u0561", 0, 1], - ["\u057E\u0565", -1, 1], - ["\u0561\u0581\u0580\u056B", -1, 1], - ["\u0561\u0581\u056B", -1, 1], - ["\u0565\u0581\u056B", -1, 1], - ["\u057E\u0565\u0581\u056B", 6, 1], - ["\u0561\u056C", -1, 1], - ["\u0568\u0561\u056C", 8, 1], - ["\u0561\u0576\u0561\u056C", 8, 1], - ["\u0565\u0576\u0561\u056C", 8, 1], - ["\u0561\u0581\u0576\u0561\u056C", 8, 1], - ["\u0565\u056C", -1, 1], - ["\u0568\u0565\u056C", 13, 1], - ["\u0576\u0565\u056C", 13, 1], - ["\u0581\u0576\u0565\u056C", 15, 1], - ["\u0565\u0581\u0576\u0565\u056C", 16, 1], - ["\u0579\u0565\u056C", 13, 1], - ["\u057E\u0565\u056C", 13, 1], - ["\u0561\u0581\u057E\u0565\u056C", 19, 1], - ["\u0565\u0581\u057E\u0565\u056C", 19, 1], - ["\u057F\u0565\u056C", 13, 1], - ["\u0561\u057F\u0565\u056C", 22, 1], - ["\u0578\u057F\u0565\u056C", 22, 1], - ["\u056F\u0578\u057F\u0565\u056C", 24, 1], - ["\u057E\u0561\u056E", -1, 1], - ["\u0578\u0582\u0574", -1, 1], - ["\u057E\u0578\u0582\u0574", 27, 1], - ["\u0561\u0576", -1, 1], - ["\u0581\u0561\u0576", 29, 1], - ["\u0561\u0581\u0561\u0576", 30, 1], - ["\u0561\u0581\u0580\u056B\u0576", -1, 1], - ["\u0561\u0581\u056B\u0576", -1, 1], - ["\u0565\u0581\u056B\u0576", -1, 1], - ["\u057E\u0565\u0581\u056B\u0576", 34, 1], - ["\u0561\u056C\u056B\u057D", -1, 1], - ["\u0565\u056C\u056B\u057D", -1, 1], - ["\u0561\u057E", -1, 1], - ["\u0561\u0581\u0561\u057E", 38, 1], - ["\u0565\u0581\u0561\u057E", 38, 1], - ["\u0561\u056C\u0578\u057E", -1, 1], - ["\u0565\u056C\u0578\u057E", -1, 1], - ["\u0561\u0580", -1, 1], - ["\u0561\u0581\u0561\u0580", 43, 1], - ["\u0565\u0581\u0561\u0580", 43, 1], - ["\u0561\u0581\u0580\u056B\u0580", -1, 1], - ["\u0561\u0581\u056B\u0580", -1, 1], - ["\u0565\u0581\u056B\u0580", -1, 1], - ["\u057E\u0565\u0581\u056B\u0580", 48, 1], - ["\u0561\u0581", -1, 1], - ["\u0565\u0581", -1, 1], - ["\u0561\u0581\u0580\u0565\u0581", 51, 1], - ["\u0561\u056C\u0578\u0582\u0581", -1, 1], - ["\u0565\u056C\u0578\u0582\u0581", -1, 1], - ["\u0561\u056C\u0578\u0582", -1, 1], - ["\u0565\u056C\u0578\u0582", -1, 1], - ["\u0561\u0584", -1, 1], - ["\u0581\u0561\u0584", 57, 1], - ["\u0561\u0581\u0561\u0584", 58, 1], - ["\u0561\u0581\u0580\u056B\u0584", -1, 1], - ["\u0561\u0581\u056B\u0584", -1, 1], - ["\u0565\u0581\u056B\u0584", -1, 1], - ["\u057E\u0565\u0581\u056B\u0584", 62, 1], - ["\u0561\u0576\u0584", -1, 1], - ["\u0581\u0561\u0576\u0584", 64, 1], - ["\u0561\u0581\u0561\u0576\u0584", 65, 1], - ["\u0561\u0581\u0580\u056B\u0576\u0584", -1, 1], - ["\u0561\u0581\u056B\u0576\u0584", -1, 1], - ["\u0565\u0581\u056B\u0576\u0584", -1, 1], - ["\u057E\u0565\u0581\u056B\u0576\u0584", 69, 1] - ]; - - /** @const */ var a_2 = [ - ["\u0578\u0580\u0564", -1, 1], - ["\u0578\u0582\u0575\u0569", -1, 1], - ["\u0578\u0582\u0570\u056B", -1, 1], - ["\u0581\u056B", -1, 1], - ["\u056B\u056C", -1, 1], - ["\u0561\u056F", -1, 1], - ["\u0575\u0561\u056F", 5, 1], - ["\u0561\u0576\u0561\u056F", 5, 1], - ["\u056B\u056F", -1, 1], - ["\u0578\u0582\u056F", -1, 1], - ["\u0561\u0576", -1, 1], - ["\u057A\u0561\u0576", 10, 1], - ["\u057D\u057F\u0561\u0576", 10, 1], - ["\u0561\u0580\u0561\u0576", 10, 1], - ["\u0565\u0572\u0567\u0576", -1, 1], - ["\u0575\u0578\u0582\u0576", -1, 1], - ["\u0578\u0582\u0569\u0575\u0578\u0582\u0576", 15, 1], - ["\u0561\u056E\u0578", -1, 1], - ["\u056B\u0579", -1, 1], - ["\u0578\u0582\u057D", -1, 1], - ["\u0578\u0582\u057D\u057F", -1, 1], - ["\u0563\u0561\u0580", -1, 1], - ["\u057E\u0578\u0580", -1, 1], - ["\u0561\u057E\u0578\u0580", 22, 1], - ["\u0578\u0581", -1, 1], - ["\u0561\u0576\u0585\u0581", -1, 1], - ["\u0578\u0582", -1, 1], - ["\u0584", -1, 1], - ["\u0579\u0565\u0584", 27, 1], - ["\u056B\u0584", 27, 1], - ["\u0561\u056C\u056B\u0584", 29, 1], - ["\u0561\u0576\u056B\u0584", 29, 1], - ["\u057E\u0561\u056E\u0584", 27, 1], - ["\u0578\u0582\u0575\u0584", 27, 1], - ["\u0565\u0576\u0584", 27, 1], - ["\u0578\u0576\u0584", 27, 1], - ["\u0578\u0582\u0576\u0584", 27, 1], - ["\u0574\u0578\u0582\u0576\u0584", 36, 1], - ["\u056B\u0579\u0584", 27, 1], - ["\u0561\u0580\u0584", 27, 1] - ]; - - /** @const */ var a_3 = [ - ["\u057D\u0561", -1, 1], - ["\u057E\u0561", -1, 1], - ["\u0561\u0574\u0562", -1, 1], - ["\u0564", -1, 1], - ["\u0561\u0576\u0564", 3, 1], - ["\u0578\u0582\u0569\u0575\u0561\u0576\u0564", 4, 1], - ["\u057E\u0561\u0576\u0564", 4, 1], - ["\u0578\u057B\u0564", 3, 1], - ["\u0565\u0580\u0564", 3, 1], - ["\u0576\u0565\u0580\u0564", 8, 1], - ["\u0578\u0582\u0564", 3, 1], - ["\u0568", -1, 1], - ["\u0561\u0576\u0568", 11, 1], - ["\u0578\u0582\u0569\u0575\u0561\u0576\u0568", 12, 1], - ["\u057E\u0561\u0576\u0568", 12, 1], - ["\u0578\u057B\u0568", 11, 1], - ["\u0565\u0580\u0568", 11, 1], - ["\u0576\u0565\u0580\u0568", 16, 1], - ["\u056B", -1, 1], - ["\u057E\u056B", 18, 1], - ["\u0565\u0580\u056B", 18, 1], - ["\u0576\u0565\u0580\u056B", 20, 1], - ["\u0561\u0576\u0578\u0582\u0574", -1, 1], - ["\u0565\u0580\u0578\u0582\u0574", -1, 1], - ["\u0576\u0565\u0580\u0578\u0582\u0574", 23, 1], - ["\u0576", -1, 1], - ["\u0561\u0576", 25, 1], - ["\u0578\u0582\u0569\u0575\u0561\u0576", 26, 1], - ["\u057E\u0561\u0576", 26, 1], - ["\u056B\u0576", 25, 1], - ["\u0565\u0580\u056B\u0576", 29, 1], - ["\u0576\u0565\u0580\u056B\u0576", 30, 1], - ["\u0578\u0582\u0569\u0575\u0561\u0576\u0576", 25, 1], - ["\u0565\u0580\u0576", 25, 1], - ["\u0576\u0565\u0580\u0576", 33, 1], - ["\u0578\u0582\u0576", 25, 1], - ["\u0578\u057B", -1, 1], - ["\u0578\u0582\u0569\u0575\u0561\u0576\u057D", -1, 1], - ["\u057E\u0561\u0576\u057D", -1, 1], - ["\u0578\u057B\u057D", -1, 1], - ["\u0578\u057E", -1, 1], - ["\u0561\u0576\u0578\u057E", 40, 1], - ["\u057E\u0578\u057E", 40, 1], - ["\u0565\u0580\u0578\u057E", 40, 1], - ["\u0576\u0565\u0580\u0578\u057E", 43, 1], - ["\u0565\u0580", -1, 1], - ["\u0576\u0565\u0580", 45, 1], - ["\u0581", -1, 1], - ["\u056B\u0581", 47, 1], - ["\u057E\u0561\u0576\u056B\u0581", 48, 1], - ["\u0578\u057B\u056B\u0581", 48, 1], - ["\u057E\u056B\u0581", 48, 1], - ["\u0565\u0580\u056B\u0581", 48, 1], - ["\u0576\u0565\u0580\u056B\u0581", 52, 1], - ["\u0581\u056B\u0581", 48, 1], - ["\u0578\u0581", 47, 1], - ["\u0578\u0582\u0581", 47, 1] - ]; - - /** @const */ var /** Array */ g_v = [209, 4, 128, 0, 18]; - - var /** number */ I_p2 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - lab2: { - if (!(base.in_grouping(g_v, 1377, 1413))) - { - break lab2; - } - break golab1; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_pV = base.cursor; - golab3: while(true) - { - lab4: { - if (!(base.out_grouping(g_v, 1377, 1413))) - { - break lab4; - } - break golab3; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 1377, 1413))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 1377, 1413))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_adjective() { - base.ket = base.cursor; - if (base.find_among_b(a_0) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_verb() { - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_noun() { - base.ket = base.cursor; - if (base.find_among_b(a_2) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_ending() { - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_3 = base.limit_backward; - base.limit_backward = I_pV; - var /** number */ v_4 = base.limit - base.cursor; - r_ending(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_verb(); - base.cursor = base.limit - v_5; - var /** number */ v_6 = base.limit - base.cursor; - r_adjective(); - base.cursor = base.limit - v_6; - var /** number */ v_7 = base.limit - base.cursor; - r_noun(); - base.cursor = base.limit - v_7; - base.limit_backward = v_3; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['ArmenianStemmer'] = ArmenianStemmer; diff --git a/js/base-stemmer.js b/js/base-stemmer.js deleted file mode 100644 index 930078b..0000000 --- a/js/base-stemmer.js +++ /dev/null @@ -1,296 +0,0 @@ -/**@constructor*/ -const BaseStemmer = function() { - this.setCurrent = function(value) { - this.current = value; - this.cursor = 0; - this.limit = this.current.length; - this.limit_backward = 0; - this.bra = this.cursor; - this.ket = this.limit; - }; - - this.getCurrent = function() { - return this.current; - }; - - this.copy_from = function(other) { - this.current = other.current; - this.cursor = other.cursor; - this.limit = other.limit; - this.limit_backward = other.limit_backward; - this.bra = other.bra; - this.ket = other.ket; - }; - - this.in_grouping = function(s, min, max) { - if (this.cursor >= this.limit) return false; - var ch = this.current.charCodeAt(this.cursor); - if (ch > max || ch < min) return false; - ch -= min; - if ((s[ch >>> 3] & (0x1 << (ch & 0x7))) == 0) return false; - this.cursor++; - return true; - }; - - this.in_grouping_b = function(s, min, max) { - if (this.cursor <= this.limit_backward) return false; - var ch = this.current.charCodeAt(this.cursor - 1); - if (ch > max || ch < min) return false; - ch -= min; - if ((s[ch >>> 3] & (0x1 << (ch & 0x7))) == 0) return false; - this.cursor--; - return true; - }; - - this.out_grouping = function(s, min, max) { - if (this.cursor >= this.limit) return false; - var ch = this.current.charCodeAt(this.cursor); - if (ch > max || ch < min) { - this.cursor++; - return true; - } - ch -= min; - if ((s[ch >>> 3] & (0X1 << (ch & 0x7))) == 0) { - this.cursor++; - return true; - } - return false; - }; - - this.out_grouping_b = function(s, min, max) { - if (this.cursor <= this.limit_backward) return false; - var ch = this.current.charCodeAt(this.cursor - 1); - if (ch > max || ch < min) { - this.cursor--; - return true; - } - ch -= min; - if ((s[ch >>> 3] & (0x1 << (ch & 0x7))) == 0) { - this.cursor--; - return true; - } - return false; - }; - - this.eq_s = function(s) - { - if (this.limit - this.cursor < s.length) return false; - if (this.current.slice(this.cursor, this.cursor + s.length) != s) - { - return false; - } - this.cursor += s.length; - return true; - }; - - this.eq_s_b = function(s) - { - if (this.cursor - this.limit_backward < s.length) return false; - if (this.current.slice(this.cursor - s.length, this.cursor) != s) - { - return false; - } - this.cursor -= s.length; - return true; - }; - - /** @return {number} */ this.find_among = function(v) - { - var i = 0; - var j = v.length; - - var c = this.cursor; - var l = this.limit; - - var common_i = 0; - var common_j = 0; - - var first_key_inspected = false; - - while (true) - { - var k = i + ((j - i) >>> 1); - var diff = 0; - var common = common_i < common_j ? common_i : common_j; // smaller - // w[0]: string, w[1]: substring_i, w[2]: result, w[3]: function (optional) - var w = v[k]; - var i2; - for (i2 = common; i2 < w[0].length; i2++) - { - if (c + common == l) - { - diff = -1; - break; - } - diff = this.current.charCodeAt(c + common) - w[0].charCodeAt(i2); - if (diff != 0) break; - common++; - } - if (diff < 0) - { - j = k; - common_j = common; - } - else - { - i = k; - common_i = common; - } - if (j - i <= 1) - { - if (i > 0) break; // v->s has been inspected - if (j == i) break; // only one item in v - - // - but now we need to go round once more to get - // v->s inspected. This looks messy, but is actually - // the optimal approach. - - if (first_key_inspected) break; - first_key_inspected = true; - } - } - do { - var w = v[i]; - if (common_i >= w[0].length) - { - this.cursor = c + w[0].length; - if (w.length < 4) return w[2]; - var res = w[3](this); - this.cursor = c + w[0].length; - if (res) return w[2]; - } - i = w[1]; - } while (i >= 0); - return 0; - }; - - // find_among_b is for backwards processing. Same comments apply - this.find_among_b = function(v) - { - var i = 0; - var j = v.length - - var c = this.cursor; - var lb = this.limit_backward; - - var common_i = 0; - var common_j = 0; - - var first_key_inspected = false; - - while (true) - { - var k = i + ((j - i) >> 1); - var diff = 0; - var common = common_i < common_j ? common_i : common_j; - var w = v[k]; - var i2; - for (i2 = w[0].length - 1 - common; i2 >= 0; i2--) - { - if (c - common == lb) - { - diff = -1; - break; - } - diff = this.current.charCodeAt(c - 1 - common) - w[0].charCodeAt(i2); - if (diff != 0) break; - common++; - } - if (diff < 0) - { - j = k; - common_j = common; - } - else - { - i = k; - common_i = common; - } - if (j - i <= 1) - { - if (i > 0) break; - if (j == i) break; - if (first_key_inspected) break; - first_key_inspected = true; - } - } - do { - var w = v[i]; - if (common_i >= w[0].length) - { - this.cursor = c - w[0].length; - if (w.length < 4) return w[2]; - var res = w[3](this); - this.cursor = c - w[0].length; - if (res) return w[2]; - } - i = w[1]; - } while (i >= 0); - return 0; - }; - - /* to replace chars between c_bra and c_ket in this.current by the - * chars in s. - */ - this.replace_s = function(c_bra, c_ket, s) - { - var adjustment = s.length - (c_ket - c_bra); - this.current = this.current.slice(0, c_bra) + s + this.current.slice(c_ket); - this.limit += adjustment; - if (this.cursor >= c_ket) this.cursor += adjustment; - else if (this.cursor > c_bra) this.cursor = c_bra; - return adjustment; - }; - - this.slice_check = function() - { - if (this.bra < 0 || - this.bra > this.ket || - this.ket > this.limit || - this.limit > this.current.length) - { - return false; - } - return true; - }; - - this.slice_from = function(s) - { - var result = false; - if (this.slice_check()) - { - this.replace_s(this.bra, this.ket, s); - result = true; - } - return result; - }; - - this.slice_del = function() - { - return this.slice_from(""); - }; - - this.insert = function(c_bra, c_ket, s) - { - var adjustment = this.replace_s(c_bra, c_ket, s); - if (c_bra <= this.bra) this.bra += adjustment; - if (c_bra <= this.ket) this.ket += adjustment; - }; - - this.slice_to = function() - { - var result = ''; - if (this.slice_check()) - { - result = this.current.slice(this.bra, this.ket); - } - return result; - }; - - this.assign_to = function() - { - return this.current.slice(0, this.limit); - }; -}; - -window['BaseStemmer'] = BaseStemmer; diff --git a/js/basque-stemmer.js b/js/basque-stemmer.js deleted file mode 100644 index dbd9e76..0000000 --- a/js/basque-stemmer.js +++ /dev/null @@ -1,849 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var BasqueStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["idea", -1, 1], - ["bidea", 0, 1], - ["kidea", 0, 1], - ["pidea", 0, 1], - ["kundea", -1, 1], - ["galea", -1, 1], - ["tailea", -1, 1], - ["tzailea", -1, 1], - ["gunea", -1, 1], - ["kunea", -1, 1], - ["tzaga", -1, 1], - ["gaia", -1, 1], - ["aldia", -1, 1], - ["taldia", 12, 1], - ["karia", -1, 1], - ["garria", -1, 2], - ["karria", -1, 1], - ["ka", -1, 1], - ["tzaka", 17, 1], - ["la", -1, 1], - ["mena", -1, 1], - ["pena", -1, 1], - ["kina", -1, 1], - ["ezina", -1, 1], - ["tezina", 23, 1], - ["kuna", -1, 1], - ["tuna", -1, 1], - ["kizuna", -1, 1], - ["era", -1, 1], - ["bera", 28, 1], - ["arabera", 29, 4], - ["kera", 28, 1], - ["pera", 28, 1], - ["orra", -1, 1], - ["korra", 33, 1], - ["dura", -1, 1], - ["gura", -1, 1], - ["kura", -1, 1], - ["tura", -1, 1], - ["eta", -1, 1], - ["keta", 39, 1], - ["gailua", -1, 1], - ["eza", -1, 1], - ["erreza", 42, 1], - ["tza", -1, 2], - ["gaitza", 44, 1], - ["kaitza", 44, 1], - ["kuntza", 44, 1], - ["ide", -1, 1], - ["bide", 48, 1], - ["kide", 48, 1], - ["pide", 48, 1], - ["kunde", -1, 1], - ["tzake", -1, 1], - ["tzeke", -1, 1], - ["le", -1, 1], - ["gale", 55, 1], - ["taile", 55, 1], - ["tzaile", 55, 1], - ["gune", -1, 1], - ["kune", -1, 1], - ["tze", -1, 1], - ["atze", 61, 1], - ["gai", -1, 1], - ["aldi", -1, 1], - ["taldi", 64, 1], - ["ki", -1, 1], - ["ari", -1, 1], - ["kari", 67, 1], - ["lari", 67, 1], - ["tari", 67, 1], - ["etari", 70, 1], - ["garri", -1, 2], - ["karri", -1, 1], - ["arazi", -1, 1], - ["tarazi", 74, 1], - ["an", -1, 1], - ["ean", 76, 1], - ["rean", 77, 1], - ["kan", 76, 1], - ["etan", 76, 1], - ["atseden", -1, 3], - ["men", -1, 1], - ["pen", -1, 1], - ["kin", -1, 1], - ["rekin", 84, 1], - ["ezin", -1, 1], - ["tezin", 86, 1], - ["tun", -1, 1], - ["kizun", -1, 1], - ["go", -1, 1], - ["ago", 90, 1], - ["tio", -1, 1], - ["dako", -1, 1], - ["or", -1, 1], - ["kor", 94, 1], - ["tzat", -1, 1], - ["du", -1, 1], - ["gailu", -1, 1], - ["tu", -1, 1], - ["atu", 99, 1], - ["aldatu", 100, 1], - ["tatu", 100, 1], - ["baditu", 99, 5], - ["ez", -1, 1], - ["errez", 104, 1], - ["tzez", 104, 1], - ["gaitz", -1, 1], - ["kaitz", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["ada", -1, 1], - ["kada", 0, 1], - ["anda", -1, 1], - ["denda", -1, 1], - ["gabea", -1, 1], - ["kabea", -1, 1], - ["aldea", -1, 1], - ["kaldea", 6, 1], - ["taldea", 6, 1], - ["ordea", -1, 1], - ["zalea", -1, 1], - ["tzalea", 10, 1], - ["gilea", -1, 1], - ["emea", -1, 1], - ["kumea", -1, 1], - ["nea", -1, 1], - ["enea", 15, 1], - ["zionea", 15, 1], - ["unea", 15, 1], - ["gunea", 18, 1], - ["pea", -1, 1], - ["aurrea", -1, 1], - ["tea", -1, 1], - ["kotea", 22, 1], - ["artea", 22, 1], - ["ostea", 22, 1], - ["etxea", -1, 1], - ["ga", -1, 1], - ["anga", 27, 1], - ["gaia", -1, 1], - ["aldia", -1, 1], - ["taldia", 30, 1], - ["handia", -1, 1], - ["mendia", -1, 1], - ["geia", -1, 1], - ["egia", -1, 1], - ["degia", 35, 1], - ["tegia", 35, 1], - ["nahia", -1, 1], - ["ohia", -1, 1], - ["kia", -1, 1], - ["tokia", 40, 1], - ["oia", -1, 1], - ["koia", 42, 1], - ["aria", -1, 1], - ["karia", 44, 1], - ["laria", 44, 1], - ["taria", 44, 1], - ["eria", -1, 1], - ["keria", 48, 1], - ["teria", 48, 1], - ["garria", -1, 2], - ["larria", -1, 1], - ["kirria", -1, 1], - ["duria", -1, 1], - ["asia", -1, 1], - ["tia", -1, 1], - ["ezia", -1, 1], - ["bizia", -1, 1], - ["ontzia", -1, 1], - ["ka", -1, 1], - ["joka", 60, 3], - ["aurka", 60, 10], - ["ska", 60, 1], - ["xka", 60, 1], - ["zka", 60, 1], - ["gibela", -1, 1], - ["gela", -1, 1], - ["kaila", -1, 1], - ["skila", -1, 1], - ["tila", -1, 1], - ["ola", -1, 1], - ["na", -1, 1], - ["kana", 72, 1], - ["ena", 72, 1], - ["garrena", 74, 1], - ["gerrena", 74, 1], - ["urrena", 74, 1], - ["zaina", 72, 1], - ["tzaina", 78, 1], - ["kina", 72, 1], - ["mina", 72, 1], - ["garna", 72, 1], - ["una", 72, 1], - ["duna", 83, 1], - ["asuna", 83, 1], - ["tasuna", 85, 1], - ["ondoa", -1, 1], - ["kondoa", 87, 1], - ["ngoa", -1, 1], - ["zioa", -1, 1], - ["koa", -1, 1], - ["takoa", 91, 1], - ["zkoa", 91, 1], - ["noa", -1, 1], - ["zinoa", 94, 1], - ["aroa", -1, 1], - ["taroa", 96, 1], - ["zaroa", 96, 1], - ["eroa", -1, 1], - ["oroa", -1, 1], - ["osoa", -1, 1], - ["toa", -1, 1], - ["ttoa", 102, 1], - ["ztoa", 102, 1], - ["txoa", -1, 1], - ["tzoa", -1, 1], - ["\u00F1oa", -1, 1], - ["ra", -1, 1], - ["ara", 108, 1], - ["dara", 109, 1], - ["liara", 109, 1], - ["tiara", 109, 1], - ["tara", 109, 1], - ["etara", 113, 1], - ["tzara", 109, 1], - ["bera", 108, 1], - ["kera", 108, 1], - ["pera", 108, 1], - ["ora", 108, 2], - ["tzarra", 108, 1], - ["korra", 108, 1], - ["tra", 108, 1], - ["sa", -1, 1], - ["osa", 123, 1], - ["ta", -1, 1], - ["eta", 125, 1], - ["keta", 126, 1], - ["sta", 125, 1], - ["dua", -1, 1], - ["mendua", 129, 1], - ["ordua", 129, 1], - ["lekua", -1, 1], - ["burua", -1, 1], - ["durua", -1, 1], - ["tsua", -1, 1], - ["tua", -1, 1], - ["mentua", 136, 1], - ["estua", 136, 1], - ["txua", -1, 1], - ["zua", -1, 1], - ["tzua", 140, 1], - ["za", -1, 1], - ["eza", 142, 1], - ["eroza", 142, 1], - ["tza", 142, 2], - ["koitza", 145, 1], - ["antza", 145, 1], - ["gintza", 145, 1], - ["kintza", 145, 1], - ["kuntza", 145, 1], - ["gabe", -1, 1], - ["kabe", -1, 1], - ["kide", -1, 1], - ["alde", -1, 1], - ["kalde", 154, 1], - ["talde", 154, 1], - ["orde", -1, 1], - ["ge", -1, 1], - ["zale", -1, 1], - ["tzale", 159, 1], - ["gile", -1, 1], - ["eme", -1, 1], - ["kume", -1, 1], - ["ne", -1, 1], - ["zione", 164, 1], - ["une", 164, 1], - ["gune", 166, 1], - ["pe", -1, 1], - ["aurre", -1, 1], - ["te", -1, 1], - ["kote", 170, 1], - ["arte", 170, 1], - ["oste", 170, 1], - ["etxe", -1, 1], - ["gai", -1, 1], - ["di", -1, 1], - ["aldi", 176, 1], - ["taldi", 177, 1], - ["geldi", 176, 8], - ["handi", 176, 1], - ["mendi", 176, 1], - ["gei", -1, 1], - ["egi", -1, 1], - ["degi", 183, 1], - ["tegi", 183, 1], - ["nahi", -1, 1], - ["ohi", -1, 1], - ["ki", -1, 1], - ["toki", 188, 1], - ["oi", -1, 1], - ["goi", 190, 1], - ["koi", 190, 1], - ["ari", -1, 1], - ["kari", 193, 1], - ["lari", 193, 1], - ["tari", 193, 1], - ["garri", -1, 2], - ["larri", -1, 1], - ["kirri", -1, 1], - ["duri", -1, 1], - ["asi", -1, 1], - ["ti", -1, 1], - ["ontzi", -1, 1], - ["\u00F1i", -1, 1], - ["ak", -1, 1], - ["ek", -1, 1], - ["tarik", -1, 1], - ["gibel", -1, 1], - ["ail", -1, 1], - ["kail", 209, 1], - ["kan", -1, 1], - ["tan", -1, 1], - ["etan", 212, 1], - ["en", -1, 4], - ["ren", 214, 2], - ["garren", 215, 1], - ["gerren", 215, 1], - ["urren", 215, 1], - ["ten", 214, 4], - ["tzen", 214, 4], - ["zain", -1, 1], - ["tzain", 221, 1], - ["kin", -1, 1], - ["min", -1, 1], - ["dun", -1, 1], - ["asun", -1, 1], - ["tasun", 226, 1], - ["aizun", -1, 1], - ["ondo", -1, 1], - ["kondo", 229, 1], - ["go", -1, 1], - ["ngo", 231, 1], - ["zio", -1, 1], - ["ko", -1, 1], - ["trako", 234, 5], - ["tako", 234, 1], - ["etako", 236, 1], - ["eko", 234, 1], - ["tariko", 234, 1], - ["sko", 234, 1], - ["tuko", 234, 1], - ["minutuko", 241, 6], - ["zko", 234, 1], - ["no", -1, 1], - ["zino", 244, 1], - ["ro", -1, 1], - ["aro", 246, 1], - ["igaro", 247, 9], - ["taro", 247, 1], - ["zaro", 247, 1], - ["ero", 246, 1], - ["giro", 246, 1], - ["oro", 246, 1], - ["oso", -1, 1], - ["to", -1, 1], - ["tto", 255, 1], - ["zto", 255, 1], - ["txo", -1, 1], - ["tzo", -1, 1], - ["gintzo", 259, 1], - ["\u00F1o", -1, 1], - ["zp", -1, 1], - ["ar", -1, 1], - ["dar", 263, 1], - ["behar", 263, 1], - ["zehar", 263, 7], - ["liar", 263, 1], - ["tiar", 263, 1], - ["tar", 263, 1], - ["tzar", 263, 1], - ["or", -1, 2], - ["kor", 271, 1], - ["os", -1, 1], - ["ket", -1, 1], - ["du", -1, 1], - ["mendu", 275, 1], - ["ordu", 275, 1], - ["leku", -1, 1], - ["buru", -1, 2], - ["duru", -1, 1], - ["tsu", -1, 1], - ["tu", -1, 1], - ["tatu", 282, 4], - ["mentu", 282, 1], - ["estu", 282, 1], - ["txu", -1, 1], - ["zu", -1, 1], - ["tzu", 287, 1], - ["gintzu", 288, 1], - ["z", -1, 1], - ["ez", 290, 1], - ["eroz", 290, 1], - ["tz", 290, 1], - ["koitz", 293, 1] - ]; - - /** @const */ var a_2 = [ - ["zlea", -1, 2], - ["keria", -1, 1], - ["la", -1, 1], - ["era", -1, 1], - ["dade", -1, 1], - ["tade", -1, 1], - ["date", -1, 1], - ["tate", -1, 1], - ["gi", -1, 1], - ["ki", -1, 1], - ["ik", -1, 1], - ["lanik", 10, 1], - ["rik", 10, 1], - ["larik", 12, 1], - ["ztik", 10, 1], - ["go", -1, 1], - ["ro", -1, 1], - ["ero", 16, 1], - ["to", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab2; - } - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab4; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab4; - } - base.cursor++; - } - break lab3; - } - base.cursor = v_3; - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab2; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - } - break lab1; - } - base.cursor = v_2; - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab0; - } - lab9: { - var /** number */ v_6 = base.cursor; - lab10: { - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab10; - } - golab11: while(true) - { - lab12: { - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab12; - } - break golab11; - } - if (base.cursor >= base.limit) - { - break lab10; - } - base.cursor++; - } - break lab9; - } - base.cursor = v_6; - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab0; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_pV = base.cursor; - } - base.cursor = v_1; - var /** number */ v_8 = base.cursor; - lab13: { - golab14: while(true) - { - lab15: { - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab15; - } - break golab14; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab16: while(true) - { - lab17: { - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab17; - } - break golab16; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p1 = base.cursor; - golab18: while(true) - { - lab19: { - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab19; - } - break golab18; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab20: while(true) - { - lab21: { - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab21; - } - break golab20; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_8; - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_aditzak() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_from("atseden")) - { - return false; - } - break; - case 4: - if (!base.slice_from("arabera")) - { - return false; - } - break; - case 5: - if (!base.slice_from("baditu")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_izenak() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_1); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_from("jok")) - { - return false; - } - break; - case 4: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 5: - if (!base.slice_from("tra")) - { - return false; - } - break; - case 6: - if (!base.slice_from("minutu")) - { - return false; - } - break; - case 7: - if (!base.slice_from("zehar")) - { - return false; - } - break; - case 8: - if (!base.slice_from("geldi")) - { - return false; - } - break; - case 9: - if (!base.slice_from("igaro")) - { - return false; - } - break; - case 10: - if (!base.slice_from("aurka")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_adjetiboak() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("z")) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - while(true) - { - var /** number */ v_2 = base.limit - base.cursor; - lab0: { - if (!r_aditzak()) - { - break lab0; - } - continue; - } - base.cursor = base.limit - v_2; - break; - } - while(true) - { - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - if (!r_izenak()) - { - break lab1; - } - continue; - } - base.cursor = base.limit - v_3; - break; - } - var /** number */ v_4 = base.limit - base.cursor; - r_adjetiboak(); - base.cursor = base.limit - v_4; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['BasqueStemmer'] = BasqueStemmer; diff --git a/js/catalan-stemmer.js b/js/catalan-stemmer.js deleted file mode 100644 index 34f535d..0000000 --- a/js/catalan-stemmer.js +++ /dev/null @@ -1,927 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var CatalanStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 7], - ["\u00B7", 0, 6], - ["\u00E0", 0, 1], - ["\u00E1", 0, 1], - ["\u00E8", 0, 2], - ["\u00E9", 0, 2], - ["\u00EC", 0, 3], - ["\u00ED", 0, 3], - ["\u00EF", 0, 3], - ["\u00F2", 0, 4], - ["\u00F3", 0, 4], - ["\u00FA", 0, 5], - ["\u00FC", 0, 5] - ]; - - /** @const */ var a_1 = [ - ["la", -1, 1], - ["-la", 0, 1], - ["sela", 0, 1], - ["le", -1, 1], - ["me", -1, 1], - ["-me", 4, 1], - ["se", -1, 1], - ["-te", -1, 1], - ["hi", -1, 1], - ["'hi", 8, 1], - ["li", -1, 1], - ["-li", 10, 1], - ["'l", -1, 1], - ["'m", -1, 1], - ["-m", -1, 1], - ["'n", -1, 1], - ["-n", -1, 1], - ["ho", -1, 1], - ["'ho", 17, 1], - ["lo", -1, 1], - ["selo", 19, 1], - ["'s", -1, 1], - ["las", -1, 1], - ["selas", 22, 1], - ["les", -1, 1], - ["-les", 24, 1], - ["'ls", -1, 1], - ["-ls", -1, 1], - ["'ns", -1, 1], - ["-ns", -1, 1], - ["ens", -1, 1], - ["los", -1, 1], - ["selos", 31, 1], - ["nos", -1, 1], - ["-nos", 33, 1], - ["vos", -1, 1], - ["us", -1, 1], - ["-us", 36, 1], - ["'t", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["ica", -1, 4], - ["l\u00F3gica", 0, 3], - ["enca", -1, 1], - ["ada", -1, 2], - ["ancia", -1, 1], - ["encia", -1, 1], - ["\u00E8ncia", -1, 1], - ["\u00EDcia", -1, 1], - ["logia", -1, 3], - ["inia", -1, 1], - ["\u00EDinia", 9, 1], - ["eria", -1, 1], - ["\u00E0ria", -1, 1], - ["at\u00F2ria", -1, 1], - ["alla", -1, 1], - ["ella", -1, 1], - ["\u00EDvola", -1, 1], - ["ima", -1, 1], - ["\u00EDssima", 17, 1], - ["qu\u00EDssima", 18, 5], - ["ana", -1, 1], - ["ina", -1, 1], - ["era", -1, 1], - ["sfera", 22, 1], - ["ora", -1, 1], - ["dora", 24, 1], - ["adora", 25, 1], - ["adura", -1, 1], - ["esa", -1, 1], - ["osa", -1, 1], - ["assa", -1, 1], - ["essa", -1, 1], - ["issa", -1, 1], - ["eta", -1, 1], - ["ita", -1, 1], - ["ota", -1, 1], - ["ista", -1, 1], - ["ialista", 36, 1], - ["ionista", 36, 1], - ["iva", -1, 1], - ["ativa", 39, 1], - ["n\u00E7a", -1, 1], - ["log\u00EDa", -1, 3], - ["ic", -1, 4], - ["\u00EDstic", 43, 1], - ["enc", -1, 1], - ["esc", -1, 1], - ["ud", -1, 1], - ["atge", -1, 1], - ["ble", -1, 1], - ["able", 49, 1], - ["ible", 49, 1], - ["isme", -1, 1], - ["ialisme", 52, 1], - ["ionisme", 52, 1], - ["ivisme", 52, 1], - ["aire", -1, 1], - ["icte", -1, 1], - ["iste", -1, 1], - ["ici", -1, 1], - ["\u00EDci", -1, 1], - ["logi", -1, 3], - ["ari", -1, 1], - ["tori", -1, 1], - ["al", -1, 1], - ["il", -1, 1], - ["all", -1, 1], - ["ell", -1, 1], - ["\u00EDvol", -1, 1], - ["isam", -1, 1], - ["issem", -1, 1], - ["\u00ECssem", -1, 1], - ["\u00EDssem", -1, 1], - ["\u00EDssim", -1, 1], - ["qu\u00EDssim", 73, 5], - ["amen", -1, 1], - ["\u00ECssin", -1, 1], - ["ar", -1, 1], - ["ificar", 77, 1], - ["egar", 77, 1], - ["ejar", 77, 1], - ["itar", 77, 1], - ["itzar", 77, 1], - ["fer", -1, 1], - ["or", -1, 1], - ["dor", 84, 1], - ["dur", -1, 1], - ["doras", -1, 1], - ["ics", -1, 4], - ["l\u00F3gics", 88, 3], - ["uds", -1, 1], - ["nces", -1, 1], - ["ades", -1, 2], - ["ancies", -1, 1], - ["encies", -1, 1], - ["\u00E8ncies", -1, 1], - ["\u00EDcies", -1, 1], - ["logies", -1, 3], - ["inies", -1, 1], - ["\u00EDnies", -1, 1], - ["eries", -1, 1], - ["\u00E0ries", -1, 1], - ["at\u00F2ries", -1, 1], - ["bles", -1, 1], - ["ables", 103, 1], - ["ibles", 103, 1], - ["imes", -1, 1], - ["\u00EDssimes", 106, 1], - ["qu\u00EDssimes", 107, 5], - ["formes", -1, 1], - ["ismes", -1, 1], - ["ialismes", 110, 1], - ["ines", -1, 1], - ["eres", -1, 1], - ["ores", -1, 1], - ["dores", 114, 1], - ["idores", 115, 1], - ["dures", -1, 1], - ["eses", -1, 1], - ["oses", -1, 1], - ["asses", -1, 1], - ["ictes", -1, 1], - ["ites", -1, 1], - ["otes", -1, 1], - ["istes", -1, 1], - ["ialistes", 124, 1], - ["ionistes", 124, 1], - ["iques", -1, 4], - ["l\u00F3giques", 127, 3], - ["ives", -1, 1], - ["atives", 129, 1], - ["log\u00EDes", -1, 3], - ["alleng\u00FCes", -1, 1], - ["icis", -1, 1], - ["\u00EDcis", -1, 1], - ["logis", -1, 3], - ["aris", -1, 1], - ["toris", -1, 1], - ["ls", -1, 1], - ["als", 138, 1], - ["ells", 138, 1], - ["ims", -1, 1], - ["\u00EDssims", 141, 1], - ["qu\u00EDssims", 142, 5], - ["ions", -1, 1], - ["cions", 144, 1], - ["acions", 145, 2], - ["esos", -1, 1], - ["osos", -1, 1], - ["assos", -1, 1], - ["issos", -1, 1], - ["ers", -1, 1], - ["ors", -1, 1], - ["dors", 152, 1], - ["adors", 153, 1], - ["idors", 153, 1], - ["ats", -1, 1], - ["itats", 156, 1], - ["bilitats", 157, 1], - ["ivitats", 157, 1], - ["ativitats", 159, 1], - ["\u00EFtats", 156, 1], - ["ets", -1, 1], - ["ants", -1, 1], - ["ents", -1, 1], - ["ments", 164, 1], - ["aments", 165, 1], - ["ots", -1, 1], - ["uts", -1, 1], - ["ius", -1, 1], - ["trius", 169, 1], - ["atius", 169, 1], - ["\u00E8s", -1, 1], - ["\u00E9s", -1, 1], - ["\u00EDs", -1, 1], - ["d\u00EDs", 174, 1], - ["\u00F3s", -1, 1], - ["itat", -1, 1], - ["bilitat", 177, 1], - ["ivitat", 177, 1], - ["ativitat", 179, 1], - ["\u00EFtat", -1, 1], - ["et", -1, 1], - ["ant", -1, 1], - ["ent", -1, 1], - ["ient", 184, 1], - ["ment", 184, 1], - ["ament", 186, 1], - ["isament", 187, 1], - ["ot", -1, 1], - ["isseu", -1, 1], - ["\u00ECsseu", -1, 1], - ["\u00EDsseu", -1, 1], - ["triu", -1, 1], - ["\u00EDssiu", -1, 1], - ["atiu", -1, 1], - ["\u00F3", -1, 1], - ["i\u00F3", 196, 1], - ["ci\u00F3", 197, 1], - ["aci\u00F3", 198, 1] - ]; - - /** @const */ var a_3 = [ - ["aba", -1, 1], - ["esca", -1, 1], - ["isca", -1, 1], - ["\u00EFsca", -1, 1], - ["ada", -1, 1], - ["ida", -1, 1], - ["uda", -1, 1], - ["\u00EFda", -1, 1], - ["ia", -1, 1], - ["aria", 8, 1], - ["iria", 8, 1], - ["ara", -1, 1], - ["iera", -1, 1], - ["ira", -1, 1], - ["adora", -1, 1], - ["\u00EFra", -1, 1], - ["ava", -1, 1], - ["ixa", -1, 1], - ["itza", -1, 1], - ["\u00EDa", -1, 1], - ["ar\u00EDa", 19, 1], - ["er\u00EDa", 19, 1], - ["ir\u00EDa", 19, 1], - ["\u00EFa", -1, 1], - ["isc", -1, 1], - ["\u00EFsc", -1, 1], - ["ad", -1, 1], - ["ed", -1, 1], - ["id", -1, 1], - ["ie", -1, 1], - ["re", -1, 1], - ["dre", 30, 1], - ["ase", -1, 1], - ["iese", -1, 1], - ["aste", -1, 1], - ["iste", -1, 1], - ["ii", -1, 1], - ["ini", -1, 1], - ["esqui", -1, 1], - ["eixi", -1, 1], - ["itzi", -1, 1], - ["am", -1, 1], - ["em", -1, 1], - ["arem", 42, 1], - ["irem", 42, 1], - ["\u00E0rem", 42, 1], - ["\u00EDrem", 42, 1], - ["\u00E0ssem", 42, 1], - ["\u00E9ssem", 42, 1], - ["iguem", 42, 1], - ["\u00EFguem", 42, 1], - ["avem", 42, 1], - ["\u00E0vem", 42, 1], - ["\u00E1vem", 42, 1], - ["ir\u00ECem", 42, 1], - ["\u00EDem", 42, 1], - ["ar\u00EDem", 55, 1], - ["ir\u00EDem", 55, 1], - ["assim", -1, 1], - ["essim", -1, 1], - ["issim", -1, 1], - ["\u00E0ssim", -1, 1], - ["\u00E8ssim", -1, 1], - ["\u00E9ssim", -1, 1], - ["\u00EDssim", -1, 1], - ["\u00EFm", -1, 1], - ["an", -1, 1], - ["aban", 66, 1], - ["arian", 66, 1], - ["aran", 66, 1], - ["ieran", 66, 1], - ["iran", 66, 1], - ["\u00EDan", 66, 1], - ["ar\u00EDan", 72, 1], - ["er\u00EDan", 72, 1], - ["ir\u00EDan", 72, 1], - ["en", -1, 1], - ["ien", 76, 1], - ["arien", 77, 1], - ["irien", 77, 1], - ["aren", 76, 1], - ["eren", 76, 1], - ["iren", 76, 1], - ["\u00E0ren", 76, 1], - ["\u00EFren", 76, 1], - ["asen", 76, 1], - ["iesen", 76, 1], - ["assen", 76, 1], - ["essen", 76, 1], - ["issen", 76, 1], - ["\u00E9ssen", 76, 1], - ["\u00EFssen", 76, 1], - ["esquen", 76, 1], - ["isquen", 76, 1], - ["\u00EFsquen", 76, 1], - ["aven", 76, 1], - ["ixen", 76, 1], - ["eixen", 96, 1], - ["\u00EFxen", 76, 1], - ["\u00EFen", 76, 1], - ["in", -1, 1], - ["inin", 100, 1], - ["sin", 100, 1], - ["isin", 102, 1], - ["assin", 102, 1], - ["essin", 102, 1], - ["issin", 102, 1], - ["\u00EFssin", 102, 1], - ["esquin", 100, 1], - ["eixin", 100, 1], - ["aron", -1, 1], - ["ieron", -1, 1], - ["ar\u00E1n", -1, 1], - ["er\u00E1n", -1, 1], - ["ir\u00E1n", -1, 1], - ["i\u00EFn", -1, 1], - ["ado", -1, 1], - ["ido", -1, 1], - ["ando", -1, 2], - ["iendo", -1, 1], - ["io", -1, 1], - ["ixo", -1, 1], - ["eixo", 121, 1], - ["\u00EFxo", -1, 1], - ["itzo", -1, 1], - ["ar", -1, 1], - ["tzar", 125, 1], - ["er", -1, 1], - ["eixer", 127, 1], - ["ir", -1, 1], - ["ador", -1, 1], - ["as", -1, 1], - ["abas", 131, 1], - ["adas", 131, 1], - ["idas", 131, 1], - ["aras", 131, 1], - ["ieras", 131, 1], - ["\u00EDas", 131, 1], - ["ar\u00EDas", 137, 1], - ["er\u00EDas", 137, 1], - ["ir\u00EDas", 137, 1], - ["ids", -1, 1], - ["es", -1, 1], - ["ades", 142, 1], - ["ides", 142, 1], - ["udes", 142, 1], - ["\u00EFdes", 142, 1], - ["atges", 142, 1], - ["ies", 142, 1], - ["aries", 148, 1], - ["iries", 148, 1], - ["ares", 142, 1], - ["ires", 142, 1], - ["adores", 142, 1], - ["\u00EFres", 142, 1], - ["ases", 142, 1], - ["ieses", 142, 1], - ["asses", 142, 1], - ["esses", 142, 1], - ["isses", 142, 1], - ["\u00EFsses", 142, 1], - ["ques", 142, 1], - ["esques", 161, 1], - ["\u00EFsques", 161, 1], - ["aves", 142, 1], - ["ixes", 142, 1], - ["eixes", 165, 1], - ["\u00EFxes", 142, 1], - ["\u00EFes", 142, 1], - ["abais", -1, 1], - ["arais", -1, 1], - ["ierais", -1, 1], - ["\u00EDais", -1, 1], - ["ar\u00EDais", 172, 1], - ["er\u00EDais", 172, 1], - ["ir\u00EDais", 172, 1], - ["aseis", -1, 1], - ["ieseis", -1, 1], - ["asteis", -1, 1], - ["isteis", -1, 1], - ["inis", -1, 1], - ["sis", -1, 1], - ["isis", 181, 1], - ["assis", 181, 1], - ["essis", 181, 1], - ["issis", 181, 1], - ["\u00EFssis", 181, 1], - ["esquis", -1, 1], - ["eixis", -1, 1], - ["itzis", -1, 1], - ["\u00E1is", -1, 1], - ["ar\u00E9is", -1, 1], - ["er\u00E9is", -1, 1], - ["ir\u00E9is", -1, 1], - ["ams", -1, 1], - ["ados", -1, 1], - ["idos", -1, 1], - ["amos", -1, 1], - ["\u00E1bamos", 197, 1], - ["\u00E1ramos", 197, 1], - ["i\u00E9ramos", 197, 1], - ["\u00EDamos", 197, 1], - ["ar\u00EDamos", 201, 1], - ["er\u00EDamos", 201, 1], - ["ir\u00EDamos", 201, 1], - ["aremos", -1, 1], - ["eremos", -1, 1], - ["iremos", -1, 1], - ["\u00E1semos", -1, 1], - ["i\u00E9semos", -1, 1], - ["imos", -1, 1], - ["adors", -1, 1], - ["ass", -1, 1], - ["erass", 212, 1], - ["ess", -1, 1], - ["ats", -1, 1], - ["its", -1, 1], - ["ents", -1, 1], - ["\u00E0s", -1, 1], - ["ar\u00E0s", 218, 1], - ["ir\u00E0s", 218, 1], - ["ar\u00E1s", -1, 1], - ["er\u00E1s", -1, 1], - ["ir\u00E1s", -1, 1], - ["\u00E9s", -1, 1], - ["ar\u00E9s", 224, 1], - ["\u00EDs", -1, 1], - ["i\u00EFs", -1, 1], - ["at", -1, 1], - ["it", -1, 1], - ["ant", -1, 1], - ["ent", -1, 1], - ["int", -1, 1], - ["ut", -1, 1], - ["\u00EFt", -1, 1], - ["au", -1, 1], - ["erau", 235, 1], - ["ieu", -1, 1], - ["ineu", -1, 1], - ["areu", -1, 1], - ["ireu", -1, 1], - ["\u00E0reu", -1, 1], - ["\u00EDreu", -1, 1], - ["asseu", -1, 1], - ["esseu", -1, 1], - ["eresseu", 244, 1], - ["\u00E0sseu", -1, 1], - ["\u00E9sseu", -1, 1], - ["igueu", -1, 1], - ["\u00EFgueu", -1, 1], - ["\u00E0veu", -1, 1], - ["\u00E1veu", -1, 1], - ["itzeu", -1, 1], - ["\u00ECeu", -1, 1], - ["ir\u00ECeu", 253, 1], - ["\u00EDeu", -1, 1], - ["ar\u00EDeu", 255, 1], - ["ir\u00EDeu", 255, 1], - ["assiu", -1, 1], - ["issiu", -1, 1], - ["\u00E0ssiu", -1, 1], - ["\u00E8ssiu", -1, 1], - ["\u00E9ssiu", -1, 1], - ["\u00EDssiu", -1, 1], - ["\u00EFu", -1, 1], - ["ix", -1, 1], - ["eix", 265, 1], - ["\u00EFx", -1, 1], - ["itz", -1, 1], - ["i\u00E0", -1, 1], - ["ar\u00E0", -1, 1], - ["ir\u00E0", -1, 1], - ["itz\u00E0", -1, 1], - ["ar\u00E1", -1, 1], - ["er\u00E1", -1, 1], - ["ir\u00E1", -1, 1], - ["ir\u00E8", -1, 1], - ["ar\u00E9", -1, 1], - ["er\u00E9", -1, 1], - ["ir\u00E9", -1, 1], - ["\u00ED", -1, 1], - ["i\u00EF", -1, 1], - ["i\u00F3", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["a", -1, 1], - ["e", -1, 1], - ["i", -1, 1], - ["\u00EFn", -1, 1], - ["o", -1, 1], - ["ir", -1, 1], - ["s", -1, 1], - ["is", 6, 1], - ["os", 6, 1], - ["\u00EFs", 6, 1], - ["it", -1, 1], - ["eu", -1, 1], - ["iu", -1, 1], - ["iqu", -1, 2], - ["itz", -1, 1], - ["\u00E0", -1, 1], - ["\u00E1", -1, 1], - ["\u00E9", -1, 1], - ["\u00EC", -1, 1], - ["\u00ED", -1, 1], - ["\u00EF", -1, 1], - ["\u00F3", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 129, 81, 6, 10]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - lab2: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab2; - } - break golab1; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab3: while(true) - { - lab4: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab4; - } - break golab3; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p1 = base.cursor; - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_cleaning() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("a")) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - case 3: - if (!base.slice_from("i")) - { - return false; - } - break; - case 4: - if (!base.slice_from("o")) - { - return false; - } - break; - case 5: - if (!base.slice_from("u")) - { - return false; - } - break; - case 6: - if (!base.slice_from(".")) - { - return false; - } - break; - case 7: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_attached_pronoun() { - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("log")) - { - return false; - } - break; - case 4: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("ic")) - { - return false; - } - break; - case 5: - if (!r_R1()) - { - return false; - } - if (!base.slice_from("c")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_verb_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_residual_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R1()) - { - return false; - } - if (!base.slice_from("ic")) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_attached_pronoun(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - if (!r_standard_suffix()) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_4; - if (!r_verb_suffix()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_3; - var /** number */ v_5 = base.limit - base.cursor; - r_residual_suffix(); - base.cursor = base.limit - v_5; - base.cursor = base.limit_backward; - var /** number */ v_6 = base.cursor; - r_cleaning(); - base.cursor = v_6; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['CatalanStemmer'] = CatalanStemmer; diff --git a/js/danish-stemmer.js b/js/danish-stemmer.js deleted file mode 100644 index 4c8941b..0000000 --- a/js/danish-stemmer.js +++ /dev/null @@ -1,312 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var DanishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["hed", -1, 1], - ["ethed", 0, 1], - ["ered", -1, 1], - ["e", -1, 1], - ["erede", 3, 1], - ["ende", 3, 1], - ["erende", 5, 1], - ["ene", 3, 1], - ["erne", 3, 1], - ["ere", 3, 1], - ["en", -1, 1], - ["heden", 10, 1], - ["eren", 10, 1], - ["er", -1, 1], - ["heder", 13, 1], - ["erer", 13, 1], - ["s", -1, 2], - ["heds", 16, 1], - ["es", 16, 1], - ["endes", 18, 1], - ["erendes", 19, 1], - ["enes", 18, 1], - ["ernes", 18, 1], - ["eres", 18, 1], - ["ens", 16, 1], - ["hedens", 24, 1], - ["erens", 24, 1], - ["ers", 16, 1], - ["ets", 16, 1], - ["erets", 28, 1], - ["et", -1, 1], - ["eret", 30, 1] - ]; - - /** @const */ var a_1 = [ - ["gd", -1, -1], - ["dt", -1, -1], - ["gt", -1, -1], - ["kt", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["ig", -1, 1], - ["lig", 0, 1], - ["elig", 1, 1], - ["els", -1, 1], - ["l\u00F8st", -1, 2] - ]; - - /** @const */ var /** Array */ g_c = [119, 223, 119, 1]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 48, 0, 128]; - - /** @const */ var /** Array */ g_s_ending = [239, 254, 42, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 16]; - - var /** number */ I_x = 0; - var /** number */ I_p1 = 0; - var /** string */ S_ch = ''; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - var /** number */ v_1 = base.cursor; - { - var /** number */ c1 = base.cursor + 3; - if (c1 > base.limit) - { - return false; - } - base.cursor = c1; - } - I_x = base.cursor; - base.cursor = v_1; - golab0: while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - if (!(base.in_grouping(g_v, 97, 248))) - { - break lab1; - } - base.cursor = v_2; - break golab0; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_v, 97, 248))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - lab4: { - if (I_p1 >= I_x) - { - break lab4; - } - I_p1 = I_x; - } - return true; - }; - - /** @return {boolean} */ - function r_main_suffix() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.in_grouping_b(g_s_ending, 97, 229))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_consonant_pair() { - var /** number */ v_1 = base.limit - base.cursor; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_3 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - base.limit_backward = v_3; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_3; - base.cursor = base.limit - v_1; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_other_suffix() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("st"))) - { - break lab0; - } - base.bra = base.cursor; - if (!(base.eq_s_b("ig"))) - { - break lab0; - } - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_1; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_3 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - base.limit_backward = v_3; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_3; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - r_consonant_pair(); - base.cursor = base.limit - v_4; - break; - case 2: - if (!base.slice_from("l\u00F8s")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_undouble() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (!(base.in_grouping_b(g_c, 98, 122))) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - S_ch = base.slice_to(); - if (S_ch == '') - { - return false; - } - base.limit_backward = v_2; - if (!(base.eq_s_b(S_ch))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_mark_regions(); - base.cursor = v_1; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_main_suffix(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_consonant_pair(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_other_suffix(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_undouble(); - base.cursor = base.limit - v_5; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['DanishStemmer'] = DanishStemmer; diff --git a/js/dutch-stemmer.js b/js/dutch-stemmer.js deleted file mode 100644 index 422d710..0000000 --- a/js/dutch-stemmer.js +++ /dev/null @@ -1,671 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var DutchStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 6], - ["\u00E1", 0, 1], - ["\u00E4", 0, 1], - ["\u00E9", 0, 2], - ["\u00EB", 0, 2], - ["\u00ED", 0, 3], - ["\u00EF", 0, 3], - ["\u00F3", 0, 4], - ["\u00F6", 0, 4], - ["\u00FA", 0, 5], - ["\u00FC", 0, 5] - ]; - - /** @const */ var a_1 = [ - ["", -1, 3], - ["I", 0, 2], - ["Y", 0, 1] - ]; - - /** @const */ var a_2 = [ - ["dd", -1, -1], - ["kk", -1, -1], - ["tt", -1, -1] - ]; - - /** @const */ var a_3 = [ - ["ene", -1, 2], - ["se", -1, 3], - ["en", -1, 2], - ["heden", 2, 1], - ["s", -1, 3] - ]; - - /** @const */ var a_4 = [ - ["end", -1, 1], - ["ig", -1, 2], - ["ing", -1, 1], - ["lijk", -1, 3], - ["baar", -1, 4], - ["bar", -1, 5] - ]; - - /** @const */ var a_5 = [ - ["aa", -1, -1], - ["ee", -1, -1], - ["oo", -1, -1], - ["uu", -1, -1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128]; - - /** @const */ var /** Array */ g_v_I = [1, 0, 0, 17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128]; - - /** @const */ var /** Array */ g_v_j = [17, 67, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** boolean */ B_e_found = false; - - - /** @return {boolean} */ - function r_prelude() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - while(true) - { - var /** number */ v_2 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("a")) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - case 3: - if (!base.slice_from("i")) - { - return false; - } - break; - case 4: - if (!base.slice_from("o")) - { - return false; - } - break; - case 5: - if (!base.slice_from("u")) - { - return false; - } - break; - case 6: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_2; - break; - } - base.cursor = v_1; - var /** number */ v_3 = base.cursor; - lab1: { - base.bra = base.cursor; - if (!(base.eq_s("y"))) - { - base.cursor = v_3; - break lab1; - } - base.ket = base.cursor; - if (!base.slice_from("Y")) - { - return false; - } - } - while(true) - { - var /** number */ v_4 = base.cursor; - lab2: { - golab3: while(true) - { - var /** number */ v_5 = base.cursor; - lab4: { - if (!(base.in_grouping(g_v, 97, 232))) - { - break lab4; - } - base.bra = base.cursor; - lab5: { - var /** number */ v_6 = base.cursor; - lab6: { - if (!(base.eq_s("i"))) - { - break lab6; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 232))) - { - break lab6; - } - if (!base.slice_from("I")) - { - return false; - } - break lab5; - } - base.cursor = v_6; - if (!(base.eq_s("y"))) - { - break lab4; - } - base.ket = base.cursor; - if (!base.slice_from("Y")) - { - return false; - } - } - base.cursor = v_5; - break golab3; - } - base.cursor = v_5; - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - continue; - } - base.cursor = v_4; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - I_p2 = base.limit; - golab0: while(true) - { - lab1: { - if (!(base.in_grouping(g_v, 97, 232))) - { - break lab1; - } - break golab0; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_v, 97, 232))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - lab4: { - if (I_p1 >= 3) - { - break lab4; - } - I_p1 = 3; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 232))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 232))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p2 = base.cursor; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_1); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("y")) - { - return false; - } - break; - case 2: - if (!base.slice_from("i")) - { - return false; - } - break; - case 3: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_undouble() { - var /** number */ v_1 = base.limit - base.cursor; - if (base.find_among_b(a_2) == 0) - { - return false; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_e_ending() { - B_e_found = false; - base.ket = base.cursor; - if (!(base.eq_s_b("e"))) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - if (!(base.out_grouping_b(g_v, 97, 232))) - { - return false; - } - base.cursor = base.limit - v_1; - if (!base.slice_del()) - { - return false; - } - B_e_found = true; - if (!r_undouble()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_en_ending() { - if (!r_R1()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - if (!(base.out_grouping_b(g_v, 97, 232))) - { - return false; - } - base.cursor = base.limit - v_1; - { - var /** number */ v_2 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("gem"))) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_2; - } - if (!base.slice_del()) - { - return false; - } - if (!r_undouble()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - break lab0; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - break lab0; - } - if (!base.slice_from("heid")) - { - return false; - } - break; - case 2: - if (!r_en_ending()) - { - break lab0; - } - break; - case 3: - if (!r_R1()) - { - break lab0; - } - if (!(base.out_grouping_b(g_v_j, 97, 232))) - { - break lab0; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - base.cursor = base.limit - v_1; - var /** number */ v_2 = base.limit - base.cursor; - r_e_ending(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (!(base.eq_s_b("heid"))) - { - break lab1; - } - base.bra = base.cursor; - if (!r_R2()) - { - break lab1; - } - { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - if (!(base.eq_s_b("c"))) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_4; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("en"))) - { - break lab1; - } - base.bra = base.cursor; - if (!r_en_ending()) - { - break lab1; - } - } - base.cursor = base.limit - v_3; - var /** number */ v_5 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - break lab3; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - break lab3; - } - if (!base.slice_del()) - { - return false; - } - lab4: { - var /** number */ v_6 = base.limit - base.cursor; - lab5: { - base.ket = base.cursor; - if (!(base.eq_s_b("ig"))) - { - break lab5; - } - base.bra = base.cursor; - if (!r_R2()) - { - break lab5; - } - { - var /** number */ v_7 = base.limit - base.cursor; - lab6: { - if (!(base.eq_s_b("e"))) - { - break lab6; - } - break lab5; - } - base.cursor = base.limit - v_7; - } - if (!base.slice_del()) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_6; - if (!r_undouble()) - { - break lab3; - } - } - break; - case 2: - if (!r_R2()) - { - break lab3; - } - { - var /** number */ v_8 = base.limit - base.cursor; - lab7: { - if (!(base.eq_s_b("e"))) - { - break lab7; - } - break lab3; - } - base.cursor = base.limit - v_8; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!r_R2()) - { - break lab3; - } - if (!base.slice_del()) - { - return false; - } - if (!r_e_ending()) - { - break lab3; - } - break; - case 4: - if (!r_R2()) - { - break lab3; - } - if (!base.slice_del()) - { - return false; - } - break; - case 5: - if (!r_R2()) - { - break lab3; - } - if (!B_e_found) - { - break lab3; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - base.cursor = base.limit - v_5; - var /** number */ v_9 = base.limit - base.cursor; - lab8: { - if (!(base.out_grouping_b(g_v_I, 73, 232))) - { - break lab8; - } - var /** number */ v_10 = base.limit - base.cursor; - if (base.find_among_b(a_5) == 0) - { - break lab8; - } - if (!(base.out_grouping_b(g_v, 97, 232))) - { - break lab8; - } - base.cursor = base.limit - v_10; - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - break lab8; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_9; - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_prelude(); - base.cursor = v_1; - var /** number */ v_2 = base.cursor; - r_mark_regions(); - base.cursor = v_2; - base.limit_backward = base.cursor; base.cursor = base.limit; - r_standard_suffix(); - base.cursor = base.limit_backward; - var /** number */ v_4 = base.cursor; - r_postlude(); - base.cursor = v_4; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['DutchStemmer'] = DutchStemmer; diff --git a/js/english-stemmer.js b/js/english-stemmer.js deleted file mode 100644 index 0f9cd7d..0000000 --- a/js/english-stemmer.js +++ /dev/null @@ -1,1086 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var EnglishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["arsen", -1, -1], - ["commun", -1, -1], - ["gener", -1, -1] - ]; - - /** @const */ var a_1 = [ - ["'", -1, 1], - ["'s'", 0, 1], - ["'s", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["ied", -1, 2], - ["s", -1, 3], - ["ies", 1, 2], - ["sses", 1, 1], - ["ss", 1, -1], - ["us", 1, -1] - ]; - - /** @const */ var a_3 = [ - ["", -1, 3], - ["bb", 0, 2], - ["dd", 0, 2], - ["ff", 0, 2], - ["gg", 0, 2], - ["bl", 0, 1], - ["mm", 0, 2], - ["nn", 0, 2], - ["pp", 0, 2], - ["rr", 0, 2], - ["at", 0, 1], - ["tt", 0, 2], - ["iz", 0, 1] - ]; - - /** @const */ var a_4 = [ - ["ed", -1, 2], - ["eed", 0, 1], - ["ing", -1, 2], - ["edly", -1, 2], - ["eedly", 3, 1], - ["ingly", -1, 2] - ]; - - /** @const */ var a_5 = [ - ["anci", -1, 3], - ["enci", -1, 2], - ["ogi", -1, 13], - ["li", -1, 15], - ["bli", 3, 12], - ["abli", 4, 4], - ["alli", 3, 8], - ["fulli", 3, 9], - ["lessli", 3, 14], - ["ousli", 3, 10], - ["entli", 3, 5], - ["aliti", -1, 8], - ["biliti", -1, 12], - ["iviti", -1, 11], - ["tional", -1, 1], - ["ational", 14, 7], - ["alism", -1, 8], - ["ation", -1, 7], - ["ization", 17, 6], - ["izer", -1, 6], - ["ator", -1, 7], - ["iveness", -1, 11], - ["fulness", -1, 9], - ["ousness", -1, 10] - ]; - - /** @const */ var a_6 = [ - ["icate", -1, 4], - ["ative", -1, 6], - ["alize", -1, 3], - ["iciti", -1, 4], - ["ical", -1, 4], - ["tional", -1, 1], - ["ational", 5, 2], - ["ful", -1, 5], - ["ness", -1, 5] - ]; - - /** @const */ var a_7 = [ - ["ic", -1, 1], - ["ance", -1, 1], - ["ence", -1, 1], - ["able", -1, 1], - ["ible", -1, 1], - ["ate", -1, 1], - ["ive", -1, 1], - ["ize", -1, 1], - ["iti", -1, 1], - ["al", -1, 1], - ["ism", -1, 1], - ["ion", -1, 2], - ["er", -1, 1], - ["ous", -1, 1], - ["ant", -1, 1], - ["ent", -1, 1], - ["ment", 15, 1], - ["ement", 16, 1] - ]; - - /** @const */ var a_8 = [ - ["e", -1, 1], - ["l", -1, 2] - ]; - - /** @const */ var a_9 = [ - ["succeed", -1, -1], - ["proceed", -1, -1], - ["exceed", -1, -1], - ["canning", -1, -1], - ["inning", -1, -1], - ["earring", -1, -1], - ["herring", -1, -1], - ["outing", -1, -1] - ]; - - /** @const */ var a_10 = [ - ["andes", -1, -1], - ["atlas", -1, -1], - ["bias", -1, -1], - ["cosmos", -1, -1], - ["dying", -1, 3], - ["early", -1, 9], - ["gently", -1, 7], - ["howe", -1, -1], - ["idly", -1, 6], - ["lying", -1, 4], - ["news", -1, -1], - ["only", -1, 10], - ["singly", -1, 11], - ["skies", -1, 2], - ["skis", -1, 1], - ["sky", -1, -1], - ["tying", -1, 5], - ["ugly", -1, 8] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1]; - - /** @const */ var /** Array */ g_v_WXY = [1, 17, 65, 208, 1]; - - /** @const */ var /** Array */ g_valid_LI = [55, 141, 2]; - - var /** boolean */ B_Y_found = false; - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_prelude() { - B_Y_found = false; - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - if (!(base.eq_s("'"))) - { - break lab0; - } - base.ket = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - base.cursor = v_1; - var /** number */ v_2 = base.cursor; - lab1: { - base.bra = base.cursor; - if (!(base.eq_s("y"))) - { - break lab1; - } - base.ket = base.cursor; - if (!base.slice_from("Y")) - { - return false; - } - B_Y_found = true; - } - base.cursor = v_2; - var /** number */ v_3 = base.cursor; - lab2: { - while(true) - { - var /** number */ v_4 = base.cursor; - lab3: { - golab4: while(true) - { - var /** number */ v_5 = base.cursor; - lab5: { - if (!(base.in_grouping(g_v, 97, 121))) - { - break lab5; - } - base.bra = base.cursor; - if (!(base.eq_s("y"))) - { - break lab5; - } - base.ket = base.cursor; - base.cursor = v_5; - break golab4; - } - base.cursor = v_5; - if (base.cursor >= base.limit) - { - break lab3; - } - base.cursor++; - } - if (!base.slice_from("Y")) - { - return false; - } - B_Y_found = true; - continue; - } - base.cursor = v_4; - break; - } - } - base.cursor = v_3; - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (base.find_among(a_0) == 0) - { - break lab2; - } - break lab1; - } - base.cursor = v_2; - golab3: while(true) - { - lab4: { - if (!(base.in_grouping(g_v, 97, 121))) - { - break lab4; - } - break golab3; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab5: while(true) - { - lab6: { - if (!(base.out_grouping(g_v, 97, 121))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_p1 = base.cursor; - golab7: while(true) - { - lab8: { - if (!(base.in_grouping(g_v, 97, 121))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab9: while(true) - { - lab10: { - if (!(base.out_grouping(g_v, 97, 121))) - { - break lab10; - } - break golab9; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_shortv() { - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.out_grouping_b(g_v_WXY, 89, 121))) - { - break lab1; - } - if (!(base.in_grouping_b(g_v, 97, 121))) - { - break lab1; - } - if (!(base.out_grouping_b(g_v, 97, 121))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.out_grouping_b(g_v, 97, 121))) - { - return false; - } - if (!(base.in_grouping_b(g_v, 97, 121))) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_Step_1a() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("ss")) - { - return false; - } - break; - case 2: - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - { - var /** number */ c1 = base.cursor - 2; - if (c1 < base.limit_backward) - { - break lab2; - } - base.cursor = c1; - } - if (!base.slice_from("i")) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - if (!base.slice_from("ie")) - { - return false; - } - } - break; - case 3: - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - golab3: while(true) - { - lab4: { - if (!(base.in_grouping_b(g_v, 97, 121))) - { - break lab4; - } - break golab3; - } - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_1b() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - return false; - } - if (!base.slice_from("ee")) - { - return false; - } - break; - case 2: - var /** number */ v_1 = base.limit - base.cursor; - golab0: while(true) - { - lab1: { - if (!(base.in_grouping_b(g_v, 97, 121))) - { - break lab1; - } - break golab0; - } - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - base.cursor = base.limit - v_1; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - among_var = base.find_among_b(a_3); - base.cursor = base.limit - v_3; - switch (among_var) { - case 1: - { - var /** number */ c1 = base.cursor; - base.insert(base.cursor, base.cursor, "e"); - base.cursor = c1; - } - break; - case 2: - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (base.cursor != I_p1) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - if (!r_shortv()) - { - return false; - } - base.cursor = base.limit - v_4; - { - var /** number */ c2 = base.cursor; - base.insert(base.cursor, base.cursor, "e"); - base.cursor = c2; - } - break; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_1c() { - base.ket = base.cursor; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("y"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("Y"))) - { - return false; - } - } - base.bra = base.cursor; - if (!(base.out_grouping_b(g_v, 97, 121))) - { - return false; - } - lab2: { - if (base.cursor > base.limit_backward) - { - break lab2; - } - return false; - } - if (!base.slice_from("i")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_2() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("tion")) - { - return false; - } - break; - case 2: - if (!base.slice_from("ence")) - { - return false; - } - break; - case 3: - if (!base.slice_from("ance")) - { - return false; - } - break; - case 4: - if (!base.slice_from("able")) - { - return false; - } - break; - case 5: - if (!base.slice_from("ent")) - { - return false; - } - break; - case 6: - if (!base.slice_from("ize")) - { - return false; - } - break; - case 7: - if (!base.slice_from("ate")) - { - return false; - } - break; - case 8: - if (!base.slice_from("al")) - { - return false; - } - break; - case 9: - if (!base.slice_from("ful")) - { - return false; - } - break; - case 10: - if (!base.slice_from("ous")) - { - return false; - } - break; - case 11: - if (!base.slice_from("ive")) - { - return false; - } - break; - case 12: - if (!base.slice_from("ble")) - { - return false; - } - break; - case 13: - if (!(base.eq_s_b("l"))) - { - return false; - } - if (!base.slice_from("og")) - { - return false; - } - break; - case 14: - if (!base.slice_from("less")) - { - return false; - } - break; - case 15: - if (!(base.in_grouping_b(g_valid_LI, 99, 116))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_3() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("tion")) - { - return false; - } - break; - case 2: - if (!base.slice_from("ate")) - { - return false; - } - break; - case 3: - if (!base.slice_from("al")) - { - return false; - } - break; - case 4: - if (!base.slice_from("ic")) - { - return false; - } - break; - case 5: - if (!base.slice_del()) - { - return false; - } - break; - case 6: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_4() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_7); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R2()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("s"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("t"))) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_5() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_8); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!r_R2()) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!r_R1()) - { - return false; - } - { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - if (!r_shortv()) - { - break lab2; - } - return false; - } - base.cursor = base.limit - v_2; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!(base.eq_s_b("l"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_exception2() { - base.ket = base.cursor; - if (base.find_among_b(a_9) == 0) - { - return false; - } - base.bra = base.cursor; - if (base.cursor > base.limit_backward) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_exception1() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_10); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - if (base.cursor < base.limit) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("ski")) - { - return false; - } - break; - case 2: - if (!base.slice_from("sky")) - { - return false; - } - break; - case 3: - if (!base.slice_from("die")) - { - return false; - } - break; - case 4: - if (!base.slice_from("lie")) - { - return false; - } - break; - case 5: - if (!base.slice_from("tie")) - { - return false; - } - break; - case 6: - if (!base.slice_from("idl")) - { - return false; - } - break; - case 7: - if (!base.slice_from("gentl")) - { - return false; - } - break; - case 8: - if (!base.slice_from("ugli")) - { - return false; - } - break; - case 9: - if (!base.slice_from("earli")) - { - return false; - } - break; - case 10: - if (!base.slice_from("onli")) - { - return false; - } - break; - case 11: - if (!base.slice_from("singl")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - if (!B_Y_found) - { - return false; - } - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - var /** number */ v_2 = base.cursor; - lab2: { - base.bra = base.cursor; - if (!(base.eq_s("Y"))) - { - break lab2; - } - base.ket = base.cursor; - base.cursor = v_2; - break golab1; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - if (!base.slice_from("y")) - { - return false; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - lab0: { - var /** number */ v_1 = base.cursor; - lab1: { - if (!r_exception1()) - { - break lab1; - } - break lab0; - } - base.cursor = v_1; - lab2: { - { - var /** number */ v_2 = base.cursor; - lab3: { - { - var /** number */ c1 = base.cursor + 3; - if (c1 > base.limit) - { - break lab3; - } - base.cursor = c1; - } - break lab2; - } - base.cursor = v_2; - } - break lab0; - } - base.cursor = v_1; - r_prelude(); - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_5 = base.limit - base.cursor; - r_Step_1a(); - base.cursor = base.limit - v_5; - lab4: { - var /** number */ v_6 = base.limit - base.cursor; - lab5: { - if (!r_exception2()) - { - break lab5; - } - break lab4; - } - base.cursor = base.limit - v_6; - var /** number */ v_7 = base.limit - base.cursor; - r_Step_1b(); - base.cursor = base.limit - v_7; - var /** number */ v_8 = base.limit - base.cursor; - r_Step_1c(); - base.cursor = base.limit - v_8; - var /** number */ v_9 = base.limit - base.cursor; - r_Step_2(); - base.cursor = base.limit - v_9; - var /** number */ v_10 = base.limit - base.cursor; - r_Step_3(); - base.cursor = base.limit - v_10; - var /** number */ v_11 = base.limit - base.cursor; - r_Step_4(); - base.cursor = base.limit - v_11; - var /** number */ v_12 = base.limit - base.cursor; - r_Step_5(); - base.cursor = base.limit - v_12; - } - base.cursor = base.limit_backward; - var /** number */ v_13 = base.cursor; - r_postlude(); - base.cursor = v_13; - } - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['EnglishStemmer'] = EnglishStemmer; diff --git a/js/estonian-stemmer.js b/js/estonian-stemmer.js deleted file mode 100644 index 4b9ef4b..0000000 --- a/js/estonian-stemmer.js +++ /dev/null @@ -1,1112 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var EstonianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["gi", -1, 1], - ["ki", -1, 2] - ]; - - /** @const */ var a_1 = [ - ["da", -1, 3], - ["mata", -1, 1], - ["b", -1, 3], - ["ksid", -1, 1], - ["nuksid", 3, 1], - ["me", -1, 3], - ["sime", 5, 1], - ["ksime", 6, 1], - ["nuksime", 7, 1], - ["akse", -1, 2], - ["dakse", 9, 1], - ["takse", 9, 1], - ["site", -1, 1], - ["ksite", 12, 1], - ["nuksite", 13, 1], - ["n", -1, 3], - ["sin", 15, 1], - ["ksin", 16, 1], - ["nuksin", 17, 1], - ["daks", -1, 1], - ["taks", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["aa", -1, -1], - ["ee", -1, -1], - ["ii", -1, -1], - ["oo", -1, -1], - ["uu", -1, -1], - ["\u00E4\u00E4", -1, -1], - ["\u00F5\u00F5", -1, -1], - ["\u00F6\u00F6", -1, -1], - ["\u00FC\u00FC", -1, -1] - ]; - - /** @const */ var a_3 = [ - ["i", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["lane", -1, 1], - ["line", -1, 3], - ["mine", -1, 2], - ["lasse", -1, 1], - ["lisse", -1, 3], - ["misse", -1, 2], - ["lasi", -1, 1], - ["lisi", -1, 3], - ["misi", -1, 2], - ["last", -1, 1], - ["list", -1, 3], - ["mist", -1, 2] - ]; - - /** @const */ var a_5 = [ - ["ga", -1, 1], - ["ta", -1, 1], - ["le", -1, 1], - ["sse", -1, 1], - ["l", -1, 1], - ["s", -1, 1], - ["ks", 5, 1], - ["t", -1, 2], - ["lt", 7, 1], - ["st", 7, 1] - ]; - - /** @const */ var a_6 = [ - ["", -1, 2], - ["las", 0, 1], - ["lis", 0, 1], - ["mis", 0, 1], - ["t", 0, -1] - ]; - - /** @const */ var a_7 = [ - ["d", -1, 4], - ["sid", 0, 2], - ["de", -1, 4], - ["ikkude", 2, 1], - ["ike", -1, 1], - ["ikke", -1, 1], - ["te", -1, 3] - ]; - - /** @const */ var a_8 = [ - ["va", -1, -1], - ["du", -1, -1], - ["nu", -1, -1], - ["tu", -1, -1] - ]; - - /** @const */ var a_9 = [ - ["kk", -1, 1], - ["pp", -1, 2], - ["tt", -1, 3] - ]; - - /** @const */ var a_10 = [ - ["ma", -1, 2], - ["mai", -1, 1], - ["m", -1, 1] - ]; - - /** @const */ var a_11 = [ - ["joob", -1, 1], - ["jood", -1, 1], - ["joodakse", 1, 1], - ["jooma", -1, 1], - ["joomata", 3, 1], - ["joome", -1, 1], - ["joon", -1, 1], - ["joote", -1, 1], - ["joovad", -1, 1], - ["juua", -1, 1], - ["juuakse", 9, 1], - ["j\u00E4i", -1, 12], - ["j\u00E4id", 11, 12], - ["j\u00E4ime", 11, 12], - ["j\u00E4in", 11, 12], - ["j\u00E4ite", 11, 12], - ["j\u00E4\u00E4b", -1, 12], - ["j\u00E4\u00E4d", -1, 12], - ["j\u00E4\u00E4da", 17, 12], - ["j\u00E4\u00E4dakse", 18, 12], - ["j\u00E4\u00E4di", 17, 12], - ["j\u00E4\u00E4ks", -1, 12], - ["j\u00E4\u00E4ksid", 21, 12], - ["j\u00E4\u00E4ksime", 21, 12], - ["j\u00E4\u00E4ksin", 21, 12], - ["j\u00E4\u00E4ksite", 21, 12], - ["j\u00E4\u00E4ma", -1, 12], - ["j\u00E4\u00E4mata", 26, 12], - ["j\u00E4\u00E4me", -1, 12], - ["j\u00E4\u00E4n", -1, 12], - ["j\u00E4\u00E4te", -1, 12], - ["j\u00E4\u00E4vad", -1, 12], - ["j\u00F5i", -1, 1], - ["j\u00F5id", 32, 1], - ["j\u00F5ime", 32, 1], - ["j\u00F5in", 32, 1], - ["j\u00F5ite", 32, 1], - ["keeb", -1, 4], - ["keed", -1, 4], - ["keedakse", 38, 4], - ["keeks", -1, 4], - ["keeksid", 40, 4], - ["keeksime", 40, 4], - ["keeksin", 40, 4], - ["keeksite", 40, 4], - ["keema", -1, 4], - ["keemata", 45, 4], - ["keeme", -1, 4], - ["keen", -1, 4], - ["kees", -1, 4], - ["keeta", -1, 4], - ["keete", -1, 4], - ["keevad", -1, 4], - ["k\u00E4ia", -1, 8], - ["k\u00E4iakse", 53, 8], - ["k\u00E4ib", -1, 8], - ["k\u00E4id", -1, 8], - ["k\u00E4idi", 56, 8], - ["k\u00E4iks", -1, 8], - ["k\u00E4iksid", 58, 8], - ["k\u00E4iksime", 58, 8], - ["k\u00E4iksin", 58, 8], - ["k\u00E4iksite", 58, 8], - ["k\u00E4ima", -1, 8], - ["k\u00E4imata", 63, 8], - ["k\u00E4ime", -1, 8], - ["k\u00E4in", -1, 8], - ["k\u00E4is", -1, 8], - ["k\u00E4ite", -1, 8], - ["k\u00E4ivad", -1, 8], - ["laob", -1, 16], - ["laod", -1, 16], - ["laoks", -1, 16], - ["laoksid", 72, 16], - ["laoksime", 72, 16], - ["laoksin", 72, 16], - ["laoksite", 72, 16], - ["laome", -1, 16], - ["laon", -1, 16], - ["laote", -1, 16], - ["laovad", -1, 16], - ["loeb", -1, 14], - ["loed", -1, 14], - ["loeks", -1, 14], - ["loeksid", 83, 14], - ["loeksime", 83, 14], - ["loeksin", 83, 14], - ["loeksite", 83, 14], - ["loeme", -1, 14], - ["loen", -1, 14], - ["loete", -1, 14], - ["loevad", -1, 14], - ["loob", -1, 7], - ["lood", -1, 7], - ["loodi", 93, 7], - ["looks", -1, 7], - ["looksid", 95, 7], - ["looksime", 95, 7], - ["looksin", 95, 7], - ["looksite", 95, 7], - ["looma", -1, 7], - ["loomata", 100, 7], - ["loome", -1, 7], - ["loon", -1, 7], - ["loote", -1, 7], - ["loovad", -1, 7], - ["luua", -1, 7], - ["luuakse", 106, 7], - ["l\u00F5i", -1, 6], - ["l\u00F5id", 108, 6], - ["l\u00F5ime", 108, 6], - ["l\u00F5in", 108, 6], - ["l\u00F5ite", 108, 6], - ["l\u00F6\u00F6b", -1, 5], - ["l\u00F6\u00F6d", -1, 5], - ["l\u00F6\u00F6dakse", 114, 5], - ["l\u00F6\u00F6di", 114, 5], - ["l\u00F6\u00F6ks", -1, 5], - ["l\u00F6\u00F6ksid", 117, 5], - ["l\u00F6\u00F6ksime", 117, 5], - ["l\u00F6\u00F6ksin", 117, 5], - ["l\u00F6\u00F6ksite", 117, 5], - ["l\u00F6\u00F6ma", -1, 5], - ["l\u00F6\u00F6mata", 122, 5], - ["l\u00F6\u00F6me", -1, 5], - ["l\u00F6\u00F6n", -1, 5], - ["l\u00F6\u00F6te", -1, 5], - ["l\u00F6\u00F6vad", -1, 5], - ["l\u00FC\u00FCa", -1, 5], - ["l\u00FC\u00FCakse", 128, 5], - ["m\u00FC\u00FCa", -1, 13], - ["m\u00FC\u00FCakse", 130, 13], - ["m\u00FC\u00FCb", -1, 13], - ["m\u00FC\u00FCd", -1, 13], - ["m\u00FC\u00FCdi", 133, 13], - ["m\u00FC\u00FCks", -1, 13], - ["m\u00FC\u00FCksid", 135, 13], - ["m\u00FC\u00FCksime", 135, 13], - ["m\u00FC\u00FCksin", 135, 13], - ["m\u00FC\u00FCksite", 135, 13], - ["m\u00FC\u00FCma", -1, 13], - ["m\u00FC\u00FCmata", 140, 13], - ["m\u00FC\u00FCme", -1, 13], - ["m\u00FC\u00FCn", -1, 13], - ["m\u00FC\u00FCs", -1, 13], - ["m\u00FC\u00FCte", -1, 13], - ["m\u00FC\u00FCvad", -1, 13], - ["n\u00E4eb", -1, 18], - ["n\u00E4ed", -1, 18], - ["n\u00E4eks", -1, 18], - ["n\u00E4eksid", 149, 18], - ["n\u00E4eksime", 149, 18], - ["n\u00E4eksin", 149, 18], - ["n\u00E4eksite", 149, 18], - ["n\u00E4eme", -1, 18], - ["n\u00E4en", -1, 18], - ["n\u00E4ete", -1, 18], - ["n\u00E4evad", -1, 18], - ["n\u00E4gema", -1, 18], - ["n\u00E4gemata", 158, 18], - ["n\u00E4ha", -1, 18], - ["n\u00E4hakse", 160, 18], - ["n\u00E4hti", -1, 18], - ["p\u00F5eb", -1, 15], - ["p\u00F5ed", -1, 15], - ["p\u00F5eks", -1, 15], - ["p\u00F5eksid", 165, 15], - ["p\u00F5eksime", 165, 15], - ["p\u00F5eksin", 165, 15], - ["p\u00F5eksite", 165, 15], - ["p\u00F5eme", -1, 15], - ["p\u00F5en", -1, 15], - ["p\u00F5ete", -1, 15], - ["p\u00F5evad", -1, 15], - ["saab", -1, 2], - ["saad", -1, 2], - ["saada", 175, 2], - ["saadakse", 176, 2], - ["saadi", 175, 2], - ["saaks", -1, 2], - ["saaksid", 179, 2], - ["saaksime", 179, 2], - ["saaksin", 179, 2], - ["saaksite", 179, 2], - ["saama", -1, 2], - ["saamata", 184, 2], - ["saame", -1, 2], - ["saan", -1, 2], - ["saate", -1, 2], - ["saavad", -1, 2], - ["sai", -1, 2], - ["said", 190, 2], - ["saime", 190, 2], - ["sain", 190, 2], - ["saite", 190, 2], - ["s\u00F5i", -1, 9], - ["s\u00F5id", 195, 9], - ["s\u00F5ime", 195, 9], - ["s\u00F5in", 195, 9], - ["s\u00F5ite", 195, 9], - ["s\u00F6\u00F6b", -1, 9], - ["s\u00F6\u00F6d", -1, 9], - ["s\u00F6\u00F6dakse", 201, 9], - ["s\u00F6\u00F6di", 201, 9], - ["s\u00F6\u00F6ks", -1, 9], - ["s\u00F6\u00F6ksid", 204, 9], - ["s\u00F6\u00F6ksime", 204, 9], - ["s\u00F6\u00F6ksin", 204, 9], - ["s\u00F6\u00F6ksite", 204, 9], - ["s\u00F6\u00F6ma", -1, 9], - ["s\u00F6\u00F6mata", 209, 9], - ["s\u00F6\u00F6me", -1, 9], - ["s\u00F6\u00F6n", -1, 9], - ["s\u00F6\u00F6te", -1, 9], - ["s\u00F6\u00F6vad", -1, 9], - ["s\u00FC\u00FCa", -1, 9], - ["s\u00FC\u00FCakse", 215, 9], - ["teeb", -1, 17], - ["teed", -1, 17], - ["teeks", -1, 17], - ["teeksid", 219, 17], - ["teeksime", 219, 17], - ["teeksin", 219, 17], - ["teeksite", 219, 17], - ["teeme", -1, 17], - ["teen", -1, 17], - ["teete", -1, 17], - ["teevad", -1, 17], - ["tegema", -1, 17], - ["tegemata", 228, 17], - ["teha", -1, 17], - ["tehakse", 230, 17], - ["tehti", -1, 17], - ["toob", -1, 10], - ["tood", -1, 10], - ["toodi", 234, 10], - ["tooks", -1, 10], - ["tooksid", 236, 10], - ["tooksime", 236, 10], - ["tooksin", 236, 10], - ["tooksite", 236, 10], - ["tooma", -1, 10], - ["toomata", 241, 10], - ["toome", -1, 10], - ["toon", -1, 10], - ["toote", -1, 10], - ["toovad", -1, 10], - ["tuua", -1, 10], - ["tuuakse", 247, 10], - ["t\u00F5i", -1, 10], - ["t\u00F5id", 249, 10], - ["t\u00F5ime", 249, 10], - ["t\u00F5in", 249, 10], - ["t\u00F5ite", 249, 10], - ["viia", -1, 3], - ["viiakse", 254, 3], - ["viib", -1, 3], - ["viid", -1, 3], - ["viidi", 257, 3], - ["viiks", -1, 3], - ["viiksid", 259, 3], - ["viiksime", 259, 3], - ["viiksin", 259, 3], - ["viiksite", 259, 3], - ["viima", -1, 3], - ["viimata", 264, 3], - ["viime", -1, 3], - ["viin", -1, 3], - ["viisime", -1, 3], - ["viisin", -1, 3], - ["viisite", -1, 3], - ["viite", -1, 3], - ["viivad", -1, 3], - ["v\u00F5ib", -1, 11], - ["v\u00F5id", -1, 11], - ["v\u00F5ida", 274, 11], - ["v\u00F5idakse", 275, 11], - ["v\u00F5idi", 274, 11], - ["v\u00F5iks", -1, 11], - ["v\u00F5iksid", 278, 11], - ["v\u00F5iksime", 278, 11], - ["v\u00F5iksin", 278, 11], - ["v\u00F5iksite", 278, 11], - ["v\u00F5ima", -1, 11], - ["v\u00F5imata", 283, 11], - ["v\u00F5ime", -1, 11], - ["v\u00F5in", -1, 11], - ["v\u00F5is", -1, 11], - ["v\u00F5ite", -1, 11], - ["v\u00F5ivad", -1, 11] - ]; - - /** @const */ var /** Array */ g_V1 = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 48, 8]; - - /** @const */ var /** Array */ g_RV = [17, 65, 16]; - - /** @const */ var /** Array */ g_KI = [117, 66, 6, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 0, 0, 0, 16]; - - /** @const */ var /** Array */ g_GI = [21, 123, 243, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 48, 8]; - - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - golab0: while(true) - { - var /** number */ v_1 = base.cursor; - lab1: { - if (!(base.in_grouping(g_V1, 97, 252))) - { - break lab1; - } - base.cursor = v_1; - break golab0; - } - base.cursor = v_1; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_V1, 97, 252))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - return true; - }; - - /** @return {boolean} */ - function r_emphasis() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - var /** number */ v_3 = base.limit - base.cursor; - { - var /** number */ c1 = base.cursor - 4; - if (c1 < base.limit_backward) - { - return false; - } - base.cursor = c1; - } - base.cursor = base.limit - v_3; - switch (among_var) { - case 1: - var /** number */ v_4 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_GI, 97, 252))) - { - return false; - } - base.cursor = base.limit - v_4; - { - var /** number */ v_5 = base.limit - base.cursor; - lab0: { - if (!r_LONGV()) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_5; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.in_grouping_b(g_KI, 98, 382))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_verb() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_1); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("a")) - { - return false; - } - break; - case 3: - if (!(base.in_grouping_b(g_V1, 97, 252))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_LONGV() { - if (base.find_among_b(a_2) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_i_plural() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - if (!(base.in_grouping_b(g_RV, 97, 117))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_special_noun_endings() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!base.slice_from("lase")) - { - return false; - } - break; - case 2: - if (!base.slice_from("mise")) - { - return false; - } - break; - case 3: - if (!base.slice_from("lise")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_case_ending() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - if (!(base.in_grouping_b(g_RV, 97, 117))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_3; - if (!r_LONGV()) - { - return false; - } - } - break; - case 2: - var /** number */ v_4 = base.limit - base.cursor; - { - var /** number */ c1 = base.cursor - 4; - if (c1 < base.limit_backward) - { - return false; - } - base.cursor = c1; - } - base.cursor = base.limit - v_4; - break; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_plural_three_first_cases() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_7); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!base.slice_from("iku")) - { - return false; - } - break; - case 2: - { - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - if (!r_LONGV()) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_3; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - var /** number */ v_5 = base.limit - base.cursor; - { - var /** number */ c1 = base.cursor - 4; - if (c1 < base.limit_backward) - { - break lab2; - } - base.cursor = c1; - } - base.cursor = base.limit - v_5; - among_var = base.find_among_b(a_6); - switch (among_var) { - case 1: - if (!base.slice_from("e")) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - break lab1; - } - base.cursor = base.limit - v_4; - if (!base.slice_from("t")) - { - return false; - } - } - break; - case 4: - lab3: { - var /** number */ v_6 = base.limit - base.cursor; - lab4: { - if (!(base.in_grouping_b(g_RV, 97, 117))) - { - break lab4; - } - break lab3; - } - base.cursor = base.limit - v_6; - if (!r_LONGV()) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_nu() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_8) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_undouble_kpt() { - var /** number */ among_var; - if (!(base.in_grouping_b(g_V1, 97, 252))) - { - return false; - } - if (I_p1 > base.cursor) - { - return false; - } - base.ket = base.cursor; - among_var = base.find_among_b(a_9); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("k")) - { - return false; - } - break; - case 2: - if (!base.slice_from("p")) - { - return false; - } - break; - case 3: - if (!base.slice_from("t")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_degrees() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_10); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!(base.in_grouping_b(g_RV, 97, 117))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_substantive() { - var /** number */ v_1 = base.limit - base.cursor; - r_special_noun_endings(); - base.cursor = base.limit - v_1; - var /** number */ v_2 = base.limit - base.cursor; - r_case_ending(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_plural_three_first_cases(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_degrees(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_i_plural(); - base.cursor = base.limit - v_5; - var /** number */ v_6 = base.limit - base.cursor; - r_nu(); - base.cursor = base.limit - v_6; - return true; - }; - - /** @return {boolean} */ - function r_verb_exceptions() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_11); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - if (base.cursor < base.limit) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("joo")) - { - return false; - } - break; - case 2: - if (!base.slice_from("saa")) - { - return false; - } - break; - case 3: - if (!base.slice_from("viima")) - { - return false; - } - break; - case 4: - if (!base.slice_from("keesi")) - { - return false; - } - break; - case 5: - if (!base.slice_from("l\u00F6\u00F6")) - { - return false; - } - break; - case 6: - if (!base.slice_from("l\u00F5i")) - { - return false; - } - break; - case 7: - if (!base.slice_from("loo")) - { - return false; - } - break; - case 8: - if (!base.slice_from("k\u00E4isi")) - { - return false; - } - break; - case 9: - if (!base.slice_from("s\u00F6\u00F6")) - { - return false; - } - break; - case 10: - if (!base.slice_from("too")) - { - return false; - } - break; - case 11: - if (!base.slice_from("v\u00F5isi")) - { - return false; - } - break; - case 12: - if (!base.slice_from("j\u00E4\u00E4ma")) - { - return false; - } - break; - case 13: - if (!base.slice_from("m\u00FC\u00FCsi")) - { - return false; - } - break; - case 14: - if (!base.slice_from("luge")) - { - return false; - } - break; - case 15: - if (!base.slice_from("p\u00F5de")) - { - return false; - } - break; - case 16: - if (!base.slice_from("ladu")) - { - return false; - } - break; - case 17: - if (!base.slice_from("tegi")) - { - return false; - } - break; - case 18: - if (!base.slice_from("n\u00E4gi")) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - { - var /** number */ v_1 = base.cursor; - lab0: { - if (!r_verb_exceptions()) - { - break lab0; - } - return false; - } - base.cursor = v_1; - } - var /** number */ v_2 = base.cursor; - r_mark_regions(); - base.cursor = v_2; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_3 = base.limit - base.cursor; - r_emphasis(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - lab1: { - lab2: { - var /** number */ v_5 = base.limit - base.cursor; - lab3: { - if (!r_verb()) - { - break lab3; - } - break lab2; - } - base.cursor = base.limit - v_5; - r_substantive(); - } - } - base.cursor = base.limit - v_4; - var /** number */ v_6 = base.limit - base.cursor; - r_undouble_kpt(); - base.cursor = base.limit - v_6; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['EstonianStemmer'] = EstonianStemmer; diff --git a/js/finnish-stemmer.js b/js/finnish-stemmer.js deleted file mode 100644 index d78ceff..0000000 --- a/js/finnish-stemmer.js +++ /dev/null @@ -1,788 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var FinnishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["pa", -1, 1], - ["sti", -1, 2], - ["kaan", -1, 1], - ["han", -1, 1], - ["kin", -1, 1], - ["h\u00E4n", -1, 1], - ["k\u00E4\u00E4n", -1, 1], - ["ko", -1, 1], - ["p\u00E4", -1, 1], - ["k\u00F6", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["lla", -1, -1], - ["na", -1, -1], - ["ssa", -1, -1], - ["ta", -1, -1], - ["lta", 3, -1], - ["sta", 3, -1] - ]; - - /** @const */ var a_2 = [ - ["ll\u00E4", -1, -1], - ["n\u00E4", -1, -1], - ["ss\u00E4", -1, -1], - ["t\u00E4", -1, -1], - ["lt\u00E4", 3, -1], - ["st\u00E4", 3, -1] - ]; - - /** @const */ var a_3 = [ - ["lle", -1, -1], - ["ine", -1, -1] - ]; - - /** @const */ var a_4 = [ - ["nsa", -1, 3], - ["mme", -1, 3], - ["nne", -1, 3], - ["ni", -1, 2], - ["si", -1, 1], - ["an", -1, 4], - ["en", -1, 6], - ["\u00E4n", -1, 5], - ["ns\u00E4", -1, 3] - ]; - - /** @const */ var a_5 = [ - ["aa", -1, -1], - ["ee", -1, -1], - ["ii", -1, -1], - ["oo", -1, -1], - ["uu", -1, -1], - ["\u00E4\u00E4", -1, -1], - ["\u00F6\u00F6", -1, -1] - ]; - - /** @const */ var a_6 = [ - ["a", -1, 8], - ["lla", 0, -1], - ["na", 0, -1], - ["ssa", 0, -1], - ["ta", 0, -1], - ["lta", 4, -1], - ["sta", 4, -1], - ["tta", 4, 2], - ["lle", -1, -1], - ["ine", -1, -1], - ["ksi", -1, -1], - ["n", -1, 7], - ["han", 11, 1], - ["den", 11, -1, r_VI], - ["seen", 11, -1, r_LONG], - ["hen", 11, 2], - ["tten", 11, -1, r_VI], - ["hin", 11, 3], - ["siin", 11, -1, r_VI], - ["hon", 11, 4], - ["h\u00E4n", 11, 5], - ["h\u00F6n", 11, 6], - ["\u00E4", -1, 8], - ["ll\u00E4", 22, -1], - ["n\u00E4", 22, -1], - ["ss\u00E4", 22, -1], - ["t\u00E4", 22, -1], - ["lt\u00E4", 26, -1], - ["st\u00E4", 26, -1], - ["tt\u00E4", 26, 2] - ]; - - /** @const */ var a_7 = [ - ["eja", -1, -1], - ["mma", -1, 1], - ["imma", 1, -1], - ["mpa", -1, 1], - ["impa", 3, -1], - ["mmi", -1, 1], - ["immi", 5, -1], - ["mpi", -1, 1], - ["impi", 7, -1], - ["ej\u00E4", -1, -1], - ["mm\u00E4", -1, 1], - ["imm\u00E4", 10, -1], - ["mp\u00E4", -1, 1], - ["imp\u00E4", 12, -1] - ]; - - /** @const */ var a_8 = [ - ["i", -1, -1], - ["j", -1, -1] - ]; - - /** @const */ var a_9 = [ - ["mma", -1, 1], - ["imma", 0, -1] - ]; - - /** @const */ var /** Array */ g_AEI = [17, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8]; - - /** @const */ var /** Array */ g_C = [119, 223, 119, 1]; - - /** @const */ var /** Array */ g_V1 = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32]; - - /** @const */ var /** Array */ g_V2 = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32]; - - /** @const */ var /** Array */ g_particle_end = [17, 97, 24, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32]; - - var /** boolean */ B_ending_removed = false; - var /** string */ S_x = ''; - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - I_p2 = base.limit; - golab0: while(true) - { - var /** number */ v_1 = base.cursor; - lab1: { - if (!(base.in_grouping(g_V1, 97, 246))) - { - break lab1; - } - base.cursor = v_1; - break golab0; - } - base.cursor = v_1; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_V1, 97, 246))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - golab4: while(true) - { - var /** number */ v_3 = base.cursor; - lab5: { - if (!(base.in_grouping(g_V1, 97, 246))) - { - break lab5; - } - base.cursor = v_3; - break golab4; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab6: while(true) - { - lab7: { - if (!(base.out_grouping(g_V1, 97, 246))) - { - break lab7; - } - break golab6; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p2 = base.cursor; - return true; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_particle_etc() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!(base.in_grouping_b(g_particle_end, 97, 246))) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - break; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_possessive() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - { - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("k"))) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_3; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("kse"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_from("ksi")) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - case 4: - if (base.find_among_b(a_1) == 0) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 5: - if (base.find_among_b(a_2) == 0) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 6: - if (base.find_among_b(a_3) == 0) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_LONG() { - if (base.find_among_b(a_5) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_VI() { - if (!(base.eq_s_b("i"))) - { - return false; - } - if (!(base.in_grouping_b(g_V2, 97, 246))) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_case_ending() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!(base.eq_s_b("a"))) - { - return false; - } - break; - case 2: - if (!(base.eq_s_b("e"))) - { - return false; - } - break; - case 3: - if (!(base.eq_s_b("i"))) - { - return false; - } - break; - case 4: - if (!(base.eq_s_b("o"))) - { - return false; - } - break; - case 5: - if (!(base.eq_s_b("\u00E4"))) - { - return false; - } - break; - case 6: - if (!(base.eq_s_b("\u00F6"))) - { - return false; - } - break; - case 7: - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - var /** number */ v_4 = base.limit - base.cursor; - lab1: { - var /** number */ v_5 = base.limit - base.cursor; - lab2: { - if (!r_LONG()) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_5; - if (!(base.eq_s_b("ie"))) - { - base.cursor = base.limit - v_3; - break lab0; - } - } - base.cursor = base.limit - v_4; - if (base.cursor <= base.limit_backward) - { - base.cursor = base.limit - v_3; - break lab0; - } - base.cursor--; - base.bra = base.cursor; - } - break; - case 8: - if (!(base.in_grouping_b(g_V1, 97, 246))) - { - return false; - } - if (!(base.in_grouping_b(g_C, 98, 122))) - { - return false; - } - break; - } - if (!base.slice_del()) - { - return false; - } - B_ending_removed = true; - return true; - }; - - /** @return {boolean} */ - function r_other_endings() { - var /** number */ among_var; - if (base.cursor < I_p2) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p2; - base.ket = base.cursor; - among_var = base.find_among_b(a_7); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - { - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("po"))) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_3; - } - break; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_i_plural() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_8) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_t_plural() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (!(base.eq_s_b("t"))) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - var /** number */ v_3 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_V1, 97, 246))) - { - base.limit_backward = v_2; - return false; - } - base.cursor = base.limit - v_3; - if (!base.slice_del()) - { - return false; - } - base.limit_backward = v_2; - if (base.cursor < I_p2) - { - return false; - } - var /** number */ v_5 = base.limit_backward; - base.limit_backward = I_p2; - base.ket = base.cursor; - among_var = base.find_among_b(a_9); - if (among_var == 0) - { - base.limit_backward = v_5; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_5; - switch (among_var) { - case 1: - { - var /** number */ v_6 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("po"))) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_6; - } - break; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_tidy() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - var /** number */ v_4 = base.limit - base.cursor; - if (!r_LONG()) - { - break lab0; - } - base.cursor = base.limit - v_4; - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - break lab0; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_3; - var /** number */ v_5 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (!(base.in_grouping_b(g_AEI, 97, 228))) - { - break lab1; - } - base.bra = base.cursor; - if (!(base.in_grouping_b(g_C, 98, 122))) - { - break lab1; - } - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_5; - var /** number */ v_6 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - if (!(base.eq_s_b("j"))) - { - break lab2; - } - base.bra = base.cursor; - lab3: { - var /** number */ v_7 = base.limit - base.cursor; - lab4: { - if (!(base.eq_s_b("o"))) - { - break lab4; - } - break lab3; - } - base.cursor = base.limit - v_7; - if (!(base.eq_s_b("u"))) - { - break lab2; - } - } - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_6; - var /** number */ v_8 = base.limit - base.cursor; - lab5: { - base.ket = base.cursor; - if (!(base.eq_s_b("o"))) - { - break lab5; - } - base.bra = base.cursor; - if (!(base.eq_s_b("j"))) - { - break lab5; - } - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_8; - base.limit_backward = v_2; - golab6: while(true) - { - var /** number */ v_9 = base.limit - base.cursor; - lab7: { - if (!(base.out_grouping_b(g_V1, 97, 246))) - { - break lab7; - } - base.cursor = base.limit - v_9; - break golab6; - } - base.cursor = base.limit - v_9; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - base.ket = base.cursor; - if (!(base.in_grouping_b(g_C, 98, 122))) - { - return false; - } - base.bra = base.cursor; - S_x = base.slice_to(); - if (S_x == '') - { - return false; - } - if (!(base.eq_s_b(S_x))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_mark_regions(); - base.cursor = v_1; - B_ending_removed = false; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_particle_etc(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_possessive(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_case_ending(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_other_endings(); - base.cursor = base.limit - v_5; - lab0: { - lab1: { - if (!B_ending_removed) - { - break lab1; - } - var /** number */ v_7 = base.limit - base.cursor; - r_i_plural(); - base.cursor = base.limit - v_7; - break lab0; - } - var /** number */ v_8 = base.limit - base.cursor; - r_t_plural(); - base.cursor = base.limit - v_8; - } - var /** number */ v_9 = base.limit - base.cursor; - r_tidy(); - base.cursor = base.limit - v_9; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['FinnishStemmer'] = FinnishStemmer; diff --git a/js/french-stemmer.js b/js/french-stemmer.js deleted file mode 100644 index 36475be..0000000 --- a/js/french-stemmer.js +++ /dev/null @@ -1,1311 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var FrenchStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["col", -1, -1], - ["par", -1, -1], - ["tap", -1, -1] - ]; - - /** @const */ var a_1 = [ - ["", -1, 7], - ["H", 0, 6], - ["He", 1, 4], - ["Hi", 1, 5], - ["I", 0, 1], - ["U", 0, 2], - ["Y", 0, 3] - ]; - - /** @const */ var a_2 = [ - ["iqU", -1, 3], - ["abl", -1, 3], - ["I\u00E8r", -1, 4], - ["i\u00E8r", -1, 4], - ["eus", -1, 2], - ["iv", -1, 1] - ]; - - /** @const */ var a_3 = [ - ["ic", -1, 2], - ["abil", -1, 1], - ["iv", -1, 3] - ]; - - /** @const */ var a_4 = [ - ["iqUe", -1, 1], - ["atrice", -1, 2], - ["ance", -1, 1], - ["ence", -1, 5], - ["logie", -1, 3], - ["able", -1, 1], - ["isme", -1, 1], - ["euse", -1, 11], - ["iste", -1, 1], - ["ive", -1, 8], - ["if", -1, 8], - ["usion", -1, 4], - ["ation", -1, 2], - ["ution", -1, 4], - ["ateur", -1, 2], - ["iqUes", -1, 1], - ["atrices", -1, 2], - ["ances", -1, 1], - ["ences", -1, 5], - ["logies", -1, 3], - ["ables", -1, 1], - ["ismes", -1, 1], - ["euses", -1, 11], - ["istes", -1, 1], - ["ives", -1, 8], - ["ifs", -1, 8], - ["usions", -1, 4], - ["ations", -1, 2], - ["utions", -1, 4], - ["ateurs", -1, 2], - ["ments", -1, 15], - ["ements", 30, 6], - ["issements", 31, 12], - ["it\u00E9s", -1, 7], - ["ment", -1, 15], - ["ement", 34, 6], - ["issement", 35, 12], - ["amment", 34, 13], - ["emment", 34, 14], - ["aux", -1, 10], - ["eaux", 39, 9], - ["eux", -1, 1], - ["it\u00E9", -1, 7] - ]; - - /** @const */ var a_5 = [ - ["ira", -1, 1], - ["ie", -1, 1], - ["isse", -1, 1], - ["issante", -1, 1], - ["i", -1, 1], - ["irai", 4, 1], - ["ir", -1, 1], - ["iras", -1, 1], - ["ies", -1, 1], - ["\u00EEmes", -1, 1], - ["isses", -1, 1], - ["issantes", -1, 1], - ["\u00EEtes", -1, 1], - ["is", -1, 1], - ["irais", 13, 1], - ["issais", 13, 1], - ["irions", -1, 1], - ["issions", -1, 1], - ["irons", -1, 1], - ["issons", -1, 1], - ["issants", -1, 1], - ["it", -1, 1], - ["irait", 21, 1], - ["issait", 21, 1], - ["issant", -1, 1], - ["iraIent", -1, 1], - ["issaIent", -1, 1], - ["irent", -1, 1], - ["issent", -1, 1], - ["iront", -1, 1], - ["\u00EEt", -1, 1], - ["iriez", -1, 1], - ["issiez", -1, 1], - ["irez", -1, 1], - ["issez", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["a", -1, 3], - ["era", 0, 2], - ["asse", -1, 3], - ["ante", -1, 3], - ["\u00E9e", -1, 2], - ["ai", -1, 3], - ["erai", 5, 2], - ["er", -1, 2], - ["as", -1, 3], - ["eras", 8, 2], - ["\u00E2mes", -1, 3], - ["asses", -1, 3], - ["antes", -1, 3], - ["\u00E2tes", -1, 3], - ["\u00E9es", -1, 2], - ["ais", -1, 3], - ["erais", 15, 2], - ["ions", -1, 1], - ["erions", 17, 2], - ["assions", 17, 3], - ["erons", -1, 2], - ["ants", -1, 3], - ["\u00E9s", -1, 2], - ["ait", -1, 3], - ["erait", 23, 2], - ["ant", -1, 3], - ["aIent", -1, 3], - ["eraIent", 26, 2], - ["\u00E8rent", -1, 2], - ["assent", -1, 3], - ["eront", -1, 2], - ["\u00E2t", -1, 3], - ["ez", -1, 2], - ["iez", 32, 2], - ["eriez", 33, 2], - ["assiez", 33, 3], - ["erez", 32, 2], - ["\u00E9", -1, 2] - ]; - - /** @const */ var a_7 = [ - ["e", -1, 3], - ["I\u00E8re", 0, 2], - ["i\u00E8re", 0, 2], - ["ion", -1, 1], - ["Ier", -1, 2], - ["ier", -1, 2] - ]; - - /** @const */ var a_8 = [ - ["ell", -1, -1], - ["eill", -1, -1], - ["enn", -1, -1], - ["onn", -1, -1], - ["ett", -1, -1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 130, 103, 8, 5]; - - /** @const */ var /** Array */ g_keep_with_s = [1, 65, 20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_prelude() { - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - var /** number */ v_2 = base.cursor; - lab2: { - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab4; - } - base.bra = base.cursor; - lab5: { - var /** number */ v_4 = base.cursor; - lab6: { - if (!(base.eq_s("u"))) - { - break lab6; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab6; - } - if (!base.slice_from("U")) - { - return false; - } - break lab5; - } - base.cursor = v_4; - lab7: { - if (!(base.eq_s("i"))) - { - break lab7; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab7; - } - if (!base.slice_from("I")) - { - return false; - } - break lab5; - } - base.cursor = v_4; - if (!(base.eq_s("y"))) - { - break lab4; - } - base.ket = base.cursor; - if (!base.slice_from("Y")) - { - return false; - } - } - break lab3; - } - base.cursor = v_3; - lab8: { - base.bra = base.cursor; - if (!(base.eq_s("\u00EB"))) - { - break lab8; - } - base.ket = base.cursor; - if (!base.slice_from("He")) - { - return false; - } - break lab3; - } - base.cursor = v_3; - lab9: { - base.bra = base.cursor; - if (!(base.eq_s("\u00EF"))) - { - break lab9; - } - base.ket = base.cursor; - if (!base.slice_from("Hi")) - { - return false; - } - break lab3; - } - base.cursor = v_3; - lab10: { - base.bra = base.cursor; - if (!(base.eq_s("y"))) - { - break lab10; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab10; - } - if (!base.slice_from("Y")) - { - return false; - } - break lab3; - } - base.cursor = v_3; - if (!(base.eq_s("q"))) - { - break lab2; - } - base.bra = base.cursor; - if (!(base.eq_s("u"))) - { - break lab2; - } - base.ket = base.cursor; - if (!base.slice_from("U")) - { - return false; - } - } - base.cursor = v_2; - break golab1; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab2; - } - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab2; - } - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - break lab1; - } - base.cursor = v_2; - lab3: { - if (base.find_among(a_0) == 0) - { - break lab3; - } - break lab1; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - golab4: while(true) - { - lab5: { - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab5; - } - break golab4; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_pV = base.cursor; - } - base.cursor = v_1; - var /** number */ v_4 = base.cursor; - lab6: { - golab7: while(true) - { - lab8: { - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab6; - } - base.cursor++; - } - golab9: while(true) - { - lab10: { - if (!(base.out_grouping(g_v, 97, 251))) - { - break lab10; - } - break golab9; - } - if (base.cursor >= base.limit) - { - break lab6; - } - base.cursor++; - } - I_p1 = base.cursor; - golab11: while(true) - { - lab12: { - if (!(base.in_grouping(g_v, 97, 251))) - { - break lab12; - } - break golab11; - } - if (base.cursor >= base.limit) - { - break lab6; - } - base.cursor++; - } - golab13: while(true) - { - lab14: { - if (!(base.out_grouping(g_v, 97, 251))) - { - break lab14; - } - break golab13; - } - if (base.cursor >= base.limit) - { - break lab6; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_4; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_1); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("i")) - { - return false; - } - break; - case 2: - if (!base.slice_from("u")) - { - return false; - } - break; - case 3: - if (!base.slice_from("y")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u00EB")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u00EF")) - { - return false; - } - break; - case 6: - if (!base.slice_del()) - { - return false; - } - break; - case 7: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("ic"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - if (!r_R2()) - { - break lab2; - } - if (!base.slice_del()) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - if (!base.slice_from("iqU")) - { - return false; - } - } - } - break; - case 3: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("log")) - { - return false; - } - break; - case 4: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("u")) - { - return false; - } - break; - case 5: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("ent")) - { - return false; - } - break; - case 6: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - base.cursor = base.limit - v_3; - break lab3; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - base.cursor = base.limit - v_3; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_3; - break lab3; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_3; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - lab4: { - var /** number */ v_4 = base.limit - base.cursor; - lab5: { - if (!r_R2()) - { - break lab5; - } - if (!base.slice_del()) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_4; - if (!r_R1()) - { - base.cursor = base.limit - v_3; - break lab3; - } - if (!base.slice_from("eux")) - { - return false; - } - } - break; - case 3: - if (!r_R2()) - { - base.cursor = base.limit - v_3; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - break; - case 4: - if (!r_RV()) - { - base.cursor = base.limit - v_3; - break lab3; - } - if (!base.slice_from("i")) - { - return false; - } - break; - } - } - break; - case 7: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_5 = base.limit - base.cursor; - lab6: { - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - base.cursor = base.limit - v_5; - break lab6; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab7: { - var /** number */ v_6 = base.limit - base.cursor; - lab8: { - if (!r_R2()) - { - break lab8; - } - if (!base.slice_del()) - { - return false; - } - break lab7; - } - base.cursor = base.limit - v_6; - if (!base.slice_from("abl")) - { - return false; - } - } - break; - case 2: - lab9: { - var /** number */ v_7 = base.limit - base.cursor; - lab10: { - if (!r_R2()) - { - break lab10; - } - if (!base.slice_del()) - { - return false; - } - break lab9; - } - base.cursor = base.limit - v_7; - if (!base.slice_from("iqU")) - { - return false; - } - } - break; - case 3: - if (!r_R2()) - { - base.cursor = base.limit - v_5; - break lab6; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - break; - case 8: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_8 = base.limit - base.cursor; - lab11: { - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_8; - break lab11; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_8; - break lab11; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("ic"))) - { - base.cursor = base.limit - v_8; - break lab11; - } - base.bra = base.cursor; - lab12: { - var /** number */ v_9 = base.limit - base.cursor; - lab13: { - if (!r_R2()) - { - break lab13; - } - if (!base.slice_del()) - { - return false; - } - break lab12; - } - base.cursor = base.limit - v_9; - if (!base.slice_from("iqU")) - { - return false; - } - } - } - break; - case 9: - if (!base.slice_from("eau")) - { - return false; - } - break; - case 10: - if (!r_R1()) - { - return false; - } - if (!base.slice_from("al")) - { - return false; - } - break; - case 11: - lab14: { - var /** number */ v_10 = base.limit - base.cursor; - lab15: { - if (!r_R2()) - { - break lab15; - } - if (!base.slice_del()) - { - return false; - } - break lab14; - } - base.cursor = base.limit - v_10; - if (!r_R1()) - { - return false; - } - if (!base.slice_from("eux")) - { - return false; - } - } - break; - case 12: - if (!r_R1()) - { - return false; - } - if (!(base.out_grouping_b(g_v, 97, 251))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 13: - if (!r_RV()) - { - return false; - } - if (!base.slice_from("ant")) - { - return false; - } - return false; - case 14: - if (!r_RV()) - { - return false; - } - if (!base.slice_from("ent")) - { - return false; - } - return false; - case 15: - var /** number */ v_11 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_v, 97, 251))) - { - return false; - } - if (!r_RV()) - { - return false; - } - base.cursor = base.limit - v_11; - if (!base.slice_del()) - { - return false; - } - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_i_verb_suffix() { - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - if (base.find_among_b(a_5) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - { - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("H"))) - { - break lab0; - } - base.limit_backward = v_2; - return false; - } - base.cursor = base.limit - v_3; - } - if (!(base.out_grouping_b(g_v, 97, 251))) - { - base.limit_backward = v_2; - return false; - } - if (!base.slice_del()) - { - return false; - } - base.limit_backward = v_2; - return true; - }; - - /** @return {boolean} */ - function r_verb_suffix() { - var /** number */ among_var; - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - base.limit_backward = v_2; - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("e"))) - { - base.cursor = base.limit - v_3; - break lab0; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - break; - } - base.limit_backward = v_2; - return true; - }; - - /** @return {boolean} */ - function r_residual_suffix() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("s"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - if (!(base.eq_s_b("Hi"))) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_3; - if (!(base.out_grouping_b(g_keep_with_s, 97, 232))) - { - base.cursor = base.limit - v_1; - break lab0; - } - } - base.cursor = base.limit - v_2; - if (!base.slice_del()) - { - return false; - } - } - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_5 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - among_var = base.find_among_b(a_7); - if (among_var == 0) - { - base.limit_backward = v_5; - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - base.limit_backward = v_5; - return false; - } - lab3: { - var /** number */ v_6 = base.limit - base.cursor; - lab4: { - if (!(base.eq_s_b("s"))) - { - break lab4; - } - break lab3; - } - base.cursor = base.limit - v_6; - if (!(base.eq_s_b("t"))) - { - base.limit_backward = v_5; - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("i")) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - } - base.limit_backward = v_5; - return true; - }; - - /** @return {boolean} */ - function r_un_double() { - var /** number */ v_1 = base.limit - base.cursor; - if (base.find_among_b(a_8) == 0) - { - return false; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_un_accent() { - { - var v_1 = 1; - while(true) - { - lab0: { - if (!(base.out_grouping_b(g_v, 97, 251))) - { - break lab0; - } - v_1--; - continue; - } - break; - } - if (v_1 > 0) - { - return false; - } - } - base.ket = base.cursor; - lab1: { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - if (!(base.eq_s_b("\u00E9"))) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_3; - if (!(base.eq_s_b("\u00E8"))) - { - return false; - } - } - base.bra = base.cursor; - if (!base.slice_from("e")) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_prelude(); - base.cursor = v_1; - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - var /** number */ v_5 = base.limit - base.cursor; - lab3: { - var /** number */ v_6 = base.limit - base.cursor; - lab4: { - if (!r_standard_suffix()) - { - break lab4; - } - break lab3; - } - base.cursor = base.limit - v_6; - lab5: { - if (!r_i_verb_suffix()) - { - break lab5; - } - break lab3; - } - base.cursor = base.limit - v_6; - if (!r_verb_suffix()) - { - break lab2; - } - } - base.cursor = base.limit - v_5; - var /** number */ v_7 = base.limit - base.cursor; - lab6: { - base.ket = base.cursor; - lab7: { - var /** number */ v_8 = base.limit - base.cursor; - lab8: { - if (!(base.eq_s_b("Y"))) - { - break lab8; - } - base.bra = base.cursor; - if (!base.slice_from("i")) - { - return false; - } - break lab7; - } - base.cursor = base.limit - v_8; - if (!(base.eq_s_b("\u00E7"))) - { - base.cursor = base.limit - v_7; - break lab6; - } - base.bra = base.cursor; - if (!base.slice_from("c")) - { - return false; - } - } - } - break lab1; - } - base.cursor = base.limit - v_4; - if (!r_residual_suffix()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_3; - var /** number */ v_9 = base.limit - base.cursor; - r_un_double(); - base.cursor = base.limit - v_9; - var /** number */ v_10 = base.limit - base.cursor; - r_un_accent(); - base.cursor = base.limit - v_10; - base.cursor = base.limit_backward; - var /** number */ v_11 = base.cursor; - r_postlude(); - base.cursor = v_11; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['FrenchStemmer'] = FrenchStemmer; diff --git a/js/german-stemmer.js b/js/german-stemmer.js deleted file mode 100644 index 93f92f8..0000000 --- a/js/german-stemmer.js +++ /dev/null @@ -1,591 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var GermanStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 5], - ["ae", 0, 2], - ["oe", 0, 3], - ["qu", 0, -1], - ["ue", 0, 4], - ["\u00DF", 0, 1] - ]; - - /** @const */ var a_1 = [ - ["", -1, 5], - ["U", 0, 2], - ["Y", 0, 1], - ["\u00E4", 0, 3], - ["\u00F6", 0, 4], - ["\u00FC", 0, 2] - ]; - - /** @const */ var a_2 = [ - ["e", -1, 2], - ["em", -1, 1], - ["en", -1, 2], - ["ern", -1, 1], - ["er", -1, 1], - ["s", -1, 3], - ["es", 5, 2] - ]; - - /** @const */ var a_3 = [ - ["en", -1, 1], - ["er", -1, 1], - ["st", -1, 2], - ["est", 2, 1] - ]; - - /** @const */ var a_4 = [ - ["ig", -1, 1], - ["lich", -1, 1] - ]; - - /** @const */ var a_5 = [ - ["end", -1, 1], - ["ig", -1, 2], - ["ung", -1, 1], - ["lich", -1, 3], - ["isch", -1, 2], - ["ik", -1, 2], - ["heit", -1, 3], - ["keit", -1, 4] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 32, 8]; - - /** @const */ var /** Array */ g_s_ending = [117, 30, 5]; - - /** @const */ var /** Array */ g_st_ending = [117, 30, 4]; - - var /** number */ I_x = 0; - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_prelude() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - while(true) - { - var /** number */ v_2 = base.cursor; - lab0: { - golab1: while(true) - { - var /** number */ v_3 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab2; - } - base.bra = base.cursor; - lab3: { - var /** number */ v_4 = base.cursor; - lab4: { - if (!(base.eq_s("u"))) - { - break lab4; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab4; - } - if (!base.slice_from("U")) - { - return false; - } - break lab3; - } - base.cursor = v_4; - if (!(base.eq_s("y"))) - { - break lab2; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab2; - } - if (!base.slice_from("Y")) - { - return false; - } - } - base.cursor = v_3; - break golab1; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - continue; - } - base.cursor = v_2; - break; - } - base.cursor = v_1; - while(true) - { - var /** number */ v_5 = base.cursor; - lab5: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("ss")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u00E4")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u00F6")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u00FC")) - { - return false; - } - break; - case 5: - if (base.cursor >= base.limit) - { - break lab5; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_5; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - { - var /** number */ c1 = base.cursor + 3; - if (c1 > base.limit) - { - return false; - } - base.cursor = c1; - } - I_x = base.cursor; - base.cursor = v_1; - golab0: while(true) - { - lab1: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab1; - } - break golab0; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - lab4: { - if (I_p1 >= I_x) - { - break lab4; - } - I_p1 = I_x; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p2 = base.cursor; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_1); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("y")) - { - return false; - } - break; - case 2: - if (!base.slice_from("u")) - { - return false; - } - break; - case 3: - if (!base.slice_from("a")) - { - return false; - } - break; - case 4: - if (!base.slice_from("o")) - { - return false; - } - break; - case 5: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!r_R1()) - { - break lab0; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (!(base.eq_s_b("s"))) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!(base.eq_s_b("nis"))) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 3: - if (!(base.in_grouping_b(g_s_ending, 98, 116))) - { - break lab0; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - base.cursor = base.limit - v_1; - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - break lab2; - } - base.bra = base.cursor; - if (!r_R1()) - { - break lab2; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.in_grouping_b(g_st_ending, 98, 116))) - { - break lab2; - } - { - var /** number */ c1 = base.cursor - 3; - if (c1 < base.limit_backward) - { - break lab2; - } - base.cursor = c1; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - break lab3; - } - base.bra = base.cursor; - if (!r_R2()) - { - break lab3; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - var /** number */ v_5 = base.limit - base.cursor; - lab4: { - base.ket = base.cursor; - if (!(base.eq_s_b("ig"))) - { - base.cursor = base.limit - v_5; - break lab4; - } - base.bra = base.cursor; - { - var /** number */ v_6 = base.limit - base.cursor; - lab5: { - if (!(base.eq_s_b("e"))) - { - break lab5; - } - base.cursor = base.limit - v_5; - break lab4; - } - base.cursor = base.limit - v_6; - } - if (!r_R2()) - { - base.cursor = base.limit - v_5; - break lab4; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 2: - { - var /** number */ v_7 = base.limit - base.cursor; - lab6: { - if (!(base.eq_s_b("e"))) - { - break lab6; - } - break lab3; - } - base.cursor = base.limit - v_7; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - var /** number */ v_8 = base.limit - base.cursor; - lab7: { - base.ket = base.cursor; - lab8: { - var /** number */ v_9 = base.limit - base.cursor; - lab9: { - if (!(base.eq_s_b("er"))) - { - break lab9; - } - break lab8; - } - base.cursor = base.limit - v_9; - if (!(base.eq_s_b("en"))) - { - base.cursor = base.limit - v_8; - break lab7; - } - } - base.bra = base.cursor; - if (!r_R1()) - { - base.cursor = base.limit - v_8; - break lab7; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 4: - if (!base.slice_del()) - { - return false; - } - var /** number */ v_10 = base.limit - base.cursor; - lab10: { - base.ket = base.cursor; - if (base.find_among_b(a_4) == 0) - { - base.cursor = base.limit - v_10; - break lab10; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_10; - break lab10; - } - if (!base.slice_del()) - { - return false; - } - } - break; - } - } - base.cursor = base.limit - v_4; - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_prelude(); - base.cursor = v_1; - var /** number */ v_2 = base.cursor; - r_mark_regions(); - base.cursor = v_2; - base.limit_backward = base.cursor; base.cursor = base.limit; - r_standard_suffix(); - base.cursor = base.limit_backward; - var /** number */ v_4 = base.cursor; - r_postlude(); - base.cursor = v_4; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['GermanStemmer'] = GermanStemmer; diff --git a/js/greek-stemmer.js b/js/greek-stemmer.js deleted file mode 100644 index 865b0ea..0000000 --- a/js/greek-stemmer.js +++ /dev/null @@ -1,2870 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var GreekStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 25], - ["\u0386", 0, 1], - ["\u0388", 0, 5], - ["\u0389", 0, 7], - ["\u038A", 0, 9], - ["\u038C", 0, 15], - ["\u038E", 0, 20], - ["\u038F", 0, 24], - ["\u0390", 0, 7], - ["\u0391", 0, 1], - ["\u0392", 0, 2], - ["\u0393", 0, 3], - ["\u0394", 0, 4], - ["\u0395", 0, 5], - ["\u0396", 0, 6], - ["\u0397", 0, 7], - ["\u0398", 0, 8], - ["\u0399", 0, 9], - ["\u039A", 0, 10], - ["\u039B", 0, 11], - ["\u039C", 0, 12], - ["\u039D", 0, 13], - ["\u039E", 0, 14], - ["\u039F", 0, 15], - ["\u03A0", 0, 16], - ["\u03A1", 0, 17], - ["\u03A3", 0, 18], - ["\u03A4", 0, 19], - ["\u03A5", 0, 20], - ["\u03A6", 0, 21], - ["\u03A7", 0, 22], - ["\u03A8", 0, 23], - ["\u03A9", 0, 24], - ["\u03AA", 0, 9], - ["\u03AB", 0, 20], - ["\u03AC", 0, 1], - ["\u03AD", 0, 5], - ["\u03AE", 0, 7], - ["\u03AF", 0, 9], - ["\u03B0", 0, 20], - ["\u03C2", 0, 18], - ["\u03CA", 0, 7], - ["\u03CB", 0, 20], - ["\u03CC", 0, 15], - ["\u03CD", 0, 20], - ["\u03CE", 0, 24] - ]; - - /** @const */ var a_1 = [ - ["\u03C3\u03BA\u03B1\u03B3\u03B9\u03B1", -1, 2], - ["\u03C6\u03B1\u03B3\u03B9\u03B1", -1, 1], - ["\u03BF\u03BB\u03BF\u03B3\u03B9\u03B1", -1, 3], - ["\u03C3\u03BF\u03B3\u03B9\u03B1", -1, 4], - ["\u03C4\u03B1\u03C4\u03BF\u03B3\u03B9\u03B1", -1, 5], - ["\u03BA\u03C1\u03B5\u03B1\u03C4\u03B1", -1, 6], - ["\u03C0\u03B5\u03C1\u03B1\u03C4\u03B1", -1, 7], - ["\u03C4\u03B5\u03C1\u03B1\u03C4\u03B1", -1, 8], - ["\u03B3\u03B5\u03B3\u03BF\u03BD\u03BF\u03C4\u03B1", -1, 11], - ["\u03BA\u03B1\u03B8\u03B5\u03C3\u03C4\u03C9\u03C4\u03B1", -1, 10], - ["\u03C6\u03C9\u03C4\u03B1", -1, 9], - ["\u03C0\u03B5\u03C1\u03B1\u03C4\u03B7", -1, 7], - ["\u03C3\u03BA\u03B1\u03B3\u03B9\u03C9\u03BD", -1, 2], - ["\u03C6\u03B1\u03B3\u03B9\u03C9\u03BD", -1, 1], - ["\u03BF\u03BB\u03BF\u03B3\u03B9\u03C9\u03BD", -1, 3], - ["\u03C3\u03BF\u03B3\u03B9\u03C9\u03BD", -1, 4], - ["\u03C4\u03B1\u03C4\u03BF\u03B3\u03B9\u03C9\u03BD", -1, 5], - ["\u03BA\u03C1\u03B5\u03B1\u03C4\u03C9\u03BD", -1, 6], - ["\u03C0\u03B5\u03C1\u03B1\u03C4\u03C9\u03BD", -1, 7], - ["\u03C4\u03B5\u03C1\u03B1\u03C4\u03C9\u03BD", -1, 8], - ["\u03B3\u03B5\u03B3\u03BF\u03BD\u03BF\u03C4\u03C9\u03BD", -1, 11], - ["\u03BA\u03B1\u03B8\u03B5\u03C3\u03C4\u03C9\u03C4\u03C9\u03BD", -1, 10], - ["\u03C6\u03C9\u03C4\u03C9\u03BD", -1, 9], - ["\u03BA\u03C1\u03B5\u03B1\u03C3", -1, 6], - ["\u03C0\u03B5\u03C1\u03B1\u03C3", -1, 7], - ["\u03C4\u03B5\u03C1\u03B1\u03C3", -1, 8], - ["\u03B3\u03B5\u03B3\u03BF\u03BD\u03BF\u03C3", -1, 11], - ["\u03BA\u03C1\u03B5\u03B1\u03C4\u03BF\u03C3", -1, 6], - ["\u03C0\u03B5\u03C1\u03B1\u03C4\u03BF\u03C3", -1, 7], - ["\u03C4\u03B5\u03C1\u03B1\u03C4\u03BF\u03C3", -1, 8], - ["\u03B3\u03B5\u03B3\u03BF\u03BD\u03BF\u03C4\u03BF\u03C3", -1, 11], - ["\u03BA\u03B1\u03B8\u03B5\u03C3\u03C4\u03C9\u03C4\u03BF\u03C3", -1, 10], - ["\u03C6\u03C9\u03C4\u03BF\u03C3", -1, 9], - ["\u03BA\u03B1\u03B8\u03B5\u03C3\u03C4\u03C9\u03C3", -1, 10], - ["\u03C6\u03C9\u03C3", -1, 9], - ["\u03C3\u03BA\u03B1\u03B3\u03B9\u03BF\u03C5", -1, 2], - ["\u03C6\u03B1\u03B3\u03B9\u03BF\u03C5", -1, 1], - ["\u03BF\u03BB\u03BF\u03B3\u03B9\u03BF\u03C5", -1, 3], - ["\u03C3\u03BF\u03B3\u03B9\u03BF\u03C5", -1, 4], - ["\u03C4\u03B1\u03C4\u03BF\u03B3\u03B9\u03BF\u03C5", -1, 5] - ]; - - /** @const */ var a_2 = [ - ["\u03C0\u03B1", -1, 1], - ["\u03BE\u03B1\u03BD\u03B1\u03C0\u03B1", 0, 1], - ["\u03B5\u03C0\u03B1", 0, 1], - ["\u03C0\u03B5\u03C1\u03B9\u03C0\u03B1", 0, 1], - ["\u03B1\u03BD\u03B1\u03BC\u03C0\u03B1", 0, 1], - ["\u03B5\u03BC\u03C0\u03B1", 0, 1], - ["\u03B2", -1, 2], - ["\u03B4\u03B1\u03BD\u03B5", -1, 1], - ["\u03B2\u03B1\u03B8\u03C5\u03C1\u03B9", -1, 2], - ["\u03B2\u03B1\u03C1\u03BA", -1, 2], - ["\u03BC\u03B1\u03C1\u03BA", -1, 2], - ["\u03BB", -1, 2], - ["\u03BC", -1, 2], - ["\u03BA\u03BF\u03C1\u03BD", -1, 2], - ["\u03B1\u03B8\u03C1\u03BF", -1, 1], - ["\u03C3\u03C5\u03BD\u03B1\u03B8\u03C1\u03BF", 14, 1], - ["\u03C0", -1, 2], - ["\u03B9\u03BC\u03C0", 16, 2], - ["\u03C1", -1, 2], - ["\u03BC\u03B1\u03C1", 18, 2], - ["\u03B1\u03BC\u03C0\u03B1\u03C1", 18, 2], - ["\u03B3\u03BA\u03C1", 18, 2], - ["\u03B2\u03BF\u03BB\u03B2\u03BF\u03C1", 18, 2], - ["\u03B3\u03BB\u03C5\u03BA\u03BF\u03C1", 18, 2], - ["\u03C0\u03B9\u03C0\u03B5\u03C1\u03BF\u03C1", 18, 2], - ["\u03C0\u03C1", 18, 2], - ["\u03BC\u03C0\u03C1", 25, 2], - ["\u03B1\u03C1\u03C1", 18, 2], - ["\u03B3\u03BB\u03C5\u03BA\u03C5\u03C1", 18, 2], - ["\u03C0\u03BF\u03BB\u03C5\u03C1", 18, 2], - ["\u03BB\u03BF\u03C5", -1, 2] - ]; - - /** @const */ var a_3 = [ - ["\u03B9\u03B6\u03B1", -1, 1], - ["\u03B9\u03B6\u03B5", -1, 1], - ["\u03B9\u03B6\u03B1\u03BC\u03B5", -1, 1], - ["\u03B9\u03B6\u03BF\u03C5\u03BC\u03B5", -1, 1], - ["\u03B9\u03B6\u03B1\u03BD\u03B5", -1, 1], - ["\u03B9\u03B6\u03BF\u03C5\u03BD\u03B5", -1, 1], - ["\u03B9\u03B6\u03B1\u03C4\u03B5", -1, 1], - ["\u03B9\u03B6\u03B5\u03C4\u03B5", -1, 1], - ["\u03B9\u03B6\u03B5\u03B9", -1, 1], - ["\u03B9\u03B6\u03B1\u03BD", -1, 1], - ["\u03B9\u03B6\u03BF\u03C5\u03BD", -1, 1], - ["\u03B9\u03B6\u03B5\u03C3", -1, 1], - ["\u03B9\u03B6\u03B5\u03B9\u03C3", -1, 1], - ["\u03B9\u03B6\u03C9", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["\u03B2\u03B9", -1, 1], - ["\u03BB\u03B9", -1, 1], - ["\u03B1\u03BB", -1, 1], - ["\u03B5\u03BD", -1, 1], - ["\u03C3", -1, 1], - ["\u03C7", -1, 1], - ["\u03C5\u03C8", -1, 1], - ["\u03B6\u03C9", -1, 1] - ]; - - /** @const */ var a_5 = [ - ["\u03C9\u03B8\u03B7\u03BA\u03B1", -1, 1], - ["\u03C9\u03B8\u03B7\u03BA\u03B5", -1, 1], - ["\u03C9\u03B8\u03B7\u03BA\u03B1\u03BC\u03B5", -1, 1], - ["\u03C9\u03B8\u03B7\u03BA\u03B1\u03BD\u03B5", -1, 1], - ["\u03C9\u03B8\u03B7\u03BA\u03B1\u03C4\u03B5", -1, 1], - ["\u03C9\u03B8\u03B7\u03BA\u03B1\u03BD", -1, 1], - ["\u03C9\u03B8\u03B7\u03BA\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["\u03BE\u03B1\u03BD\u03B1\u03C0\u03B1", -1, 1], - ["\u03B5\u03C0\u03B1", -1, 1], - ["\u03C0\u03B5\u03C1\u03B9\u03C0\u03B1", -1, 1], - ["\u03B1\u03BD\u03B1\u03BC\u03C0\u03B1", -1, 1], - ["\u03B5\u03BC\u03C0\u03B1", -1, 1], - ["\u03C7\u03B1\u03C1\u03C4\u03BF\u03C0\u03B1", -1, 1], - ["\u03B5\u03BE\u03B1\u03C1\u03C7\u03B1", -1, 1], - ["\u03B3\u03B5", -1, 2], - ["\u03B3\u03BA\u03B5", -1, 2], - ["\u03BA\u03BB\u03B5", -1, 1], - ["\u03B5\u03BA\u03BB\u03B5", 9, 1], - ["\u03B1\u03C0\u03B5\u03BA\u03BB\u03B5", 10, 1], - ["\u03B1\u03C0\u03BF\u03BA\u03BB\u03B5", 9, 1], - ["\u03B5\u03C3\u03C9\u03BA\u03BB\u03B5", 9, 1], - ["\u03B4\u03B1\u03BD\u03B5", -1, 1], - ["\u03C0\u03B5", -1, 1], - ["\u03B5\u03C0\u03B5", 15, 1], - ["\u03BC\u03B5\u03C4\u03B5\u03C0\u03B5", 16, 1], - ["\u03B5\u03C3\u03B5", -1, 1], - ["\u03B3\u03BA", -1, 2], - ["\u03BC", -1, 2], - ["\u03C0\u03BF\u03C5\u03BA\u03B1\u03BC", 20, 2], - ["\u03BA\u03BF\u03BC", 20, 2], - ["\u03B1\u03BD", -1, 2], - ["\u03BF\u03BB\u03BF", -1, 2], - ["\u03B1\u03B8\u03C1\u03BF", -1, 1], - ["\u03C3\u03C5\u03BD\u03B1\u03B8\u03C1\u03BF", 25, 1], - ["\u03C0", -1, 2], - ["\u03BB\u03B1\u03C1", -1, 2], - ["\u03B4\u03B7\u03BC\u03BF\u03BA\u03C1\u03B1\u03C4", -1, 2], - ["\u03B1\u03C6", -1, 2], - ["\u03B3\u03B9\u03B3\u03B1\u03BD\u03C4\u03BF\u03B1\u03C6", 30, 2] - ]; - - /** @const */ var a_7 = [ - ["\u03B9\u03C3\u03B1", -1, 1], - ["\u03B9\u03C3\u03B1\u03BC\u03B5", -1, 1], - ["\u03B9\u03C3\u03B1\u03BD\u03B5", -1, 1], - ["\u03B9\u03C3\u03B5", -1, 1], - ["\u03B9\u03C3\u03B1\u03C4\u03B5", -1, 1], - ["\u03B9\u03C3\u03B1\u03BD", -1, 1], - ["\u03B9\u03C3\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_8 = [ - ["\u03BE\u03B1\u03BD\u03B1\u03C0\u03B1", -1, 1], - ["\u03B5\u03C0\u03B1", -1, 1], - ["\u03C0\u03B5\u03C1\u03B9\u03C0\u03B1", -1, 1], - ["\u03B1\u03BD\u03B1\u03BC\u03C0\u03B1", -1, 1], - ["\u03B5\u03BC\u03C0\u03B1", -1, 1], - ["\u03C7\u03B1\u03C1\u03C4\u03BF\u03C0\u03B1", -1, 1], - ["\u03B5\u03BE\u03B1\u03C1\u03C7\u03B1", -1, 1], - ["\u03BA\u03BB\u03B5", -1, 1], - ["\u03B5\u03BA\u03BB\u03B5", 7, 1], - ["\u03B1\u03C0\u03B5\u03BA\u03BB\u03B5", 8, 1], - ["\u03B1\u03C0\u03BF\u03BA\u03BB\u03B5", 7, 1], - ["\u03B5\u03C3\u03C9\u03BA\u03BB\u03B5", 7, 1], - ["\u03B4\u03B1\u03BD\u03B5", -1, 1], - ["\u03C0\u03B5", -1, 1], - ["\u03B5\u03C0\u03B5", 13, 1], - ["\u03BC\u03B5\u03C4\u03B5\u03C0\u03B5", 14, 1], - ["\u03B5\u03C3\u03B5", -1, 1], - ["\u03B1\u03B8\u03C1\u03BF", -1, 1], - ["\u03C3\u03C5\u03BD\u03B1\u03B8\u03C1\u03BF", 17, 1] - ]; - - /** @const */ var a_9 = [ - ["\u03B9\u03C3\u03BF\u03C5\u03BC\u03B5", -1, 1], - ["\u03B9\u03C3\u03BF\u03C5\u03BD\u03B5", -1, 1], - ["\u03B9\u03C3\u03B5\u03C4\u03B5", -1, 1], - ["\u03B9\u03C3\u03B5\u03B9", -1, 1], - ["\u03B9\u03C3\u03BF\u03C5\u03BD", -1, 1], - ["\u03B9\u03C3\u03B5\u03B9\u03C3", -1, 1], - ["\u03B9\u03C3\u03C9", -1, 1] - ]; - - /** @const */ var a_10 = [ - ["\u03B1\u03C4\u03B1", -1, 2], - ["\u03C6\u03B1", -1, 2], - ["\u03B7\u03C6\u03B1", 1, 2], - ["\u03BC\u03B5\u03B3", -1, 2], - ["\u03BB\u03C5\u03B3", -1, 2], - ["\u03B7\u03B4", -1, 2], - ["\u03BA\u03BB\u03B5", -1, 1], - ["\u03B5\u03C3\u03C9\u03BA\u03BB\u03B5", 6, 1], - ["\u03C0\u03BB\u03B5", -1, 1], - ["\u03B4\u03B1\u03BD\u03B5", -1, 1], - ["\u03C3\u03B5", -1, 1], - ["\u03B1\u03C3\u03B5", 10, 1], - ["\u03BA\u03B1\u03B8", -1, 2], - ["\u03B5\u03C7\u03B8", -1, 2], - ["\u03BA\u03B1\u03BA", -1, 2], - ["\u03BC\u03B1\u03BA", -1, 2], - ["\u03C3\u03BA", -1, 2], - ["\u03C6\u03B9\u03BB", -1, 2], - ["\u03BA\u03C5\u03BB", -1, 2], - ["\u03BC", -1, 2], - ["\u03B3\u03B5\u03BC", 19, 2], - ["\u03B1\u03C7\u03BD", -1, 2], - ["\u03C3\u03C5\u03BD\u03B1\u03B8\u03C1\u03BF", -1, 1], - ["\u03C0", -1, 2], - ["\u03B1\u03C0", 23, 2], - ["\u03B5\u03BC\u03C0", 23, 2], - ["\u03B5\u03C5\u03C0", 23, 2], - ["\u03B1\u03C1", -1, 2], - ["\u03B1\u03BF\u03C1", -1, 2], - ["\u03B3\u03C5\u03C1", -1, 2], - ["\u03C7\u03C1", -1, 2], - ["\u03C7\u03C9\u03C1", -1, 2], - ["\u03BA\u03C4", -1, 2], - ["\u03B1\u03BA\u03C4", 32, 2], - ["\u03C7\u03C4", -1, 2], - ["\u03B1\u03C7\u03C4", 34, 2], - ["\u03C4\u03B1\u03C7", -1, 2], - ["\u03C3\u03C7", -1, 2], - ["\u03B1\u03C3\u03C7", 37, 2], - ["\u03C5\u03C8", -1, 2] - ]; - - /** @const */ var a_11 = [ - ["\u03B9\u03C3\u03C4\u03B1", -1, 1], - ["\u03B9\u03C3\u03C4\u03B5", -1, 1], - ["\u03B9\u03C3\u03C4\u03B7", -1, 1], - ["\u03B9\u03C3\u03C4\u03BF\u03B9", -1, 1], - ["\u03B9\u03C3\u03C4\u03C9\u03BD", -1, 1], - ["\u03B9\u03C3\u03C4\u03BF", -1, 1], - ["\u03B9\u03C3\u03C4\u03B5\u03C3", -1, 1], - ["\u03B9\u03C3\u03C4\u03B7\u03C3", -1, 1], - ["\u03B9\u03C3\u03C4\u03BF\u03C3", -1, 1], - ["\u03B9\u03C3\u03C4\u03BF\u03C5\u03C3", -1, 1], - ["\u03B9\u03C3\u03C4\u03BF\u03C5", -1, 1] - ]; - - /** @const */ var a_12 = [ - ["\u03B5\u03B3\u03BA\u03BB\u03B5", -1, 1], - ["\u03B1\u03C0\u03BF\u03BA\u03BB\u03B5", -1, 1], - ["\u03B4\u03B1\u03BD\u03B5", -1, 2], - ["\u03B1\u03BD\u03C4\u03B9\u03B4\u03B1\u03BD\u03B5", 2, 2], - ["\u03C3\u03B5", -1, 1], - ["\u03BC\u03B5\u03C4\u03B1\u03C3\u03B5", 4, 1], - ["\u03BC\u03B9\u03BA\u03C1\u03BF\u03C3\u03B5", 4, 1] - ]; - - /** @const */ var a_13 = [ - ["\u03B1\u03C4\u03BF\u03BC\u03B9\u03BA", -1, 2], - ["\u03B5\u03B8\u03BD\u03B9\u03BA", -1, 4], - ["\u03C4\u03BF\u03C0\u03B9\u03BA", -1, 7], - ["\u03B5\u03BA\u03BB\u03B5\u03BA\u03C4\u03B9\u03BA", -1, 5], - ["\u03C3\u03BA\u03B5\u03C0\u03C4\u03B9\u03BA", -1, 6], - ["\u03B3\u03BD\u03C9\u03C3\u03C4\u03B9\u03BA", -1, 3], - ["\u03B1\u03B3\u03BD\u03C9\u03C3\u03C4\u03B9\u03BA", 5, 1], - ["\u03B1\u03BB\u03B5\u03BE\u03B1\u03BD\u03B4\u03C1\u03B9\u03BD", -1, 8], - ["\u03B8\u03B5\u03B1\u03C4\u03C1\u03B9\u03BD", -1, 10], - ["\u03B2\u03C5\u03B6\u03B1\u03BD\u03C4\u03B9\u03BD", -1, 9] - ]; - - /** @const */ var a_14 = [ - ["\u03B9\u03C3\u03BC\u03BF\u03B9", -1, 1], - ["\u03B9\u03C3\u03BC\u03C9\u03BD", -1, 1], - ["\u03B9\u03C3\u03BC\u03BF", -1, 1], - ["\u03B9\u03C3\u03BC\u03BF\u03C3", -1, 1], - ["\u03B9\u03C3\u03BC\u03BF\u03C5\u03C3", -1, 1], - ["\u03B9\u03C3\u03BC\u03BF\u03C5", -1, 1] - ]; - - /** @const */ var a_15 = [ - ["\u03C3", -1, 1], - ["\u03C7", -1, 1] - ]; - - /** @const */ var a_16 = [ - ["\u03BF\u03C5\u03B4\u03B1\u03BA\u03B9\u03B1", -1, 1], - ["\u03B1\u03C1\u03B1\u03BA\u03B9\u03B1", -1, 1], - ["\u03BF\u03C5\u03B4\u03B1\u03BA\u03B9", -1, 1], - ["\u03B1\u03C1\u03B1\u03BA\u03B9", -1, 1] - ]; - - /** @const */ var a_17 = [ - ["\u03B2", -1, 2], - ["\u03B2\u03B1\u03BC\u03B2", 0, 1], - ["\u03C3\u03BB\u03BF\u03B2", 0, 1], - ["\u03C4\u03C3\u03B5\u03C7\u03BF\u03C3\u03BB\u03BF\u03B2", 2, 1], - ["\u03BA\u03B1\u03C1\u03B4", -1, 2], - ["\u03B6", -1, 2], - ["\u03C4\u03B6", 5, 1], - ["\u03BA", -1, 1], - ["\u03BA\u03B1\u03C0\u03B1\u03BA", 7, 1], - ["\u03C3\u03BF\u03BA", 7, 1], - ["\u03C3\u03BA", 7, 1], - ["\u03B2\u03B1\u03BB", -1, 2], - ["\u03BC\u03B1\u03BB", -1, 1], - ["\u03B3\u03BB", -1, 2], - ["\u03C4\u03C1\u03B9\u03C0\u03BF\u03BB", -1, 2], - ["\u03C0\u03BB", -1, 1], - ["\u03BB\u03BF\u03C5\u03BB", -1, 1], - ["\u03C6\u03C5\u03BB", -1, 1], - ["\u03BA\u03B1\u03B9\u03BC", -1, 1], - ["\u03BA\u03BB\u03B9\u03BC", -1, 1], - ["\u03C6\u03B1\u03C1\u03BC", -1, 1], - ["\u03B3\u03B9\u03B1\u03BD", -1, 2], - ["\u03C3\u03C0\u03B1\u03BD", -1, 1], - ["\u03B7\u03B3\u03BF\u03C5\u03BC\u03B5\u03BD", -1, 2], - ["\u03BA\u03BF\u03BD", -1, 1], - ["\u03BC\u03B1\u03BA\u03C1\u03C5\u03BD", -1, 2], - ["\u03C0", -1, 2], - ["\u03BA\u03B1\u03C4\u03C1\u03B1\u03C0", 26, 1], - ["\u03C1", -1, 1], - ["\u03B2\u03C1", 28, 1], - ["\u03BB\u03B1\u03B2\u03C1", 29, 1], - ["\u03B1\u03BC\u03B2\u03C1", 29, 1], - ["\u03BC\u03B5\u03C1", 28, 1], - ["\u03C0\u03B1\u03C4\u03B5\u03C1", 28, 2], - ["\u03B1\u03BD\u03B8\u03C1", 28, 1], - ["\u03BA\u03BF\u03C1", 28, 1], - ["\u03C3", -1, 1], - ["\u03BD\u03B1\u03B3\u03BA\u03B1\u03C3", 36, 1], - ["\u03C4\u03BF\u03C3", 36, 2], - ["\u03BC\u03BF\u03C5\u03C3\u03C4", -1, 1], - ["\u03C1\u03C5", -1, 1], - ["\u03C6", -1, 1], - ["\u03C3\u03C6", 41, 1], - ["\u03B1\u03BB\u03B9\u03C3\u03C6", 42, 1], - ["\u03BD\u03C5\u03C6", 41, 2], - ["\u03C7", -1, 1] - ]; - - /** @const */ var a_18 = [ - ["\u03B1\u03BA\u03B9\u03B1", -1, 1], - ["\u03B1\u03C1\u03B1\u03BA\u03B9\u03B1", 0, 1], - ["\u03B9\u03C4\u03C3\u03B1", -1, 1], - ["\u03B1\u03BA\u03B9", -1, 1], - ["\u03B1\u03C1\u03B1\u03BA\u03B9", 3, 1], - ["\u03B9\u03C4\u03C3\u03C9\u03BD", -1, 1], - ["\u03B9\u03C4\u03C3\u03B1\u03C3", -1, 1], - ["\u03B9\u03C4\u03C3\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_19 = [ - ["\u03C8\u03B1\u03BB", -1, 1], - ["\u03B1\u03B9\u03C6\u03BD", -1, 1], - ["\u03BF\u03BB\u03BF", -1, 1], - ["\u03B9\u03C1", -1, 1] - ]; - - /** @const */ var a_20 = [ - ["\u03B5", -1, 1], - ["\u03C0\u03B1\u03B9\u03C7\u03BD", -1, 1] - ]; - - /** @const */ var a_21 = [ - ["\u03B9\u03B4\u03B9\u03B1", -1, 1], - ["\u03B9\u03B4\u03B9\u03C9\u03BD", -1, 1], - ["\u03B9\u03B4\u03B9\u03BF", -1, 1] - ]; - - /** @const */ var a_22 = [ - ["\u03B9\u03B2", -1, 1], - ["\u03B4", -1, 1], - ["\u03C6\u03C1\u03B1\u03B3\u03BA", -1, 1], - ["\u03BB\u03C5\u03BA", -1, 1], - ["\u03BF\u03B2\u03B5\u03BB", -1, 1], - ["\u03BC\u03B7\u03BD", -1, 1], - ["\u03C1", -1, 1] - ]; - - /** @const */ var a_23 = [ - ["\u03B9\u03C3\u03BA\u03B5", -1, 1], - ["\u03B9\u03C3\u03BA\u03BF", -1, 1], - ["\u03B9\u03C3\u03BA\u03BF\u03C3", -1, 1], - ["\u03B9\u03C3\u03BA\u03BF\u03C5", -1, 1] - ]; - - /** @const */ var a_24 = [ - ["\u03B1\u03B4\u03C9\u03BD", -1, 1], - ["\u03B1\u03B4\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_25 = [ - ["\u03B3\u03B9\u03B1\u03B3\u03B9", -1, -1], - ["\u03B8\u03B5\u03B9", -1, -1], - ["\u03BF\u03BA", -1, -1], - ["\u03BC\u03B1\u03BC", -1, -1], - ["\u03BC\u03B1\u03BD", -1, -1], - ["\u03BC\u03C0\u03B1\u03BC\u03C0", -1, -1], - ["\u03C0\u03B5\u03B8\u03B5\u03C1", -1, -1], - ["\u03C0\u03B1\u03C4\u03B5\u03C1", -1, -1], - ["\u03BA\u03C5\u03C1", -1, -1], - ["\u03BD\u03C4\u03B1\u03BD\u03C4", -1, -1] - ]; - - /** @const */ var a_26 = [ - ["\u03B5\u03B4\u03C9\u03BD", -1, 1], - ["\u03B5\u03B4\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_27 = [ - ["\u03BC\u03B9\u03BB", -1, 1], - ["\u03B4\u03B1\u03C0", -1, 1], - ["\u03B3\u03B7\u03C0", -1, 1], - ["\u03B9\u03C0", -1, 1], - ["\u03B5\u03BC\u03C0", -1, 1], - ["\u03BF\u03C0", -1, 1], - ["\u03BA\u03C1\u03B1\u03C3\u03C0", -1, 1], - ["\u03C5\u03C0", -1, 1] - ]; - - /** @const */ var a_28 = [ - ["\u03BF\u03C5\u03B4\u03C9\u03BD", -1, 1], - ["\u03BF\u03C5\u03B4\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_29 = [ - ["\u03C4\u03C1\u03B1\u03B3", -1, 1], - ["\u03C6\u03B5", -1, 1], - ["\u03BA\u03B1\u03BB\u03B9\u03B1\u03BA", -1, 1], - ["\u03B1\u03C1\u03BA", -1, 1], - ["\u03C3\u03BA", -1, 1], - ["\u03C0\u03B5\u03C4\u03B1\u03BB", -1, 1], - ["\u03B2\u03B5\u03BB", -1, 1], - ["\u03BB\u03BF\u03C5\u03BB", -1, 1], - ["\u03C6\u03BB", -1, 1], - ["\u03C7\u03BD", -1, 1], - ["\u03C0\u03BB\u03B5\u03BE", -1, 1], - ["\u03C3\u03C0", -1, 1], - ["\u03C6\u03C1", -1, 1], - ["\u03C3", -1, 1], - ["\u03BB\u03B9\u03C7", -1, 1] - ]; - - /** @const */ var a_30 = [ - ["\u03B5\u03C9\u03BD", -1, 1], - ["\u03B5\u03C9\u03C3", -1, 1] - ]; - - /** @const */ var a_31 = [ - ["\u03B4", -1, 1], - ["\u03B9\u03B4", 0, 1], - ["\u03B8", -1, 1], - ["\u03B3\u03B1\u03BB", -1, 1], - ["\u03B5\u03BB", -1, 1], - ["\u03BD", -1, 1], - ["\u03C0", -1, 1], - ["\u03C0\u03B1\u03C1", -1, 1] - ]; - - /** @const */ var a_32 = [ - ["\u03B9\u03B1", -1, 1], - ["\u03B9\u03C9\u03BD", -1, 1], - ["\u03B9\u03BF\u03C5", -1, 1] - ]; - - /** @const */ var a_33 = [ - ["\u03B9\u03BA\u03B1", -1, 1], - ["\u03B9\u03BA\u03C9\u03BD", -1, 1], - ["\u03B9\u03BA\u03BF", -1, 1], - ["\u03B9\u03BA\u03BF\u03C5", -1, 1] - ]; - - /** @const */ var a_34 = [ - ["\u03B1\u03B4", -1, 1], - ["\u03C3\u03C5\u03BD\u03B1\u03B4", 0, 1], - ["\u03BA\u03B1\u03C4\u03B1\u03B4", 0, 1], - ["\u03B1\u03BD\u03C4\u03B9\u03B4", -1, 1], - ["\u03B5\u03BD\u03B4", -1, 1], - ["\u03C6\u03C5\u03BB\u03BF\u03B4", -1, 1], - ["\u03C5\u03C0\u03BF\u03B4", -1, 1], - ["\u03C0\u03C1\u03C9\u03C4\u03BF\u03B4", -1, 1], - ["\u03B5\u03BE\u03C9\u03B4", -1, 1], - ["\u03B7\u03B8", -1, 1], - ["\u03B1\u03BD\u03B7\u03B8", 9, 1], - ["\u03BE\u03B9\u03BA", -1, 1], - ["\u03B1\u03BB", -1, 1], - ["\u03B1\u03BC\u03BC\u03BF\u03C7\u03B1\u03BB", 12, 1], - ["\u03C3\u03C5\u03BD\u03BF\u03BC\u03B7\u03BB", -1, 1], - ["\u03BC\u03C0\u03BF\u03BB", -1, 1], - ["\u03BC\u03BF\u03C5\u03BB", -1, 1], - ["\u03C4\u03C3\u03B1\u03BC", -1, 1], - ["\u03B2\u03C1\u03C9\u03BC", -1, 1], - ["\u03B1\u03BC\u03B1\u03BD", -1, 1], - ["\u03BC\u03C0\u03B1\u03BD", -1, 1], - ["\u03BA\u03B1\u03BB\u03BB\u03B9\u03BD", -1, 1], - ["\u03C0\u03BF\u03C3\u03C4\u03B5\u03BB\u03BD", -1, 1], - ["\u03C6\u03B9\u03BB\u03BF\u03BD", -1, 1], - ["\u03BA\u03B1\u03BB\u03C0", -1, 1], - ["\u03B3\u03B5\u03C1", -1, 1], - ["\u03C7\u03B1\u03C3", -1, 1], - ["\u03BC\u03C0\u03BF\u03C3", -1, 1], - ["\u03C0\u03BB\u03B9\u03B1\u03C4\u03C3", -1, 1], - ["\u03C0\u03B5\u03C4\u03C3", -1, 1], - ["\u03C0\u03B9\u03C4\u03C3", -1, 1], - ["\u03C6\u03C5\u03C3", -1, 1], - ["\u03BC\u03C0\u03B1\u03B3\u03B9\u03B1\u03C4", -1, 1], - ["\u03BD\u03B9\u03C4", -1, 1], - ["\u03C0\u03B9\u03BA\u03B1\u03BD\u03C4", -1, 1], - ["\u03C3\u03B5\u03C1\u03C4", -1, 1] - ]; - - /** @const */ var a_35 = [ - ["\u03B1\u03B3\u03B1\u03BC\u03B5", -1, 1], - ["\u03B7\u03BA\u03B1\u03BC\u03B5", -1, 1], - ["\u03B7\u03B8\u03B7\u03BA\u03B1\u03BC\u03B5", 1, 1], - ["\u03B7\u03C3\u03B1\u03BC\u03B5", -1, 1], - ["\u03BF\u03C5\u03C3\u03B1\u03BC\u03B5", -1, 1] - ]; - - /** @const */ var a_36 = [ - ["\u03B2\u03BF\u03C5\u03B2", -1, 1], - ["\u03BE\u03B5\u03B8", -1, 1], - ["\u03C0\u03B5\u03B8", -1, 1], - ["\u03B1\u03C0\u03BF\u03B8", -1, 1], - ["\u03B1\u03C0\u03BF\u03BA", -1, 1], - ["\u03BF\u03C5\u03BB", -1, 1], - ["\u03B1\u03BD\u03B1\u03C0", -1, 1], - ["\u03C0\u03B9\u03BA\u03C1", -1, 1], - ["\u03C0\u03BF\u03C4", -1, 1], - ["\u03B1\u03C0\u03BF\u03C3\u03C4", -1, 1], - ["\u03C7", -1, 1], - ["\u03C3\u03B9\u03C7", 10, 1] - ]; - - /** @const */ var a_37 = [ - ["\u03C4\u03C1", -1, 1], - ["\u03C4\u03C3", -1, 1] - ]; - - /** @const */ var a_38 = [ - ["\u03B1\u03B3\u03B1\u03BD\u03B5", -1, 1], - ["\u03B7\u03BA\u03B1\u03BD\u03B5", -1, 1], - ["\u03B7\u03B8\u03B7\u03BA\u03B1\u03BD\u03B5", 1, 1], - ["\u03B7\u03C3\u03B1\u03BD\u03B5", -1, 1], - ["\u03BF\u03C5\u03C3\u03B1\u03BD\u03B5", -1, 1], - ["\u03BF\u03BD\u03C4\u03B1\u03BD\u03B5", -1, 1], - ["\u03B9\u03BF\u03BD\u03C4\u03B1\u03BD\u03B5", 5, 1], - ["\u03BF\u03C5\u03BD\u03C4\u03B1\u03BD\u03B5", -1, 1], - ["\u03B9\u03BF\u03C5\u03BD\u03C4\u03B1\u03BD\u03B5", 7, 1], - ["\u03BF\u03C4\u03B1\u03BD\u03B5", -1, 1], - ["\u03B9\u03BF\u03C4\u03B1\u03BD\u03B5", 9, 1] - ]; - - /** @const */ var a_39 = [ - ["\u03C4\u03B1\u03B2", -1, 1], - ["\u03BD\u03C4\u03B1\u03B2", 0, 1], - ["\u03C8\u03B7\u03BB\u03BF\u03C4\u03B1\u03B2", 0, 1], - ["\u03BB\u03B9\u03B2", -1, 1], - ["\u03BA\u03BB\u03B9\u03B2", 3, 1], - ["\u03BE\u03B7\u03C1\u03BF\u03BA\u03BB\u03B9\u03B2", 4, 1], - ["\u03B3", -1, 1], - ["\u03B1\u03B3", 6, 1], - ["\u03C4\u03C1\u03B1\u03B3", 7, 1], - ["\u03C4\u03C3\u03B1\u03B3", 7, 1], - ["\u03B1\u03B8\u03B9\u03B3\u03B3", 6, 1], - ["\u03C4\u03C3\u03B9\u03B3\u03B3", 6, 1], - ["\u03B1\u03C4\u03C3\u03B9\u03B3\u03B3", 11, 1], - ["\u03C3\u03C4\u03B5\u03B3", 6, 1], - ["\u03B1\u03C0\u03B7\u03B3", 6, 1], - ["\u03C3\u03B9\u03B3", 6, 1], - ["\u03B1\u03BD\u03BF\u03C1\u03B3", 6, 1], - ["\u03B5\u03BD\u03BF\u03C1\u03B3", 6, 1], - ["\u03BA\u03B1\u03BB\u03C0\u03BF\u03C5\u03B6", -1, 1], - ["\u03B8", -1, 1], - ["\u03BC\u03C9\u03B1\u03BC\u03B5\u03B8", 19, 1], - ["\u03C0\u03B9\u03B8", 19, 1], - ["\u03B1\u03C0\u03B9\u03B8", 21, 1], - ["\u03B4\u03B5\u03BA", -1, 1], - ["\u03C0\u03B5\u03BB\u03B5\u03BA", -1, 1], - ["\u03B9\u03BA", -1, 1], - ["\u03B1\u03BD\u03B9\u03BA", 25, 1], - ["\u03B2\u03BF\u03C5\u03BB\u03BA", -1, 1], - ["\u03B2\u03B1\u03C3\u03BA", -1, 1], - ["\u03B2\u03C1\u03B1\u03C7\u03C5\u03BA", -1, 1], - ["\u03B3\u03B1\u03BB", -1, 1], - ["\u03BA\u03B1\u03C4\u03B1\u03B3\u03B1\u03BB", 30, 1], - ["\u03BF\u03BB\u03BF\u03B3\u03B1\u03BB", 30, 1], - ["\u03B2\u03B1\u03B8\u03C5\u03B3\u03B1\u03BB", 30, 1], - ["\u03BC\u03B5\u03BB", -1, 1], - ["\u03BA\u03B1\u03C3\u03C4\u03B5\u03BB", -1, 1], - ["\u03C0\u03BF\u03C1\u03C4\u03BF\u03BB", -1, 1], - ["\u03C0\u03BB", -1, 1], - ["\u03B4\u03B9\u03C0\u03BB", 37, 1], - ["\u03BB\u03B1\u03BF\u03C0\u03BB", 37, 1], - ["\u03C8\u03C5\u03C7\u03BF\u03C0\u03BB", 37, 1], - ["\u03BF\u03C5\u03BB", -1, 1], - ["\u03BC", -1, 1], - ["\u03BF\u03BB\u03B9\u03B3\u03BF\u03B4\u03B1\u03BC", 42, 1], - ["\u03BC\u03BF\u03C5\u03C3\u03BF\u03C5\u03BB\u03BC", 42, 1], - ["\u03B4\u03C1\u03B1\u03B4\u03BF\u03C5\u03BC", 42, 1], - ["\u03B2\u03C1\u03B1\u03C7\u03BC", 42, 1], - ["\u03BD", -1, 1], - ["\u03B1\u03BC\u03B5\u03C1\u03B9\u03BA\u03B1\u03BD", 47, 1], - ["\u03C0", -1, 1], - ["\u03B1\u03B4\u03B1\u03C0", 49, 1], - ["\u03C7\u03B1\u03BC\u03B7\u03BB\u03BF\u03B4\u03B1\u03C0", 49, 1], - ["\u03C0\u03BF\u03BB\u03C5\u03B4\u03B1\u03C0", 49, 1], - ["\u03BA\u03BF\u03C0", 49, 1], - ["\u03C5\u03C0\u03BF\u03BA\u03BF\u03C0", 53, 1], - ["\u03C4\u03C3\u03BF\u03C0", 49, 1], - ["\u03C3\u03C0", 49, 1], - ["\u03B5\u03C1", -1, 1], - ["\u03B3\u03B5\u03C1", 57, 1], - ["\u03B2\u03B5\u03C4\u03B5\u03C1", 57, 1], - ["\u03BB\u03BF\u03C5\u03B8\u03B7\u03C1", -1, 1], - ["\u03BA\u03BF\u03C1\u03BC\u03BF\u03C1", -1, 1], - ["\u03C0\u03B5\u03C1\u03B9\u03C4\u03C1", -1, 1], - ["\u03BF\u03C5\u03C1", -1, 1], - ["\u03C3", -1, 1], - ["\u03B2\u03B1\u03C3", 64, 1], - ["\u03C0\u03BF\u03BB\u03B9\u03C3", 64, 1], - ["\u03C3\u03B1\u03C1\u03B1\u03BA\u03B1\u03C4\u03C3", 64, 1], - ["\u03B8\u03C5\u03C3", 64, 1], - ["\u03B4\u03B9\u03B1\u03C4", -1, 1], - ["\u03C0\u03BB\u03B1\u03C4", -1, 1], - ["\u03C4\u03C3\u03B1\u03C1\u03BB\u03B1\u03C4", -1, 1], - ["\u03C4\u03B5\u03C4", -1, 1], - ["\u03C0\u03BF\u03C5\u03C1\u03B9\u03C4", -1, 1], - ["\u03C3\u03BF\u03C5\u03BB\u03C4", -1, 1], - ["\u03BC\u03B1\u03B9\u03BD\u03C4", -1, 1], - ["\u03B6\u03C9\u03BD\u03C4", -1, 1], - ["\u03BA\u03B1\u03C3\u03C4", -1, 1], - ["\u03C6", -1, 1], - ["\u03B4\u03B9\u03B1\u03C6", 78, 1], - ["\u03C3\u03C4\u03B5\u03C6", 78, 1], - ["\u03C6\u03C9\u03C4\u03BF\u03C3\u03C4\u03B5\u03C6", 80, 1], - ["\u03C0\u03B5\u03C1\u03B7\u03C6", 78, 1], - ["\u03C5\u03C0\u03B5\u03C1\u03B7\u03C6", 82, 1], - ["\u03BA\u03BF\u03B9\u03BB\u03B1\u03C1\u03C6", 78, 1], - ["\u03C0\u03B5\u03BD\u03C4\u03B1\u03C1\u03C6", 78, 1], - ["\u03BF\u03C1\u03C6", 78, 1], - ["\u03C7", -1, 1], - ["\u03B1\u03BC\u03B7\u03C7", 87, 1], - ["\u03B2\u03B9\u03BF\u03BC\u03B7\u03C7", 87, 1], - ["\u03BC\u03B5\u03B3\u03BB\u03BF\u03B2\u03B9\u03BF\u03BC\u03B7\u03C7", 89, 1], - ["\u03BA\u03B1\u03C0\u03BD\u03BF\u03B2\u03B9\u03BF\u03BC\u03B7\u03C7", 89, 1], - ["\u03BC\u03B9\u03BA\u03C1\u03BF\u03B2\u03B9\u03BF\u03BC\u03B7\u03C7", 89, 1], - ["\u03C0\u03BF\u03BB\u03C5\u03BC\u03B7\u03C7", 87, 1], - ["\u03BB\u03B9\u03C7", 87, 1] - ]; - - /** @const */ var a_40 = [ - ["\u03B7\u03C3\u03B5\u03C4\u03B5", -1, 1] - ]; - - /** @const */ var a_41 = [ - ["\u03B5\u03BD\u03B4", -1, 1], - ["\u03C3\u03C5\u03BD\u03B4", -1, 1], - ["\u03BF\u03B4", -1, 1], - ["\u03B4\u03B9\u03B1\u03B8", -1, 1], - ["\u03BA\u03B1\u03B8", -1, 1], - ["\u03C1\u03B1\u03B8", -1, 1], - ["\u03C4\u03B1\u03B8", -1, 1], - ["\u03C4\u03B9\u03B8", -1, 1], - ["\u03B5\u03BA\u03B8", -1, 1], - ["\u03B5\u03BD\u03B8", -1, 1], - ["\u03C3\u03C5\u03BD\u03B8", -1, 1], - ["\u03C1\u03BF\u03B8", -1, 1], - ["\u03C5\u03C0\u03B5\u03C1\u03B8", -1, 1], - ["\u03C3\u03B8", -1, 1], - ["\u03B5\u03C5\u03B8", -1, 1], - ["\u03B1\u03C1\u03BA", -1, 1], - ["\u03C9\u03C6\u03B5\u03BB", -1, 1], - ["\u03B2\u03BF\u03BB", -1, 1], - ["\u03B1\u03B9\u03BD", -1, 1], - ["\u03C0\u03BF\u03BD", -1, 1], - ["\u03C1\u03BF\u03BD", -1, 1], - ["\u03C3\u03C5\u03BD", -1, 1], - ["\u03B2\u03B1\u03C1", -1, 1], - ["\u03B2\u03C1", -1, 1], - ["\u03B1\u03B9\u03C1", -1, 1], - ["\u03C6\u03BF\u03C1", -1, 1], - ["\u03B5\u03C5\u03C1", -1, 1], - ["\u03C0\u03C5\u03C1", -1, 1], - ["\u03C7\u03C9\u03C1", -1, 1], - ["\u03BD\u03B5\u03C4", -1, 1], - ["\u03C3\u03C7", -1, 1] - ]; - - /** @const */ var a_42 = [ - ["\u03C0\u03B1\u03B3", -1, 1], - ["\u03B4", -1, 1], - ["\u03B1\u03B4", 1, 1], - ["\u03B8", -1, 1], - ["\u03B1\u03B8", 3, 1], - ["\u03C4\u03BF\u03BA", -1, 1], - ["\u03C3\u03BA", -1, 1], - ["\u03C0\u03B1\u03C1\u03B1\u03BA\u03B1\u03BB", -1, 1], - ["\u03C3\u03BA\u03B5\u03BB", -1, 1], - ["\u03B1\u03C0\u03BB", -1, 1], - ["\u03B5\u03BC", -1, 1], - ["\u03B1\u03BD", -1, 1], - ["\u03B2\u03B5\u03BD", -1, 1], - ["\u03B2\u03B1\u03C1\u03BF\u03BD", -1, 1], - ["\u03BA\u03BF\u03C0", -1, 1], - ["\u03C3\u03B5\u03C1\u03C0", -1, 1], - ["\u03B1\u03B2\u03B1\u03C1", -1, 1], - ["\u03B5\u03BD\u03B1\u03C1", -1, 1], - ["\u03B1\u03B2\u03C1", -1, 1], - ["\u03BC\u03C0\u03BF\u03C1", -1, 1], - ["\u03B8\u03B1\u03C1\u03C1", -1, 1], - ["\u03BD\u03C4\u03C1", -1, 1], - ["\u03C5", -1, 1], - ["\u03BD\u03B9\u03C6", -1, 1], - ["\u03C3\u03C5\u03C1\u03C6", -1, 1] - ]; - - /** @const */ var a_43 = [ - ["\u03BF\u03BD\u03C4\u03B1\u03C3", -1, 1], - ["\u03C9\u03BD\u03C4\u03B1\u03C3", -1, 1] - ]; - - /** @const */ var a_44 = [ - ["\u03BF\u03BC\u03B1\u03C3\u03C4\u03B5", -1, 1], - ["\u03B9\u03BF\u03BC\u03B1\u03C3\u03C4\u03B5", 0, 1] - ]; - - /** @const */ var a_45 = [ - ["\u03C0", -1, 1], - ["\u03B1\u03C0", 0, 1], - ["\u03B1\u03BA\u03B1\u03C4\u03B1\u03C0", 1, 1], - ["\u03C3\u03C5\u03BC\u03C0", 0, 1], - ["\u03B1\u03C3\u03C5\u03BC\u03C0", 3, 1], - ["\u03B1\u03BC\u03B5\u03C4\u03B1\u03BC\u03C6", -1, 1] - ]; - - /** @const */ var a_46 = [ - ["\u03B6", -1, 1], - ["\u03B1\u03BB", -1, 1], - ["\u03C0\u03B1\u03C1\u03B1\u03BA\u03B1\u03BB", 1, 1], - ["\u03B5\u03BA\u03C4\u03B5\u03BB", -1, 1], - ["\u03BC", -1, 1], - ["\u03BE", -1, 1], - ["\u03C0\u03C1\u03BF", -1, 1], - ["\u03B1\u03C1", -1, 1], - ["\u03BD\u03B9\u03C3", -1, 1] - ]; - - /** @const */ var a_47 = [ - ["\u03B7\u03B8\u03B7\u03BA\u03B1", -1, 1], - ["\u03B7\u03B8\u03B7\u03BA\u03B5", -1, 1], - ["\u03B7\u03B8\u03B7\u03BA\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_48 = [ - ["\u03C0\u03B9\u03B8", -1, 1], - ["\u03BF\u03B8", -1, 1], - ["\u03BD\u03B1\u03C1\u03B8", -1, 1], - ["\u03C3\u03BA\u03BF\u03C5\u03BB", -1, 1], - ["\u03C3\u03BA\u03C9\u03BB", -1, 1], - ["\u03C3\u03C6", -1, 1] - ]; - - /** @const */ var a_49 = [ - ["\u03B8", -1, 1], - ["\u03B4\u03B9\u03B1\u03B8", 0, 1], - ["\u03C0\u03B1\u03C1\u03B1\u03BA\u03B1\u03C4\u03B1\u03B8", 0, 1], - ["\u03C3\u03C5\u03BD\u03B8", 0, 1], - ["\u03C0\u03C1\u03BF\u03C3\u03B8", 0, 1] - ]; - - /** @const */ var a_50 = [ - ["\u03B7\u03BA\u03B1", -1, 1], - ["\u03B7\u03BA\u03B5", -1, 1], - ["\u03B7\u03BA\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_51 = [ - ["\u03C6\u03B1\u03B3", -1, 1], - ["\u03BB\u03B7\u03B3", -1, 1], - ["\u03C6\u03C1\u03C5\u03B4", -1, 1], - ["\u03BC\u03B1\u03BD\u03C4\u03B9\u03BB", -1, 1], - ["\u03BC\u03B1\u03BB\u03BB", -1, 1], - ["\u03BF\u03BC", -1, 1], - ["\u03B2\u03BB\u03B5\u03C0", -1, 1], - ["\u03C0\u03BF\u03B4\u03B1\u03C1", -1, 1], - ["\u03BA\u03C5\u03BC\u03B1\u03C4", -1, 1], - ["\u03C0\u03C1\u03C9\u03C4", -1, 1], - ["\u03BB\u03B1\u03C7", -1, 1], - ["\u03C0\u03B1\u03BD\u03C4\u03B1\u03C7", -1, 1] - ]; - - /** @const */ var a_52 = [ - ["\u03C4\u03C3\u03B1", -1, 1], - ["\u03C7\u03B1\u03B4", -1, 1], - ["\u03BC\u03B5\u03B4", -1, 1], - ["\u03BB\u03B1\u03BC\u03C0\u03B9\u03B4", -1, 1], - ["\u03B4\u03B5", -1, 1], - ["\u03C0\u03BB\u03B5", -1, 1], - ["\u03BC\u03B5\u03C3\u03B1\u03B6", -1, 1], - ["\u03B4\u03B5\u03C3\u03C0\u03BF\u03B6", -1, 1], - ["\u03B1\u03B9\u03B8", -1, 1], - ["\u03C6\u03B1\u03C1\u03BC\u03B1\u03BA", -1, 1], - ["\u03B1\u03B3\u03BA", -1, 1], - ["\u03B1\u03BD\u03B7\u03BA", -1, 1], - ["\u03BB", -1, 1], - ["\u03BC", -1, 1], - ["\u03B1\u03BC", 13, 1], - ["\u03B2\u03C1\u03BF\u03BC", 13, 1], - ["\u03C5\u03C0\u03BF\u03C4\u03B5\u03B9\u03BD", -1, 1], - ["\u03B5\u03BA\u03BB\u03B9\u03C0", -1, 1], - ["\u03C1", -1, 1], - ["\u03B5\u03BD\u03B4\u03B9\u03B1\u03C6\u03B5\u03C1", 18, 1], - ["\u03B1\u03BD\u03B1\u03C1\u03C1", 18, 1], - ["\u03C0\u03B1\u03C4", -1, 1], - ["\u03BA\u03B1\u03B8\u03B1\u03C1\u03B5\u03C5", -1, 1], - ["\u03B4\u03B5\u03C5\u03C4\u03B5\u03C1\u03B5\u03C5", -1, 1], - ["\u03BB\u03B5\u03C7", -1, 1] - ]; - - /** @const */ var a_53 = [ - ["\u03BF\u03C5\u03C3\u03B1", -1, 1], - ["\u03BF\u03C5\u03C3\u03B5", -1, 1], - ["\u03BF\u03C5\u03C3\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_54 = [ - ["\u03C0\u03B5\u03BB", -1, 1], - ["\u03BB\u03BB", -1, 1], - ["\u03C3\u03BC\u03B7\u03BD", -1, 1], - ["\u03C1\u03C0", -1, 1], - ["\u03C0\u03C1", -1, 1], - ["\u03C6\u03C1", -1, 1], - ["\u03C7\u03BF\u03C1\u03C4", -1, 1], - ["\u03BF\u03C6", -1, 1], - ["\u03C8\u03BF\u03C6", 7, -1], - ["\u03C3\u03C6", -1, 1], - ["\u03BB\u03BF\u03C7", -1, 1], - ["\u03BD\u03B1\u03C5\u03BB\u03BF\u03C7", 10, -1] - ]; - - /** @const */ var a_55 = [ - ["\u03B1\u03BC\u03B1\u03BB\u03BB\u03B9", -1, 1], - ["\u03BB", -1, 1], - ["\u03B1\u03BC\u03B1\u03BB", 1, 1], - ["\u03BC", -1, 1], - ["\u03BF\u03C5\u03BB\u03B1\u03BC", 3, 1], - ["\u03B5\u03BD", -1, 1], - ["\u03B4\u03B5\u03C1\u03B2\u03B5\u03BD", 5, 1], - ["\u03C0", -1, 1], - ["\u03B1\u03B5\u03B9\u03C0", 7, 1], - ["\u03B1\u03C1\u03C4\u03B9\u03C0", 7, 1], - ["\u03C3\u03C5\u03BC\u03C0", 7, 1], - ["\u03BD\u03B5\u03BF\u03C0", 7, 1], - ["\u03BA\u03C1\u03BF\u03BA\u03B1\u03BB\u03BF\u03C0", 7, 1], - ["\u03BF\u03BB\u03BF\u03C0", 7, 1], - ["\u03C0\u03C1\u03BF\u03C3\u03C9\u03C0\u03BF\u03C0", 7, 1], - ["\u03C3\u03B9\u03B4\u03B7\u03C1\u03BF\u03C0", 7, 1], - ["\u03B4\u03C1\u03BF\u03C3\u03BF\u03C0", 7, 1], - ["\u03B1\u03C3\u03C0", 7, 1], - ["\u03B1\u03BD\u03C5\u03C0", 7, 1], - ["\u03C1", -1, 1], - ["\u03B1\u03C3\u03C0\u03B1\u03C1", 19, 1], - ["\u03C7\u03B1\u03C1", 19, 1], - ["\u03B1\u03C7\u03B1\u03C1", 21, 1], - ["\u03B1\u03C0\u03B5\u03C1", 19, 1], - ["\u03C4\u03C1", 19, 1], - ["\u03BF\u03C5\u03C1", 19, 1], - ["\u03C4", -1, 1], - ["\u03B4\u03B9\u03B1\u03C4", 26, 1], - ["\u03B5\u03C0\u03B9\u03C4", 26, 1], - ["\u03C3\u03C5\u03BD\u03C4", 26, 1], - ["\u03BF\u03BC\u03BF\u03C4", 26, 1], - ["\u03BD\u03BF\u03BC\u03BF\u03C4", 30, 1], - ["\u03B1\u03C0\u03BF\u03C4", 26, 1], - ["\u03C5\u03C0\u03BF\u03C4", 26, 1], - ["\u03B1\u03B2\u03B1\u03C3\u03C4", 26, 1], - ["\u03B1\u03B9\u03BC\u03BF\u03C3\u03C4", 26, 1], - ["\u03C0\u03C1\u03BF\u03C3\u03C4", 26, 1], - ["\u03B1\u03BD\u03C5\u03C3\u03C4", 26, 1], - ["\u03BD\u03B1\u03C5", -1, 1], - ["\u03B1\u03C6", -1, 1], - ["\u03BE\u03B5\u03C6", -1, 1], - ["\u03B1\u03B4\u03B7\u03C6", -1, 1], - ["\u03C0\u03B1\u03BC\u03C6", -1, 1], - ["\u03C0\u03BF\u03BB\u03C5\u03C6", -1, 1] - ]; - - /** @const */ var a_56 = [ - ["\u03B1\u03B3\u03B1", -1, 1], - ["\u03B1\u03B3\u03B5", -1, 1], - ["\u03B1\u03B3\u03B5\u03C3", -1, 1] - ]; - - /** @const */ var a_57 = [ - ["\u03B7\u03C3\u03B1", -1, 1], - ["\u03B7\u03C3\u03B5", -1, 1], - ["\u03B7\u03C3\u03BF\u03C5", -1, 1] - ]; - - /** @const */ var a_58 = [ - ["\u03BD", -1, 1], - ["\u03B4\u03C9\u03B4\u03B5\u03BA\u03B1\u03BD", 0, 1], - ["\u03B5\u03C0\u03C4\u03B1\u03BD", 0, 1], - ["\u03BC\u03B5\u03B3\u03B1\u03BB\u03BF\u03BD", 0, 1], - ["\u03B5\u03C1\u03B7\u03BC\u03BF\u03BD", 0, 1], - ["\u03C7\u03B5\u03C1\u03C3\u03BF\u03BD", 0, 1] - ]; - - /** @const */ var a_59 = [ - ["\u03B7\u03C3\u03C4\u03B5", -1, 1] - ]; - - /** @const */ var a_60 = [ - ["\u03C3\u03B2", -1, 1], - ["\u03B1\u03C3\u03B2", 0, 1], - ["\u03B1\u03C0\u03BB", -1, 1], - ["\u03B1\u03B5\u03B9\u03BC\u03BD", -1, 1], - ["\u03C7\u03C1", -1, 1], - ["\u03B1\u03C7\u03C1", 4, 1], - ["\u03BA\u03BF\u03B9\u03BD\u03BF\u03C7\u03C1", 4, 1], - ["\u03B4\u03C5\u03C3\u03C7\u03C1", 4, 1], - ["\u03B5\u03C5\u03C7\u03C1", 4, 1], - ["\u03C0\u03B1\u03BB\u03B9\u03BC\u03C8", -1, 1] - ]; - - /** @const */ var a_61 = [ - ["\u03BF\u03C5\u03BD\u03B5", -1, 1], - ["\u03B7\u03B8\u03BF\u03C5\u03BD\u03B5", 0, 1], - ["\u03B7\u03C3\u03BF\u03C5\u03BD\u03B5", 0, 1] - ]; - - /** @const */ var a_62 = [ - ["\u03C3\u03C0\u03B9", -1, 1], - ["\u03BD", -1, 1], - ["\u03B5\u03BE\u03C9\u03BD", 1, 1], - ["\u03C1", -1, 1], - ["\u03C3\u03C4\u03C1\u03B1\u03B2\u03BF\u03BC\u03BF\u03C5\u03C4\u03C3", -1, 1], - ["\u03BA\u03B1\u03BA\u03BF\u03BC\u03BF\u03C5\u03C4\u03C3", -1, 1] - ]; - - /** @const */ var a_63 = [ - ["\u03BF\u03C5\u03BC\u03B5", -1, 1], - ["\u03B7\u03B8\u03BF\u03C5\u03BC\u03B5", 0, 1], - ["\u03B7\u03C3\u03BF\u03C5\u03BC\u03B5", 0, 1] - ]; - - /** @const */ var a_64 = [ - ["\u03B1\u03B6", -1, 1], - ["\u03C9\u03C1\u03B9\u03BF\u03C0\u03BB", -1, 1], - ["\u03B1\u03C3\u03BF\u03C5\u03C3", -1, 1], - ["\u03C0\u03B1\u03C1\u03B1\u03C3\u03BF\u03C5\u03C3", 2, 1], - ["\u03B1\u03BB\u03BB\u03BF\u03C3\u03BF\u03C5\u03C3", -1, 1], - ["\u03C6", -1, 1], - ["\u03C7", -1, 1] - ]; - - /** @const */ var a_65 = [ - ["\u03BC\u03B1\u03C4\u03B1", -1, 1], - ["\u03BC\u03B1\u03C4\u03C9\u03BD", -1, 1], - ["\u03BC\u03B1\u03C4\u03BF\u03C3", -1, 1] - ]; - - /** @const */ var a_66 = [ - ["\u03B1", -1, 1], - ["\u03B9\u03BF\u03C5\u03BC\u03B1", 0, 1], - ["\u03BF\u03BC\u03BF\u03C5\u03BD\u03B1", 0, 1], - ["\u03B9\u03BF\u03BC\u03BF\u03C5\u03BD\u03B1", 2, 1], - ["\u03BF\u03C3\u03BF\u03C5\u03BD\u03B1", 0, 1], - ["\u03B9\u03BF\u03C3\u03BF\u03C5\u03BD\u03B1", 4, 1], - ["\u03B5", -1, 1], - ["\u03B1\u03B3\u03B1\u03C4\u03B5", 6, 1], - ["\u03B7\u03BA\u03B1\u03C4\u03B5", 6, 1], - ["\u03B7\u03B8\u03B7\u03BA\u03B1\u03C4\u03B5", 8, 1], - ["\u03B7\u03C3\u03B1\u03C4\u03B5", 6, 1], - ["\u03BF\u03C5\u03C3\u03B1\u03C4\u03B5", 6, 1], - ["\u03B5\u03B9\u03C4\u03B5", 6, 1], - ["\u03B7\u03B8\u03B5\u03B9\u03C4\u03B5", 12, 1], - ["\u03B9\u03B5\u03BC\u03B1\u03C3\u03C4\u03B5", 6, 1], - ["\u03BF\u03C5\u03BC\u03B1\u03C3\u03C4\u03B5", 6, 1], - ["\u03B9\u03BF\u03C5\u03BC\u03B1\u03C3\u03C4\u03B5", 15, 1], - ["\u03B9\u03B5\u03C3\u03B1\u03C3\u03C4\u03B5", 6, 1], - ["\u03BF\u03C3\u03B1\u03C3\u03C4\u03B5", 6, 1], - ["\u03B9\u03BF\u03C3\u03B1\u03C3\u03C4\u03B5", 18, 1], - ["\u03B7", -1, 1], - ["\u03B9", -1, 1], - ["\u03B1\u03BC\u03B1\u03B9", 21, 1], - ["\u03B9\u03B5\u03BC\u03B1\u03B9", 21, 1], - ["\u03BF\u03BC\u03B1\u03B9", 21, 1], - ["\u03BF\u03C5\u03BC\u03B1\u03B9", 21, 1], - ["\u03B1\u03C3\u03B1\u03B9", 21, 1], - ["\u03B5\u03C3\u03B1\u03B9", 21, 1], - ["\u03B9\u03B5\u03C3\u03B1\u03B9", 27, 1], - ["\u03B1\u03C4\u03B1\u03B9", 21, 1], - ["\u03B5\u03C4\u03B1\u03B9", 21, 1], - ["\u03B9\u03B5\u03C4\u03B1\u03B9", 30, 1], - ["\u03BF\u03BD\u03C4\u03B1\u03B9", 21, 1], - ["\u03BF\u03C5\u03BD\u03C4\u03B1\u03B9", 21, 1], - ["\u03B9\u03BF\u03C5\u03BD\u03C4\u03B1\u03B9", 33, 1], - ["\u03B5\u03B9", 21, 1], - ["\u03B1\u03B5\u03B9", 35, 1], - ["\u03B7\u03B8\u03B5\u03B9", 35, 1], - ["\u03B7\u03C3\u03B5\u03B9", 35, 1], - ["\u03BF\u03B9", 21, 1], - ["\u03B1\u03BD", -1, 1], - ["\u03B1\u03B3\u03B1\u03BD", 40, 1], - ["\u03B7\u03BA\u03B1\u03BD", 40, 1], - ["\u03B7\u03B8\u03B7\u03BA\u03B1\u03BD", 42, 1], - ["\u03B7\u03C3\u03B1\u03BD", 40, 1], - ["\u03BF\u03C5\u03C3\u03B1\u03BD", 40, 1], - ["\u03BF\u03BD\u03C4\u03BF\u03C5\u03C3\u03B1\u03BD", 45, 1], - ["\u03B9\u03BF\u03BD\u03C4\u03BF\u03C5\u03C3\u03B1\u03BD", 46, 1], - ["\u03BF\u03BD\u03C4\u03B1\u03BD", 40, 1], - ["\u03B9\u03BF\u03BD\u03C4\u03B1\u03BD", 48, 1], - ["\u03BF\u03C5\u03BD\u03C4\u03B1\u03BD", 40, 1], - ["\u03B9\u03BF\u03C5\u03BD\u03C4\u03B1\u03BD", 50, 1], - ["\u03BF\u03C4\u03B1\u03BD", 40, 1], - ["\u03B9\u03BF\u03C4\u03B1\u03BD", 52, 1], - ["\u03BF\u03BC\u03B1\u03C3\u03C4\u03B1\u03BD", 40, 1], - ["\u03B9\u03BF\u03BC\u03B1\u03C3\u03C4\u03B1\u03BD", 54, 1], - ["\u03BF\u03C3\u03B1\u03C3\u03C4\u03B1\u03BD", 40, 1], - ["\u03B9\u03BF\u03C3\u03B1\u03C3\u03C4\u03B1\u03BD", 56, 1], - ["\u03BF\u03C5\u03BD", -1, 1], - ["\u03B7\u03B8\u03BF\u03C5\u03BD", 58, 1], - ["\u03BF\u03BC\u03BF\u03C5\u03BD", 58, 1], - ["\u03B9\u03BF\u03BC\u03BF\u03C5\u03BD", 60, 1], - ["\u03B7\u03C3\u03BF\u03C5\u03BD", 58, 1], - ["\u03BF\u03C3\u03BF\u03C5\u03BD", 58, 1], - ["\u03B9\u03BF\u03C3\u03BF\u03C5\u03BD", 63, 1], - ["\u03C9\u03BD", -1, 1], - ["\u03B7\u03B4\u03C9\u03BD", 65, 1], - ["\u03BF", -1, 1], - ["\u03B1\u03C3", -1, 1], - ["\u03B5\u03C3", -1, 1], - ["\u03B7\u03B4\u03B5\u03C3", 69, 1], - ["\u03B7\u03C3\u03B5\u03C3", 69, 1], - ["\u03B7\u03C3", -1, 1], - ["\u03B5\u03B9\u03C3", -1, 1], - ["\u03B7\u03B8\u03B5\u03B9\u03C3", 73, 1], - ["\u03BF\u03C3", -1, 1], - ["\u03C5\u03C3", -1, 1], - ["\u03BF\u03C5\u03C3", 76, 1], - ["\u03C5", -1, 1], - ["\u03BF\u03C5", 78, 1], - ["\u03C9", -1, 1], - ["\u03B1\u03C9", 80, 1], - ["\u03B7\u03B8\u03C9", 80, 1], - ["\u03B7\u03C3\u03C9", 80, 1] - ]; - - /** @const */ var a_67 = [ - ["\u03BF\u03C4\u03B5\u03C1", -1, 1], - ["\u03B5\u03C3\u03C4\u03B5\u03C1", -1, 1], - ["\u03C5\u03C4\u03B5\u03C1", -1, 1], - ["\u03C9\u03C4\u03B5\u03C1", -1, 1], - ["\u03BF\u03C4\u03B1\u03C4", -1, 1], - ["\u03B5\u03C3\u03C4\u03B1\u03C4", -1, 1], - ["\u03C5\u03C4\u03B1\u03C4", -1, 1], - ["\u03C9\u03C4\u03B1\u03C4", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [81, 65, 16, 1]; - - /** @const */ var /** Array */ g_v2 = [81, 65, 0, 1]; - - var /** boolean */ B_test1 = false; - - - /** @return {boolean} */ - function r_has_min_length() { - return base.current.length >= 3; - }; - - /** @return {boolean} */ - function r_tolower() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u03B1")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B2")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u03B3")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u03B4")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u03B5")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u03B6")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u03B7")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u03B8")) - { - return false; - } - break; - case 9: - if (!base.slice_from("\u03B9")) - { - return false; - } - break; - case 10: - if (!base.slice_from("\u03BA")) - { - return false; - } - break; - case 11: - if (!base.slice_from("\u03BB")) - { - return false; - } - break; - case 12: - if (!base.slice_from("\u03BC")) - { - return false; - } - break; - case 13: - if (!base.slice_from("\u03BD")) - { - return false; - } - break; - case 14: - if (!base.slice_from("\u03BE")) - { - return false; - } - break; - case 15: - if (!base.slice_from("\u03BF")) - { - return false; - } - break; - case 16: - if (!base.slice_from("\u03C0")) - { - return false; - } - break; - case 17: - if (!base.slice_from("\u03C1")) - { - return false; - } - break; - case 18: - if (!base.slice_from("\u03C3")) - { - return false; - } - break; - case 19: - if (!base.slice_from("\u03C4")) - { - return false; - } - break; - case 20: - if (!base.slice_from("\u03C5")) - { - return false; - } - break; - case 21: - if (!base.slice_from("\u03C6")) - { - return false; - } - break; - case 22: - if (!base.slice_from("\u03C7")) - { - return false; - } - break; - case 23: - if (!base.slice_from("\u03C8")) - { - return false; - } - break; - case 24: - if (!base.slice_from("\u03C9")) - { - return false; - } - break; - case 25: - if (base.cursor <= base.limit_backward) - { - break lab0; - } - base.cursor--; - break; - } - continue; - } - base.cursor = base.limit - v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_step1() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_1); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u03C6\u03B1")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03C3\u03BA\u03B1")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u03BF\u03BB\u03BF")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u03C3\u03BF")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u03C4\u03B1\u03C4\u03BF")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u03BA\u03C1\u03B5")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u03C0\u03B5\u03C1")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u03C4\u03B5\u03C1")) - { - return false; - } - break; - case 9: - if (!base.slice_from("\u03C6\u03C9")) - { - return false; - } - break; - case 10: - if (!base.slice_from("\u03BA\u03B1\u03B8\u03B5\u03C3\u03C4")) - { - return false; - } - break; - case 11: - if (!base.slice_from("\u03B3\u03B5\u03B3\u03BF\u03BD")) - { - return false; - } - break; - } - B_test1 = false; - return true; - }; - - /** @return {boolean} */ - function r_steps1() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("\u03B9")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B9\u03B6")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_steps2() { - base.ket = base.cursor; - if (base.find_among_b(a_5) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_4) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03C9\u03BD")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_steps3() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_7) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("\u03B9\u03C3\u03B1"))) - { - break lab1; - } - if (base.cursor > base.limit_backward) - { - break lab1; - } - if (!base.slice_from("\u03B9\u03C3")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - base.bra = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("\u03B9")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B9\u03C3")) - { - return false; - } - break; - } - } - return true; - }; - - /** @return {boolean} */ - function r_steps4() { - base.ket = base.cursor; - if (base.find_among_b(a_9) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_8) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B9")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_steps5() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_11) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - among_var = base.find_among_b(a_10); - if (among_var == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("\u03B9")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B9\u03C3\u03C4")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_steps6() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_14) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - among_var = base.find_among_b(a_12); - if (among_var == 0) - { - break lab1; - } - if (base.cursor > base.limit_backward) - { - break lab1; - } - switch (among_var) { - case 1: - if (!base.slice_from("\u03B9\u03C3\u03BC")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B9")) - { - return false; - } - break; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - among_var = base.find_among_b(a_13); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u03B1\u03B3\u03BD\u03C9\u03C3\u03C4")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B1\u03C4\u03BF\u03BC")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u03B3\u03BD\u03C9\u03C3\u03C4")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u03B5\u03B8\u03BD")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u03B5\u03BA\u03BB\u03B5\u03BA\u03C4")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u03C3\u03BA\u03B5\u03C0\u03C4")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u03C4\u03BF\u03C0")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u03B1\u03BB\u03B5\u03BE\u03B1\u03BD\u03B4\u03C1")) - { - return false; - } - break; - case 9: - if (!base.slice_from("\u03B2\u03C5\u03B6\u03B1\u03BD\u03C4")) - { - return false; - } - break; - case 10: - if (!base.slice_from("\u03B8\u03B5\u03B1\u03C4\u03C1")) - { - return false; - } - break; - } - } - return true; - }; - - /** @return {boolean} */ - function r_steps7() { - base.ket = base.cursor; - if (base.find_among_b(a_16) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_15) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B1\u03C1\u03B1\u03BA")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_steps8() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_18) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - among_var = base.find_among_b(a_17); - if (among_var == 0) - { - break lab1; - } - if (base.cursor > base.limit_backward) - { - break lab1; - } - switch (among_var) { - case 1: - if (!base.slice_from("\u03B1\u03BA")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u03B9\u03C4\u03C3")) - { - return false; - } - break; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.eq_s_b("\u03BA\u03BF\u03C1"))) - { - return false; - } - if (!base.slice_from("\u03B9\u03C4\u03C3")) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_steps9() { - base.ket = base.cursor; - if (base.find_among_b(a_21) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_19) == 0) - { - break lab1; - } - if (base.cursor > base.limit_backward) - { - break lab1; - } - if (!base.slice_from("\u03B9\u03B4")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_20) == 0) - { - return false; - } - if (!base.slice_from("\u03B9\u03B4")) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_steps10() { - base.ket = base.cursor; - if (base.find_among_b(a_23) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_22) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B9\u03C3\u03BA")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step2a() { - base.ket = base.cursor; - if (base.find_among_b(a_24) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (base.find_among_b(a_25) == 0) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_1; - } - { - var /** number */ c1 = base.cursor; - base.insert(base.cursor, base.cursor, "\u03B1\u03B4"); - base.cursor = c1; - } - return true; - }; - - /** @return {boolean} */ - function r_step2b() { - base.ket = base.cursor; - if (base.find_among_b(a_26) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_27) == 0) - { - return false; - } - if (!base.slice_from("\u03B5\u03B4")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step2c() { - base.ket = base.cursor; - if (base.find_among_b(a_28) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_29) == 0) - { - return false; - } - if (!base.slice_from("\u03BF\u03C5\u03B4")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step2d() { - base.ket = base.cursor; - if (base.find_among_b(a_30) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_31) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B5")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step3() { - base.ket = base.cursor; - if (base.find_among_b(a_32) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.in_grouping_b(g_v, 945, 969))) - { - return false; - } - if (!base.slice_from("\u03B9")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step4() { - base.ket = base.cursor; - if (base.find_among_b(a_33) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.in_grouping_b(g_v, 945, 969))) - { - break lab1; - } - if (!base.slice_from("\u03B9\u03BA")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - } - base.bra = base.cursor; - if (base.find_among_b(a_34) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B9\u03BA")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5a() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("\u03B1\u03B3\u03B1\u03BC\u03B5"))) - { - break lab0; - } - if (base.cursor > base.limit_backward) - { - break lab0; - } - if (!base.slice_from("\u03B1\u03B3\u03B1\u03BC")) - { - return false; - } - } - base.cursor = base.limit - v_1; - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (base.find_among_b(a_35) == 0) - { - break lab1; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - } - base.cursor = base.limit - v_2; - base.ket = base.cursor; - if (!(base.eq_s_b("\u03B1\u03BC\u03B5"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_36) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B1\u03BC")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5b() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (base.find_among_b(a_38) == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_37) == 0) - { - break lab0; - } - if (base.cursor > base.limit_backward) - { - break lab0; - } - if (!base.slice_from("\u03B1\u03B3\u03B1\u03BD")) - { - return false; - } - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (!(base.eq_s_b("\u03B1\u03BD\u03B5"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.in_grouping_b(g_v2, 945, 969))) - { - break lab2; - } - if (!base.slice_from("\u03B1\u03BD")) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - base.ket = base.cursor; - } - base.bra = base.cursor; - if (base.find_among_b(a_39) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B1\u03BD")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5c() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (base.find_among_b(a_40) == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (!(base.eq_s_b("\u03B5\u03C4\u03B5"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.in_grouping_b(g_v2, 945, 969))) - { - break lab2; - } - if (!base.slice_from("\u03B5\u03C4")) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - lab3: { - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_41) == 0) - { - break lab3; - } - if (!base.slice_from("\u03B5\u03C4")) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - base.ket = base.cursor; - } - base.bra = base.cursor; - if (base.find_among_b(a_42) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B5\u03C4")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5d() { - base.ket = base.cursor; - if (base.find_among_b(a_43) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.eq_s_b("\u03B1\u03C1\u03C7"))) - { - break lab1; - } - if (base.cursor > base.limit_backward) - { - break lab1; - } - if (!base.slice_from("\u03BF\u03BD\u03C4")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.eq_s_b("\u03BA\u03C1\u03B5"))) - { - return false; - } - if (!base.slice_from("\u03C9\u03BD\u03C4")) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_step5e() { - base.ket = base.cursor; - if (base.find_among_b(a_44) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.eq_s_b("\u03BF\u03BD"))) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03BF\u03BC\u03B1\u03C3\u03C4")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5f() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("\u03B9\u03B5\u03C3\u03C4\u03B5"))) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_45) == 0) - { - break lab0; - } - if (base.cursor > base.limit_backward) - { - break lab0; - } - if (!base.slice_from("\u03B9\u03B5\u03C3\u03C4")) - { - return false; - } - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (!(base.eq_s_b("\u03B5\u03C3\u03C4\u03B5"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_46) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B9\u03B5\u03C3\u03C4")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5g() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (base.find_among_b(a_47) == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (base.find_among_b(a_50) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_48) == 0) - { - break lab2; - } - if (!base.slice_from("\u03B7\u03BA")) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_49) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B7\u03BA")) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_step5h() { - base.ket = base.cursor; - if (base.find_among_b(a_53) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_51) == 0) - { - break lab1; - } - if (!base.slice_from("\u03BF\u03C5\u03C3")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_52) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03BF\u03C5\u03C3")) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_step5i() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_56) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - base.bra = base.cursor; - if (!(base.eq_s_b("\u03BA\u03BF\u03BB\u03BB"))) - { - break lab1; - } - if (!base.slice_from("\u03B1\u03B3")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - lab2: { - var /** number */ v_2 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - base.bra = base.cursor; - among_var = base.find_among_b(a_54); - if (among_var == 0) - { - break lab3; - } - switch (among_var) { - case 1: - if (!base.slice_from("\u03B1\u03B3")) - { - return false; - } - break; - } - break lab2; - } - base.cursor = base.limit - v_2; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_55) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B1\u03B3")) - { - return false; - } - } - } - return true; - }; - - /** @return {boolean} */ - function r_step5j() { - base.ket = base.cursor; - if (base.find_among_b(a_57) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_58) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B7\u03C3")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5k() { - base.ket = base.cursor; - if (base.find_among_b(a_59) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_60) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03B7\u03C3\u03C4")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5l() { - base.ket = base.cursor; - if (base.find_among_b(a_61) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_62) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03BF\u03C5\u03BD")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step5m() { - base.ket = base.cursor; - if (base.find_among_b(a_63) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_test1 = false; - base.ket = base.cursor; - base.bra = base.cursor; - if (base.find_among_b(a_64) == 0) - { - return false; - } - if (base.cursor > base.limit_backward) - { - return false; - } - if (!base.slice_from("\u03BF\u03C5\u03BC")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step6() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (base.find_among_b(a_65) == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_from("\u03BC\u03B1")) - { - return false; - } - } - base.cursor = base.limit - v_1; - if (!B_test1) - { - return false; - } - base.ket = base.cursor; - if (base.find_among_b(a_66) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step7() { - base.ket = base.cursor; - if (base.find_among_b(a_67) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_1 = base.limit - base.cursor; - r_tolower(); - base.cursor = base.limit - v_1; - if (!r_has_min_length()) - { - return false; - } - B_test1 = true; - var /** number */ v_2 = base.limit - base.cursor; - r_step1(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_steps1(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_steps2(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_steps3(); - base.cursor = base.limit - v_5; - var /** number */ v_6 = base.limit - base.cursor; - r_steps4(); - base.cursor = base.limit - v_6; - var /** number */ v_7 = base.limit - base.cursor; - r_steps5(); - base.cursor = base.limit - v_7; - var /** number */ v_8 = base.limit - base.cursor; - r_steps6(); - base.cursor = base.limit - v_8; - var /** number */ v_9 = base.limit - base.cursor; - r_steps7(); - base.cursor = base.limit - v_9; - var /** number */ v_10 = base.limit - base.cursor; - r_steps8(); - base.cursor = base.limit - v_10; - var /** number */ v_11 = base.limit - base.cursor; - r_steps9(); - base.cursor = base.limit - v_11; - var /** number */ v_12 = base.limit - base.cursor; - r_steps10(); - base.cursor = base.limit - v_12; - var /** number */ v_13 = base.limit - base.cursor; - r_step2a(); - base.cursor = base.limit - v_13; - var /** number */ v_14 = base.limit - base.cursor; - r_step2b(); - base.cursor = base.limit - v_14; - var /** number */ v_15 = base.limit - base.cursor; - r_step2c(); - base.cursor = base.limit - v_15; - var /** number */ v_16 = base.limit - base.cursor; - r_step2d(); - base.cursor = base.limit - v_16; - var /** number */ v_17 = base.limit - base.cursor; - r_step3(); - base.cursor = base.limit - v_17; - var /** number */ v_18 = base.limit - base.cursor; - r_step4(); - base.cursor = base.limit - v_18; - var /** number */ v_19 = base.limit - base.cursor; - r_step5a(); - base.cursor = base.limit - v_19; - var /** number */ v_20 = base.limit - base.cursor; - r_step5b(); - base.cursor = base.limit - v_20; - var /** number */ v_21 = base.limit - base.cursor; - r_step5c(); - base.cursor = base.limit - v_21; - var /** number */ v_22 = base.limit - base.cursor; - r_step5d(); - base.cursor = base.limit - v_22; - var /** number */ v_23 = base.limit - base.cursor; - r_step5e(); - base.cursor = base.limit - v_23; - var /** number */ v_24 = base.limit - base.cursor; - r_step5f(); - base.cursor = base.limit - v_24; - var /** number */ v_25 = base.limit - base.cursor; - r_step5g(); - base.cursor = base.limit - v_25; - var /** number */ v_26 = base.limit - base.cursor; - r_step5h(); - base.cursor = base.limit - v_26; - var /** number */ v_27 = base.limit - base.cursor; - r_step5j(); - base.cursor = base.limit - v_27; - var /** number */ v_28 = base.limit - base.cursor; - r_step5i(); - base.cursor = base.limit - v_28; - var /** number */ v_29 = base.limit - base.cursor; - r_step5k(); - base.cursor = base.limit - v_29; - var /** number */ v_30 = base.limit - base.cursor; - r_step5l(); - base.cursor = base.limit - v_30; - var /** number */ v_31 = base.limit - base.cursor; - r_step5m(); - base.cursor = base.limit - v_31; - var /** number */ v_32 = base.limit - base.cursor; - r_step6(); - base.cursor = base.limit - v_32; - var /** number */ v_33 = base.limit - base.cursor; - r_step7(); - base.cursor = base.limit - v_33; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['GreekStemmer'] = GreekStemmer; diff --git a/js/hindi-stemmer.js b/js/hindi-stemmer.js deleted file mode 100644 index 20bf6f6..0000000 --- a/js/hindi-stemmer.js +++ /dev/null @@ -1,183 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var HindiStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0906\u0901", -1, -1], - ["\u093E\u0901", -1, -1], - ["\u0907\u092F\u093E\u0901", 1, -1], - ["\u0906\u0907\u092F\u093E\u0901", 2, -1], - ["\u093E\u0907\u092F\u093E\u0901", 2, -1], - ["\u093F\u092F\u093E\u0901", 1, -1], - ["\u0906\u0902", -1, -1], - ["\u0909\u0906\u0902", 6, -1], - ["\u0941\u0906\u0902", 6, -1], - ["\u0908\u0902", -1, -1], - ["\u0906\u0908\u0902", 9, -1], - ["\u093E\u0908\u0902", 9, -1], - ["\u090F\u0902", -1, -1], - ["\u0906\u090F\u0902", 12, -1], - ["\u0909\u090F\u0902", 12, -1], - ["\u093E\u090F\u0902", 12, -1], - ["\u0924\u093E\u090F\u0902", 15, -1, r_CONSONANT], - ["\u0905\u0924\u093E\u090F\u0902", 16, -1], - ["\u0928\u093E\u090F\u0902", 15, -1, r_CONSONANT], - ["\u0905\u0928\u093E\u090F\u0902", 18, -1], - ["\u0941\u090F\u0902", 12, -1], - ["\u0913\u0902", -1, -1], - ["\u0906\u0913\u0902", 21, -1], - ["\u0909\u0913\u0902", 21, -1], - ["\u093E\u0913\u0902", 21, -1], - ["\u0924\u093E\u0913\u0902", 24, -1, r_CONSONANT], - ["\u0905\u0924\u093E\u0913\u0902", 25, -1], - ["\u0928\u093E\u0913\u0902", 24, -1, r_CONSONANT], - ["\u0905\u0928\u093E\u0913\u0902", 27, -1], - ["\u0941\u0913\u0902", 21, -1], - ["\u093E\u0902", -1, -1], - ["\u0907\u092F\u093E\u0902", 30, -1], - ["\u0906\u0907\u092F\u093E\u0902", 31, -1], - ["\u093E\u0907\u092F\u093E\u0902", 31, -1], - ["\u093F\u092F\u093E\u0902", 30, -1], - ["\u0940\u0902", -1, -1], - ["\u0924\u0940\u0902", 35, -1, r_CONSONANT], - ["\u0905\u0924\u0940\u0902", 36, -1], - ["\u0906\u0924\u0940\u0902", 36, -1], - ["\u093E\u0924\u0940\u0902", 36, -1], - ["\u0947\u0902", -1, -1], - ["\u094B\u0902", -1, -1], - ["\u0907\u092F\u094B\u0902", 41, -1], - ["\u0906\u0907\u092F\u094B\u0902", 42, -1], - ["\u093E\u0907\u092F\u094B\u0902", 42, -1], - ["\u093F\u092F\u094B\u0902", 41, -1], - ["\u0905", -1, -1], - ["\u0906", -1, -1], - ["\u0907", -1, -1], - ["\u0908", -1, -1], - ["\u0906\u0908", 49, -1], - ["\u093E\u0908", 49, -1], - ["\u0909", -1, -1], - ["\u090A", -1, -1], - ["\u090F", -1, -1], - ["\u0906\u090F", 54, -1], - ["\u0907\u090F", 54, -1], - ["\u0906\u0907\u090F", 56, -1], - ["\u093E\u0907\u090F", 56, -1], - ["\u093E\u090F", 54, -1], - ["\u093F\u090F", 54, -1], - ["\u0913", -1, -1], - ["\u0906\u0913", 61, -1], - ["\u093E\u0913", 61, -1], - ["\u0915\u0930", -1, -1, r_CONSONANT], - ["\u0905\u0915\u0930", 64, -1], - ["\u0906\u0915\u0930", 64, -1], - ["\u093E\u0915\u0930", 64, -1], - ["\u093E", -1, -1], - ["\u090A\u0902\u0917\u093E", 68, -1], - ["\u0906\u090A\u0902\u0917\u093E", 69, -1], - ["\u093E\u090A\u0902\u0917\u093E", 69, -1], - ["\u0942\u0902\u0917\u093E", 68, -1], - ["\u090F\u0917\u093E", 68, -1], - ["\u0906\u090F\u0917\u093E", 73, -1], - ["\u093E\u090F\u0917\u093E", 73, -1], - ["\u0947\u0917\u093E", 68, -1], - ["\u0924\u093E", 68, -1, r_CONSONANT], - ["\u0905\u0924\u093E", 77, -1], - ["\u0906\u0924\u093E", 77, -1], - ["\u093E\u0924\u093E", 77, -1], - ["\u0928\u093E", 68, -1, r_CONSONANT], - ["\u0905\u0928\u093E", 81, -1], - ["\u0906\u0928\u093E", 81, -1], - ["\u093E\u0928\u093E", 81, -1], - ["\u0906\u092F\u093E", 68, -1], - ["\u093E\u092F\u093E", 68, -1], - ["\u093F", -1, -1], - ["\u0940", -1, -1], - ["\u090A\u0902\u0917\u0940", 88, -1], - ["\u0906\u090A\u0902\u0917\u0940", 89, -1], - ["\u093E\u090A\u0902\u0917\u0940", 89, -1], - ["\u090F\u0902\u0917\u0940", 88, -1], - ["\u0906\u090F\u0902\u0917\u0940", 92, -1], - ["\u093E\u090F\u0902\u0917\u0940", 92, -1], - ["\u0942\u0902\u0917\u0940", 88, -1], - ["\u0947\u0902\u0917\u0940", 88, -1], - ["\u090F\u0917\u0940", 88, -1], - ["\u0906\u090F\u0917\u0940", 97, -1], - ["\u093E\u090F\u0917\u0940", 97, -1], - ["\u0913\u0917\u0940", 88, -1], - ["\u0906\u0913\u0917\u0940", 100, -1], - ["\u093E\u0913\u0917\u0940", 100, -1], - ["\u0947\u0917\u0940", 88, -1], - ["\u094B\u0917\u0940", 88, -1], - ["\u0924\u0940", 88, -1, r_CONSONANT], - ["\u0905\u0924\u0940", 105, -1], - ["\u0906\u0924\u0940", 105, -1], - ["\u093E\u0924\u0940", 105, -1], - ["\u0928\u0940", 88, -1, r_CONSONANT], - ["\u0905\u0928\u0940", 109, -1], - ["\u0941", -1, -1], - ["\u0942", -1, -1], - ["\u0947", -1, -1], - ["\u090F\u0902\u0917\u0947", 113, -1], - ["\u0906\u090F\u0902\u0917\u0947", 114, -1], - ["\u093E\u090F\u0902\u0917\u0947", 114, -1], - ["\u0947\u0902\u0917\u0947", 113, -1], - ["\u0913\u0917\u0947", 113, -1], - ["\u0906\u0913\u0917\u0947", 118, -1], - ["\u093E\u0913\u0917\u0947", 118, -1], - ["\u094B\u0917\u0947", 113, -1], - ["\u0924\u0947", 113, -1, r_CONSONANT], - ["\u0905\u0924\u0947", 122, -1], - ["\u0906\u0924\u0947", 122, -1], - ["\u093E\u0924\u0947", 122, -1], - ["\u0928\u0947", 113, -1, r_CONSONANT], - ["\u0905\u0928\u0947", 126, -1], - ["\u0906\u0928\u0947", 126, -1], - ["\u093E\u0928\u0947", 126, -1], - ["\u094B", -1, -1], - ["\u094D", -1, -1] - ]; - - /** @const */ var /** Array */ g_consonant = [255, 255, 255, 255, 159, 0, 0, 0, 248, 7]; - - - - /** @return {boolean} */ - function r_CONSONANT() { - if (!(base.in_grouping_b(g_consonant, 2325, 2399))) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - base.limit_backward = base.cursor; base.cursor = base.limit; - base.ket = base.cursor; - if (base.find_among_b(a_0) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['HindiStemmer'] = HindiStemmer; diff --git a/js/hungarian-stemmer.js b/js/hungarian-stemmer.js deleted file mode 100644 index d1c8c56..0000000 --- a/js/hungarian-stemmer.js +++ /dev/null @@ -1,709 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var HungarianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["cs", -1, -1], - ["dzs", -1, -1], - ["gy", -1, -1], - ["ly", -1, -1], - ["ny", -1, -1], - ["sz", -1, -1], - ["ty", -1, -1], - ["zs", -1, -1] - ]; - - /** @const */ var a_1 = [ - ["\u00E1", -1, 1], - ["\u00E9", -1, 2] - ]; - - /** @const */ var a_2 = [ - ["bb", -1, -1], - ["cc", -1, -1], - ["dd", -1, -1], - ["ff", -1, -1], - ["gg", -1, -1], - ["jj", -1, -1], - ["kk", -1, -1], - ["ll", -1, -1], - ["mm", -1, -1], - ["nn", -1, -1], - ["pp", -1, -1], - ["rr", -1, -1], - ["ccs", -1, -1], - ["ss", -1, -1], - ["zzs", -1, -1], - ["tt", -1, -1], - ["vv", -1, -1], - ["ggy", -1, -1], - ["lly", -1, -1], - ["nny", -1, -1], - ["tty", -1, -1], - ["ssz", -1, -1], - ["zz", -1, -1] - ]; - - /** @const */ var a_3 = [ - ["al", -1, 1], - ["el", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["ba", -1, -1], - ["ra", -1, -1], - ["be", -1, -1], - ["re", -1, -1], - ["ig", -1, -1], - ["nak", -1, -1], - ["nek", -1, -1], - ["val", -1, -1], - ["vel", -1, -1], - ["ul", -1, -1], - ["n\u00E1l", -1, -1], - ["n\u00E9l", -1, -1], - ["b\u00F3l", -1, -1], - ["r\u00F3l", -1, -1], - ["t\u00F3l", -1, -1], - ["\u00FCl", -1, -1], - ["b\u0151l", -1, -1], - ["r\u0151l", -1, -1], - ["t\u0151l", -1, -1], - ["n", -1, -1], - ["an", 19, -1], - ["ban", 20, -1], - ["en", 19, -1], - ["ben", 22, -1], - ["k\u00E9ppen", 22, -1], - ["on", 19, -1], - ["\u00F6n", 19, -1], - ["k\u00E9pp", -1, -1], - ["kor", -1, -1], - ["t", -1, -1], - ["at", 29, -1], - ["et", 29, -1], - ["k\u00E9nt", 29, -1], - ["ank\u00E9nt", 32, -1], - ["enk\u00E9nt", 32, -1], - ["onk\u00E9nt", 32, -1], - ["ot", 29, -1], - ["\u00E9rt", 29, -1], - ["\u00F6t", 29, -1], - ["hez", -1, -1], - ["hoz", -1, -1], - ["h\u00F6z", -1, -1], - ["v\u00E1", -1, -1], - ["v\u00E9", -1, -1] - ]; - - /** @const */ var a_5 = [ - ["\u00E1n", -1, 2], - ["\u00E9n", -1, 1], - ["\u00E1nk\u00E9nt", -1, 2] - ]; - - /** @const */ var a_6 = [ - ["stul", -1, 1], - ["astul", 0, 1], - ["\u00E1stul", 0, 2], - ["st\u00FCl", -1, 1], - ["est\u00FCl", 3, 1], - ["\u00E9st\u00FCl", 3, 3] - ]; - - /** @const */ var a_7 = [ - ["\u00E1", -1, 1], - ["\u00E9", -1, 1] - ]; - - /** @const */ var a_8 = [ - ["k", -1, 3], - ["ak", 0, 3], - ["ek", 0, 3], - ["ok", 0, 3], - ["\u00E1k", 0, 1], - ["\u00E9k", 0, 2], - ["\u00F6k", 0, 3] - ]; - - /** @const */ var a_9 = [ - ["\u00E9i", -1, 1], - ["\u00E1\u00E9i", 0, 3], - ["\u00E9\u00E9i", 0, 2], - ["\u00E9", -1, 1], - ["k\u00E9", 3, 1], - ["ak\u00E9", 4, 1], - ["ek\u00E9", 4, 1], - ["ok\u00E9", 4, 1], - ["\u00E1k\u00E9", 4, 3], - ["\u00E9k\u00E9", 4, 2], - ["\u00F6k\u00E9", 4, 1], - ["\u00E9\u00E9", 3, 2] - ]; - - /** @const */ var a_10 = [ - ["a", -1, 1], - ["ja", 0, 1], - ["d", -1, 1], - ["ad", 2, 1], - ["ed", 2, 1], - ["od", 2, 1], - ["\u00E1d", 2, 2], - ["\u00E9d", 2, 3], - ["\u00F6d", 2, 1], - ["e", -1, 1], - ["je", 9, 1], - ["nk", -1, 1], - ["unk", 11, 1], - ["\u00E1nk", 11, 2], - ["\u00E9nk", 11, 3], - ["\u00FCnk", 11, 1], - ["uk", -1, 1], - ["juk", 16, 1], - ["\u00E1juk", 17, 2], - ["\u00FCk", -1, 1], - ["j\u00FCk", 19, 1], - ["\u00E9j\u00FCk", 20, 3], - ["m", -1, 1], - ["am", 22, 1], - ["em", 22, 1], - ["om", 22, 1], - ["\u00E1m", 22, 2], - ["\u00E9m", 22, 3], - ["o", -1, 1], - ["\u00E1", -1, 2], - ["\u00E9", -1, 3] - ]; - - /** @const */ var a_11 = [ - ["id", -1, 1], - ["aid", 0, 1], - ["jaid", 1, 1], - ["eid", 0, 1], - ["jeid", 3, 1], - ["\u00E1id", 0, 2], - ["\u00E9id", 0, 3], - ["i", -1, 1], - ["ai", 7, 1], - ["jai", 8, 1], - ["ei", 7, 1], - ["jei", 10, 1], - ["\u00E1i", 7, 2], - ["\u00E9i", 7, 3], - ["itek", -1, 1], - ["eitek", 14, 1], - ["jeitek", 15, 1], - ["\u00E9itek", 14, 3], - ["ik", -1, 1], - ["aik", 18, 1], - ["jaik", 19, 1], - ["eik", 18, 1], - ["jeik", 21, 1], - ["\u00E1ik", 18, 2], - ["\u00E9ik", 18, 3], - ["ink", -1, 1], - ["aink", 25, 1], - ["jaink", 26, 1], - ["eink", 25, 1], - ["jeink", 28, 1], - ["\u00E1ink", 25, 2], - ["\u00E9ink", 25, 3], - ["aitok", -1, 1], - ["jaitok", 32, 1], - ["\u00E1itok", -1, 2], - ["im", -1, 1], - ["aim", 35, 1], - ["jaim", 36, 1], - ["eim", 35, 1], - ["jeim", 38, 1], - ["\u00E1im", 35, 2], - ["\u00E9im", 35, 3] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 17, 36, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1]; - - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - lab0: { - var /** number */ v_1 = base.cursor; - lab1: { - if (!(base.in_grouping(g_v, 97, 369))) - { - break lab1; - } - golab2: while(true) - { - var /** number */ v_2 = base.cursor; - lab3: { - if (!(base.out_grouping(g_v, 97, 369))) - { - break lab3; - } - base.cursor = v_2; - break golab2; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - lab4: { - var /** number */ v_3 = base.cursor; - lab5: { - if (base.find_among(a_0) == 0) - { - break lab5; - } - break lab4; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - I_p1 = base.cursor; - break lab0; - } - base.cursor = v_1; - if (!(base.out_grouping(g_v, 97, 369))) - { - return false; - } - golab6: while(true) - { - lab7: { - if (!(base.in_grouping(g_v, 97, 369))) - { - break lab7; - } - break golab6; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_v_ending() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_1); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("a")) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_double() { - var /** number */ v_1 = base.limit - base.cursor; - if (base.find_among_b(a_2) == 0) - { - return false; - } - base.cursor = base.limit - v_1; - return true; - }; - - /** @return {boolean} */ - function r_undouble() { - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.ket = base.cursor; - { - var /** number */ c1 = base.cursor - 1; - if (c1 < base.limit_backward) - { - return false; - } - base.cursor = c1; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_instrum() { - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - if (!r_double()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - if (!r_undouble()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_case() { - base.ket = base.cursor; - if (base.find_among_b(a_4) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - if (!r_v_ending()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_case_special() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("e")) - { - return false; - } - break; - case 2: - if (!base.slice_from("a")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_case_other() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("a")) - { - return false; - } - break; - case 3: - if (!base.slice_from("e")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_factive() { - base.ket = base.cursor; - if (base.find_among_b(a_7) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - if (!r_double()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - if (!r_undouble()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_plural() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_8); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("a")) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_owned() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_9); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - case 3: - if (!base.slice_from("a")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_sing_owner() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_10); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("a")) - { - return false; - } - break; - case 3: - if (!base.slice_from("e")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_plur_owner() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_11); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("a")) - { - return false; - } - break; - case 3: - if (!base.slice_from("e")) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_mark_regions(); - base.cursor = v_1; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_instrum(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_case(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_case_special(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_case_other(); - base.cursor = base.limit - v_5; - var /** number */ v_6 = base.limit - base.cursor; - r_factive(); - base.cursor = base.limit - v_6; - var /** number */ v_7 = base.limit - base.cursor; - r_owned(); - base.cursor = base.limit - v_7; - var /** number */ v_8 = base.limit - base.cursor; - r_sing_owner(); - base.cursor = base.limit - v_8; - var /** number */ v_9 = base.limit - base.cursor; - r_plur_owner(); - base.cursor = base.limit - v_9; - var /** number */ v_10 = base.limit - base.cursor; - r_plural(); - base.cursor = base.limit - v_10; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['HungarianStemmer'] = HungarianStemmer; diff --git a/js/indonesian-stemmer.js b/js/indonesian-stemmer.js deleted file mode 100644 index eb9663b..0000000 --- a/js/indonesian-stemmer.js +++ /dev/null @@ -1,422 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var IndonesianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["kah", -1, 1], - ["lah", -1, 1], - ["pun", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["nya", -1, 1], - ["ku", -1, 1], - ["mu", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["i", -1, 1, r_SUFFIX_I_OK], - ["an", -1, 1, r_SUFFIX_AN_OK], - ["kan", 1, 1, r_SUFFIX_KAN_OK] - ]; - - /** @const */ var a_3 = [ - ["di", -1, 1], - ["ke", -1, 2], - ["me", -1, 1], - ["mem", 2, 5], - ["men", 2, 1], - ["meng", 4, 1], - ["meny", 4, 3, r_VOWEL], - ["pem", -1, 6], - ["pen", -1, 2], - ["peng", 8, 2], - ["peny", 8, 4, r_VOWEL], - ["ter", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["be", -1, 3, r_KER], - ["belajar", 0, 4], - ["ber", 0, 3], - ["pe", -1, 1], - ["pelajar", 3, 2], - ["per", 3, 1] - ]; - - /** @const */ var /** Array */ g_vowel = [17, 65, 16]; - - var /** number */ I_prefix = 0; - var /** number */ I_measure = 0; - - - /** @return {boolean} */ - function r_remove_particle() { - base.ket = base.cursor; - if (base.find_among_b(a_0) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - I_measure -= 1; - return true; - }; - - /** @return {boolean} */ - function r_remove_possessive_pronoun() { - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - I_measure -= 1; - return true; - }; - - /** @return {boolean} */ - function r_SUFFIX_KAN_OK() { - if (I_prefix == 3) - { - return false; - } - if (I_prefix == 2) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_SUFFIX_AN_OK() { - return I_prefix != 1; - }; - - /** @return {boolean} */ - function r_SUFFIX_I_OK() { - if (I_prefix > 2) - { - return false; - } - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("s"))) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_1; - } - return true; - }; - - /** @return {boolean} */ - function r_remove_suffix() { - base.ket = base.cursor; - if (base.find_among_b(a_2) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - I_measure -= 1; - return true; - }; - - /** @return {boolean} */ - function r_VOWEL() { - if (!(base.in_grouping(g_vowel, 97, 117))) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_KER() { - if (!(base.out_grouping(g_vowel, 97, 117))) - { - return false; - } - if (!(base.eq_s("er"))) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_remove_first_order_prefix() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_3); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - I_prefix = 1; - I_measure -= 1; - break; - case 2: - if (!base.slice_del()) - { - return false; - } - I_prefix = 3; - I_measure -= 1; - break; - case 3: - I_prefix = 1; - if (!base.slice_from("s")) - { - return false; - } - I_measure -= 1; - break; - case 4: - I_prefix = 3; - if (!base.slice_from("s")) - { - return false; - } - I_measure -= 1; - break; - case 5: - I_prefix = 1; - I_measure -= 1; - lab0: { - var /** number */ v_1 = base.cursor; - lab1: { - var /** number */ v_2 = base.cursor; - if (!(base.in_grouping(g_vowel, 97, 117))) - { - break lab1; - } - base.cursor = v_2; - if (!base.slice_from("p")) - { - return false; - } - break lab0; - } - base.cursor = v_1; - if (!base.slice_del()) - { - return false; - } - } - break; - case 6: - I_prefix = 3; - I_measure -= 1; - lab2: { - var /** number */ v_3 = base.cursor; - lab3: { - var /** number */ v_4 = base.cursor; - if (!(base.in_grouping(g_vowel, 97, 117))) - { - break lab3; - } - base.cursor = v_4; - if (!base.slice_from("p")) - { - return false; - } - break lab2; - } - base.cursor = v_3; - if (!base.slice_del()) - { - return false; - } - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_remove_second_order_prefix() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_4); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - I_prefix = 2; - I_measure -= 1; - break; - case 2: - if (!base.slice_from("ajar")) - { - return false; - } - I_measure -= 1; - break; - case 3: - if (!base.slice_del()) - { - return false; - } - I_prefix = 4; - I_measure -= 1; - break; - case 4: - if (!base.slice_from("ajar")) - { - return false; - } - I_prefix = 4; - I_measure -= 1; - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - I_measure = 0; - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - golab2: while(true) - { - lab3: { - if (!(base.in_grouping(g_vowel, 97, 117))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - I_measure += 1; - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - if (I_measure <= 2) - { - return false; - } - I_prefix = 0; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_4 = base.limit - base.cursor; - r_remove_particle(); - base.cursor = base.limit - v_4; - if (I_measure <= 2) - { - return false; - } - var /** number */ v_5 = base.limit - base.cursor; - r_remove_possessive_pronoun(); - base.cursor = base.limit - v_5; - base.cursor = base.limit_backward; - if (I_measure <= 2) - { - return false; - } - lab4: { - var /** number */ v_6 = base.cursor; - lab5: { - var /** number */ v_7 = base.cursor; - if (!r_remove_first_order_prefix()) - { - break lab5; - } - var /** number */ v_8 = base.cursor; - lab6: { - var /** number */ v_9 = base.cursor; - if (I_measure <= 2) - { - break lab6; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - if (!r_remove_suffix()) - { - break lab6; - } - base.cursor = base.limit_backward; - base.cursor = v_9; - if (I_measure <= 2) - { - break lab6; - } - if (!r_remove_second_order_prefix()) - { - break lab6; - } - } - base.cursor = v_8; - base.cursor = v_7; - break lab4; - } - base.cursor = v_6; - var /** number */ v_10 = base.cursor; - r_remove_second_order_prefix(); - base.cursor = v_10; - var /** number */ v_11 = base.cursor; - lab7: { - if (I_measure <= 2) - { - break lab7; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - if (!r_remove_suffix()) - { - break lab7; - } - base.cursor = base.limit_backward; - } - base.cursor = v_11; - } - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['IndonesianStemmer'] = IndonesianStemmer; diff --git a/js/irish-stemmer.js b/js/irish-stemmer.js deleted file mode 100644 index 9051a97..0000000 --- a/js/irish-stemmer.js +++ /dev/null @@ -1,419 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var IrishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["b'", -1, 1], - ["bh", -1, 4], - ["bhf", 1, 2], - ["bp", -1, 8], - ["ch", -1, 5], - ["d'", -1, 1], - ["d'fh", 5, 2], - ["dh", -1, 6], - ["dt", -1, 9], - ["fh", -1, 2], - ["gc", -1, 5], - ["gh", -1, 7], - ["h-", -1, 1], - ["m'", -1, 1], - ["mb", -1, 4], - ["mh", -1, 10], - ["n-", -1, 1], - ["nd", -1, 6], - ["ng", -1, 7], - ["ph", -1, 8], - ["sh", -1, 3], - ["t-", -1, 1], - ["th", -1, 9], - ["ts", -1, 3] - ]; - - /** @const */ var a_1 = [ - ["\u00EDochta", -1, 1], - ["a\u00EDochta", 0, 1], - ["ire", -1, 2], - ["aire", 2, 2], - ["abh", -1, 1], - ["eabh", 4, 1], - ["ibh", -1, 1], - ["aibh", 6, 1], - ["amh", -1, 1], - ["eamh", 8, 1], - ["imh", -1, 1], - ["aimh", 10, 1], - ["\u00EDocht", -1, 1], - ["a\u00EDocht", 12, 1], - ["ir\u00ED", -1, 2], - ["air\u00ED", 14, 2] - ]; - - /** @const */ var a_2 = [ - ["\u00F3ideacha", -1, 6], - ["patacha", -1, 5], - ["achta", -1, 1], - ["arcachta", 2, 2], - ["eachta", 2, 1], - ["grafa\u00EDochta", -1, 4], - ["paite", -1, 5], - ["ach", -1, 1], - ["each", 7, 1], - ["\u00F3ideach", 8, 6], - ["gineach", 8, 3], - ["patach", 7, 5], - ["grafa\u00EDoch", -1, 4], - ["pataigh", -1, 5], - ["\u00F3idigh", -1, 6], - ["acht\u00FAil", -1, 1], - ["eacht\u00FAil", 15, 1], - ["gineas", -1, 3], - ["ginis", -1, 3], - ["acht", -1, 1], - ["arcacht", 19, 2], - ["eacht", 19, 1], - ["grafa\u00EDocht", -1, 4], - ["arcachta\u00ED", -1, 2], - ["grafa\u00EDochta\u00ED", -1, 4] - ]; - - /** @const */ var a_3 = [ - ["imid", -1, 1], - ["aimid", 0, 1], - ["\u00EDmid", -1, 1], - ["a\u00EDmid", 2, 1], - ["adh", -1, 2], - ["eadh", 4, 2], - ["faidh", -1, 1], - ["fidh", -1, 1], - ["\u00E1il", -1, 2], - ["ain", -1, 2], - ["tear", -1, 2], - ["tar", -1, 2] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 17, 4, 2]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - lab2: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab2; - } - break golab1; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_pV = base.cursor; - golab3: while(true) - { - lab4: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab4; - } - break golab3; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p1 = base.cursor; - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_initial_morph() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_0); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("f")) - { - return false; - } - break; - case 3: - if (!base.slice_from("s")) - { - return false; - } - break; - case 4: - if (!base.slice_from("b")) - { - return false; - } - break; - case 5: - if (!base.slice_from("c")) - { - return false; - } - break; - case 6: - if (!base.slice_from("d")) - { - return false; - } - break; - case 7: - if (!base.slice_from("g")) - { - return false; - } - break; - case 8: - if (!base.slice_from("p")) - { - return false; - } - break; - case 9: - if (!base.slice_from("t")) - { - return false; - } - break; - case 10: - if (!base.slice_from("m")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_noun_sfx() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_1); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_deriv() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("arc")) - { - return false; - } - break; - case 3: - if (!base.slice_from("gin")) - { - return false; - } - break; - case 4: - if (!base.slice_from("graf")) - { - return false; - } - break; - case 5: - if (!base.slice_from("paite")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u00F3id")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_verb_sfx() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_initial_morph(); - base.cursor = v_1; - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_3 = base.limit - base.cursor; - r_noun_sfx(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_deriv(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_verb_sfx(); - base.cursor = base.limit - v_5; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['IrishStemmer'] = IrishStemmer; diff --git a/js/italian-stemmer.js b/js/italian-stemmer.js deleted file mode 100644 index 193cbf8..0000000 --- a/js/italian-stemmer.js +++ /dev/null @@ -1,1008 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var ItalianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 7], - ["qu", 0, 6], - ["\u00E1", 0, 1], - ["\u00E9", 0, 2], - ["\u00ED", 0, 3], - ["\u00F3", 0, 4], - ["\u00FA", 0, 5] - ]; - - /** @const */ var a_1 = [ - ["", -1, 3], - ["I", 0, 1], - ["U", 0, 2] - ]; - - /** @const */ var a_2 = [ - ["la", -1, -1], - ["cela", 0, -1], - ["gliela", 0, -1], - ["mela", 0, -1], - ["tela", 0, -1], - ["vela", 0, -1], - ["le", -1, -1], - ["cele", 6, -1], - ["gliele", 6, -1], - ["mele", 6, -1], - ["tele", 6, -1], - ["vele", 6, -1], - ["ne", -1, -1], - ["cene", 12, -1], - ["gliene", 12, -1], - ["mene", 12, -1], - ["sene", 12, -1], - ["tene", 12, -1], - ["vene", 12, -1], - ["ci", -1, -1], - ["li", -1, -1], - ["celi", 20, -1], - ["glieli", 20, -1], - ["meli", 20, -1], - ["teli", 20, -1], - ["veli", 20, -1], - ["gli", 20, -1], - ["mi", -1, -1], - ["si", -1, -1], - ["ti", -1, -1], - ["vi", -1, -1], - ["lo", -1, -1], - ["celo", 31, -1], - ["glielo", 31, -1], - ["melo", 31, -1], - ["telo", 31, -1], - ["velo", 31, -1] - ]; - - /** @const */ var a_3 = [ - ["ando", -1, 1], - ["endo", -1, 1], - ["ar", -1, 2], - ["er", -1, 2], - ["ir", -1, 2] - ]; - - /** @const */ var a_4 = [ - ["ic", -1, -1], - ["abil", -1, -1], - ["os", -1, -1], - ["iv", -1, 1] - ]; - - /** @const */ var a_5 = [ - ["ic", -1, 1], - ["abil", -1, 1], - ["iv", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["ica", -1, 1], - ["logia", -1, 3], - ["osa", -1, 1], - ["ista", -1, 1], - ["iva", -1, 9], - ["anza", -1, 1], - ["enza", -1, 5], - ["ice", -1, 1], - ["atrice", 7, 1], - ["iche", -1, 1], - ["logie", -1, 3], - ["abile", -1, 1], - ["ibile", -1, 1], - ["usione", -1, 4], - ["azione", -1, 2], - ["uzione", -1, 4], - ["atore", -1, 2], - ["ose", -1, 1], - ["ante", -1, 1], - ["mente", -1, 1], - ["amente", 19, 7], - ["iste", -1, 1], - ["ive", -1, 9], - ["anze", -1, 1], - ["enze", -1, 5], - ["ici", -1, 1], - ["atrici", 25, 1], - ["ichi", -1, 1], - ["abili", -1, 1], - ["ibili", -1, 1], - ["ismi", -1, 1], - ["usioni", -1, 4], - ["azioni", -1, 2], - ["uzioni", -1, 4], - ["atori", -1, 2], - ["osi", -1, 1], - ["anti", -1, 1], - ["amenti", -1, 6], - ["imenti", -1, 6], - ["isti", -1, 1], - ["ivi", -1, 9], - ["ico", -1, 1], - ["ismo", -1, 1], - ["oso", -1, 1], - ["amento", -1, 6], - ["imento", -1, 6], - ["ivo", -1, 9], - ["it\u00E0", -1, 8], - ["ist\u00E0", -1, 1], - ["ist\u00E8", -1, 1], - ["ist\u00EC", -1, 1] - ]; - - /** @const */ var a_7 = [ - ["isca", -1, 1], - ["enda", -1, 1], - ["ata", -1, 1], - ["ita", -1, 1], - ["uta", -1, 1], - ["ava", -1, 1], - ["eva", -1, 1], - ["iva", -1, 1], - ["erebbe", -1, 1], - ["irebbe", -1, 1], - ["isce", -1, 1], - ["ende", -1, 1], - ["are", -1, 1], - ["ere", -1, 1], - ["ire", -1, 1], - ["asse", -1, 1], - ["ate", -1, 1], - ["avate", 16, 1], - ["evate", 16, 1], - ["ivate", 16, 1], - ["ete", -1, 1], - ["erete", 20, 1], - ["irete", 20, 1], - ["ite", -1, 1], - ["ereste", -1, 1], - ["ireste", -1, 1], - ["ute", -1, 1], - ["erai", -1, 1], - ["irai", -1, 1], - ["isci", -1, 1], - ["endi", -1, 1], - ["erei", -1, 1], - ["irei", -1, 1], - ["assi", -1, 1], - ["ati", -1, 1], - ["iti", -1, 1], - ["eresti", -1, 1], - ["iresti", -1, 1], - ["uti", -1, 1], - ["avi", -1, 1], - ["evi", -1, 1], - ["ivi", -1, 1], - ["isco", -1, 1], - ["ando", -1, 1], - ["endo", -1, 1], - ["Yamo", -1, 1], - ["iamo", -1, 1], - ["avamo", -1, 1], - ["evamo", -1, 1], - ["ivamo", -1, 1], - ["eremo", -1, 1], - ["iremo", -1, 1], - ["assimo", -1, 1], - ["ammo", -1, 1], - ["emmo", -1, 1], - ["eremmo", 54, 1], - ["iremmo", 54, 1], - ["immo", -1, 1], - ["ano", -1, 1], - ["iscano", 58, 1], - ["avano", 58, 1], - ["evano", 58, 1], - ["ivano", 58, 1], - ["eranno", -1, 1], - ["iranno", -1, 1], - ["ono", -1, 1], - ["iscono", 65, 1], - ["arono", 65, 1], - ["erono", 65, 1], - ["irono", 65, 1], - ["erebbero", -1, 1], - ["irebbero", -1, 1], - ["assero", -1, 1], - ["essero", -1, 1], - ["issero", -1, 1], - ["ato", -1, 1], - ["ito", -1, 1], - ["uto", -1, 1], - ["avo", -1, 1], - ["evo", -1, 1], - ["ivo", -1, 1], - ["ar", -1, 1], - ["ir", -1, 1], - ["er\u00E0", -1, 1], - ["ir\u00E0", -1, 1], - ["er\u00F2", -1, 1], - ["ir\u00F2", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 128, 8, 2, 1]; - - /** @const */ var /** Array */ g_AEIO = [17, 65, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 128, 8, 2]; - - /** @const */ var /** Array */ g_CG = [17]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_prelude() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - while(true) - { - var /** number */ v_2 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u00E0")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u00E8")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u00EC")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u00F2")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u00F9")) - { - return false; - } - break; - case 6: - if (!base.slice_from("qU")) - { - return false; - } - break; - case 7: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_2; - break; - } - base.cursor = v_1; - while(true) - { - var /** number */ v_3 = base.cursor; - lab1: { - golab2: while(true) - { - var /** number */ v_4 = base.cursor; - lab3: { - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab3; - } - base.bra = base.cursor; - lab4: { - var /** number */ v_5 = base.cursor; - lab5: { - if (!(base.eq_s("u"))) - { - break lab5; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab5; - } - if (!base.slice_from("U")) - { - return false; - } - break lab4; - } - base.cursor = v_5; - if (!(base.eq_s("i"))) - { - break lab3; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab3; - } - if (!base.slice_from("I")) - { - return false; - } - } - base.cursor = v_4; - break golab2; - } - base.cursor = v_4; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - continue; - } - base.cursor = v_3; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab2; - } - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.out_grouping(g_v, 97, 249))) - { - break lab4; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab4; - } - base.cursor++; - } - break lab3; - } - base.cursor = v_3; - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab2; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 249))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - } - break lab1; - } - base.cursor = v_2; - if (!(base.out_grouping(g_v, 97, 249))) - { - break lab0; - } - lab9: { - var /** number */ v_6 = base.cursor; - lab10: { - if (!(base.out_grouping(g_v, 97, 249))) - { - break lab10; - } - golab11: while(true) - { - lab12: { - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab12; - } - break golab11; - } - if (base.cursor >= base.limit) - { - break lab10; - } - base.cursor++; - } - break lab9; - } - base.cursor = v_6; - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab0; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_pV = base.cursor; - } - base.cursor = v_1; - var /** number */ v_8 = base.cursor; - lab13: { - golab14: while(true) - { - lab15: { - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab15; - } - break golab14; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab16: while(true) - { - lab17: { - if (!(base.out_grouping(g_v, 97, 249))) - { - break lab17; - } - break golab16; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p1 = base.cursor; - golab18: while(true) - { - lab19: { - if (!(base.in_grouping(g_v, 97, 249))) - { - break lab19; - } - break golab18; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab20: while(true) - { - lab21: { - if (!(base.out_grouping(g_v, 97, 249))) - { - break lab21; - } - break golab20; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_8; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_1); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("i")) - { - return false; - } - break; - case 2: - if (!base.slice_from("u")) - { - return false; - } - break; - case 3: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_attached_pronoun() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_2) == 0) - { - return false; - } - base.bra = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - return false; - } - if (!r_RV()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("ic"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 3: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("log")) - { - return false; - } - break; - case 4: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("u")) - { - return false; - } - break; - case 5: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("ente")) - { - return false; - } - break; - case 6: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 7: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - switch (among_var) { - case 1: - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - break; - case 8: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - if (base.find_among_b(a_5) == 0) - { - base.cursor = base.limit - v_3; - break lab2; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_3; - break lab2; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 9: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_4; - break lab3; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_4; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("ic"))) - { - base.cursor = base.limit - v_4; - break lab3; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_4; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_verb_suffix() { - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - if (base.find_among_b(a_7) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.limit_backward = v_2; - return true; - }; - - /** @return {boolean} */ - function r_vowel_suffix() { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.in_grouping_b(g_AEIO, 97, 242))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!r_RV()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("i"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!r_RV()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - } - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (!(base.eq_s_b("h"))) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!(base.in_grouping_b(g_CG, 99, 103))) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!r_RV()) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_exceptions() { - base.bra = base.cursor; - if (!(base.eq_s("divano"))) - { - return false; - } - if (base.cursor < base.limit) - { - return false; - } - base.ket = base.cursor; - if (!base.slice_from("divan")) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - lab0: { - var /** number */ v_1 = base.cursor; - lab1: { - if (!r_exceptions()) - { - break lab1; - } - break lab0; - } - base.cursor = v_1; - var /** number */ v_2 = base.cursor; - r_prelude(); - base.cursor = v_2; - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_4 = base.limit - base.cursor; - r_attached_pronoun(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - lab2: { - lab3: { - var /** number */ v_6 = base.limit - base.cursor; - lab4: { - if (!r_standard_suffix()) - { - break lab4; - } - break lab3; - } - base.cursor = base.limit - v_6; - if (!r_verb_suffix()) - { - break lab2; - } - } - } - base.cursor = base.limit - v_5; - var /** number */ v_7 = base.limit - base.cursor; - r_vowel_suffix(); - base.cursor = base.limit - v_7; - base.cursor = base.limit_backward; - var /** number */ v_8 = base.cursor; - r_postlude(); - base.cursor = v_8; - } - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['ItalianStemmer'] = ItalianStemmer; diff --git a/js/lithuanian-stemmer.js b/js/lithuanian-stemmer.js deleted file mode 100644 index 4d1d886..0000000 --- a/js/lithuanian-stemmer.js +++ /dev/null @@ -1,558 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var LithuanianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["a", -1, -1], - ["ia", 0, -1], - ["eria", 1, -1], - ["osna", 0, -1], - ["iosna", 3, -1], - ["uosna", 3, -1], - ["iuosna", 5, -1], - ["ysna", 0, -1], - ["\u0117sna", 0, -1], - ["e", -1, -1], - ["ie", 9, -1], - ["enie", 10, -1], - ["erie", 10, -1], - ["oje", 9, -1], - ["ioje", 13, -1], - ["uje", 9, -1], - ["iuje", 15, -1], - ["yje", 9, -1], - ["enyje", 17, -1], - ["eryje", 17, -1], - ["\u0117je", 9, -1], - ["ame", 9, -1], - ["iame", 21, -1], - ["sime", 9, -1], - ["ome", 9, -1], - ["\u0117me", 9, -1], - ["tum\u0117me", 25, -1], - ["ose", 9, -1], - ["iose", 27, -1], - ["uose", 27, -1], - ["iuose", 29, -1], - ["yse", 9, -1], - ["enyse", 31, -1], - ["eryse", 31, -1], - ["\u0117se", 9, -1], - ["ate", 9, -1], - ["iate", 35, -1], - ["ite", 9, -1], - ["kite", 37, -1], - ["site", 37, -1], - ["ote", 9, -1], - ["tute", 9, -1], - ["\u0117te", 9, -1], - ["tum\u0117te", 42, -1], - ["i", -1, -1], - ["ai", 44, -1], - ["iai", 45, -1], - ["eriai", 46, -1], - ["ei", 44, -1], - ["tumei", 48, -1], - ["ki", 44, -1], - ["imi", 44, -1], - ["erimi", 51, -1], - ["umi", 44, -1], - ["iumi", 53, -1], - ["si", 44, -1], - ["asi", 55, -1], - ["iasi", 56, -1], - ["esi", 55, -1], - ["iesi", 58, -1], - ["siesi", 59, -1], - ["isi", 55, -1], - ["aisi", 61, -1], - ["eisi", 61, -1], - ["tumeisi", 63, -1], - ["uisi", 61, -1], - ["osi", 55, -1], - ["\u0117josi", 66, -1], - ["uosi", 66, -1], - ["iuosi", 68, -1], - ["siuosi", 69, -1], - ["usi", 55, -1], - ["ausi", 71, -1], - ["\u010Diausi", 72, -1], - ["\u0105si", 55, -1], - ["\u0117si", 55, -1], - ["\u0173si", 55, -1], - ["t\u0173si", 76, -1], - ["ti", 44, -1], - ["enti", 78, -1], - ["inti", 78, -1], - ["oti", 78, -1], - ["ioti", 81, -1], - ["uoti", 81, -1], - ["iuoti", 83, -1], - ["auti", 78, -1], - ["iauti", 85, -1], - ["yti", 78, -1], - ["\u0117ti", 78, -1], - ["tel\u0117ti", 88, -1], - ["in\u0117ti", 88, -1], - ["ter\u0117ti", 88, -1], - ["ui", 44, -1], - ["iui", 92, -1], - ["eniui", 93, -1], - ["oj", -1, -1], - ["\u0117j", -1, -1], - ["k", -1, -1], - ["am", -1, -1], - ["iam", 98, -1], - ["iem", -1, -1], - ["im", -1, -1], - ["sim", 101, -1], - ["om", -1, -1], - ["tum", -1, -1], - ["\u0117m", -1, -1], - ["tum\u0117m", 105, -1], - ["an", -1, -1], - ["on", -1, -1], - ["ion", 108, -1], - ["un", -1, -1], - ["iun", 110, -1], - ["\u0117n", -1, -1], - ["o", -1, -1], - ["io", 113, -1], - ["enio", 114, -1], - ["\u0117jo", 113, -1], - ["uo", 113, -1], - ["s", -1, -1], - ["as", 118, -1], - ["ias", 119, -1], - ["es", 118, -1], - ["ies", 121, -1], - ["is", 118, -1], - ["ais", 123, -1], - ["iais", 124, -1], - ["tumeis", 123, -1], - ["imis", 123, -1], - ["enimis", 127, -1], - ["omis", 123, -1], - ["iomis", 129, -1], - ["umis", 123, -1], - ["\u0117mis", 123, -1], - ["enis", 123, -1], - ["asis", 123, -1], - ["ysis", 123, -1], - ["ams", 118, -1], - ["iams", 136, -1], - ["iems", 118, -1], - ["ims", 118, -1], - ["enims", 139, -1], - ["erims", 139, -1], - ["oms", 118, -1], - ["ioms", 142, -1], - ["ums", 118, -1], - ["\u0117ms", 118, -1], - ["ens", 118, -1], - ["os", 118, -1], - ["ios", 147, -1], - ["uos", 147, -1], - ["iuos", 149, -1], - ["ers", 118, -1], - ["us", 118, -1], - ["aus", 152, -1], - ["iaus", 153, -1], - ["ius", 152, -1], - ["ys", 118, -1], - ["enys", 156, -1], - ["erys", 156, -1], - ["\u0105s", 118, -1], - ["i\u0105s", 159, -1], - ["\u0117s", 118, -1], - ["am\u0117s", 161, -1], - ["iam\u0117s", 162, -1], - ["im\u0117s", 161, -1], - ["kim\u0117s", 164, -1], - ["sim\u0117s", 164, -1], - ["om\u0117s", 161, -1], - ["\u0117m\u0117s", 161, -1], - ["tum\u0117m\u0117s", 168, -1], - ["at\u0117s", 161, -1], - ["iat\u0117s", 170, -1], - ["sit\u0117s", 161, -1], - ["ot\u0117s", 161, -1], - ["\u0117t\u0117s", 161, -1], - ["tum\u0117t\u0117s", 174, -1], - ["\u012Fs", 118, -1], - ["\u016Bs", 118, -1], - ["t\u0173s", 118, -1], - ["at", -1, -1], - ["iat", 179, -1], - ["it", -1, -1], - ["sit", 181, -1], - ["ot", -1, -1], - ["\u0117t", -1, -1], - ["tum\u0117t", 184, -1], - ["u", -1, -1], - ["au", 186, -1], - ["iau", 187, -1], - ["\u010Diau", 188, -1], - ["iu", 186, -1], - ["eniu", 190, -1], - ["siu", 190, -1], - ["y", -1, -1], - ["\u0105", -1, -1], - ["i\u0105", 194, -1], - ["\u0117", -1, -1], - ["\u0119", -1, -1], - ["\u012F", -1, -1], - ["en\u012F", 198, -1], - ["er\u012F", 198, -1], - ["\u0173", -1, -1], - ["i\u0173", 201, -1], - ["er\u0173", 201, -1] - ]; - - /** @const */ var a_1 = [ - ["ing", -1, -1], - ["aj", -1, -1], - ["iaj", 1, -1], - ["iej", -1, -1], - ["oj", -1, -1], - ["ioj", 4, -1], - ["uoj", 4, -1], - ["iuoj", 6, -1], - ["auj", -1, -1], - ["\u0105j", -1, -1], - ["i\u0105j", 9, -1], - ["\u0117j", -1, -1], - ["\u0173j", -1, -1], - ["i\u0173j", 12, -1], - ["ok", -1, -1], - ["iok", 14, -1], - ["iuk", -1, -1], - ["uliuk", 16, -1], - ["u\u010Diuk", 16, -1], - ["i\u0161k", -1, -1], - ["iul", -1, -1], - ["yl", -1, -1], - ["\u0117l", -1, -1], - ["am", -1, -1], - ["dam", 23, -1], - ["jam", 23, -1], - ["zgan", -1, -1], - ["ain", -1, -1], - ["esn", -1, -1], - ["op", -1, -1], - ["iop", 29, -1], - ["ias", -1, -1], - ["ies", -1, -1], - ["ais", -1, -1], - ["iais", 33, -1], - ["os", -1, -1], - ["ios", 35, -1], - ["uos", 35, -1], - ["iuos", 37, -1], - ["aus", -1, -1], - ["iaus", 39, -1], - ["\u0105s", -1, -1], - ["i\u0105s", 41, -1], - ["\u0119s", -1, -1], - ["ut\u0117ait", -1, -1], - ["ant", -1, -1], - ["iant", 45, -1], - ["siant", 46, -1], - ["int", -1, -1], - ["ot", -1, -1], - ["uot", 49, -1], - ["iuot", 50, -1], - ["yt", -1, -1], - ["\u0117t", -1, -1], - ["yk\u0161t", -1, -1], - ["iau", -1, -1], - ["dav", -1, -1], - ["sv", -1, -1], - ["\u0161v", -1, -1], - ["yk\u0161\u010D", -1, -1], - ["\u0119", -1, -1], - ["\u0117j\u0119", 60, -1] - ]; - - /** @const */ var a_2 = [ - ["ojime", -1, 7], - ["\u0117jime", -1, 3], - ["avime", -1, 6], - ["okate", -1, 8], - ["aite", -1, 1], - ["uote", -1, 2], - ["asius", -1, 5], - ["okat\u0117s", -1, 8], - ["ait\u0117s", -1, 1], - ["uot\u0117s", -1, 2], - ["esiu", -1, 4] - ]; - - /** @const */ var a_3 = [ - ["\u010D", -1, 1], - ["d\u017E", -1, 2] - ]; - - /** @const */ var a_4 = [ - ["gd", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 16, 0, 64, 1, 0, 64, 0, 0, 0, 0, 0, 0, 0, 4, 4]; - - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_step1() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_0) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_step2() { - while(true) - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (base.cursor < I_p1) - { - break lab0; - } - var /** number */ v_3 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - base.limit_backward = v_3; - break lab0; - } - base.bra = base.cursor; - base.limit_backward = v_3; - if (!base.slice_del()) - { - return false; - } - continue; - } - base.cursor = base.limit - v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_fix_conflicts() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("ait\u0117")) - { - return false; - } - break; - case 2: - if (!base.slice_from("uot\u0117")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u0117jimas")) - { - return false; - } - break; - case 4: - if (!base.slice_from("esys")) - { - return false; - } - break; - case 5: - if (!base.slice_from("asys")) - { - return false; - } - break; - case 6: - if (!base.slice_from("avimas")) - { - return false; - } - break; - case 7: - if (!base.slice_from("ojimas")) - { - return false; - } - break; - case 8: - if (!base.slice_from("okat\u0117")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_fix_chdz() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("t")) - { - return false; - } - break; - case 2: - if (!base.slice_from("d")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_fix_gd() { - base.ket = base.cursor; - if (base.find_among_b(a_4) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_from("g")) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - I_p1 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - var /** number */ v_2 = base.cursor; - lab1: { - var /** number */ v_3 = base.cursor; - if (!(base.eq_s("a"))) - { - base.cursor = v_2; - break lab1; - } - base.cursor = v_3; - if (base.current.length <= 6) - { - base.cursor = v_2; - break lab1; - } - { - var /** number */ c1 = base.cursor + 1; - if (c1 > base.limit) - { - base.cursor = v_2; - break lab1; - } - base.cursor = c1; - } - } - golab2: while(true) - { - lab3: { - if (!(base.in_grouping(g_v, 97, 371))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab4: while(true) - { - lab5: { - if (!(base.out_grouping(g_v, 97, 371))) - { - break lab5; - } - break golab4; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p1 = base.cursor; - } - base.cursor = v_1; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_6 = base.limit - base.cursor; - r_fix_conflicts(); - base.cursor = base.limit - v_6; - var /** number */ v_7 = base.limit - base.cursor; - r_step1(); - base.cursor = base.limit - v_7; - var /** number */ v_8 = base.limit - base.cursor; - r_fix_chdz(); - base.cursor = base.limit - v_8; - var /** number */ v_9 = base.limit - base.cursor; - r_step2(); - base.cursor = base.limit - v_9; - var /** number */ v_10 = base.limit - base.cursor; - r_fix_chdz(); - base.cursor = base.limit - v_10; - var /** number */ v_11 = base.limit - base.cursor; - r_fix_gd(); - base.cursor = base.limit - v_11; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['LithuanianStemmer'] = LithuanianStemmer; diff --git a/js/nepali-stemmer.js b/js/nepali-stemmer.js deleted file mode 100644 index 500c7bd..0000000 --- a/js/nepali-stemmer.js +++ /dev/null @@ -1,319 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var NepaliStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0932\u093E\u0907", -1, 1], - ["\u0932\u093E\u0908", -1, 1], - ["\u0938\u0901\u0917", -1, 1], - ["\u0938\u0902\u0917", -1, 1], - ["\u092E\u093E\u0930\u094D\u092B\u0924", -1, 1], - ["\u0930\u0924", -1, 1], - ["\u0915\u093E", -1, 2], - ["\u092E\u093E", -1, 1], - ["\u0926\u094D\u0935\u093E\u0930\u093E", -1, 1], - ["\u0915\u093F", -1, 2], - ["\u092A\u091B\u093F", -1, 1], - ["\u0915\u0940", -1, 2], - ["\u0932\u0947", -1, 1], - ["\u0915\u0948", -1, 2], - ["\u0938\u0901\u0917\u0948", -1, 1], - ["\u092E\u0948", -1, 1], - ["\u0915\u094B", -1, 2] - ]; - - /** @const */ var a_1 = [ - ["\u0901", -1, -1], - ["\u0902", -1, -1], - ["\u0948", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["\u0901", -1, 1], - ["\u0902", -1, 1], - ["\u0948", -1, 2] - ]; - - /** @const */ var a_3 = [ - ["\u0925\u093F\u090F", -1, 1], - ["\u091B", -1, 1], - ["\u0907\u091B", 1, 1], - ["\u090F\u091B", 1, 1], - ["\u093F\u091B", 1, 1], - ["\u0947\u091B", 1, 1], - ["\u0928\u0947\u091B", 5, 1], - ["\u0939\u0941\u0928\u0947\u091B", 6, 1], - ["\u0907\u0928\u094D\u091B", 1, 1], - ["\u093F\u0928\u094D\u091B", 1, 1], - ["\u0939\u0941\u0928\u094D\u091B", 1, 1], - ["\u090F\u0915\u093E", -1, 1], - ["\u0907\u090F\u0915\u093E", 11, 1], - ["\u093F\u090F\u0915\u093E", 11, 1], - ["\u0947\u0915\u093E", -1, 1], - ["\u0928\u0947\u0915\u093E", 14, 1], - ["\u0926\u093E", -1, 1], - ["\u0907\u0926\u093E", 16, 1], - ["\u093F\u0926\u093E", 16, 1], - ["\u0926\u0947\u0916\u093F", -1, 1], - ["\u092E\u093E\u0925\u093F", -1, 1], - ["\u090F\u0915\u0940", -1, 1], - ["\u0907\u090F\u0915\u0940", 21, 1], - ["\u093F\u090F\u0915\u0940", 21, 1], - ["\u0947\u0915\u0940", -1, 1], - ["\u0926\u0947\u0916\u0940", -1, 1], - ["\u0925\u0940", -1, 1], - ["\u0926\u0940", -1, 1], - ["\u091B\u0941", -1, 1], - ["\u090F\u091B\u0941", 28, 1], - ["\u0947\u091B\u0941", 28, 1], - ["\u0928\u0947\u091B\u0941", 30, 1], - ["\u0928\u0941", -1, 1], - ["\u0939\u0930\u0941", -1, 1], - ["\u0939\u0930\u0942", -1, 1], - ["\u091B\u0947", -1, 1], - ["\u0925\u0947", -1, 1], - ["\u0928\u0947", -1, 1], - ["\u090F\u0915\u0948", -1, 1], - ["\u0947\u0915\u0948", -1, 1], - ["\u0928\u0947\u0915\u0948", 39, 1], - ["\u0926\u0948", -1, 1], - ["\u0907\u0926\u0948", 41, 1], - ["\u093F\u0926\u0948", 41, 1], - ["\u090F\u0915\u094B", -1, 1], - ["\u0907\u090F\u0915\u094B", 44, 1], - ["\u093F\u090F\u0915\u094B", 44, 1], - ["\u0947\u0915\u094B", -1, 1], - ["\u0928\u0947\u0915\u094B", 47, 1], - ["\u0926\u094B", -1, 1], - ["\u0907\u0926\u094B", 49, 1], - ["\u093F\u0926\u094B", 49, 1], - ["\u092F\u094B", -1, 1], - ["\u0907\u092F\u094B", 52, 1], - ["\u092D\u092F\u094B", 52, 1], - ["\u093F\u092F\u094B", 52, 1], - ["\u0925\u093F\u092F\u094B", 55, 1], - ["\u0926\u093F\u092F\u094B", 55, 1], - ["\u0925\u094D\u092F\u094B", 52, 1], - ["\u091B\u094C", -1, 1], - ["\u0907\u091B\u094C", 59, 1], - ["\u090F\u091B\u094C", 59, 1], - ["\u093F\u091B\u094C", 59, 1], - ["\u0947\u091B\u094C", 59, 1], - ["\u0928\u0947\u091B\u094C", 63, 1], - ["\u092F\u094C", -1, 1], - ["\u0925\u093F\u092F\u094C", 65, 1], - ["\u091B\u094D\u092F\u094C", 65, 1], - ["\u0925\u094D\u092F\u094C", 65, 1], - ["\u091B\u0928\u094D", -1, 1], - ["\u0907\u091B\u0928\u094D", 69, 1], - ["\u090F\u091B\u0928\u094D", 69, 1], - ["\u093F\u091B\u0928\u094D", 69, 1], - ["\u0947\u091B\u0928\u094D", 69, 1], - ["\u0928\u0947\u091B\u0928\u094D", 73, 1], - ["\u0932\u093E\u0928\u094D", -1, 1], - ["\u091B\u093F\u0928\u094D", -1, 1], - ["\u0925\u093F\u0928\u094D", -1, 1], - ["\u092A\u0930\u094D", -1, 1], - ["\u0907\u0938\u094D", -1, 1], - ["\u0925\u093F\u0907\u0938\u094D", 79, 1], - ["\u091B\u0938\u094D", -1, 1], - ["\u0907\u091B\u0938\u094D", 81, 1], - ["\u090F\u091B\u0938\u094D", 81, 1], - ["\u093F\u091B\u0938\u094D", 81, 1], - ["\u0947\u091B\u0938\u094D", 81, 1], - ["\u0928\u0947\u091B\u0938\u094D", 85, 1], - ["\u093F\u0938\u094D", -1, 1], - ["\u0925\u093F\u0938\u094D", 87, 1], - ["\u091B\u0947\u0938\u094D", -1, 1], - ["\u0939\u094B\u0938\u094D", -1, 1] - ]; - - - - /** @return {boolean} */ - function r_remove_category_1() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - lab2: { - var /** number */ v_2 = base.limit - base.cursor; - lab3: { - if (!(base.eq_s_b("\u090F"))) - { - break lab3; - } - break lab2; - } - base.cursor = base.limit - v_2; - if (!(base.eq_s_b("\u0947"))) - { - break lab1; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!base.slice_del()) - { - return false; - } - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_check_category_2() { - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - return false; - } - base.bra = base.cursor; - return true; - }; - - /** @return {boolean} */ - function r_remove_category_2() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("\u092F\u094C"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - lab2: { - if (!(base.eq_s_b("\u091B\u094C"))) - { - break lab2; - } - break lab0; - } - base.cursor = base.limit - v_1; - lab3: { - if (!(base.eq_s_b("\u0928\u094C"))) - { - break lab3; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("\u0925\u0947"))) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.eq_s_b("\u0924\u094D\u0930"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_remove_category_3() { - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_1 = base.limit - base.cursor; - r_remove_category_1(); - base.cursor = base.limit - v_1; - var /** number */ v_2 = base.limit - base.cursor; - lab0: { - while(true) - { - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - var /** number */ v_5 = base.limit - base.cursor; - if (!r_check_category_2()) - { - break lab2; - } - base.cursor = base.limit - v_5; - if (!r_remove_category_2()) - { - break lab2; - } - } - base.cursor = base.limit - v_4; - if (!r_remove_category_3()) - { - break lab1; - } - continue; - } - base.cursor = base.limit - v_3; - break; - } - } - base.cursor = base.limit - v_2; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['NepaliStemmer'] = NepaliStemmer; diff --git a/js/norwegian-stemmer.js b/js/norwegian-stemmer.js deleted file mode 100644 index a037992..0000000 --- a/js/norwegian-stemmer.js +++ /dev/null @@ -1,263 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var NorwegianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["a", -1, 1], - ["e", -1, 1], - ["ede", 1, 1], - ["ande", 1, 1], - ["ende", 1, 1], - ["ane", 1, 1], - ["ene", 1, 1], - ["hetene", 6, 1], - ["erte", 1, 3], - ["en", -1, 1], - ["heten", 9, 1], - ["ar", -1, 1], - ["er", -1, 1], - ["heter", 12, 1], - ["s", -1, 2], - ["as", 14, 1], - ["es", 14, 1], - ["edes", 16, 1], - ["endes", 16, 1], - ["enes", 16, 1], - ["hetenes", 19, 1], - ["ens", 14, 1], - ["hetens", 21, 1], - ["ers", 14, 1], - ["ets", 14, 1], - ["et", -1, 1], - ["het", 25, 1], - ["ert", -1, 3], - ["ast", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["dt", -1, -1], - ["vt", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["leg", -1, 1], - ["eleg", 0, 1], - ["ig", -1, 1], - ["eig", 2, 1], - ["lig", 2, 1], - ["elig", 4, 1], - ["els", -1, 1], - ["lov", -1, 1], - ["elov", 7, 1], - ["slov", 7, 1], - ["hetslov", 9, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 48, 0, 128]; - - /** @const */ var /** Array */ g_s_ending = [119, 125, 149, 1]; - - var /** number */ I_x = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - var /** number */ v_1 = base.cursor; - { - var /** number */ c1 = base.cursor + 3; - if (c1 > base.limit) - { - return false; - } - base.cursor = c1; - } - I_x = base.cursor; - base.cursor = v_1; - golab0: while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - if (!(base.in_grouping(g_v, 97, 248))) - { - break lab1; - } - base.cursor = v_2; - break golab0; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_v, 97, 248))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - lab4: { - if (I_p1 >= I_x) - { - break lab4; - } - I_p1 = I_x; - } - return true; - }; - - /** @return {boolean} */ - function r_main_suffix() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - lab0: { - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - if (!(base.in_grouping_b(g_s_ending, 98, 122))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_3; - if (!(base.eq_s_b("k"))) - { - return false; - } - if (!(base.out_grouping_b(g_v, 97, 248))) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_from("er")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_consonant_pair() { - var /** number */ v_1 = base.limit - base.cursor; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_3 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - base.limit_backward = v_3; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_3; - base.cursor = base.limit - v_1; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_other_suffix() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - if (base.find_among_b(a_2) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_mark_regions(); - base.cursor = v_1; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_main_suffix(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_consonant_pair(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_other_suffix(); - base.cursor = base.limit - v_4; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['NorwegianStemmer'] = NorwegianStemmer; diff --git a/js/porter-stemmer.js b/js/porter-stemmer.js deleted file mode 100644 index 8a1fcc8..0000000 --- a/js/porter-stemmer.js +++ /dev/null @@ -1,739 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var PorterStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["s", -1, 3], - ["ies", 0, 2], - ["sses", 0, 1], - ["ss", 0, -1] - ]; - - /** @const */ var a_1 = [ - ["", -1, 3], - ["bb", 0, 2], - ["dd", 0, 2], - ["ff", 0, 2], - ["gg", 0, 2], - ["bl", 0, 1], - ["mm", 0, 2], - ["nn", 0, 2], - ["pp", 0, 2], - ["rr", 0, 2], - ["at", 0, 1], - ["tt", 0, 2], - ["iz", 0, 1] - ]; - - /** @const */ var a_2 = [ - ["ed", -1, 2], - ["eed", 0, 1], - ["ing", -1, 2] - ]; - - /** @const */ var a_3 = [ - ["anci", -1, 3], - ["enci", -1, 2], - ["abli", -1, 4], - ["eli", -1, 6], - ["alli", -1, 9], - ["ousli", -1, 11], - ["entli", -1, 5], - ["aliti", -1, 9], - ["biliti", -1, 13], - ["iviti", -1, 12], - ["tional", -1, 1], - ["ational", 10, 8], - ["alism", -1, 9], - ["ation", -1, 8], - ["ization", 13, 7], - ["izer", -1, 7], - ["ator", -1, 8], - ["iveness", -1, 12], - ["fulness", -1, 10], - ["ousness", -1, 11] - ]; - - /** @const */ var a_4 = [ - ["icate", -1, 2], - ["ative", -1, 3], - ["alize", -1, 1], - ["iciti", -1, 2], - ["ical", -1, 2], - ["ful", -1, 3], - ["ness", -1, 3] - ]; - - /** @const */ var a_5 = [ - ["ic", -1, 1], - ["ance", -1, 1], - ["ence", -1, 1], - ["able", -1, 1], - ["ible", -1, 1], - ["ate", -1, 1], - ["ive", -1, 1], - ["ize", -1, 1], - ["iti", -1, 1], - ["al", -1, 1], - ["ism", -1, 1], - ["ion", -1, 2], - ["er", -1, 1], - ["ous", -1, 1], - ["ant", -1, 1], - ["ent", -1, 1], - ["ment", 15, 1], - ["ement", 16, 1], - ["ou", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1]; - - /** @const */ var /** Array */ g_v_WXY = [1, 17, 65, 208, 1]; - - var /** boolean */ B_Y_found = false; - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_shortv() { - if (!(base.out_grouping_b(g_v_WXY, 89, 121))) - { - return false; - } - if (!(base.in_grouping_b(g_v, 97, 121))) - { - return false; - } - if (!(base.out_grouping_b(g_v, 97, 121))) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_Step_1a() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("ss")) - { - return false; - } - break; - case 2: - if (!base.slice_from("i")) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_1b() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - return false; - } - if (!base.slice_from("ee")) - { - return false; - } - break; - case 2: - var /** number */ v_1 = base.limit - base.cursor; - golab0: while(true) - { - lab1: { - if (!(base.in_grouping_b(g_v, 97, 121))) - { - break lab1; - } - break golab0; - } - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - base.cursor = base.limit - v_1; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - among_var = base.find_among_b(a_1); - base.cursor = base.limit - v_3; - switch (among_var) { - case 1: - { - var /** number */ c1 = base.cursor; - base.insert(base.cursor, base.cursor, "e"); - base.cursor = c1; - } - break; - case 2: - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (base.cursor != I_p1) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - if (!r_shortv()) - { - return false; - } - base.cursor = base.limit - v_4; - { - var /** number */ c2 = base.cursor; - base.insert(base.cursor, base.cursor, "e"); - base.cursor = c2; - } - break; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_1c() { - base.ket = base.cursor; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("y"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("Y"))) - { - return false; - } - } - base.bra = base.cursor; - golab2: while(true) - { - lab3: { - if (!(base.in_grouping_b(g_v, 97, 121))) - { - break lab3; - } - break golab2; - } - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - if (!base.slice_from("i")) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_2() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("tion")) - { - return false; - } - break; - case 2: - if (!base.slice_from("ence")) - { - return false; - } - break; - case 3: - if (!base.slice_from("ance")) - { - return false; - } - break; - case 4: - if (!base.slice_from("able")) - { - return false; - } - break; - case 5: - if (!base.slice_from("ent")) - { - return false; - } - break; - case 6: - if (!base.slice_from("e")) - { - return false; - } - break; - case 7: - if (!base.slice_from("ize")) - { - return false; - } - break; - case 8: - if (!base.slice_from("ate")) - { - return false; - } - break; - case 9: - if (!base.slice_from("al")) - { - return false; - } - break; - case 10: - if (!base.slice_from("ful")) - { - return false; - } - break; - case 11: - if (!base.slice_from("ous")) - { - return false; - } - break; - case 12: - if (!base.slice_from("ive")) - { - return false; - } - break; - case 13: - if (!base.slice_from("ble")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_3() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("al")) - { - return false; - } - break; - case 2: - if (!base.slice_from("ic")) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_4() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R2()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("s"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("t"))) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_5a() { - base.ket = base.cursor; - if (!(base.eq_s_b("e"))) - { - return false; - } - base.bra = base.cursor; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!r_R2()) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!r_R1()) - { - return false; - } - { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - if (!r_shortv()) - { - break lab2; - } - return false; - } - base.cursor = base.limit - v_2; - } - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_5b() { - base.ket = base.cursor; - if (!(base.eq_s_b("l"))) - { - return false; - } - base.bra = base.cursor; - if (!r_R2()) - { - return false; - } - if (!(base.eq_s_b("l"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - B_Y_found = false; - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - if (!(base.eq_s("y"))) - { - break lab0; - } - base.ket = base.cursor; - if (!base.slice_from("Y")) - { - return false; - } - B_Y_found = true; - } - base.cursor = v_1; - var /** number */ v_2 = base.cursor; - lab1: { - while(true) - { - var /** number */ v_3 = base.cursor; - lab2: { - golab3: while(true) - { - var /** number */ v_4 = base.cursor; - lab4: { - if (!(base.in_grouping(g_v, 97, 121))) - { - break lab4; - } - base.bra = base.cursor; - if (!(base.eq_s("y"))) - { - break lab4; - } - base.ket = base.cursor; - base.cursor = v_4; - break golab3; - } - base.cursor = v_4; - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - if (!base.slice_from("Y")) - { - return false; - } - B_Y_found = true; - continue; - } - base.cursor = v_3; - break; - } - } - base.cursor = v_2; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_5 = base.cursor; - lab5: { - golab6: while(true) - { - lab7: { - if (!(base.in_grouping(g_v, 97, 121))) - { - break lab7; - } - break golab6; - } - if (base.cursor >= base.limit) - { - break lab5; - } - base.cursor++; - } - golab8: while(true) - { - lab9: { - if (!(base.out_grouping(g_v, 97, 121))) - { - break lab9; - } - break golab8; - } - if (base.cursor >= base.limit) - { - break lab5; - } - base.cursor++; - } - I_p1 = base.cursor; - golab10: while(true) - { - lab11: { - if (!(base.in_grouping(g_v, 97, 121))) - { - break lab11; - } - break golab10; - } - if (base.cursor >= base.limit) - { - break lab5; - } - base.cursor++; - } - golab12: while(true) - { - lab13: { - if (!(base.out_grouping(g_v, 97, 121))) - { - break lab13; - } - break golab12; - } - if (base.cursor >= base.limit) - { - break lab5; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_5; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_10 = base.limit - base.cursor; - r_Step_1a(); - base.cursor = base.limit - v_10; - var /** number */ v_11 = base.limit - base.cursor; - r_Step_1b(); - base.cursor = base.limit - v_11; - var /** number */ v_12 = base.limit - base.cursor; - r_Step_1c(); - base.cursor = base.limit - v_12; - var /** number */ v_13 = base.limit - base.cursor; - r_Step_2(); - base.cursor = base.limit - v_13; - var /** number */ v_14 = base.limit - base.cursor; - r_Step_3(); - base.cursor = base.limit - v_14; - var /** number */ v_15 = base.limit - base.cursor; - r_Step_4(); - base.cursor = base.limit - v_15; - var /** number */ v_16 = base.limit - base.cursor; - r_Step_5a(); - base.cursor = base.limit - v_16; - var /** number */ v_17 = base.limit - base.cursor; - r_Step_5b(); - base.cursor = base.limit - v_17; - base.cursor = base.limit_backward; - var /** number */ v_18 = base.cursor; - lab14: { - if (!B_Y_found) - { - break lab14; - } - while(true) - { - var /** number */ v_19 = base.cursor; - lab15: { - golab16: while(true) - { - var /** number */ v_20 = base.cursor; - lab17: { - base.bra = base.cursor; - if (!(base.eq_s("Y"))) - { - break lab17; - } - base.ket = base.cursor; - base.cursor = v_20; - break golab16; - } - base.cursor = v_20; - if (base.cursor >= base.limit) - { - break lab15; - } - base.cursor++; - } - if (!base.slice_from("y")) - { - return false; - } - continue; - } - base.cursor = v_19; - break; - } - } - base.cursor = v_18; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['PorterStemmer'] = PorterStemmer; diff --git a/js/portuguese-stemmer.js b/js/portuguese-stemmer.js deleted file mode 100644 index ef5bcfc..0000000 --- a/js/portuguese-stemmer.js +++ /dev/null @@ -1,896 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var PortugueseStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 3], - ["\u00E3", 0, 1], - ["\u00F5", 0, 2] - ]; - - /** @const */ var a_1 = [ - ["", -1, 3], - ["a~", 0, 1], - ["o~", 0, 2] - ]; - - /** @const */ var a_2 = [ - ["ic", -1, -1], - ["ad", -1, -1], - ["os", -1, -1], - ["iv", -1, 1] - ]; - - /** @const */ var a_3 = [ - ["ante", -1, 1], - ["avel", -1, 1], - ["\u00EDvel", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["ic", -1, 1], - ["abil", -1, 1], - ["iv", -1, 1] - ]; - - /** @const */ var a_5 = [ - ["ica", -1, 1], - ["\u00E2ncia", -1, 1], - ["\u00EAncia", -1, 4], - ["logia", -1, 2], - ["ira", -1, 9], - ["adora", -1, 1], - ["osa", -1, 1], - ["ista", -1, 1], - ["iva", -1, 8], - ["eza", -1, 1], - ["idade", -1, 7], - ["ante", -1, 1], - ["mente", -1, 6], - ["amente", 12, 5], - ["\u00E1vel", -1, 1], - ["\u00EDvel", -1, 1], - ["ico", -1, 1], - ["ismo", -1, 1], - ["oso", -1, 1], - ["amento", -1, 1], - ["imento", -1, 1], - ["ivo", -1, 8], - ["a\u00E7a~o", -1, 1], - ["u\u00E7a~o", -1, 3], - ["ador", -1, 1], - ["icas", -1, 1], - ["\u00EAncias", -1, 4], - ["logias", -1, 2], - ["iras", -1, 9], - ["adoras", -1, 1], - ["osas", -1, 1], - ["istas", -1, 1], - ["ivas", -1, 8], - ["ezas", -1, 1], - ["idades", -1, 7], - ["adores", -1, 1], - ["antes", -1, 1], - ["a\u00E7o~es", -1, 1], - ["u\u00E7o~es", -1, 3], - ["icos", -1, 1], - ["ismos", -1, 1], - ["osos", -1, 1], - ["amentos", -1, 1], - ["imentos", -1, 1], - ["ivos", -1, 8] - ]; - - /** @const */ var a_6 = [ - ["ada", -1, 1], - ["ida", -1, 1], - ["ia", -1, 1], - ["aria", 2, 1], - ["eria", 2, 1], - ["iria", 2, 1], - ["ara", -1, 1], - ["era", -1, 1], - ["ira", -1, 1], - ["ava", -1, 1], - ["asse", -1, 1], - ["esse", -1, 1], - ["isse", -1, 1], - ["aste", -1, 1], - ["este", -1, 1], - ["iste", -1, 1], - ["ei", -1, 1], - ["arei", 16, 1], - ["erei", 16, 1], - ["irei", 16, 1], - ["am", -1, 1], - ["iam", 20, 1], - ["ariam", 21, 1], - ["eriam", 21, 1], - ["iriam", 21, 1], - ["aram", 20, 1], - ["eram", 20, 1], - ["iram", 20, 1], - ["avam", 20, 1], - ["em", -1, 1], - ["arem", 29, 1], - ["erem", 29, 1], - ["irem", 29, 1], - ["assem", 29, 1], - ["essem", 29, 1], - ["issem", 29, 1], - ["ado", -1, 1], - ["ido", -1, 1], - ["ando", -1, 1], - ["endo", -1, 1], - ["indo", -1, 1], - ["ara~o", -1, 1], - ["era~o", -1, 1], - ["ira~o", -1, 1], - ["ar", -1, 1], - ["er", -1, 1], - ["ir", -1, 1], - ["as", -1, 1], - ["adas", 47, 1], - ["idas", 47, 1], - ["ias", 47, 1], - ["arias", 50, 1], - ["erias", 50, 1], - ["irias", 50, 1], - ["aras", 47, 1], - ["eras", 47, 1], - ["iras", 47, 1], - ["avas", 47, 1], - ["es", -1, 1], - ["ardes", 58, 1], - ["erdes", 58, 1], - ["irdes", 58, 1], - ["ares", 58, 1], - ["eres", 58, 1], - ["ires", 58, 1], - ["asses", 58, 1], - ["esses", 58, 1], - ["isses", 58, 1], - ["astes", 58, 1], - ["estes", 58, 1], - ["istes", 58, 1], - ["is", -1, 1], - ["ais", 71, 1], - ["eis", 71, 1], - ["areis", 73, 1], - ["ereis", 73, 1], - ["ireis", 73, 1], - ["\u00E1reis", 73, 1], - ["\u00E9reis", 73, 1], - ["\u00EDreis", 73, 1], - ["\u00E1sseis", 73, 1], - ["\u00E9sseis", 73, 1], - ["\u00EDsseis", 73, 1], - ["\u00E1veis", 73, 1], - ["\u00EDeis", 73, 1], - ["ar\u00EDeis", 84, 1], - ["er\u00EDeis", 84, 1], - ["ir\u00EDeis", 84, 1], - ["ados", -1, 1], - ["idos", -1, 1], - ["amos", -1, 1], - ["\u00E1ramos", 90, 1], - ["\u00E9ramos", 90, 1], - ["\u00EDramos", 90, 1], - ["\u00E1vamos", 90, 1], - ["\u00EDamos", 90, 1], - ["ar\u00EDamos", 95, 1], - ["er\u00EDamos", 95, 1], - ["ir\u00EDamos", 95, 1], - ["emos", -1, 1], - ["aremos", 99, 1], - ["eremos", 99, 1], - ["iremos", 99, 1], - ["\u00E1ssemos", 99, 1], - ["\u00EAssemos", 99, 1], - ["\u00EDssemos", 99, 1], - ["imos", -1, 1], - ["armos", -1, 1], - ["ermos", -1, 1], - ["irmos", -1, 1], - ["\u00E1mos", -1, 1], - ["ar\u00E1s", -1, 1], - ["er\u00E1s", -1, 1], - ["ir\u00E1s", -1, 1], - ["eu", -1, 1], - ["iu", -1, 1], - ["ou", -1, 1], - ["ar\u00E1", -1, 1], - ["er\u00E1", -1, 1], - ["ir\u00E1", -1, 1] - ]; - - /** @const */ var a_7 = [ - ["a", -1, 1], - ["i", -1, 1], - ["o", -1, 1], - ["os", -1, 1], - ["\u00E1", -1, 1], - ["\u00ED", -1, 1], - ["\u00F3", -1, 1] - ]; - - /** @const */ var a_8 = [ - ["e", -1, 1], - ["\u00E7", -1, 2], - ["\u00E9", -1, 1], - ["\u00EA", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 19, 12, 2]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_prelude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("a~")) - { - return false; - } - break; - case 2: - if (!base.slice_from("o~")) - { - return false; - } - break; - case 3: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab2; - } - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab4; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab4; - } - base.cursor++; - } - break lab3; - } - base.cursor = v_3; - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab2; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - } - break lab1; - } - base.cursor = v_2; - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab0; - } - lab9: { - var /** number */ v_6 = base.cursor; - lab10: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab10; - } - golab11: while(true) - { - lab12: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab12; - } - break golab11; - } - if (base.cursor >= base.limit) - { - break lab10; - } - base.cursor++; - } - break lab9; - } - base.cursor = v_6; - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab0; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_pV = base.cursor; - } - base.cursor = v_1; - var /** number */ v_8 = base.cursor; - lab13: { - golab14: while(true) - { - lab15: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab15; - } - break golab14; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab16: while(true) - { - lab17: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab17; - } - break golab16; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p1 = base.cursor; - golab18: while(true) - { - lab19: { - if (!(base.in_grouping(g_v, 97, 250))) - { - break lab19; - } - break golab18; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab20: while(true) - { - lab21: { - if (!(base.out_grouping(g_v, 97, 250))) - { - break lab21; - } - break golab20; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_8; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_1); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u00E3")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u00F5")) - { - return false; - } - break; - case 3: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("log")) - { - return false; - } - break; - case 3: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("u")) - { - return false; - } - break; - case 4: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("ente")) - { - return false; - } - break; - case 5: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - switch (among_var) { - case 1: - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - break; - case 6: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 7: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - if (base.find_among_b(a_4) == 0) - { - base.cursor = base.limit - v_3; - break lab2; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_3; - break lab2; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 8: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_4; - break lab3; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_4; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 9: - if (!r_RV()) - { - return false; - } - if (!(base.eq_s_b("e"))) - { - return false; - } - if (!base.slice_from("ir")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_verb_suffix() { - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - if (base.find_among_b(a_6) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.limit_backward = v_2; - return true; - }; - - /** @return {boolean} */ - function r_residual_suffix() { - base.ket = base.cursor; - if (base.find_among_b(a_7) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_residual_form() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_8); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("u"))) - { - break lab1; - } - base.bra = base.cursor; - var /** number */ v_2 = base.limit - base.cursor; - if (!(base.eq_s_b("g"))) - { - break lab1; - } - base.cursor = base.limit - v_2; - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("i"))) - { - return false; - } - base.bra = base.cursor; - var /** number */ v_3 = base.limit - base.cursor; - if (!(base.eq_s_b("c"))) - { - return false; - } - base.cursor = base.limit - v_3; - } - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("c")) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_prelude(); - base.cursor = v_1; - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - var /** number */ v_5 = base.limit - base.cursor; - lab3: { - var /** number */ v_6 = base.limit - base.cursor; - lab4: { - if (!r_standard_suffix()) - { - break lab4; - } - break lab3; - } - base.cursor = base.limit - v_6; - if (!r_verb_suffix()) - { - break lab2; - } - } - base.cursor = base.limit - v_5; - var /** number */ v_7 = base.limit - base.cursor; - lab5: { - base.ket = base.cursor; - if (!(base.eq_s_b("i"))) - { - break lab5; - } - base.bra = base.cursor; - var /** number */ v_8 = base.limit - base.cursor; - if (!(base.eq_s_b("c"))) - { - break lab5; - } - base.cursor = base.limit - v_8; - if (!r_RV()) - { - break lab5; - } - if (!base.slice_del()) - { - return false; - } - } - base.cursor = base.limit - v_7; - break lab1; - } - base.cursor = base.limit - v_4; - if (!r_residual_suffix()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_3; - var /** number */ v_9 = base.limit - base.cursor; - r_residual_form(); - base.cursor = base.limit - v_9; - base.cursor = base.limit_backward; - var /** number */ v_10 = base.cursor; - r_postlude(); - base.cursor = v_10; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['PortugueseStemmer'] = PortugueseStemmer; diff --git a/js/romanian-stemmer.js b/js/romanian-stemmer.js deleted file mode 100644 index 995e3b6..0000000 --- a/js/romanian-stemmer.js +++ /dev/null @@ -1,918 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var RomanianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u015F", -1, 1], - ["\u0163", -1, 2] - ]; - - /** @const */ var a_1 = [ - ["", -1, 3], - ["I", 0, 1], - ["U", 0, 2] - ]; - - /** @const */ var a_2 = [ - ["ea", -1, 3], - ["a\u021Bia", -1, 7], - ["aua", -1, 2], - ["iua", -1, 4], - ["a\u021Bie", -1, 7], - ["ele", -1, 3], - ["ile", -1, 5], - ["iile", 6, 4], - ["iei", -1, 4], - ["atei", -1, 6], - ["ii", -1, 4], - ["ului", -1, 1], - ["ul", -1, 1], - ["elor", -1, 3], - ["ilor", -1, 4], - ["iilor", 14, 4] - ]; - - /** @const */ var a_3 = [ - ["icala", -1, 4], - ["iciva", -1, 4], - ["ativa", -1, 5], - ["itiva", -1, 6], - ["icale", -1, 4], - ["a\u021Biune", -1, 5], - ["i\u021Biune", -1, 6], - ["atoare", -1, 5], - ["itoare", -1, 6], - ["\u0103toare", -1, 5], - ["icitate", -1, 4], - ["abilitate", -1, 1], - ["ibilitate", -1, 2], - ["ivitate", -1, 3], - ["icive", -1, 4], - ["ative", -1, 5], - ["itive", -1, 6], - ["icali", -1, 4], - ["atori", -1, 5], - ["icatori", 18, 4], - ["itori", -1, 6], - ["\u0103tori", -1, 5], - ["icitati", -1, 4], - ["abilitati", -1, 1], - ["ivitati", -1, 3], - ["icivi", -1, 4], - ["ativi", -1, 5], - ["itivi", -1, 6], - ["icit\u0103i", -1, 4], - ["abilit\u0103i", -1, 1], - ["ivit\u0103i", -1, 3], - ["icit\u0103\u021Bi", -1, 4], - ["abilit\u0103\u021Bi", -1, 1], - ["ivit\u0103\u021Bi", -1, 3], - ["ical", -1, 4], - ["ator", -1, 5], - ["icator", 35, 4], - ["itor", -1, 6], - ["\u0103tor", -1, 5], - ["iciv", -1, 4], - ["ativ", -1, 5], - ["itiv", -1, 6], - ["ical\u0103", -1, 4], - ["iciv\u0103", -1, 4], - ["ativ\u0103", -1, 5], - ["itiv\u0103", -1, 6] - ]; - - /** @const */ var a_4 = [ - ["ica", -1, 1], - ["abila", -1, 1], - ["ibila", -1, 1], - ["oasa", -1, 1], - ["ata", -1, 1], - ["ita", -1, 1], - ["anta", -1, 1], - ["ista", -1, 3], - ["uta", -1, 1], - ["iva", -1, 1], - ["ic", -1, 1], - ["ice", -1, 1], - ["abile", -1, 1], - ["ibile", -1, 1], - ["isme", -1, 3], - ["iune", -1, 2], - ["oase", -1, 1], - ["ate", -1, 1], - ["itate", 17, 1], - ["ite", -1, 1], - ["ante", -1, 1], - ["iste", -1, 3], - ["ute", -1, 1], - ["ive", -1, 1], - ["ici", -1, 1], - ["abili", -1, 1], - ["ibili", -1, 1], - ["iuni", -1, 2], - ["atori", -1, 1], - ["osi", -1, 1], - ["ati", -1, 1], - ["itati", 30, 1], - ["iti", -1, 1], - ["anti", -1, 1], - ["isti", -1, 3], - ["uti", -1, 1], - ["i\u0219ti", -1, 3], - ["ivi", -1, 1], - ["it\u0103i", -1, 1], - ["o\u0219i", -1, 1], - ["it\u0103\u021Bi", -1, 1], - ["abil", -1, 1], - ["ibil", -1, 1], - ["ism", -1, 3], - ["ator", -1, 1], - ["os", -1, 1], - ["at", -1, 1], - ["it", -1, 1], - ["ant", -1, 1], - ["ist", -1, 3], - ["ut", -1, 1], - ["iv", -1, 1], - ["ic\u0103", -1, 1], - ["abil\u0103", -1, 1], - ["ibil\u0103", -1, 1], - ["oas\u0103", -1, 1], - ["at\u0103", -1, 1], - ["it\u0103", -1, 1], - ["ant\u0103", -1, 1], - ["ist\u0103", -1, 3], - ["ut\u0103", -1, 1], - ["iv\u0103", -1, 1] - ]; - - /** @const */ var a_5 = [ - ["ea", -1, 1], - ["ia", -1, 1], - ["esc", -1, 1], - ["\u0103sc", -1, 1], - ["ind", -1, 1], - ["\u00E2nd", -1, 1], - ["are", -1, 1], - ["ere", -1, 1], - ["ire", -1, 1], - ["\u00E2re", -1, 1], - ["se", -1, 2], - ["ase", 10, 1], - ["sese", 10, 2], - ["ise", 10, 1], - ["use", 10, 1], - ["\u00E2se", 10, 1], - ["e\u0219te", -1, 1], - ["\u0103\u0219te", -1, 1], - ["eze", -1, 1], - ["ai", -1, 1], - ["eai", 19, 1], - ["iai", 19, 1], - ["sei", -1, 2], - ["e\u0219ti", -1, 1], - ["\u0103\u0219ti", -1, 1], - ["ui", -1, 1], - ["ezi", -1, 1], - ["\u00E2i", -1, 1], - ["a\u0219i", -1, 1], - ["se\u0219i", -1, 2], - ["ase\u0219i", 29, 1], - ["sese\u0219i", 29, 2], - ["ise\u0219i", 29, 1], - ["use\u0219i", 29, 1], - ["\u00E2se\u0219i", 29, 1], - ["i\u0219i", -1, 1], - ["u\u0219i", -1, 1], - ["\u00E2\u0219i", -1, 1], - ["a\u021Bi", -1, 2], - ["ea\u021Bi", 38, 1], - ["ia\u021Bi", 38, 1], - ["e\u021Bi", -1, 2], - ["i\u021Bi", -1, 2], - ["\u00E2\u021Bi", -1, 2], - ["ar\u0103\u021Bi", -1, 1], - ["ser\u0103\u021Bi", -1, 2], - ["aser\u0103\u021Bi", 45, 1], - ["seser\u0103\u021Bi", 45, 2], - ["iser\u0103\u021Bi", 45, 1], - ["user\u0103\u021Bi", 45, 1], - ["\u00E2ser\u0103\u021Bi", 45, 1], - ["ir\u0103\u021Bi", -1, 1], - ["ur\u0103\u021Bi", -1, 1], - ["\u00E2r\u0103\u021Bi", -1, 1], - ["am", -1, 1], - ["eam", 54, 1], - ["iam", 54, 1], - ["em", -1, 2], - ["asem", 57, 1], - ["sesem", 57, 2], - ["isem", 57, 1], - ["usem", 57, 1], - ["\u00E2sem", 57, 1], - ["im", -1, 2], - ["\u00E2m", -1, 2], - ["\u0103m", -1, 2], - ["ar\u0103m", 65, 1], - ["ser\u0103m", 65, 2], - ["aser\u0103m", 67, 1], - ["seser\u0103m", 67, 2], - ["iser\u0103m", 67, 1], - ["user\u0103m", 67, 1], - ["\u00E2ser\u0103m", 67, 1], - ["ir\u0103m", 65, 1], - ["ur\u0103m", 65, 1], - ["\u00E2r\u0103m", 65, 1], - ["au", -1, 1], - ["eau", 76, 1], - ["iau", 76, 1], - ["indu", -1, 1], - ["\u00E2ndu", -1, 1], - ["ez", -1, 1], - ["easc\u0103", -1, 1], - ["ar\u0103", -1, 1], - ["ser\u0103", -1, 2], - ["aser\u0103", 84, 1], - ["seser\u0103", 84, 2], - ["iser\u0103", 84, 1], - ["user\u0103", 84, 1], - ["\u00E2ser\u0103", 84, 1], - ["ir\u0103", -1, 1], - ["ur\u0103", -1, 1], - ["\u00E2r\u0103", -1, 1], - ["eaz\u0103", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["a", -1, 1], - ["e", -1, 1], - ["ie", 1, 1], - ["i", -1, 1], - ["\u0103", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 32, 0, 0, 4]; - - var /** boolean */ B_standard_suffix_removed = false; - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_norm() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - golab2: while(true) - { - var /** number */ v_3 = base.cursor; - lab3: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - if (among_var == 0) - { - break lab3; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u0219")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u021B")) - { - return false; - } - break; - } - base.cursor = v_3; - break golab2; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_prelude() { - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab2; - } - base.bra = base.cursor; - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.eq_s("u"))) - { - break lab4; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab4; - } - if (!base.slice_from("U")) - { - return false; - } - break lab3; - } - base.cursor = v_3; - if (!(base.eq_s("i"))) - { - break lab2; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab2; - } - if (!base.slice_from("I")) - { - return false; - } - } - base.cursor = v_2; - break golab1; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab2; - } - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.out_grouping(g_v, 97, 259))) - { - break lab4; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab4; - } - base.cursor++; - } - break lab3; - } - base.cursor = v_3; - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab2; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 259))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - } - break lab1; - } - base.cursor = v_2; - if (!(base.out_grouping(g_v, 97, 259))) - { - break lab0; - } - lab9: { - var /** number */ v_6 = base.cursor; - lab10: { - if (!(base.out_grouping(g_v, 97, 259))) - { - break lab10; - } - golab11: while(true) - { - lab12: { - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab12; - } - break golab11; - } - if (base.cursor >= base.limit) - { - break lab10; - } - base.cursor++; - } - break lab9; - } - base.cursor = v_6; - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab0; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_pV = base.cursor; - } - base.cursor = v_1; - var /** number */ v_8 = base.cursor; - lab13: { - golab14: while(true) - { - lab15: { - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab15; - } - break golab14; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab16: while(true) - { - lab17: { - if (!(base.out_grouping(g_v, 97, 259))) - { - break lab17; - } - break golab16; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p1 = base.cursor; - golab18: while(true) - { - lab19: { - if (!(base.in_grouping(g_v, 97, 259))) - { - break lab19; - } - break golab18; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab20: while(true) - { - lab21: { - if (!(base.out_grouping(g_v, 97, 259))) - { - break lab21; - } - break golab20; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_8; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_1); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("i")) - { - return false; - } - break; - case 2: - if (!base.slice_from("u")) - { - return false; - } - break; - case 3: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_step_0() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("a")) - { - return false; - } - break; - case 3: - if (!base.slice_from("e")) - { - return false; - } - break; - case 4: - if (!base.slice_from("i")) - { - return false; - } - break; - case 5: - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("ab"))) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_1; - } - if (!base.slice_from("i")) - { - return false; - } - break; - case 6: - if (!base.slice_from("at")) - { - return false; - } - break; - case 7: - if (!base.slice_from("a\u021Bi")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_combo_suffix() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("abil")) - { - return false; - } - break; - case 2: - if (!base.slice_from("ibil")) - { - return false; - } - break; - case 3: - if (!base.slice_from("iv")) - { - return false; - } - break; - case 4: - if (!base.slice_from("ic")) - { - return false; - } - break; - case 5: - if (!base.slice_from("at")) - { - return false; - } - break; - case 6: - if (!base.slice_from("it")) - { - return false; - } - break; - } - B_standard_suffix_removed = true; - base.cursor = base.limit - v_1; - return true; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - B_standard_suffix_removed = false; - while(true) - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (!r_combo_suffix()) - { - break lab0; - } - continue; - } - base.cursor = base.limit - v_1; - break; - } - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R2()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.eq_s_b("\u021B"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_from("t")) - { - return false; - } - break; - case 3: - if (!base.slice_from("ist")) - { - return false; - } - break; - } - B_standard_suffix_removed = true; - return true; - }; - - /** @return {boolean} */ - function r_verb_suffix() { - var /** number */ among_var; - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - if (!(base.out_grouping_b(g_v, 97, 259))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_3; - if (!(base.eq_s_b("u"))) - { - base.limit_backward = v_2; - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - base.limit_backward = v_2; - return true; - }; - - /** @return {boolean} */ - function r_vowel_suffix() { - base.ket = base.cursor; - if (base.find_among_b(a_6) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_norm(); - var /** number */ v_2 = base.cursor; - r_prelude(); - base.cursor = v_2; - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_4 = base.limit - base.cursor; - r_step_0(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - r_standard_suffix(); - base.cursor = base.limit - v_5; - var /** number */ v_6 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_7 = base.limit - base.cursor; - lab2: { - if (!B_standard_suffix_removed) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_7; - if (!r_verb_suffix()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_6; - var /** number */ v_8 = base.limit - base.cursor; - r_vowel_suffix(); - base.cursor = base.limit - v_8; - base.cursor = base.limit_backward; - var /** number */ v_9 = base.cursor; - r_postlude(); - base.cursor = v_9; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['RomanianStemmer'] = RomanianStemmer; diff --git a/js/russian-stemmer.js b/js/russian-stemmer.js deleted file mode 100644 index 1f2aafb..0000000 --- a/js/russian-stemmer.js +++ /dev/null @@ -1,622 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var RussianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0432", -1, 1], - ["\u0438\u0432", 0, 2], - ["\u044B\u0432", 0, 2], - ["\u0432\u0448\u0438", -1, 1], - ["\u0438\u0432\u0448\u0438", 3, 2], - ["\u044B\u0432\u0448\u0438", 3, 2], - ["\u0432\u0448\u0438\u0441\u044C", -1, 1], - ["\u0438\u0432\u0448\u0438\u0441\u044C", 6, 2], - ["\u044B\u0432\u0448\u0438\u0441\u044C", 6, 2] - ]; - - /** @const */ var a_1 = [ - ["\u0435\u0435", -1, 1], - ["\u0438\u0435", -1, 1], - ["\u043E\u0435", -1, 1], - ["\u044B\u0435", -1, 1], - ["\u0438\u043C\u0438", -1, 1], - ["\u044B\u043C\u0438", -1, 1], - ["\u0435\u0439", -1, 1], - ["\u0438\u0439", -1, 1], - ["\u043E\u0439", -1, 1], - ["\u044B\u0439", -1, 1], - ["\u0435\u043C", -1, 1], - ["\u0438\u043C", -1, 1], - ["\u043E\u043C", -1, 1], - ["\u044B\u043C", -1, 1], - ["\u0435\u0433\u043E", -1, 1], - ["\u043E\u0433\u043E", -1, 1], - ["\u0435\u043C\u0443", -1, 1], - ["\u043E\u043C\u0443", -1, 1], - ["\u0438\u0445", -1, 1], - ["\u044B\u0445", -1, 1], - ["\u0435\u044E", -1, 1], - ["\u043E\u044E", -1, 1], - ["\u0443\u044E", -1, 1], - ["\u044E\u044E", -1, 1], - ["\u0430\u044F", -1, 1], - ["\u044F\u044F", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["\u0435\u043C", -1, 1], - ["\u043D\u043D", -1, 1], - ["\u0432\u0448", -1, 1], - ["\u0438\u0432\u0448", 2, 2], - ["\u044B\u0432\u0448", 2, 2], - ["\u0449", -1, 1], - ["\u044E\u0449", 5, 1], - ["\u0443\u044E\u0449", 6, 2] - ]; - - /** @const */ var a_3 = [ - ["\u0441\u044C", -1, 1], - ["\u0441\u044F", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["\u043B\u0430", -1, 1], - ["\u0438\u043B\u0430", 0, 2], - ["\u044B\u043B\u0430", 0, 2], - ["\u043D\u0430", -1, 1], - ["\u0435\u043D\u0430", 3, 2], - ["\u0435\u0442\u0435", -1, 1], - ["\u0438\u0442\u0435", -1, 2], - ["\u0439\u0442\u0435", -1, 1], - ["\u0435\u0439\u0442\u0435", 7, 2], - ["\u0443\u0439\u0442\u0435", 7, 2], - ["\u043B\u0438", -1, 1], - ["\u0438\u043B\u0438", 10, 2], - ["\u044B\u043B\u0438", 10, 2], - ["\u0439", -1, 1], - ["\u0435\u0439", 13, 2], - ["\u0443\u0439", 13, 2], - ["\u043B", -1, 1], - ["\u0438\u043B", 16, 2], - ["\u044B\u043B", 16, 2], - ["\u0435\u043C", -1, 1], - ["\u0438\u043C", -1, 2], - ["\u044B\u043C", -1, 2], - ["\u043D", -1, 1], - ["\u0435\u043D", 22, 2], - ["\u043B\u043E", -1, 1], - ["\u0438\u043B\u043E", 24, 2], - ["\u044B\u043B\u043E", 24, 2], - ["\u043D\u043E", -1, 1], - ["\u0435\u043D\u043E", 27, 2], - ["\u043D\u043D\u043E", 27, 1], - ["\u0435\u0442", -1, 1], - ["\u0443\u0435\u0442", 30, 2], - ["\u0438\u0442", -1, 2], - ["\u044B\u0442", -1, 2], - ["\u044E\u0442", -1, 1], - ["\u0443\u044E\u0442", 34, 2], - ["\u044F\u0442", -1, 2], - ["\u043D\u044B", -1, 1], - ["\u0435\u043D\u044B", 37, 2], - ["\u0442\u044C", -1, 1], - ["\u0438\u0442\u044C", 39, 2], - ["\u044B\u0442\u044C", 39, 2], - ["\u0435\u0448\u044C", -1, 1], - ["\u0438\u0448\u044C", -1, 2], - ["\u044E", -1, 2], - ["\u0443\u044E", 44, 2] - ]; - - /** @const */ var a_5 = [ - ["\u0430", -1, 1], - ["\u0435\u0432", -1, 1], - ["\u043E\u0432", -1, 1], - ["\u0435", -1, 1], - ["\u0438\u0435", 3, 1], - ["\u044C\u0435", 3, 1], - ["\u0438", -1, 1], - ["\u0435\u0438", 6, 1], - ["\u0438\u0438", 6, 1], - ["\u0430\u043C\u0438", 6, 1], - ["\u044F\u043C\u0438", 6, 1], - ["\u0438\u044F\u043C\u0438", 10, 1], - ["\u0439", -1, 1], - ["\u0435\u0439", 12, 1], - ["\u0438\u0435\u0439", 13, 1], - ["\u0438\u0439", 12, 1], - ["\u043E\u0439", 12, 1], - ["\u0430\u043C", -1, 1], - ["\u0435\u043C", -1, 1], - ["\u0438\u0435\u043C", 18, 1], - ["\u043E\u043C", -1, 1], - ["\u044F\u043C", -1, 1], - ["\u0438\u044F\u043C", 21, 1], - ["\u043E", -1, 1], - ["\u0443", -1, 1], - ["\u0430\u0445", -1, 1], - ["\u044F\u0445", -1, 1], - ["\u0438\u044F\u0445", 26, 1], - ["\u044B", -1, 1], - ["\u044C", -1, 1], - ["\u044E", -1, 1], - ["\u0438\u044E", 30, 1], - ["\u044C\u044E", 30, 1], - ["\u044F", -1, 1], - ["\u0438\u044F", 33, 1], - ["\u044C\u044F", 33, 1] - ]; - - /** @const */ var a_6 = [ - ["\u043E\u0441\u0442", -1, 1], - ["\u043E\u0441\u0442\u044C", -1, 1] - ]; - - /** @const */ var a_7 = [ - ["\u0435\u0439\u0448\u0435", -1, 1], - ["\u043D", -1, 2], - ["\u0435\u0439\u0448", -1, 1], - ["\u044C", -1, 3] - ]; - - /** @const */ var /** Array */ g_v = [33, 65, 8, 232]; - - var /** number */ I_p2 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - lab2: { - if (!(base.in_grouping(g_v, 1072, 1103))) - { - break lab2; - } - break golab1; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_pV = base.cursor; - golab3: while(true) - { - lab4: { - if (!(base.out_grouping(g_v, 1072, 1103))) - { - break lab4; - } - break golab3; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 1072, 1103))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 1072, 1103))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_perfective_gerund() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("\u0430"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("\u044F"))) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_adjective() { - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_adjectival() { - var /** number */ among_var; - if (!r_adjective()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - if (!(base.eq_s_b("\u0430"))) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_2; - if (!(base.eq_s_b("\u044F"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - } - return true; - }; - - /** @return {boolean} */ - function r_reflexive() { - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_verb() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("\u0430"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("\u044F"))) - { - return false; - } - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_noun() { - base.ket = base.cursor; - if (base.find_among_b(a_5) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_derivational() { - base.ket = base.cursor; - if (base.find_among_b(a_6) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_tidy_up() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_7); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!(base.eq_s_b("\u043D"))) - { - return false; - } - base.bra = base.cursor; - if (!(base.eq_s_b("\u043D"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.eq_s_b("\u043D"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - golab2: while(true) - { - var /** number */ v_3 = base.cursor; - lab3: { - base.bra = base.cursor; - if (!(base.eq_s("\u0451"))) - { - break lab3; - } - base.ket = base.cursor; - base.cursor = v_3; - break golab2; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - if (!base.slice_from("\u0435")) - { - return false; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_6 = base.limit_backward; - base.limit_backward = I_pV; - var /** number */ v_7 = base.limit - base.cursor; - lab4: { - lab5: { - var /** number */ v_8 = base.limit - base.cursor; - lab6: { - if (!r_perfective_gerund()) - { - break lab6; - } - break lab5; - } - base.cursor = base.limit - v_8; - var /** number */ v_9 = base.limit - base.cursor; - lab7: { - if (!r_reflexive()) - { - base.cursor = base.limit - v_9; - break lab7; - } - } - lab8: { - var /** number */ v_10 = base.limit - base.cursor; - lab9: { - if (!r_adjectival()) - { - break lab9; - } - break lab8; - } - base.cursor = base.limit - v_10; - lab10: { - if (!r_verb()) - { - break lab10; - } - break lab8; - } - base.cursor = base.limit - v_10; - if (!r_noun()) - { - break lab4; - } - } - } - } - base.cursor = base.limit - v_7; - var /** number */ v_11 = base.limit - base.cursor; - lab11: { - base.ket = base.cursor; - if (!(base.eq_s_b("\u0438"))) - { - base.cursor = base.limit - v_11; - break lab11; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - var /** number */ v_12 = base.limit - base.cursor; - r_derivational(); - base.cursor = base.limit - v_12; - var /** number */ v_13 = base.limit - base.cursor; - r_tidy_up(); - base.cursor = base.limit - v_13; - base.limit_backward = v_6; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['RussianStemmer'] = RussianStemmer; diff --git a/js/serbian-stemmer.js b/js/serbian-stemmer.js deleted file mode 100644 index f7c8c56..0000000 --- a/js/serbian-stemmer.js +++ /dev/null @@ -1,4557 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var SerbianStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0430", -1, 1], - ["\u0431", -1, 2], - ["\u0432", -1, 3], - ["\u0433", -1, 4], - ["\u0434", -1, 5], - ["\u0435", -1, 7], - ["\u0436", -1, 8], - ["\u0437", -1, 9], - ["\u0438", -1, 10], - ["\u043A", -1, 12], - ["\u043B", -1, 13], - ["\u043C", -1, 15], - ["\u043D", -1, 16], - ["\u043E", -1, 18], - ["\u043F", -1, 19], - ["\u0440", -1, 20], - ["\u0441", -1, 21], - ["\u0442", -1, 22], - ["\u0443", -1, 24], - ["\u0444", -1, 25], - ["\u0445", -1, 26], - ["\u0446", -1, 27], - ["\u0447", -1, 28], - ["\u0448", -1, 30], - ["\u0452", -1, 6], - ["\u0458", -1, 11], - ["\u0459", -1, 14], - ["\u045A", -1, 17], - ["\u045B", -1, 23], - ["\u045F", -1, 29] - ]; - - /** @const */ var a_1 = [ - ["daba", -1, 73], - ["ajaca", -1, 12], - ["ejaca", -1, 14], - ["ljaca", -1, 13], - ["njaca", -1, 85], - ["ojaca", -1, 15], - ["alaca", -1, 82], - ["elaca", -1, 83], - ["olaca", -1, 84], - ["maca", -1, 75], - ["naca", -1, 76], - ["raca", -1, 81], - ["saca", -1, 80], - ["vaca", -1, 79], - ["\u0161aca", -1, 18], - ["aoca", -1, 82], - ["acaka", -1, 55], - ["ajaka", -1, 16], - ["ojaka", -1, 17], - ["anaka", -1, 78], - ["ataka", -1, 58], - ["etaka", -1, 59], - ["itaka", -1, 60], - ["otaka", -1, 61], - ["utaka", -1, 62], - ["a\u010Daka", -1, 54], - ["esama", -1, 67], - ["izama", -1, 87], - ["jacima", -1, 5], - ["nicima", -1, 23], - ["ticima", -1, 24], - ["teticima", 30, 21], - ["zicima", -1, 25], - ["atcima", -1, 58], - ["utcima", -1, 62], - ["\u010Dcima", -1, 74], - ["pesima", -1, 2], - ["inzima", -1, 19], - ["lozima", -1, 1], - ["metara", -1, 68], - ["centara", -1, 69], - ["istara", -1, 70], - ["ekata", -1, 86], - ["anata", -1, 53], - ["nstava", -1, 22], - ["kustava", -1, 29], - ["ajac", -1, 12], - ["ejac", -1, 14], - ["ljac", -1, 13], - ["njac", -1, 85], - ["anjac", 49, 11], - ["ojac", -1, 15], - ["alac", -1, 82], - ["elac", -1, 83], - ["olac", -1, 84], - ["mac", -1, 75], - ["nac", -1, 76], - ["rac", -1, 81], - ["sac", -1, 80], - ["vac", -1, 79], - ["\u0161ac", -1, 18], - ["jebe", -1, 88], - ["olce", -1, 84], - ["kuse", -1, 27], - ["rave", -1, 42], - ["save", -1, 52], - ["\u0161ave", -1, 51], - ["baci", -1, 89], - ["jaci", -1, 5], - ["tvenici", -1, 20], - ["snici", -1, 26], - ["tetici", -1, 21], - ["bojci", -1, 4], - ["vojci", -1, 3], - ["ojsci", -1, 66], - ["atci", -1, 58], - ["itci", -1, 60], - ["utci", -1, 62], - ["\u010Dci", -1, 74], - ["pesi", -1, 2], - ["inzi", -1, 19], - ["lozi", -1, 1], - ["acak", -1, 55], - ["usak", -1, 57], - ["atak", -1, 58], - ["etak", -1, 59], - ["itak", -1, 60], - ["otak", -1, 61], - ["utak", -1, 62], - ["a\u010Dak", -1, 54], - ["u\u0161ak", -1, 56], - ["izam", -1, 87], - ["tican", -1, 65], - ["cajan", -1, 7], - ["\u010Dajan", -1, 6], - ["voljan", -1, 77], - ["eskan", -1, 63], - ["alan", -1, 40], - ["bilan", -1, 33], - ["gilan", -1, 37], - ["nilan", -1, 39], - ["rilan", -1, 38], - ["silan", -1, 36], - ["tilan", -1, 34], - ["avilan", -1, 35], - ["laran", -1, 9], - ["eran", -1, 8], - ["asan", -1, 91], - ["esan", -1, 10], - ["dusan", -1, 31], - ["kusan", -1, 28], - ["atan", -1, 47], - ["pletan", -1, 50], - ["tetan", -1, 49], - ["antan", -1, 32], - ["pravan", -1, 44], - ["stavan", -1, 43], - ["sivan", -1, 46], - ["tivan", -1, 45], - ["ozan", -1, 41], - ["ti\u010Dan", -1, 64], - ["a\u0161an", -1, 90], - ["du\u0161an", -1, 30], - ["metar", -1, 68], - ["centar", -1, 69], - ["istar", -1, 70], - ["ekat", -1, 86], - ["enat", -1, 48], - ["oscu", -1, 72], - ["o\u0161\u0107u", -1, 71] - ]; - - /** @const */ var a_2 = [ - ["aca", -1, 124], - ["eca", -1, 125], - ["uca", -1, 126], - ["ga", -1, 20], - ["acega", 3, 124], - ["ecega", 3, 125], - ["ucega", 3, 126], - ["anjijega", 3, 84], - ["enjijega", 3, 85], - ["snjijega", 3, 122], - ["\u0161njijega", 3, 86], - ["kijega", 3, 95], - ["skijega", 11, 1], - ["\u0161kijega", 11, 2], - ["elijega", 3, 83], - ["nijega", 3, 13], - ["osijega", 3, 123], - ["atijega", 3, 120], - ["evitijega", 3, 92], - ["ovitijega", 3, 93], - ["astijega", 3, 94], - ["avijega", 3, 77], - ["evijega", 3, 78], - ["ivijega", 3, 79], - ["ovijega", 3, 80], - ["o\u0161ijega", 3, 91], - ["anjega", 3, 84], - ["enjega", 3, 85], - ["snjega", 3, 122], - ["\u0161njega", 3, 86], - ["kega", 3, 95], - ["skega", 30, 1], - ["\u0161kega", 30, 2], - ["elega", 3, 83], - ["nega", 3, 13], - ["anega", 34, 10], - ["enega", 34, 87], - ["snega", 34, 159], - ["\u0161nega", 34, 88], - ["osega", 3, 123], - ["atega", 3, 120], - ["evitega", 3, 92], - ["ovitega", 3, 93], - ["astega", 3, 94], - ["avega", 3, 77], - ["evega", 3, 78], - ["ivega", 3, 79], - ["ovega", 3, 80], - ["a\u0107ega", 3, 14], - ["e\u0107ega", 3, 15], - ["u\u0107ega", 3, 16], - ["o\u0161ega", 3, 91], - ["acoga", 3, 124], - ["ecoga", 3, 125], - ["ucoga", 3, 126], - ["anjoga", 3, 84], - ["enjoga", 3, 85], - ["snjoga", 3, 122], - ["\u0161njoga", 3, 86], - ["koga", 3, 95], - ["skoga", 59, 1], - ["\u0161koga", 59, 2], - ["loga", 3, 19], - ["eloga", 62, 83], - ["noga", 3, 13], - ["cinoga", 64, 137], - ["\u010Dinoga", 64, 89], - ["osoga", 3, 123], - ["atoga", 3, 120], - ["evitoga", 3, 92], - ["ovitoga", 3, 93], - ["astoga", 3, 94], - ["avoga", 3, 77], - ["evoga", 3, 78], - ["ivoga", 3, 79], - ["ovoga", 3, 80], - ["a\u0107oga", 3, 14], - ["e\u0107oga", 3, 15], - ["u\u0107oga", 3, 16], - ["o\u0161oga", 3, 91], - ["uga", 3, 18], - ["aja", -1, 109], - ["caja", 81, 26], - ["laja", 81, 30], - ["raja", 81, 31], - ["\u0107aja", 81, 28], - ["\u010Daja", 81, 27], - ["\u0111aja", 81, 29], - ["bija", -1, 32], - ["cija", -1, 33], - ["dija", -1, 34], - ["fija", -1, 40], - ["gija", -1, 39], - ["anjija", -1, 84], - ["enjija", -1, 85], - ["snjija", -1, 122], - ["\u0161njija", -1, 86], - ["kija", -1, 95], - ["skija", 97, 1], - ["\u0161kija", 97, 2], - ["lija", -1, 24], - ["elija", 100, 83], - ["mija", -1, 37], - ["nija", -1, 13], - ["ganija", 103, 9], - ["manija", 103, 6], - ["panija", 103, 7], - ["ranija", 103, 8], - ["tanija", 103, 5], - ["pija", -1, 41], - ["rija", -1, 42], - ["rarija", 110, 21], - ["sija", -1, 23], - ["osija", 112, 123], - ["tija", -1, 44], - ["atija", 114, 120], - ["evitija", 114, 92], - ["ovitija", 114, 93], - ["otija", 114, 22], - ["astija", 114, 94], - ["avija", -1, 77], - ["evija", -1, 78], - ["ivija", -1, 79], - ["ovija", -1, 80], - ["zija", -1, 45], - ["o\u0161ija", -1, 91], - ["\u017Eija", -1, 38], - ["anja", -1, 84], - ["enja", -1, 85], - ["snja", -1, 122], - ["\u0161nja", -1, 86], - ["ka", -1, 95], - ["ska", 131, 1], - ["\u0161ka", 131, 2], - ["ala", -1, 104], - ["acala", 134, 128], - ["astajala", 134, 106], - ["istajala", 134, 107], - ["ostajala", 134, 108], - ["ijala", 134, 47], - ["injala", 134, 114], - ["nala", 134, 46], - ["irala", 134, 100], - ["urala", 134, 105], - ["tala", 134, 113], - ["astala", 144, 110], - ["istala", 144, 111], - ["ostala", 144, 112], - ["avala", 134, 97], - ["evala", 134, 96], - ["ivala", 134, 98], - ["ovala", 134, 76], - ["uvala", 134, 99], - ["a\u010Dala", 134, 102], - ["ela", -1, 83], - ["ila", -1, 116], - ["acila", 155, 124], - ["lucila", 155, 121], - ["nila", 155, 103], - ["astanila", 158, 110], - ["istanila", 158, 111], - ["ostanila", 158, 112], - ["rosila", 155, 127], - ["jetila", 155, 118], - ["ozila", 155, 48], - ["a\u010Dila", 155, 101], - ["lu\u010Dila", 155, 117], - ["ro\u0161ila", 155, 90], - ["ola", -1, 50], - ["asla", -1, 115], - ["nula", -1, 13], - ["gama", -1, 20], - ["logama", 171, 19], - ["ugama", 171, 18], - ["ajama", -1, 109], - ["cajama", 174, 26], - ["lajama", 174, 30], - ["rajama", 174, 31], - ["\u0107ajama", 174, 28], - ["\u010Dajama", 174, 27], - ["\u0111ajama", 174, 29], - ["bijama", -1, 32], - ["cijama", -1, 33], - ["dijama", -1, 34], - ["fijama", -1, 40], - ["gijama", -1, 39], - ["lijama", -1, 35], - ["mijama", -1, 37], - ["nijama", -1, 36], - ["ganijama", 188, 9], - ["manijama", 188, 6], - ["panijama", 188, 7], - ["ranijama", 188, 8], - ["tanijama", 188, 5], - ["pijama", -1, 41], - ["rijama", -1, 42], - ["sijama", -1, 43], - ["tijama", -1, 44], - ["zijama", -1, 45], - ["\u017Eijama", -1, 38], - ["alama", -1, 104], - ["ijalama", 200, 47], - ["nalama", 200, 46], - ["elama", -1, 119], - ["ilama", -1, 116], - ["ramama", -1, 52], - ["lemama", -1, 51], - ["inama", -1, 11], - ["cinama", 207, 137], - ["\u010Dinama", 207, 89], - ["rama", -1, 52], - ["arama", 210, 53], - ["drama", 210, 54], - ["erama", 210, 55], - ["orama", 210, 56], - ["basama", -1, 135], - ["gasama", -1, 131], - ["jasama", -1, 129], - ["kasama", -1, 133], - ["nasama", -1, 132], - ["tasama", -1, 130], - ["vasama", -1, 134], - ["esama", -1, 152], - ["isama", -1, 154], - ["etama", -1, 70], - ["estama", -1, 71], - ["istama", -1, 72], - ["kstama", -1, 73], - ["ostama", -1, 74], - ["avama", -1, 77], - ["evama", -1, 78], - ["ivama", -1, 79], - ["ba\u0161ama", -1, 63], - ["ga\u0161ama", -1, 64], - ["ja\u0161ama", -1, 61], - ["ka\u0161ama", -1, 62], - ["na\u0161ama", -1, 60], - ["ta\u0161ama", -1, 59], - ["va\u0161ama", -1, 65], - ["e\u0161ama", -1, 66], - ["i\u0161ama", -1, 67], - ["lema", -1, 51], - ["acima", -1, 124], - ["ecima", -1, 125], - ["ucima", -1, 126], - ["ajima", -1, 109], - ["cajima", 245, 26], - ["lajima", 245, 30], - ["rajima", 245, 31], - ["\u0107ajima", 245, 28], - ["\u010Dajima", 245, 27], - ["\u0111ajima", 245, 29], - ["bijima", -1, 32], - ["cijima", -1, 33], - ["dijima", -1, 34], - ["fijima", -1, 40], - ["gijima", -1, 39], - ["anjijima", -1, 84], - ["enjijima", -1, 85], - ["snjijima", -1, 122], - ["\u0161njijima", -1, 86], - ["kijima", -1, 95], - ["skijima", 261, 1], - ["\u0161kijima", 261, 2], - ["lijima", -1, 35], - ["elijima", 264, 83], - ["mijima", -1, 37], - ["nijima", -1, 13], - ["ganijima", 267, 9], - ["manijima", 267, 6], - ["panijima", 267, 7], - ["ranijima", 267, 8], - ["tanijima", 267, 5], - ["pijima", -1, 41], - ["rijima", -1, 42], - ["sijima", -1, 43], - ["osijima", 275, 123], - ["tijima", -1, 44], - ["atijima", 277, 120], - ["evitijima", 277, 92], - ["ovitijima", 277, 93], - ["astijima", 277, 94], - ["avijima", -1, 77], - ["evijima", -1, 78], - ["ivijima", -1, 79], - ["ovijima", -1, 80], - ["zijima", -1, 45], - ["o\u0161ijima", -1, 91], - ["\u017Eijima", -1, 38], - ["anjima", -1, 84], - ["enjima", -1, 85], - ["snjima", -1, 122], - ["\u0161njima", -1, 86], - ["kima", -1, 95], - ["skima", 293, 1], - ["\u0161kima", 293, 2], - ["alima", -1, 104], - ["ijalima", 296, 47], - ["nalima", 296, 46], - ["elima", -1, 83], - ["ilima", -1, 116], - ["ozilima", 300, 48], - ["olima", -1, 50], - ["lemima", -1, 51], - ["nima", -1, 13], - ["anima", 304, 10], - ["inima", 304, 11], - ["cinima", 306, 137], - ["\u010Dinima", 306, 89], - ["onima", 304, 12], - ["arima", -1, 53], - ["drima", -1, 54], - ["erima", -1, 55], - ["orima", -1, 56], - ["basima", -1, 135], - ["gasima", -1, 131], - ["jasima", -1, 129], - ["kasima", -1, 133], - ["nasima", -1, 132], - ["tasima", -1, 130], - ["vasima", -1, 134], - ["esima", -1, 57], - ["isima", -1, 58], - ["osima", -1, 123], - ["atima", -1, 120], - ["ikatima", 324, 68], - ["latima", 324, 69], - ["etima", -1, 70], - ["evitima", -1, 92], - ["ovitima", -1, 93], - ["astima", -1, 94], - ["estima", -1, 71], - ["istima", -1, 72], - ["kstima", -1, 73], - ["ostima", -1, 74], - ["i\u0161tima", -1, 75], - ["avima", -1, 77], - ["evima", -1, 78], - ["ajevima", 337, 109], - ["cajevima", 338, 26], - ["lajevima", 338, 30], - ["rajevima", 338, 31], - ["\u0107ajevima", 338, 28], - ["\u010Dajevima", 338, 27], - ["\u0111ajevima", 338, 29], - ["ivima", -1, 79], - ["ovima", -1, 80], - ["govima", 346, 20], - ["ugovima", 347, 17], - ["lovima", 346, 82], - ["olovima", 349, 49], - ["movima", 346, 81], - ["onovima", 346, 12], - ["stvima", -1, 3], - ["\u0161tvima", -1, 4], - ["a\u0107ima", -1, 14], - ["e\u0107ima", -1, 15], - ["u\u0107ima", -1, 16], - ["ba\u0161ima", -1, 63], - ["ga\u0161ima", -1, 64], - ["ja\u0161ima", -1, 61], - ["ka\u0161ima", -1, 62], - ["na\u0161ima", -1, 60], - ["ta\u0161ima", -1, 59], - ["va\u0161ima", -1, 65], - ["e\u0161ima", -1, 66], - ["i\u0161ima", -1, 67], - ["o\u0161ima", -1, 91], - ["na", -1, 13], - ["ana", 368, 10], - ["acana", 369, 128], - ["urana", 369, 105], - ["tana", 369, 113], - ["avana", 369, 97], - ["evana", 369, 96], - ["ivana", 369, 98], - ["uvana", 369, 99], - ["a\u010Dana", 369, 102], - ["acena", 368, 124], - ["lucena", 368, 121], - ["a\u010Dena", 368, 101], - ["lu\u010Dena", 368, 117], - ["ina", 368, 11], - ["cina", 382, 137], - ["anina", 382, 10], - ["\u010Dina", 382, 89], - ["ona", 368, 12], - ["ara", -1, 53], - ["dra", -1, 54], - ["era", -1, 55], - ["ora", -1, 56], - ["basa", -1, 135], - ["gasa", -1, 131], - ["jasa", -1, 129], - ["kasa", -1, 133], - ["nasa", -1, 132], - ["tasa", -1, 130], - ["vasa", -1, 134], - ["esa", -1, 57], - ["isa", -1, 58], - ["osa", -1, 123], - ["ata", -1, 120], - ["ikata", 401, 68], - ["lata", 401, 69], - ["eta", -1, 70], - ["evita", -1, 92], - ["ovita", -1, 93], - ["asta", -1, 94], - ["esta", -1, 71], - ["ista", -1, 72], - ["ksta", -1, 73], - ["osta", -1, 74], - ["nuta", -1, 13], - ["i\u0161ta", -1, 75], - ["ava", -1, 77], - ["eva", -1, 78], - ["ajeva", 415, 109], - ["cajeva", 416, 26], - ["lajeva", 416, 30], - ["rajeva", 416, 31], - ["\u0107ajeva", 416, 28], - ["\u010Dajeva", 416, 27], - ["\u0111ajeva", 416, 29], - ["iva", -1, 79], - ["ova", -1, 80], - ["gova", 424, 20], - ["ugova", 425, 17], - ["lova", 424, 82], - ["olova", 427, 49], - ["mova", 424, 81], - ["onova", 424, 12], - ["stva", -1, 3], - ["\u0161tva", -1, 4], - ["a\u0107a", -1, 14], - ["e\u0107a", -1, 15], - ["u\u0107a", -1, 16], - ["ba\u0161a", -1, 63], - ["ga\u0161a", -1, 64], - ["ja\u0161a", -1, 61], - ["ka\u0161a", -1, 62], - ["na\u0161a", -1, 60], - ["ta\u0161a", -1, 59], - ["va\u0161a", -1, 65], - ["e\u0161a", -1, 66], - ["i\u0161a", -1, 67], - ["o\u0161a", -1, 91], - ["ace", -1, 124], - ["ece", -1, 125], - ["uce", -1, 126], - ["luce", 448, 121], - ["astade", -1, 110], - ["istade", -1, 111], - ["ostade", -1, 112], - ["ge", -1, 20], - ["loge", 453, 19], - ["uge", 453, 18], - ["aje", -1, 104], - ["caje", 456, 26], - ["laje", 456, 30], - ["raje", 456, 31], - ["astaje", 456, 106], - ["istaje", 456, 107], - ["ostaje", 456, 108], - ["\u0107aje", 456, 28], - ["\u010Daje", 456, 27], - ["\u0111aje", 456, 29], - ["ije", -1, 116], - ["bije", 466, 32], - ["cije", 466, 33], - ["dije", 466, 34], - ["fije", 466, 40], - ["gije", 466, 39], - ["anjije", 466, 84], - ["enjije", 466, 85], - ["snjije", 466, 122], - ["\u0161njije", 466, 86], - ["kije", 466, 95], - ["skije", 476, 1], - ["\u0161kije", 476, 2], - ["lije", 466, 35], - ["elije", 479, 83], - ["mije", 466, 37], - ["nije", 466, 13], - ["ganije", 482, 9], - ["manije", 482, 6], - ["panije", 482, 7], - ["ranije", 482, 8], - ["tanije", 482, 5], - ["pije", 466, 41], - ["rije", 466, 42], - ["sije", 466, 43], - ["osije", 490, 123], - ["tije", 466, 44], - ["atije", 492, 120], - ["evitije", 492, 92], - ["ovitije", 492, 93], - ["astije", 492, 94], - ["avije", 466, 77], - ["evije", 466, 78], - ["ivije", 466, 79], - ["ovije", 466, 80], - ["zije", 466, 45], - ["o\u0161ije", 466, 91], - ["\u017Eije", 466, 38], - ["anje", -1, 84], - ["enje", -1, 85], - ["snje", -1, 122], - ["\u0161nje", -1, 86], - ["uje", -1, 25], - ["lucuje", 508, 121], - ["iruje", 508, 100], - ["lu\u010Duje", 508, 117], - ["ke", -1, 95], - ["ske", 512, 1], - ["\u0161ke", 512, 2], - ["ale", -1, 104], - ["acale", 515, 128], - ["astajale", 515, 106], - ["istajale", 515, 107], - ["ostajale", 515, 108], - ["ijale", 515, 47], - ["injale", 515, 114], - ["nale", 515, 46], - ["irale", 515, 100], - ["urale", 515, 105], - ["tale", 515, 113], - ["astale", 525, 110], - ["istale", 525, 111], - ["ostale", 525, 112], - ["avale", 515, 97], - ["evale", 515, 96], - ["ivale", 515, 98], - ["ovale", 515, 76], - ["uvale", 515, 99], - ["a\u010Dale", 515, 102], - ["ele", -1, 83], - ["ile", -1, 116], - ["acile", 536, 124], - ["lucile", 536, 121], - ["nile", 536, 103], - ["rosile", 536, 127], - ["jetile", 536, 118], - ["ozile", 536, 48], - ["a\u010Dile", 536, 101], - ["lu\u010Dile", 536, 117], - ["ro\u0161ile", 536, 90], - ["ole", -1, 50], - ["asle", -1, 115], - ["nule", -1, 13], - ["rame", -1, 52], - ["leme", -1, 51], - ["acome", -1, 124], - ["ecome", -1, 125], - ["ucome", -1, 126], - ["anjome", -1, 84], - ["enjome", -1, 85], - ["snjome", -1, 122], - ["\u0161njome", -1, 86], - ["kome", -1, 95], - ["skome", 558, 1], - ["\u0161kome", 558, 2], - ["elome", -1, 83], - ["nome", -1, 13], - ["cinome", 562, 137], - ["\u010Dinome", 562, 89], - ["osome", -1, 123], - ["atome", -1, 120], - ["evitome", -1, 92], - ["ovitome", -1, 93], - ["astome", -1, 94], - ["avome", -1, 77], - ["evome", -1, 78], - ["ivome", -1, 79], - ["ovome", -1, 80], - ["a\u0107ome", -1, 14], - ["e\u0107ome", -1, 15], - ["u\u0107ome", -1, 16], - ["o\u0161ome", -1, 91], - ["ne", -1, 13], - ["ane", 578, 10], - ["acane", 579, 128], - ["urane", 579, 105], - ["tane", 579, 113], - ["astane", 582, 110], - ["istane", 582, 111], - ["ostane", 582, 112], - ["avane", 579, 97], - ["evane", 579, 96], - ["ivane", 579, 98], - ["uvane", 579, 99], - ["a\u010Dane", 579, 102], - ["acene", 578, 124], - ["lucene", 578, 121], - ["a\u010Dene", 578, 101], - ["lu\u010Dene", 578, 117], - ["ine", 578, 11], - ["cine", 595, 137], - ["anine", 595, 10], - ["\u010Dine", 595, 89], - ["one", 578, 12], - ["are", -1, 53], - ["dre", -1, 54], - ["ere", -1, 55], - ["ore", -1, 56], - ["ase", -1, 161], - ["base", 604, 135], - ["acase", 604, 128], - ["gase", 604, 131], - ["jase", 604, 129], - ["astajase", 608, 138], - ["istajase", 608, 139], - ["ostajase", 608, 140], - ["injase", 608, 150], - ["kase", 604, 133], - ["nase", 604, 132], - ["irase", 604, 155], - ["urase", 604, 156], - ["tase", 604, 130], - ["vase", 604, 134], - ["avase", 618, 144], - ["evase", 618, 145], - ["ivase", 618, 146], - ["ovase", 618, 148], - ["uvase", 618, 147], - ["ese", -1, 57], - ["ise", -1, 58], - ["acise", 625, 124], - ["lucise", 625, 121], - ["rosise", 625, 127], - ["jetise", 625, 149], - ["ose", -1, 123], - ["astadose", 630, 141], - ["istadose", 630, 142], - ["ostadose", 630, 143], - ["ate", -1, 104], - ["acate", 634, 128], - ["ikate", 634, 68], - ["late", 634, 69], - ["irate", 634, 100], - ["urate", 634, 105], - ["tate", 634, 113], - ["avate", 634, 97], - ["evate", 634, 96], - ["ivate", 634, 98], - ["uvate", 634, 99], - ["a\u010Date", 634, 102], - ["ete", -1, 70], - ["astadete", 646, 110], - ["istadete", 646, 111], - ["ostadete", 646, 112], - ["astajete", 646, 106], - ["istajete", 646, 107], - ["ostajete", 646, 108], - ["ijete", 646, 116], - ["injete", 646, 114], - ["ujete", 646, 25], - ["lucujete", 655, 121], - ["irujete", 655, 100], - ["lu\u010Dujete", 655, 117], - ["nete", 646, 13], - ["astanete", 659, 110], - ["istanete", 659, 111], - ["ostanete", 659, 112], - ["astete", 646, 115], - ["ite", -1, 116], - ["acite", 664, 124], - ["lucite", 664, 121], - ["nite", 664, 13], - ["astanite", 667, 110], - ["istanite", 667, 111], - ["ostanite", 667, 112], - ["rosite", 664, 127], - ["jetite", 664, 118], - ["astite", 664, 115], - ["evite", 664, 92], - ["ovite", 664, 93], - ["a\u010Dite", 664, 101], - ["lu\u010Dite", 664, 117], - ["ro\u0161ite", 664, 90], - ["ajte", -1, 104], - ["urajte", 679, 105], - ["tajte", 679, 113], - ["astajte", 681, 106], - ["istajte", 681, 107], - ["ostajte", 681, 108], - ["avajte", 679, 97], - ["evajte", 679, 96], - ["ivajte", 679, 98], - ["uvajte", 679, 99], - ["ijte", -1, 116], - ["lucujte", -1, 121], - ["irujte", -1, 100], - ["lu\u010Dujte", -1, 117], - ["aste", -1, 94], - ["acaste", 693, 128], - ["astajaste", 693, 106], - ["istajaste", 693, 107], - ["ostajaste", 693, 108], - ["injaste", 693, 114], - ["iraste", 693, 100], - ["uraste", 693, 105], - ["taste", 693, 113], - ["avaste", 693, 97], - ["evaste", 693, 96], - ["ivaste", 693, 98], - ["ovaste", 693, 76], - ["uvaste", 693, 99], - ["a\u010Daste", 693, 102], - ["este", -1, 71], - ["iste", -1, 72], - ["aciste", 709, 124], - ["luciste", 709, 121], - ["niste", 709, 103], - ["rosiste", 709, 127], - ["jetiste", 709, 118], - ["a\u010Diste", 709, 101], - ["lu\u010Diste", 709, 117], - ["ro\u0161iste", 709, 90], - ["kste", -1, 73], - ["oste", -1, 74], - ["astadoste", 719, 110], - ["istadoste", 719, 111], - ["ostadoste", 719, 112], - ["nuste", -1, 13], - ["i\u0161te", -1, 75], - ["ave", -1, 77], - ["eve", -1, 78], - ["ajeve", 726, 109], - ["cajeve", 727, 26], - ["lajeve", 727, 30], - ["rajeve", 727, 31], - ["\u0107ajeve", 727, 28], - ["\u010Dajeve", 727, 27], - ["\u0111ajeve", 727, 29], - ["ive", -1, 79], - ["ove", -1, 80], - ["gove", 735, 20], - ["ugove", 736, 17], - ["love", 735, 82], - ["olove", 738, 49], - ["move", 735, 81], - ["onove", 735, 12], - ["a\u0107e", -1, 14], - ["e\u0107e", -1, 15], - ["u\u0107e", -1, 16], - ["a\u010De", -1, 101], - ["lu\u010De", -1, 117], - ["a\u0161e", -1, 104], - ["ba\u0161e", 747, 63], - ["ga\u0161e", 747, 64], - ["ja\u0161e", 747, 61], - ["astaja\u0161e", 750, 106], - ["istaja\u0161e", 750, 107], - ["ostaja\u0161e", 750, 108], - ["inja\u0161e", 750, 114], - ["ka\u0161e", 747, 62], - ["na\u0161e", 747, 60], - ["ira\u0161e", 747, 100], - ["ura\u0161e", 747, 105], - ["ta\u0161e", 747, 59], - ["va\u0161e", 747, 65], - ["ava\u0161e", 760, 97], - ["eva\u0161e", 760, 96], - ["iva\u0161e", 760, 98], - ["ova\u0161e", 760, 76], - ["uva\u0161e", 760, 99], - ["a\u010Da\u0161e", 747, 102], - ["e\u0161e", -1, 66], - ["i\u0161e", -1, 67], - ["jeti\u0161e", 768, 118], - ["a\u010Di\u0161e", 768, 101], - ["lu\u010Di\u0161e", 768, 117], - ["ro\u0161i\u0161e", 768, 90], - ["o\u0161e", -1, 91], - ["astado\u0161e", 773, 110], - ["istado\u0161e", 773, 111], - ["ostado\u0161e", 773, 112], - ["aceg", -1, 124], - ["eceg", -1, 125], - ["uceg", -1, 126], - ["anjijeg", -1, 84], - ["enjijeg", -1, 85], - ["snjijeg", -1, 122], - ["\u0161njijeg", -1, 86], - ["kijeg", -1, 95], - ["skijeg", 784, 1], - ["\u0161kijeg", 784, 2], - ["elijeg", -1, 83], - ["nijeg", -1, 13], - ["osijeg", -1, 123], - ["atijeg", -1, 120], - ["evitijeg", -1, 92], - ["ovitijeg", -1, 93], - ["astijeg", -1, 94], - ["avijeg", -1, 77], - ["evijeg", -1, 78], - ["ivijeg", -1, 79], - ["ovijeg", -1, 80], - ["o\u0161ijeg", -1, 91], - ["anjeg", -1, 84], - ["enjeg", -1, 85], - ["snjeg", -1, 122], - ["\u0161njeg", -1, 86], - ["keg", -1, 95], - ["eleg", -1, 83], - ["neg", -1, 13], - ["aneg", 805, 10], - ["eneg", 805, 87], - ["sneg", 805, 159], - ["\u0161neg", 805, 88], - ["oseg", -1, 123], - ["ateg", -1, 120], - ["aveg", -1, 77], - ["eveg", -1, 78], - ["iveg", -1, 79], - ["oveg", -1, 80], - ["a\u0107eg", -1, 14], - ["e\u0107eg", -1, 15], - ["u\u0107eg", -1, 16], - ["o\u0161eg", -1, 91], - ["acog", -1, 124], - ["ecog", -1, 125], - ["ucog", -1, 126], - ["anjog", -1, 84], - ["enjog", -1, 85], - ["snjog", -1, 122], - ["\u0161njog", -1, 86], - ["kog", -1, 95], - ["skog", 827, 1], - ["\u0161kog", 827, 2], - ["elog", -1, 83], - ["nog", -1, 13], - ["cinog", 831, 137], - ["\u010Dinog", 831, 89], - ["osog", -1, 123], - ["atog", -1, 120], - ["evitog", -1, 92], - ["ovitog", -1, 93], - ["astog", -1, 94], - ["avog", -1, 77], - ["evog", -1, 78], - ["ivog", -1, 79], - ["ovog", -1, 80], - ["a\u0107og", -1, 14], - ["e\u0107og", -1, 15], - ["u\u0107og", -1, 16], - ["o\u0161og", -1, 91], - ["ah", -1, 104], - ["acah", 847, 128], - ["astajah", 847, 106], - ["istajah", 847, 107], - ["ostajah", 847, 108], - ["injah", 847, 114], - ["irah", 847, 100], - ["urah", 847, 105], - ["tah", 847, 113], - ["avah", 847, 97], - ["evah", 847, 96], - ["ivah", 847, 98], - ["ovah", 847, 76], - ["uvah", 847, 99], - ["a\u010Dah", 847, 102], - ["ih", -1, 116], - ["acih", 862, 124], - ["ecih", 862, 125], - ["ucih", 862, 126], - ["lucih", 865, 121], - ["anjijih", 862, 84], - ["enjijih", 862, 85], - ["snjijih", 862, 122], - ["\u0161njijih", 862, 86], - ["kijih", 862, 95], - ["skijih", 871, 1], - ["\u0161kijih", 871, 2], - ["elijih", 862, 83], - ["nijih", 862, 13], - ["osijih", 862, 123], - ["atijih", 862, 120], - ["evitijih", 862, 92], - ["ovitijih", 862, 93], - ["astijih", 862, 94], - ["avijih", 862, 77], - ["evijih", 862, 78], - ["ivijih", 862, 79], - ["ovijih", 862, 80], - ["o\u0161ijih", 862, 91], - ["anjih", 862, 84], - ["enjih", 862, 85], - ["snjih", 862, 122], - ["\u0161njih", 862, 86], - ["kih", 862, 95], - ["skih", 890, 1], - ["\u0161kih", 890, 2], - ["elih", 862, 83], - ["nih", 862, 13], - ["cinih", 894, 137], - ["\u010Dinih", 894, 89], - ["osih", 862, 123], - ["rosih", 897, 127], - ["atih", 862, 120], - ["jetih", 862, 118], - ["evitih", 862, 92], - ["ovitih", 862, 93], - ["astih", 862, 94], - ["avih", 862, 77], - ["evih", 862, 78], - ["ivih", 862, 79], - ["ovih", 862, 80], - ["a\u0107ih", 862, 14], - ["e\u0107ih", 862, 15], - ["u\u0107ih", 862, 16], - ["a\u010Dih", 862, 101], - ["lu\u010Dih", 862, 117], - ["o\u0161ih", 862, 91], - ["ro\u0161ih", 913, 90], - ["astadoh", -1, 110], - ["istadoh", -1, 111], - ["ostadoh", -1, 112], - ["acuh", -1, 124], - ["ecuh", -1, 125], - ["ucuh", -1, 126], - ["a\u0107uh", -1, 14], - ["e\u0107uh", -1, 15], - ["u\u0107uh", -1, 16], - ["aci", -1, 124], - ["aceci", -1, 124], - ["ieci", -1, 162], - ["ajuci", -1, 161], - ["irajuci", 927, 155], - ["urajuci", 927, 156], - ["astajuci", 927, 138], - ["istajuci", 927, 139], - ["ostajuci", 927, 140], - ["avajuci", 927, 144], - ["evajuci", 927, 145], - ["ivajuci", 927, 146], - ["uvajuci", 927, 147], - ["ujuci", -1, 157], - ["lucujuci", 937, 121], - ["irujuci", 937, 155], - ["luci", -1, 121], - ["nuci", -1, 164], - ["etuci", -1, 153], - ["astuci", -1, 136], - ["gi", -1, 20], - ["ugi", 944, 18], - ["aji", -1, 109], - ["caji", 946, 26], - ["laji", 946, 30], - ["raji", 946, 31], - ["\u0107aji", 946, 28], - ["\u010Daji", 946, 27], - ["\u0111aji", 946, 29], - ["biji", -1, 32], - ["ciji", -1, 33], - ["diji", -1, 34], - ["fiji", -1, 40], - ["giji", -1, 39], - ["anjiji", -1, 84], - ["enjiji", -1, 85], - ["snjiji", -1, 122], - ["\u0161njiji", -1, 86], - ["kiji", -1, 95], - ["skiji", 962, 1], - ["\u0161kiji", 962, 2], - ["liji", -1, 35], - ["eliji", 965, 83], - ["miji", -1, 37], - ["niji", -1, 13], - ["ganiji", 968, 9], - ["maniji", 968, 6], - ["paniji", 968, 7], - ["raniji", 968, 8], - ["taniji", 968, 5], - ["piji", -1, 41], - ["riji", -1, 42], - ["siji", -1, 43], - ["osiji", 976, 123], - ["tiji", -1, 44], - ["atiji", 978, 120], - ["evitiji", 978, 92], - ["ovitiji", 978, 93], - ["astiji", 978, 94], - ["aviji", -1, 77], - ["eviji", -1, 78], - ["iviji", -1, 79], - ["oviji", -1, 80], - ["ziji", -1, 45], - ["o\u0161iji", -1, 91], - ["\u017Eiji", -1, 38], - ["anji", -1, 84], - ["enji", -1, 85], - ["snji", -1, 122], - ["\u0161nji", -1, 86], - ["ki", -1, 95], - ["ski", 994, 1], - ["\u0161ki", 994, 2], - ["ali", -1, 104], - ["acali", 997, 128], - ["astajali", 997, 106], - ["istajali", 997, 107], - ["ostajali", 997, 108], - ["ijali", 997, 47], - ["injali", 997, 114], - ["nali", 997, 46], - ["irali", 997, 100], - ["urali", 997, 105], - ["tali", 997, 113], - ["astali", 1007, 110], - ["istali", 1007, 111], - ["ostali", 1007, 112], - ["avali", 997, 97], - ["evali", 997, 96], - ["ivali", 997, 98], - ["ovali", 997, 76], - ["uvali", 997, 99], - ["a\u010Dali", 997, 102], - ["eli", -1, 83], - ["ili", -1, 116], - ["acili", 1018, 124], - ["lucili", 1018, 121], - ["nili", 1018, 103], - ["rosili", 1018, 127], - ["jetili", 1018, 118], - ["ozili", 1018, 48], - ["a\u010Dili", 1018, 101], - ["lu\u010Dili", 1018, 117], - ["ro\u0161ili", 1018, 90], - ["oli", -1, 50], - ["asli", -1, 115], - ["nuli", -1, 13], - ["rami", -1, 52], - ["lemi", -1, 51], - ["ni", -1, 13], - ["ani", 1033, 10], - ["acani", 1034, 128], - ["urani", 1034, 105], - ["tani", 1034, 113], - ["avani", 1034, 97], - ["evani", 1034, 96], - ["ivani", 1034, 98], - ["uvani", 1034, 99], - ["a\u010Dani", 1034, 102], - ["aceni", 1033, 124], - ["luceni", 1033, 121], - ["a\u010Deni", 1033, 101], - ["lu\u010Deni", 1033, 117], - ["ini", 1033, 11], - ["cini", 1047, 137], - ["\u010Dini", 1047, 89], - ["oni", 1033, 12], - ["ari", -1, 53], - ["dri", -1, 54], - ["eri", -1, 55], - ["ori", -1, 56], - ["basi", -1, 135], - ["gasi", -1, 131], - ["jasi", -1, 129], - ["kasi", -1, 133], - ["nasi", -1, 132], - ["tasi", -1, 130], - ["vasi", -1, 134], - ["esi", -1, 152], - ["isi", -1, 154], - ["osi", -1, 123], - ["avsi", -1, 161], - ["acavsi", 1065, 128], - ["iravsi", 1065, 155], - ["tavsi", 1065, 160], - ["etavsi", 1068, 153], - ["astavsi", 1068, 141], - ["istavsi", 1068, 142], - ["ostavsi", 1068, 143], - ["ivsi", -1, 162], - ["nivsi", 1073, 158], - ["rosivsi", 1073, 127], - ["nuvsi", -1, 164], - ["ati", -1, 104], - ["acati", 1077, 128], - ["astajati", 1077, 106], - ["istajati", 1077, 107], - ["ostajati", 1077, 108], - ["injati", 1077, 114], - ["ikati", 1077, 68], - ["lati", 1077, 69], - ["irati", 1077, 100], - ["urati", 1077, 105], - ["tati", 1077, 113], - ["astati", 1087, 110], - ["istati", 1087, 111], - ["ostati", 1087, 112], - ["avati", 1077, 97], - ["evati", 1077, 96], - ["ivati", 1077, 98], - ["ovati", 1077, 76], - ["uvati", 1077, 99], - ["a\u010Dati", 1077, 102], - ["eti", -1, 70], - ["iti", -1, 116], - ["aciti", 1098, 124], - ["luciti", 1098, 121], - ["niti", 1098, 103], - ["rositi", 1098, 127], - ["jetiti", 1098, 118], - ["eviti", 1098, 92], - ["oviti", 1098, 93], - ["a\u010Diti", 1098, 101], - ["lu\u010Diti", 1098, 117], - ["ro\u0161iti", 1098, 90], - ["asti", -1, 94], - ["esti", -1, 71], - ["isti", -1, 72], - ["ksti", -1, 73], - ["osti", -1, 74], - ["nuti", -1, 13], - ["avi", -1, 77], - ["evi", -1, 78], - ["ajevi", 1116, 109], - ["cajevi", 1117, 26], - ["lajevi", 1117, 30], - ["rajevi", 1117, 31], - ["\u0107ajevi", 1117, 28], - ["\u010Dajevi", 1117, 27], - ["\u0111ajevi", 1117, 29], - ["ivi", -1, 79], - ["ovi", -1, 80], - ["govi", 1125, 20], - ["ugovi", 1126, 17], - ["lovi", 1125, 82], - ["olovi", 1128, 49], - ["movi", 1125, 81], - ["onovi", 1125, 12], - ["ie\u0107i", -1, 116], - ["a\u010De\u0107i", -1, 101], - ["aju\u0107i", -1, 104], - ["iraju\u0107i", 1134, 100], - ["uraju\u0107i", 1134, 105], - ["astaju\u0107i", 1134, 106], - ["istaju\u0107i", 1134, 107], - ["ostaju\u0107i", 1134, 108], - ["avaju\u0107i", 1134, 97], - ["evaju\u0107i", 1134, 96], - ["ivaju\u0107i", 1134, 98], - ["uvaju\u0107i", 1134, 99], - ["uju\u0107i", -1, 25], - ["iruju\u0107i", 1144, 100], - ["lu\u010Duju\u0107i", 1144, 117], - ["nu\u0107i", -1, 13], - ["etu\u0107i", -1, 70], - ["astu\u0107i", -1, 115], - ["a\u010Di", -1, 101], - ["lu\u010Di", -1, 117], - ["ba\u0161i", -1, 63], - ["ga\u0161i", -1, 64], - ["ja\u0161i", -1, 61], - ["ka\u0161i", -1, 62], - ["na\u0161i", -1, 60], - ["ta\u0161i", -1, 59], - ["va\u0161i", -1, 65], - ["e\u0161i", -1, 66], - ["i\u0161i", -1, 67], - ["o\u0161i", -1, 91], - ["av\u0161i", -1, 104], - ["irav\u0161i", 1162, 100], - ["tav\u0161i", 1162, 113], - ["etav\u0161i", 1164, 70], - ["astav\u0161i", 1164, 110], - ["istav\u0161i", 1164, 111], - ["ostav\u0161i", 1164, 112], - ["a\u010Dav\u0161i", 1162, 102], - ["iv\u0161i", -1, 116], - ["niv\u0161i", 1170, 103], - ["ro\u0161iv\u0161i", 1170, 90], - ["nuv\u0161i", -1, 13], - ["aj", -1, 104], - ["uraj", 1174, 105], - ["taj", 1174, 113], - ["avaj", 1174, 97], - ["evaj", 1174, 96], - ["ivaj", 1174, 98], - ["uvaj", 1174, 99], - ["ij", -1, 116], - ["acoj", -1, 124], - ["ecoj", -1, 125], - ["ucoj", -1, 126], - ["anjijoj", -1, 84], - ["enjijoj", -1, 85], - ["snjijoj", -1, 122], - ["\u0161njijoj", -1, 86], - ["kijoj", -1, 95], - ["skijoj", 1189, 1], - ["\u0161kijoj", 1189, 2], - ["elijoj", -1, 83], - ["nijoj", -1, 13], - ["osijoj", -1, 123], - ["evitijoj", -1, 92], - ["ovitijoj", -1, 93], - ["astijoj", -1, 94], - ["avijoj", -1, 77], - ["evijoj", -1, 78], - ["ivijoj", -1, 79], - ["ovijoj", -1, 80], - ["o\u0161ijoj", -1, 91], - ["anjoj", -1, 84], - ["enjoj", -1, 85], - ["snjoj", -1, 122], - ["\u0161njoj", -1, 86], - ["koj", -1, 95], - ["skoj", 1207, 1], - ["\u0161koj", 1207, 2], - ["aloj", -1, 104], - ["eloj", -1, 83], - ["noj", -1, 13], - ["cinoj", 1212, 137], - ["\u010Dinoj", 1212, 89], - ["osoj", -1, 123], - ["atoj", -1, 120], - ["evitoj", -1, 92], - ["ovitoj", -1, 93], - ["astoj", -1, 94], - ["avoj", -1, 77], - ["evoj", -1, 78], - ["ivoj", -1, 79], - ["ovoj", -1, 80], - ["a\u0107oj", -1, 14], - ["e\u0107oj", -1, 15], - ["u\u0107oj", -1, 16], - ["o\u0161oj", -1, 91], - ["lucuj", -1, 121], - ["iruj", -1, 100], - ["lu\u010Duj", -1, 117], - ["al", -1, 104], - ["iral", 1231, 100], - ["ural", 1231, 105], - ["el", -1, 119], - ["il", -1, 116], - ["am", -1, 104], - ["acam", 1236, 128], - ["iram", 1236, 100], - ["uram", 1236, 105], - ["tam", 1236, 113], - ["avam", 1236, 97], - ["evam", 1236, 96], - ["ivam", 1236, 98], - ["uvam", 1236, 99], - ["a\u010Dam", 1236, 102], - ["em", -1, 119], - ["acem", 1246, 124], - ["ecem", 1246, 125], - ["ucem", 1246, 126], - ["astadem", 1246, 110], - ["istadem", 1246, 111], - ["ostadem", 1246, 112], - ["ajem", 1246, 104], - ["cajem", 1253, 26], - ["lajem", 1253, 30], - ["rajem", 1253, 31], - ["astajem", 1253, 106], - ["istajem", 1253, 107], - ["ostajem", 1253, 108], - ["\u0107ajem", 1253, 28], - ["\u010Dajem", 1253, 27], - ["\u0111ajem", 1253, 29], - ["ijem", 1246, 116], - ["anjijem", 1263, 84], - ["enjijem", 1263, 85], - ["snjijem", 1263, 123], - ["\u0161njijem", 1263, 86], - ["kijem", 1263, 95], - ["skijem", 1268, 1], - ["\u0161kijem", 1268, 2], - ["lijem", 1263, 24], - ["elijem", 1271, 83], - ["nijem", 1263, 13], - ["rarijem", 1263, 21], - ["sijem", 1263, 23], - ["osijem", 1275, 123], - ["atijem", 1263, 120], - ["evitijem", 1263, 92], - ["ovitijem", 1263, 93], - ["otijem", 1263, 22], - ["astijem", 1263, 94], - ["avijem", 1263, 77], - ["evijem", 1263, 78], - ["ivijem", 1263, 79], - ["ovijem", 1263, 80], - ["o\u0161ijem", 1263, 91], - ["anjem", 1246, 84], - ["enjem", 1246, 85], - ["injem", 1246, 114], - ["snjem", 1246, 122], - ["\u0161njem", 1246, 86], - ["ujem", 1246, 25], - ["lucujem", 1292, 121], - ["irujem", 1292, 100], - ["lu\u010Dujem", 1292, 117], - ["kem", 1246, 95], - ["skem", 1296, 1], - ["\u0161kem", 1296, 2], - ["elem", 1246, 83], - ["nem", 1246, 13], - ["anem", 1300, 10], - ["astanem", 1301, 110], - ["istanem", 1301, 111], - ["ostanem", 1301, 112], - ["enem", 1300, 87], - ["snem", 1300, 159], - ["\u0161nem", 1300, 88], - ["basem", 1246, 135], - ["gasem", 1246, 131], - ["jasem", 1246, 129], - ["kasem", 1246, 133], - ["nasem", 1246, 132], - ["tasem", 1246, 130], - ["vasem", 1246, 134], - ["esem", 1246, 152], - ["isem", 1246, 154], - ["osem", 1246, 123], - ["atem", 1246, 120], - ["etem", 1246, 70], - ["evitem", 1246, 92], - ["ovitem", 1246, 93], - ["astem", 1246, 94], - ["istem", 1246, 151], - ["i\u0161tem", 1246, 75], - ["avem", 1246, 77], - ["evem", 1246, 78], - ["ivem", 1246, 79], - ["a\u0107em", 1246, 14], - ["e\u0107em", 1246, 15], - ["u\u0107em", 1246, 16], - ["ba\u0161em", 1246, 63], - ["ga\u0161em", 1246, 64], - ["ja\u0161em", 1246, 61], - ["ka\u0161em", 1246, 62], - ["na\u0161em", 1246, 60], - ["ta\u0161em", 1246, 59], - ["va\u0161em", 1246, 65], - ["e\u0161em", 1246, 66], - ["i\u0161em", 1246, 67], - ["o\u0161em", 1246, 91], - ["im", -1, 116], - ["acim", 1341, 124], - ["ecim", 1341, 125], - ["ucim", 1341, 126], - ["lucim", 1344, 121], - ["anjijim", 1341, 84], - ["enjijim", 1341, 85], - ["snjijim", 1341, 122], - ["\u0161njijim", 1341, 86], - ["kijim", 1341, 95], - ["skijim", 1350, 1], - ["\u0161kijim", 1350, 2], - ["elijim", 1341, 83], - ["nijim", 1341, 13], - ["osijim", 1341, 123], - ["atijim", 1341, 120], - ["evitijim", 1341, 92], - ["ovitijim", 1341, 93], - ["astijim", 1341, 94], - ["avijim", 1341, 77], - ["evijim", 1341, 78], - ["ivijim", 1341, 79], - ["ovijim", 1341, 80], - ["o\u0161ijim", 1341, 91], - ["anjim", 1341, 84], - ["enjim", 1341, 85], - ["snjim", 1341, 122], - ["\u0161njim", 1341, 86], - ["kim", 1341, 95], - ["skim", 1369, 1], - ["\u0161kim", 1369, 2], - ["elim", 1341, 83], - ["nim", 1341, 13], - ["cinim", 1373, 137], - ["\u010Dinim", 1373, 89], - ["osim", 1341, 123], - ["rosim", 1376, 127], - ["atim", 1341, 120], - ["jetim", 1341, 118], - ["evitim", 1341, 92], - ["ovitim", 1341, 93], - ["astim", 1341, 94], - ["avim", 1341, 77], - ["evim", 1341, 78], - ["ivim", 1341, 79], - ["ovim", 1341, 80], - ["a\u0107im", 1341, 14], - ["e\u0107im", 1341, 15], - ["u\u0107im", 1341, 16], - ["a\u010Dim", 1341, 101], - ["lu\u010Dim", 1341, 117], - ["o\u0161im", 1341, 91], - ["ro\u0161im", 1392, 90], - ["acom", -1, 124], - ["ecom", -1, 125], - ["ucom", -1, 126], - ["gom", -1, 20], - ["logom", 1397, 19], - ["ugom", 1397, 18], - ["bijom", -1, 32], - ["cijom", -1, 33], - ["dijom", -1, 34], - ["fijom", -1, 40], - ["gijom", -1, 39], - ["lijom", -1, 35], - ["mijom", -1, 37], - ["nijom", -1, 36], - ["ganijom", 1407, 9], - ["manijom", 1407, 6], - ["panijom", 1407, 7], - ["ranijom", 1407, 8], - ["tanijom", 1407, 5], - ["pijom", -1, 41], - ["rijom", -1, 42], - ["sijom", -1, 43], - ["tijom", -1, 44], - ["zijom", -1, 45], - ["\u017Eijom", -1, 38], - ["anjom", -1, 84], - ["enjom", -1, 85], - ["snjom", -1, 122], - ["\u0161njom", -1, 86], - ["kom", -1, 95], - ["skom", 1423, 1], - ["\u0161kom", 1423, 2], - ["alom", -1, 104], - ["ijalom", 1426, 47], - ["nalom", 1426, 46], - ["elom", -1, 83], - ["ilom", -1, 116], - ["ozilom", 1430, 48], - ["olom", -1, 50], - ["ramom", -1, 52], - ["lemom", -1, 51], - ["nom", -1, 13], - ["anom", 1435, 10], - ["inom", 1435, 11], - ["cinom", 1437, 137], - ["aninom", 1437, 10], - ["\u010Dinom", 1437, 89], - ["onom", 1435, 12], - ["arom", -1, 53], - ["drom", -1, 54], - ["erom", -1, 55], - ["orom", -1, 56], - ["basom", -1, 135], - ["gasom", -1, 131], - ["jasom", -1, 129], - ["kasom", -1, 133], - ["nasom", -1, 132], - ["tasom", -1, 130], - ["vasom", -1, 134], - ["esom", -1, 57], - ["isom", -1, 58], - ["osom", -1, 123], - ["atom", -1, 120], - ["ikatom", 1456, 68], - ["latom", 1456, 69], - ["etom", -1, 70], - ["evitom", -1, 92], - ["ovitom", -1, 93], - ["astom", -1, 94], - ["estom", -1, 71], - ["istom", -1, 72], - ["kstom", -1, 73], - ["ostom", -1, 74], - ["avom", -1, 77], - ["evom", -1, 78], - ["ivom", -1, 79], - ["ovom", -1, 80], - ["lovom", 1470, 82], - ["movom", 1470, 81], - ["stvom", -1, 3], - ["\u0161tvom", -1, 4], - ["a\u0107om", -1, 14], - ["e\u0107om", -1, 15], - ["u\u0107om", -1, 16], - ["ba\u0161om", -1, 63], - ["ga\u0161om", -1, 64], - ["ja\u0161om", -1, 61], - ["ka\u0161om", -1, 62], - ["na\u0161om", -1, 60], - ["ta\u0161om", -1, 59], - ["va\u0161om", -1, 65], - ["e\u0161om", -1, 66], - ["i\u0161om", -1, 67], - ["o\u0161om", -1, 91], - ["an", -1, 104], - ["acan", 1488, 128], - ["iran", 1488, 100], - ["uran", 1488, 105], - ["tan", 1488, 113], - ["avan", 1488, 97], - ["evan", 1488, 96], - ["ivan", 1488, 98], - ["uvan", 1488, 99], - ["a\u010Dan", 1488, 102], - ["acen", -1, 124], - ["lucen", -1, 121], - ["a\u010Den", -1, 101], - ["lu\u010Den", -1, 117], - ["anin", -1, 10], - ["ao", -1, 104], - ["acao", 1503, 128], - ["astajao", 1503, 106], - ["istajao", 1503, 107], - ["ostajao", 1503, 108], - ["injao", 1503, 114], - ["irao", 1503, 100], - ["urao", 1503, 105], - ["tao", 1503, 113], - ["astao", 1511, 110], - ["istao", 1511, 111], - ["ostao", 1511, 112], - ["avao", 1503, 97], - ["evao", 1503, 96], - ["ivao", 1503, 98], - ["ovao", 1503, 76], - ["uvao", 1503, 99], - ["a\u010Dao", 1503, 102], - ["go", -1, 20], - ["ugo", 1521, 18], - ["io", -1, 116], - ["acio", 1523, 124], - ["lucio", 1523, 121], - ["lio", 1523, 24], - ["nio", 1523, 103], - ["rario", 1523, 21], - ["sio", 1523, 23], - ["rosio", 1529, 127], - ["jetio", 1523, 118], - ["otio", 1523, 22], - ["a\u010Dio", 1523, 101], - ["lu\u010Dio", 1523, 117], - ["ro\u0161io", 1523, 90], - ["bijo", -1, 32], - ["cijo", -1, 33], - ["dijo", -1, 34], - ["fijo", -1, 40], - ["gijo", -1, 39], - ["lijo", -1, 35], - ["mijo", -1, 37], - ["nijo", -1, 36], - ["pijo", -1, 41], - ["rijo", -1, 42], - ["sijo", -1, 43], - ["tijo", -1, 44], - ["zijo", -1, 45], - ["\u017Eijo", -1, 38], - ["anjo", -1, 84], - ["enjo", -1, 85], - ["snjo", -1, 122], - ["\u0161njo", -1, 86], - ["ko", -1, 95], - ["sko", 1554, 1], - ["\u0161ko", 1554, 2], - ["alo", -1, 104], - ["acalo", 1557, 128], - ["astajalo", 1557, 106], - ["istajalo", 1557, 107], - ["ostajalo", 1557, 108], - ["ijalo", 1557, 47], - ["injalo", 1557, 114], - ["nalo", 1557, 46], - ["iralo", 1557, 100], - ["uralo", 1557, 105], - ["talo", 1557, 113], - ["astalo", 1567, 110], - ["istalo", 1567, 111], - ["ostalo", 1567, 112], - ["avalo", 1557, 97], - ["evalo", 1557, 96], - ["ivalo", 1557, 98], - ["ovalo", 1557, 76], - ["uvalo", 1557, 99], - ["a\u010Dalo", 1557, 102], - ["elo", -1, 83], - ["ilo", -1, 116], - ["acilo", 1578, 124], - ["lucilo", 1578, 121], - ["nilo", 1578, 103], - ["rosilo", 1578, 127], - ["jetilo", 1578, 118], - ["a\u010Dilo", 1578, 101], - ["lu\u010Dilo", 1578, 117], - ["ro\u0161ilo", 1578, 90], - ["aslo", -1, 115], - ["nulo", -1, 13], - ["amo", -1, 104], - ["acamo", 1589, 128], - ["ramo", 1589, 52], - ["iramo", 1591, 100], - ["uramo", 1591, 105], - ["tamo", 1589, 113], - ["avamo", 1589, 97], - ["evamo", 1589, 96], - ["ivamo", 1589, 98], - ["uvamo", 1589, 99], - ["a\u010Damo", 1589, 102], - ["emo", -1, 119], - ["astademo", 1600, 110], - ["istademo", 1600, 111], - ["ostademo", 1600, 112], - ["astajemo", 1600, 106], - ["istajemo", 1600, 107], - ["ostajemo", 1600, 108], - ["ijemo", 1600, 116], - ["injemo", 1600, 114], - ["ujemo", 1600, 25], - ["lucujemo", 1609, 121], - ["irujemo", 1609, 100], - ["lu\u010Dujemo", 1609, 117], - ["lemo", 1600, 51], - ["nemo", 1600, 13], - ["astanemo", 1614, 110], - ["istanemo", 1614, 111], - ["ostanemo", 1614, 112], - ["etemo", 1600, 70], - ["astemo", 1600, 115], - ["imo", -1, 116], - ["acimo", 1620, 124], - ["lucimo", 1620, 121], - ["nimo", 1620, 13], - ["astanimo", 1623, 110], - ["istanimo", 1623, 111], - ["ostanimo", 1623, 112], - ["rosimo", 1620, 127], - ["etimo", 1620, 70], - ["jetimo", 1628, 118], - ["astimo", 1620, 115], - ["a\u010Dimo", 1620, 101], - ["lu\u010Dimo", 1620, 117], - ["ro\u0161imo", 1620, 90], - ["ajmo", -1, 104], - ["urajmo", 1634, 105], - ["tajmo", 1634, 113], - ["astajmo", 1636, 106], - ["istajmo", 1636, 107], - ["ostajmo", 1636, 108], - ["avajmo", 1634, 97], - ["evajmo", 1634, 96], - ["ivajmo", 1634, 98], - ["uvajmo", 1634, 99], - ["ijmo", -1, 116], - ["ujmo", -1, 25], - ["lucujmo", 1645, 121], - ["irujmo", 1645, 100], - ["lu\u010Dujmo", 1645, 117], - ["asmo", -1, 104], - ["acasmo", 1649, 128], - ["astajasmo", 1649, 106], - ["istajasmo", 1649, 107], - ["ostajasmo", 1649, 108], - ["injasmo", 1649, 114], - ["irasmo", 1649, 100], - ["urasmo", 1649, 105], - ["tasmo", 1649, 113], - ["avasmo", 1649, 97], - ["evasmo", 1649, 96], - ["ivasmo", 1649, 98], - ["ovasmo", 1649, 76], - ["uvasmo", 1649, 99], - ["a\u010Dasmo", 1649, 102], - ["ismo", -1, 116], - ["acismo", 1664, 124], - ["lucismo", 1664, 121], - ["nismo", 1664, 103], - ["rosismo", 1664, 127], - ["jetismo", 1664, 118], - ["a\u010Dismo", 1664, 101], - ["lu\u010Dismo", 1664, 117], - ["ro\u0161ismo", 1664, 90], - ["astadosmo", -1, 110], - ["istadosmo", -1, 111], - ["ostadosmo", -1, 112], - ["nusmo", -1, 13], - ["no", -1, 13], - ["ano", 1677, 104], - ["acano", 1678, 128], - ["urano", 1678, 105], - ["tano", 1678, 113], - ["avano", 1678, 97], - ["evano", 1678, 96], - ["ivano", 1678, 98], - ["uvano", 1678, 99], - ["a\u010Dano", 1678, 102], - ["aceno", 1677, 124], - ["luceno", 1677, 121], - ["a\u010Deno", 1677, 101], - ["lu\u010Deno", 1677, 117], - ["ino", 1677, 11], - ["cino", 1691, 137], - ["\u010Dino", 1691, 89], - ["ato", -1, 120], - ["ikato", 1694, 68], - ["lato", 1694, 69], - ["eto", -1, 70], - ["evito", -1, 92], - ["ovito", -1, 93], - ["asto", -1, 94], - ["esto", -1, 71], - ["isto", -1, 72], - ["ksto", -1, 73], - ["osto", -1, 74], - ["nuto", -1, 13], - ["nuo", -1, 13], - ["avo", -1, 77], - ["evo", -1, 78], - ["ivo", -1, 79], - ["ovo", -1, 80], - ["stvo", -1, 3], - ["\u0161tvo", -1, 4], - ["as", -1, 161], - ["acas", 1713, 128], - ["iras", 1713, 155], - ["uras", 1713, 156], - ["tas", 1713, 160], - ["avas", 1713, 144], - ["evas", 1713, 145], - ["ivas", 1713, 146], - ["uvas", 1713, 147], - ["es", -1, 163], - ["astades", 1722, 141], - ["istades", 1722, 142], - ["ostades", 1722, 143], - ["astajes", 1722, 138], - ["istajes", 1722, 139], - ["ostajes", 1722, 140], - ["ijes", 1722, 162], - ["injes", 1722, 150], - ["ujes", 1722, 157], - ["lucujes", 1731, 121], - ["irujes", 1731, 155], - ["nes", 1722, 164], - ["astanes", 1734, 141], - ["istanes", 1734, 142], - ["ostanes", 1734, 143], - ["etes", 1722, 153], - ["astes", 1722, 136], - ["is", -1, 162], - ["acis", 1740, 124], - ["lucis", 1740, 121], - ["nis", 1740, 158], - ["rosis", 1740, 127], - ["jetis", 1740, 149], - ["at", -1, 104], - ["acat", 1746, 128], - ["astajat", 1746, 106], - ["istajat", 1746, 107], - ["ostajat", 1746, 108], - ["injat", 1746, 114], - ["irat", 1746, 100], - ["urat", 1746, 105], - ["tat", 1746, 113], - ["astat", 1754, 110], - ["istat", 1754, 111], - ["ostat", 1754, 112], - ["avat", 1746, 97], - ["evat", 1746, 96], - ["ivat", 1746, 98], - ["irivat", 1760, 100], - ["ovat", 1746, 76], - ["uvat", 1746, 99], - ["a\u010Dat", 1746, 102], - ["it", -1, 116], - ["acit", 1765, 124], - ["lucit", 1765, 121], - ["rosit", 1765, 127], - ["jetit", 1765, 118], - ["a\u010Dit", 1765, 101], - ["lu\u010Dit", 1765, 117], - ["ro\u0161it", 1765, 90], - ["nut", -1, 13], - ["astadu", -1, 110], - ["istadu", -1, 111], - ["ostadu", -1, 112], - ["gu", -1, 20], - ["logu", 1777, 19], - ["ugu", 1777, 18], - ["ahu", -1, 104], - ["acahu", 1780, 128], - ["astajahu", 1780, 106], - ["istajahu", 1780, 107], - ["ostajahu", 1780, 108], - ["injahu", 1780, 114], - ["irahu", 1780, 100], - ["urahu", 1780, 105], - ["avahu", 1780, 97], - ["evahu", 1780, 96], - ["ivahu", 1780, 98], - ["ovahu", 1780, 76], - ["uvahu", 1780, 99], - ["a\u010Dahu", 1780, 102], - ["aju", -1, 104], - ["caju", 1794, 26], - ["acaju", 1795, 128], - ["laju", 1794, 30], - ["raju", 1794, 31], - ["iraju", 1798, 100], - ["uraju", 1798, 105], - ["taju", 1794, 113], - ["astaju", 1801, 106], - ["istaju", 1801, 107], - ["ostaju", 1801, 108], - ["avaju", 1794, 97], - ["evaju", 1794, 96], - ["ivaju", 1794, 98], - ["uvaju", 1794, 99], - ["\u0107aju", 1794, 28], - ["\u010Daju", 1794, 27], - ["a\u010Daju", 1810, 102], - ["\u0111aju", 1794, 29], - ["iju", -1, 116], - ["biju", 1813, 32], - ["ciju", 1813, 33], - ["diju", 1813, 34], - ["fiju", 1813, 40], - ["giju", 1813, 39], - ["anjiju", 1813, 84], - ["enjiju", 1813, 85], - ["snjiju", 1813, 122], - ["\u0161njiju", 1813, 86], - ["kiju", 1813, 95], - ["liju", 1813, 24], - ["eliju", 1824, 83], - ["miju", 1813, 37], - ["niju", 1813, 13], - ["ganiju", 1827, 9], - ["maniju", 1827, 6], - ["paniju", 1827, 7], - ["raniju", 1827, 8], - ["taniju", 1827, 5], - ["piju", 1813, 41], - ["riju", 1813, 42], - ["rariju", 1834, 21], - ["siju", 1813, 23], - ["osiju", 1836, 123], - ["tiju", 1813, 44], - ["atiju", 1838, 120], - ["otiju", 1838, 22], - ["aviju", 1813, 77], - ["eviju", 1813, 78], - ["iviju", 1813, 79], - ["oviju", 1813, 80], - ["ziju", 1813, 45], - ["o\u0161iju", 1813, 91], - ["\u017Eiju", 1813, 38], - ["anju", -1, 84], - ["enju", -1, 85], - ["snju", -1, 122], - ["\u0161nju", -1, 86], - ["uju", -1, 25], - ["lucuju", 1852, 121], - ["iruju", 1852, 100], - ["lu\u010Duju", 1852, 117], - ["ku", -1, 95], - ["sku", 1856, 1], - ["\u0161ku", 1856, 2], - ["alu", -1, 104], - ["ijalu", 1859, 47], - ["nalu", 1859, 46], - ["elu", -1, 83], - ["ilu", -1, 116], - ["ozilu", 1863, 48], - ["olu", -1, 50], - ["ramu", -1, 52], - ["acemu", -1, 124], - ["ecemu", -1, 125], - ["ucemu", -1, 126], - ["anjijemu", -1, 84], - ["enjijemu", -1, 85], - ["snjijemu", -1, 122], - ["\u0161njijemu", -1, 86], - ["kijemu", -1, 95], - ["skijemu", 1874, 1], - ["\u0161kijemu", 1874, 2], - ["elijemu", -1, 83], - ["nijemu", -1, 13], - ["osijemu", -1, 123], - ["atijemu", -1, 120], - ["evitijemu", -1, 92], - ["ovitijemu", -1, 93], - ["astijemu", -1, 94], - ["avijemu", -1, 77], - ["evijemu", -1, 78], - ["ivijemu", -1, 79], - ["ovijemu", -1, 80], - ["o\u0161ijemu", -1, 91], - ["anjemu", -1, 84], - ["enjemu", -1, 85], - ["snjemu", -1, 122], - ["\u0161njemu", -1, 86], - ["kemu", -1, 95], - ["skemu", 1893, 1], - ["\u0161kemu", 1893, 2], - ["lemu", -1, 51], - ["elemu", 1896, 83], - ["nemu", -1, 13], - ["anemu", 1898, 10], - ["enemu", 1898, 87], - ["snemu", 1898, 159], - ["\u0161nemu", 1898, 88], - ["osemu", -1, 123], - ["atemu", -1, 120], - ["evitemu", -1, 92], - ["ovitemu", -1, 93], - ["astemu", -1, 94], - ["avemu", -1, 77], - ["evemu", -1, 78], - ["ivemu", -1, 79], - ["ovemu", -1, 80], - ["a\u0107emu", -1, 14], - ["e\u0107emu", -1, 15], - ["u\u0107emu", -1, 16], - ["o\u0161emu", -1, 91], - ["acomu", -1, 124], - ["ecomu", -1, 125], - ["ucomu", -1, 126], - ["anjomu", -1, 84], - ["enjomu", -1, 85], - ["snjomu", -1, 122], - ["\u0161njomu", -1, 86], - ["komu", -1, 95], - ["skomu", 1923, 1], - ["\u0161komu", 1923, 2], - ["elomu", -1, 83], - ["nomu", -1, 13], - ["cinomu", 1927, 137], - ["\u010Dinomu", 1927, 89], - ["osomu", -1, 123], - ["atomu", -1, 120], - ["evitomu", -1, 92], - ["ovitomu", -1, 93], - ["astomu", -1, 94], - ["avomu", -1, 77], - ["evomu", -1, 78], - ["ivomu", -1, 79], - ["ovomu", -1, 80], - ["a\u0107omu", -1, 14], - ["e\u0107omu", -1, 15], - ["u\u0107omu", -1, 16], - ["o\u0161omu", -1, 91], - ["nu", -1, 13], - ["anu", 1943, 10], - ["astanu", 1944, 110], - ["istanu", 1944, 111], - ["ostanu", 1944, 112], - ["inu", 1943, 11], - ["cinu", 1948, 137], - ["aninu", 1948, 10], - ["\u010Dinu", 1948, 89], - ["onu", 1943, 12], - ["aru", -1, 53], - ["dru", -1, 54], - ["eru", -1, 55], - ["oru", -1, 56], - ["basu", -1, 135], - ["gasu", -1, 131], - ["jasu", -1, 129], - ["kasu", -1, 133], - ["nasu", -1, 132], - ["tasu", -1, 130], - ["vasu", -1, 134], - ["esu", -1, 57], - ["isu", -1, 58], - ["osu", -1, 123], - ["atu", -1, 120], - ["ikatu", 1967, 68], - ["latu", 1967, 69], - ["etu", -1, 70], - ["evitu", -1, 92], - ["ovitu", -1, 93], - ["astu", -1, 94], - ["estu", -1, 71], - ["istu", -1, 72], - ["kstu", -1, 73], - ["ostu", -1, 74], - ["i\u0161tu", -1, 75], - ["avu", -1, 77], - ["evu", -1, 78], - ["ivu", -1, 79], - ["ovu", -1, 80], - ["lovu", 1982, 82], - ["movu", 1982, 81], - ["stvu", -1, 3], - ["\u0161tvu", -1, 4], - ["ba\u0161u", -1, 63], - ["ga\u0161u", -1, 64], - ["ja\u0161u", -1, 61], - ["ka\u0161u", -1, 62], - ["na\u0161u", -1, 60], - ["ta\u0161u", -1, 59], - ["va\u0161u", -1, 65], - ["e\u0161u", -1, 66], - ["i\u0161u", -1, 67], - ["o\u0161u", -1, 91], - ["avav", -1, 97], - ["evav", -1, 96], - ["ivav", -1, 98], - ["uvav", -1, 99], - ["kov", -1, 95], - ["a\u0161", -1, 104], - ["ira\u0161", 2002, 100], - ["ura\u0161", 2002, 105], - ["ta\u0161", 2002, 113], - ["ava\u0161", 2002, 97], - ["eva\u0161", 2002, 96], - ["iva\u0161", 2002, 98], - ["uva\u0161", 2002, 99], - ["a\u010Da\u0161", 2002, 102], - ["e\u0161", -1, 119], - ["astade\u0161", 2011, 110], - ["istade\u0161", 2011, 111], - ["ostade\u0161", 2011, 112], - ["astaje\u0161", 2011, 106], - ["istaje\u0161", 2011, 107], - ["ostaje\u0161", 2011, 108], - ["ije\u0161", 2011, 116], - ["inje\u0161", 2011, 114], - ["uje\u0161", 2011, 25], - ["iruje\u0161", 2020, 100], - ["lu\u010Duje\u0161", 2020, 117], - ["ne\u0161", 2011, 13], - ["astane\u0161", 2023, 110], - ["istane\u0161", 2023, 111], - ["ostane\u0161", 2023, 112], - ["ete\u0161", 2011, 70], - ["aste\u0161", 2011, 115], - ["i\u0161", -1, 116], - ["ni\u0161", 2029, 103], - ["jeti\u0161", 2029, 118], - ["a\u010Di\u0161", 2029, 101], - ["lu\u010Di\u0161", 2029, 117], - ["ro\u0161i\u0161", 2029, 90] - ]; - - /** @const */ var a_3 = [ - ["a", -1, 1], - ["oga", 0, 1], - ["ama", 0, 1], - ["ima", 0, 1], - ["ena", 0, 1], - ["e", -1, 1], - ["og", -1, 1], - ["anog", 6, 1], - ["enog", 6, 1], - ["anih", -1, 1], - ["enih", -1, 1], - ["i", -1, 1], - ["ani", 11, 1], - ["eni", 11, 1], - ["anoj", -1, 1], - ["enoj", -1, 1], - ["anim", -1, 1], - ["enim", -1, 1], - ["om", -1, 1], - ["enom", 18, 1], - ["o", -1, 1], - ["ano", 20, 1], - ["eno", 20, 1], - ["ost", -1, 1], - ["u", -1, 1], - ["enu", 24, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16]; - - /** @const */ var /** Array */ g_sa = [65, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 0, 0, 128]; - - /** @const */ var /** Array */ g_ca = [119, 95, 23, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 32, 136, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128, 0, 0, 0, 16]; - - /** @const */ var /** Array */ g_rg = [1]; - - var /** number */ I_p1 = 0; - var /** boolean */ B_no_diacritics = false; - - - /** @return {boolean} */ - function r_cyr_to_lat() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - golab2: while(true) - { - var /** number */ v_3 = base.cursor; - lab3: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - if (among_var == 0) - { - break lab3; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("a")) - { - return false; - } - break; - case 2: - if (!base.slice_from("b")) - { - return false; - } - break; - case 3: - if (!base.slice_from("v")) - { - return false; - } - break; - case 4: - if (!base.slice_from("g")) - { - return false; - } - break; - case 5: - if (!base.slice_from("d")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u0111")) - { - return false; - } - break; - case 7: - if (!base.slice_from("e")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u017E")) - { - return false; - } - break; - case 9: - if (!base.slice_from("z")) - { - return false; - } - break; - case 10: - if (!base.slice_from("i")) - { - return false; - } - break; - case 11: - if (!base.slice_from("j")) - { - return false; - } - break; - case 12: - if (!base.slice_from("k")) - { - return false; - } - break; - case 13: - if (!base.slice_from("l")) - { - return false; - } - break; - case 14: - if (!base.slice_from("lj")) - { - return false; - } - break; - case 15: - if (!base.slice_from("m")) - { - return false; - } - break; - case 16: - if (!base.slice_from("n")) - { - return false; - } - break; - case 17: - if (!base.slice_from("nj")) - { - return false; - } - break; - case 18: - if (!base.slice_from("o")) - { - return false; - } - break; - case 19: - if (!base.slice_from("p")) - { - return false; - } - break; - case 20: - if (!base.slice_from("r")) - { - return false; - } - break; - case 21: - if (!base.slice_from("s")) - { - return false; - } - break; - case 22: - if (!base.slice_from("t")) - { - return false; - } - break; - case 23: - if (!base.slice_from("\u0107")) - { - return false; - } - break; - case 24: - if (!base.slice_from("u")) - { - return false; - } - break; - case 25: - if (!base.slice_from("f")) - { - return false; - } - break; - case 26: - if (!base.slice_from("h")) - { - return false; - } - break; - case 27: - if (!base.slice_from("c")) - { - return false; - } - break; - case 28: - if (!base.slice_from("\u010D")) - { - return false; - } - break; - case 29: - if (!base.slice_from("d\u017E")) - { - return false; - } - break; - case 30: - if (!base.slice_from("\u0161")) - { - return false; - } - break; - } - base.cursor = v_3; - break golab2; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_prelude() { - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - golab2: while(true) - { - var /** number */ v_3 = base.cursor; - lab3: { - if (!(base.in_grouping(g_ca, 98, 382))) - { - break lab3; - } - base.bra = base.cursor; - if (!(base.eq_s("ije"))) - { - break lab3; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_ca, 98, 382))) - { - break lab3; - } - if (!base.slice_from("e")) - { - return false; - } - base.cursor = v_3; - break golab2; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - var /** number */ v_4 = base.cursor; - lab4: { - while(true) - { - var /** number */ v_5 = base.cursor; - lab5: { - golab6: while(true) - { - var /** number */ v_6 = base.cursor; - lab7: { - if (!(base.in_grouping(g_ca, 98, 382))) - { - break lab7; - } - base.bra = base.cursor; - if (!(base.eq_s("je"))) - { - break lab7; - } - base.ket = base.cursor; - if (!(base.in_grouping(g_ca, 98, 382))) - { - break lab7; - } - if (!base.slice_from("e")) - { - return false; - } - base.cursor = v_6; - break golab6; - } - base.cursor = v_6; - if (base.cursor >= base.limit) - { - break lab5; - } - base.cursor++; - } - continue; - } - base.cursor = v_5; - break; - } - } - base.cursor = v_4; - var /** number */ v_7 = base.cursor; - lab8: { - while(true) - { - var /** number */ v_8 = base.cursor; - lab9: { - golab10: while(true) - { - var /** number */ v_9 = base.cursor; - lab11: { - base.bra = base.cursor; - if (!(base.eq_s("dj"))) - { - break lab11; - } - base.ket = base.cursor; - if (!base.slice_from("\u0111")) - { - return false; - } - base.cursor = v_9; - break golab10; - } - base.cursor = v_9; - if (base.cursor >= base.limit) - { - break lab9; - } - base.cursor++; - } - continue; - } - base.cursor = v_8; - break; - } - } - base.cursor = v_7; - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - B_no_diacritics = true; - var /** number */ v_1 = base.cursor; - lab0: { - golab1: while(true) - { - lab2: { - if (!(base.in_grouping(g_sa, 263, 382))) - { - break lab2; - } - break golab1; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - B_no_diacritics = false; - } - base.cursor = v_1; - I_p1 = base.limit; - var /** number */ v_3 = base.cursor; - lab3: { - golab4: while(true) - { - lab5: { - if (!(base.in_grouping(g_v, 97, 117))) - { - break lab5; - } - break golab4; - } - if (base.cursor >= base.limit) - { - break lab3; - } - base.cursor++; - } - I_p1 = base.cursor; - if (I_p1 >= 2) - { - break lab3; - } - golab6: while(true) - { - lab7: { - if (!(base.out_grouping(g_v, 97, 117))) - { - break lab7; - } - break golab6; - } - if (base.cursor >= base.limit) - { - break lab3; - } - base.cursor++; - } - I_p1 = base.cursor; - } - base.cursor = v_3; - var /** number */ v_6 = base.cursor; - lab8: { - golab9: while(true) - { - lab10: { - if (!(base.eq_s("r"))) - { - break lab10; - } - break golab9; - } - if (base.cursor >= base.limit) - { - break lab8; - } - base.cursor++; - } - lab11: { - var /** number */ v_8 = base.cursor; - lab12: { - if (base.cursor < 2) - { - break lab12; - } - break lab11; - } - base.cursor = v_8; - golab13: while(true) - { - lab14: { - if (!(base.out_grouping(g_rg, 114, 114))) - { - break lab14; - } - break golab13; - } - if (base.cursor >= base.limit) - { - break lab8; - } - base.cursor++; - } - } - if ((I_p1 - base.cursor) <= 1) - { - break lab8; - } - I_p1 = base.cursor; - } - base.cursor = v_6; - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_Step_1() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_1); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("loga")) - { - return false; - } - break; - case 2: - if (!base.slice_from("peh")) - { - return false; - } - break; - case 3: - if (!base.slice_from("vojka")) - { - return false; - } - break; - case 4: - if (!base.slice_from("bojka")) - { - return false; - } - break; - case 5: - if (!base.slice_from("jak")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u010Dajni")) - { - return false; - } - break; - case 7: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("cajni")) - { - return false; - } - break; - case 8: - if (!base.slice_from("erni")) - { - return false; - } - break; - case 9: - if (!base.slice_from("larni")) - { - return false; - } - break; - case 10: - if (!base.slice_from("esni")) - { - return false; - } - break; - case 11: - if (!base.slice_from("anjca")) - { - return false; - } - break; - case 12: - if (!base.slice_from("ajca")) - { - return false; - } - break; - case 13: - if (!base.slice_from("ljca")) - { - return false; - } - break; - case 14: - if (!base.slice_from("ejca")) - { - return false; - } - break; - case 15: - if (!base.slice_from("ojca")) - { - return false; - } - break; - case 16: - if (!base.slice_from("ajka")) - { - return false; - } - break; - case 17: - if (!base.slice_from("ojka")) - { - return false; - } - break; - case 18: - if (!base.slice_from("\u0161ca")) - { - return false; - } - break; - case 19: - if (!base.slice_from("ing")) - { - return false; - } - break; - case 20: - if (!base.slice_from("tvenik")) - { - return false; - } - break; - case 21: - if (!base.slice_from("tetika")) - { - return false; - } - break; - case 22: - if (!base.slice_from("nstva")) - { - return false; - } - break; - case 23: - if (!base.slice_from("nik")) - { - return false; - } - break; - case 24: - if (!base.slice_from("tik")) - { - return false; - } - break; - case 25: - if (!base.slice_from("zik")) - { - return false; - } - break; - case 26: - if (!base.slice_from("snik")) - { - return false; - } - break; - case 27: - if (!base.slice_from("kusi")) - { - return false; - } - break; - case 28: - if (!base.slice_from("kusni")) - { - return false; - } - break; - case 29: - if (!base.slice_from("kustva")) - { - return false; - } - break; - case 30: - if (!base.slice_from("du\u0161ni")) - { - return false; - } - break; - case 31: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("dusni")) - { - return false; - } - break; - case 32: - if (!base.slice_from("antni")) - { - return false; - } - break; - case 33: - if (!base.slice_from("bilni")) - { - return false; - } - break; - case 34: - if (!base.slice_from("tilni")) - { - return false; - } - break; - case 35: - if (!base.slice_from("avilni")) - { - return false; - } - break; - case 36: - if (!base.slice_from("silni")) - { - return false; - } - break; - case 37: - if (!base.slice_from("gilni")) - { - return false; - } - break; - case 38: - if (!base.slice_from("rilni")) - { - return false; - } - break; - case 39: - if (!base.slice_from("nilni")) - { - return false; - } - break; - case 40: - if (!base.slice_from("alni")) - { - return false; - } - break; - case 41: - if (!base.slice_from("ozni")) - { - return false; - } - break; - case 42: - if (!base.slice_from("ravi")) - { - return false; - } - break; - case 43: - if (!base.slice_from("stavni")) - { - return false; - } - break; - case 44: - if (!base.slice_from("pravni")) - { - return false; - } - break; - case 45: - if (!base.slice_from("tivni")) - { - return false; - } - break; - case 46: - if (!base.slice_from("sivni")) - { - return false; - } - break; - case 47: - if (!base.slice_from("atni")) - { - return false; - } - break; - case 48: - if (!base.slice_from("enta")) - { - return false; - } - break; - case 49: - if (!base.slice_from("tetni")) - { - return false; - } - break; - case 50: - if (!base.slice_from("pletni")) - { - return false; - } - break; - case 51: - if (!base.slice_from("\u0161avi")) - { - return false; - } - break; - case 52: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("savi")) - { - return false; - } - break; - case 53: - if (!base.slice_from("anta")) - { - return false; - } - break; - case 54: - if (!base.slice_from("a\u010Dka")) - { - return false; - } - break; - case 55: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("acka")) - { - return false; - } - break; - case 56: - if (!base.slice_from("u\u0161ka")) - { - return false; - } - break; - case 57: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("uska")) - { - return false; - } - break; - case 58: - if (!base.slice_from("atka")) - { - return false; - } - break; - case 59: - if (!base.slice_from("etka")) - { - return false; - } - break; - case 60: - if (!base.slice_from("itka")) - { - return false; - } - break; - case 61: - if (!base.slice_from("otka")) - { - return false; - } - break; - case 62: - if (!base.slice_from("utka")) - { - return false; - } - break; - case 63: - if (!base.slice_from("eskna")) - { - return false; - } - break; - case 64: - if (!base.slice_from("ti\u010Dni")) - { - return false; - } - break; - case 65: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ticni")) - { - return false; - } - break; - case 66: - if (!base.slice_from("ojska")) - { - return false; - } - break; - case 67: - if (!base.slice_from("esma")) - { - return false; - } - break; - case 68: - if (!base.slice_from("metra")) - { - return false; - } - break; - case 69: - if (!base.slice_from("centra")) - { - return false; - } - break; - case 70: - if (!base.slice_from("istra")) - { - return false; - } - break; - case 71: - if (!base.slice_from("osti")) - { - return false; - } - break; - case 72: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("osti")) - { - return false; - } - break; - case 73: - if (!base.slice_from("dba")) - { - return false; - } - break; - case 74: - if (!base.slice_from("\u010Dka")) - { - return false; - } - break; - case 75: - if (!base.slice_from("mca")) - { - return false; - } - break; - case 76: - if (!base.slice_from("nca")) - { - return false; - } - break; - case 77: - if (!base.slice_from("voljni")) - { - return false; - } - break; - case 78: - if (!base.slice_from("anki")) - { - return false; - } - break; - case 79: - if (!base.slice_from("vca")) - { - return false; - } - break; - case 80: - if (!base.slice_from("sca")) - { - return false; - } - break; - case 81: - if (!base.slice_from("rca")) - { - return false; - } - break; - case 82: - if (!base.slice_from("alca")) - { - return false; - } - break; - case 83: - if (!base.slice_from("elca")) - { - return false; - } - break; - case 84: - if (!base.slice_from("olca")) - { - return false; - } - break; - case 85: - if (!base.slice_from("njca")) - { - return false; - } - break; - case 86: - if (!base.slice_from("ekta")) - { - return false; - } - break; - case 87: - if (!base.slice_from("izma")) - { - return false; - } - break; - case 88: - if (!base.slice_from("jebi")) - { - return false; - } - break; - case 89: - if (!base.slice_from("baci")) - { - return false; - } - break; - case 90: - if (!base.slice_from("a\u0161ni")) - { - return false; - } - break; - case 91: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("asni")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_2() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - switch (among_var) { - case 1: - if (!base.slice_from("sk")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u0161k")) - { - return false; - } - break; - case 3: - if (!base.slice_from("stv")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u0161tv")) - { - return false; - } - break; - case 5: - if (!base.slice_from("tanij")) - { - return false; - } - break; - case 6: - if (!base.slice_from("manij")) - { - return false; - } - break; - case 7: - if (!base.slice_from("panij")) - { - return false; - } - break; - case 8: - if (!base.slice_from("ranij")) - { - return false; - } - break; - case 9: - if (!base.slice_from("ganij")) - { - return false; - } - break; - case 10: - if (!base.slice_from("an")) - { - return false; - } - break; - case 11: - if (!base.slice_from("in")) - { - return false; - } - break; - case 12: - if (!base.slice_from("on")) - { - return false; - } - break; - case 13: - if (!base.slice_from("n")) - { - return false; - } - break; - case 14: - if (!base.slice_from("a\u0107")) - { - return false; - } - break; - case 15: - if (!base.slice_from("e\u0107")) - { - return false; - } - break; - case 16: - if (!base.slice_from("u\u0107")) - { - return false; - } - break; - case 17: - if (!base.slice_from("ugov")) - { - return false; - } - break; - case 18: - if (!base.slice_from("ug")) - { - return false; - } - break; - case 19: - if (!base.slice_from("log")) - { - return false; - } - break; - case 20: - if (!base.slice_from("g")) - { - return false; - } - break; - case 21: - if (!base.slice_from("rari")) - { - return false; - } - break; - case 22: - if (!base.slice_from("oti")) - { - return false; - } - break; - case 23: - if (!base.slice_from("si")) - { - return false; - } - break; - case 24: - if (!base.slice_from("li")) - { - return false; - } - break; - case 25: - if (!base.slice_from("uj")) - { - return false; - } - break; - case 26: - if (!base.slice_from("caj")) - { - return false; - } - break; - case 27: - if (!base.slice_from("\u010Daj")) - { - return false; - } - break; - case 28: - if (!base.slice_from("\u0107aj")) - { - return false; - } - break; - case 29: - if (!base.slice_from("\u0111aj")) - { - return false; - } - break; - case 30: - if (!base.slice_from("laj")) - { - return false; - } - break; - case 31: - if (!base.slice_from("raj")) - { - return false; - } - break; - case 32: - if (!base.slice_from("bij")) - { - return false; - } - break; - case 33: - if (!base.slice_from("cij")) - { - return false; - } - break; - case 34: - if (!base.slice_from("dij")) - { - return false; - } - break; - case 35: - if (!base.slice_from("lij")) - { - return false; - } - break; - case 36: - if (!base.slice_from("nij")) - { - return false; - } - break; - case 37: - if (!base.slice_from("mij")) - { - return false; - } - break; - case 38: - if (!base.slice_from("\u017Eij")) - { - return false; - } - break; - case 39: - if (!base.slice_from("gij")) - { - return false; - } - break; - case 40: - if (!base.slice_from("fij")) - { - return false; - } - break; - case 41: - if (!base.slice_from("pij")) - { - return false; - } - break; - case 42: - if (!base.slice_from("rij")) - { - return false; - } - break; - case 43: - if (!base.slice_from("sij")) - { - return false; - } - break; - case 44: - if (!base.slice_from("tij")) - { - return false; - } - break; - case 45: - if (!base.slice_from("zij")) - { - return false; - } - break; - case 46: - if (!base.slice_from("nal")) - { - return false; - } - break; - case 47: - if (!base.slice_from("ijal")) - { - return false; - } - break; - case 48: - if (!base.slice_from("ozil")) - { - return false; - } - break; - case 49: - if (!base.slice_from("olov")) - { - return false; - } - break; - case 50: - if (!base.slice_from("ol")) - { - return false; - } - break; - case 51: - if (!base.slice_from("lem")) - { - return false; - } - break; - case 52: - if (!base.slice_from("ram")) - { - return false; - } - break; - case 53: - if (!base.slice_from("ar")) - { - return false; - } - break; - case 54: - if (!base.slice_from("dr")) - { - return false; - } - break; - case 55: - if (!base.slice_from("er")) - { - return false; - } - break; - case 56: - if (!base.slice_from("or")) - { - return false; - } - break; - case 57: - if (!base.slice_from("es")) - { - return false; - } - break; - case 58: - if (!base.slice_from("is")) - { - return false; - } - break; - case 59: - if (!base.slice_from("ta\u0161")) - { - return false; - } - break; - case 60: - if (!base.slice_from("na\u0161")) - { - return false; - } - break; - case 61: - if (!base.slice_from("ja\u0161")) - { - return false; - } - break; - case 62: - if (!base.slice_from("ka\u0161")) - { - return false; - } - break; - case 63: - if (!base.slice_from("ba\u0161")) - { - return false; - } - break; - case 64: - if (!base.slice_from("ga\u0161")) - { - return false; - } - break; - case 65: - if (!base.slice_from("va\u0161")) - { - return false; - } - break; - case 66: - if (!base.slice_from("e\u0161")) - { - return false; - } - break; - case 67: - if (!base.slice_from("i\u0161")) - { - return false; - } - break; - case 68: - if (!base.slice_from("ikat")) - { - return false; - } - break; - case 69: - if (!base.slice_from("lat")) - { - return false; - } - break; - case 70: - if (!base.slice_from("et")) - { - return false; - } - break; - case 71: - if (!base.slice_from("est")) - { - return false; - } - break; - case 72: - if (!base.slice_from("ist")) - { - return false; - } - break; - case 73: - if (!base.slice_from("kst")) - { - return false; - } - break; - case 74: - if (!base.slice_from("ost")) - { - return false; - } - break; - case 75: - if (!base.slice_from("i\u0161t")) - { - return false; - } - break; - case 76: - if (!base.slice_from("ova")) - { - return false; - } - break; - case 77: - if (!base.slice_from("av")) - { - return false; - } - break; - case 78: - if (!base.slice_from("ev")) - { - return false; - } - break; - case 79: - if (!base.slice_from("iv")) - { - return false; - } - break; - case 80: - if (!base.slice_from("ov")) - { - return false; - } - break; - case 81: - if (!base.slice_from("mov")) - { - return false; - } - break; - case 82: - if (!base.slice_from("lov")) - { - return false; - } - break; - case 83: - if (!base.slice_from("el")) - { - return false; - } - break; - case 84: - if (!base.slice_from("anj")) - { - return false; - } - break; - case 85: - if (!base.slice_from("enj")) - { - return false; - } - break; - case 86: - if (!base.slice_from("\u0161nj")) - { - return false; - } - break; - case 87: - if (!base.slice_from("en")) - { - return false; - } - break; - case 88: - if (!base.slice_from("\u0161n")) - { - return false; - } - break; - case 89: - if (!base.slice_from("\u010Din")) - { - return false; - } - break; - case 90: - if (!base.slice_from("ro\u0161i")) - { - return false; - } - break; - case 91: - if (!base.slice_from("o\u0161")) - { - return false; - } - break; - case 92: - if (!base.slice_from("evit")) - { - return false; - } - break; - case 93: - if (!base.slice_from("ovit")) - { - return false; - } - break; - case 94: - if (!base.slice_from("ast")) - { - return false; - } - break; - case 95: - if (!base.slice_from("k")) - { - return false; - } - break; - case 96: - if (!base.slice_from("eva")) - { - return false; - } - break; - case 97: - if (!base.slice_from("ava")) - { - return false; - } - break; - case 98: - if (!base.slice_from("iva")) - { - return false; - } - break; - case 99: - if (!base.slice_from("uva")) - { - return false; - } - break; - case 100: - if (!base.slice_from("ir")) - { - return false; - } - break; - case 101: - if (!base.slice_from("a\u010D")) - { - return false; - } - break; - case 102: - if (!base.slice_from("a\u010Da")) - { - return false; - } - break; - case 103: - if (!base.slice_from("ni")) - { - return false; - } - break; - case 104: - if (!base.slice_from("a")) - { - return false; - } - break; - case 105: - if (!base.slice_from("ur")) - { - return false; - } - break; - case 106: - if (!base.slice_from("astaj")) - { - return false; - } - break; - case 107: - if (!base.slice_from("istaj")) - { - return false; - } - break; - case 108: - if (!base.slice_from("ostaj")) - { - return false; - } - break; - case 109: - if (!base.slice_from("aj")) - { - return false; - } - break; - case 110: - if (!base.slice_from("asta")) - { - return false; - } - break; - case 111: - if (!base.slice_from("ista")) - { - return false; - } - break; - case 112: - if (!base.slice_from("osta")) - { - return false; - } - break; - case 113: - if (!base.slice_from("ta")) - { - return false; - } - break; - case 114: - if (!base.slice_from("inj")) - { - return false; - } - break; - case 115: - if (!base.slice_from("as")) - { - return false; - } - break; - case 116: - if (!base.slice_from("i")) - { - return false; - } - break; - case 117: - if (!base.slice_from("lu\u010D")) - { - return false; - } - break; - case 118: - if (!base.slice_from("jeti")) - { - return false; - } - break; - case 119: - if (!base.slice_from("e")) - { - return false; - } - break; - case 120: - if (!base.slice_from("at")) - { - return false; - } - break; - case 121: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("luc")) - { - return false; - } - break; - case 122: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("snj")) - { - return false; - } - break; - case 123: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("os")) - { - return false; - } - break; - case 124: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ac")) - { - return false; - } - break; - case 125: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ec")) - { - return false; - } - break; - case 126: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("uc")) - { - return false; - } - break; - case 127: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("rosi")) - { - return false; - } - break; - case 128: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("aca")) - { - return false; - } - break; - case 129: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("jas")) - { - return false; - } - break; - case 130: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("tas")) - { - return false; - } - break; - case 131: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("gas")) - { - return false; - } - break; - case 132: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("nas")) - { - return false; - } - break; - case 133: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("kas")) - { - return false; - } - break; - case 134: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("vas")) - { - return false; - } - break; - case 135: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("bas")) - { - return false; - } - break; - case 136: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("as")) - { - return false; - } - break; - case 137: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("cin")) - { - return false; - } - break; - case 138: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("astaj")) - { - return false; - } - break; - case 139: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("istaj")) - { - return false; - } - break; - case 140: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ostaj")) - { - return false; - } - break; - case 141: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("asta")) - { - return false; - } - break; - case 142: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ista")) - { - return false; - } - break; - case 143: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("osta")) - { - return false; - } - break; - case 144: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ava")) - { - return false; - } - break; - case 145: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("eva")) - { - return false; - } - break; - case 146: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("iva")) - { - return false; - } - break; - case 147: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("uva")) - { - return false; - } - break; - case 148: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ova")) - { - return false; - } - break; - case 149: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("jeti")) - { - return false; - } - break; - case 150: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("inj")) - { - return false; - } - break; - case 151: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ist")) - { - return false; - } - break; - case 152: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("es")) - { - return false; - } - break; - case 153: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("et")) - { - return false; - } - break; - case 154: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("is")) - { - return false; - } - break; - case 155: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ir")) - { - return false; - } - break; - case 156: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ur")) - { - return false; - } - break; - case 157: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("uj")) - { - return false; - } - break; - case 158: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ni")) - { - return false; - } - break; - case 159: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("sn")) - { - return false; - } - break; - case 160: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("ta")) - { - return false; - } - break; - case 161: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("a")) - { - return false; - } - break; - case 162: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("i")) - { - return false; - } - break; - case 163: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("e")) - { - return false; - } - break; - case 164: - if (!B_no_diacritics) - { - return false; - } - if (!base.slice_from("n")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_Step_3() { - base.ket = base.cursor; - if (base.find_among_b(a_3) == 0) - { - return false; - } - base.bra = base.cursor; - if (!r_R1()) - { - return false; - } - if (!base.slice_from("")) - { - return false; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_cyr_to_lat(); - r_prelude(); - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_4 = base.limit - base.cursor; - r_Step_1(); - base.cursor = base.limit - v_4; - var /** number */ v_5 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_6 = base.limit - base.cursor; - lab2: { - if (!r_Step_2()) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_6; - if (!r_Step_3()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_5; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['SerbianStemmer'] = SerbianStemmer; diff --git a/js/spanish-stemmer.js b/js/spanish-stemmer.js deleted file mode 100644 index 9137989..0000000 --- a/js/spanish-stemmer.js +++ /dev/null @@ -1,976 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var SpanishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["", -1, 6], - ["\u00E1", 0, 1], - ["\u00E9", 0, 2], - ["\u00ED", 0, 3], - ["\u00F3", 0, 4], - ["\u00FA", 0, 5] - ]; - - /** @const */ var a_1 = [ - ["la", -1, -1], - ["sela", 0, -1], - ["le", -1, -1], - ["me", -1, -1], - ["se", -1, -1], - ["lo", -1, -1], - ["selo", 5, -1], - ["las", -1, -1], - ["selas", 7, -1], - ["les", -1, -1], - ["los", -1, -1], - ["selos", 10, -1], - ["nos", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["ando", -1, 6], - ["iendo", -1, 6], - ["yendo", -1, 7], - ["\u00E1ndo", -1, 2], - ["i\u00E9ndo", -1, 1], - ["ar", -1, 6], - ["er", -1, 6], - ["ir", -1, 6], - ["\u00E1r", -1, 3], - ["\u00E9r", -1, 4], - ["\u00EDr", -1, 5] - ]; - - /** @const */ var a_3 = [ - ["ic", -1, -1], - ["ad", -1, -1], - ["os", -1, -1], - ["iv", -1, 1] - ]; - - /** @const */ var a_4 = [ - ["able", -1, 1], - ["ible", -1, 1], - ["ante", -1, 1] - ]; - - /** @const */ var a_5 = [ - ["ic", -1, 1], - ["abil", -1, 1], - ["iv", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["ica", -1, 1], - ["ancia", -1, 2], - ["encia", -1, 5], - ["adora", -1, 2], - ["osa", -1, 1], - ["ista", -1, 1], - ["iva", -1, 9], - ["anza", -1, 1], - ["log\u00EDa", -1, 3], - ["idad", -1, 8], - ["able", -1, 1], - ["ible", -1, 1], - ["ante", -1, 2], - ["mente", -1, 7], - ["amente", 13, 6], - ["aci\u00F3n", -1, 2], - ["uci\u00F3n", -1, 4], - ["ico", -1, 1], - ["ismo", -1, 1], - ["oso", -1, 1], - ["amiento", -1, 1], - ["imiento", -1, 1], - ["ivo", -1, 9], - ["ador", -1, 2], - ["icas", -1, 1], - ["ancias", -1, 2], - ["encias", -1, 5], - ["adoras", -1, 2], - ["osas", -1, 1], - ["istas", -1, 1], - ["ivas", -1, 9], - ["anzas", -1, 1], - ["log\u00EDas", -1, 3], - ["idades", -1, 8], - ["ables", -1, 1], - ["ibles", -1, 1], - ["aciones", -1, 2], - ["uciones", -1, 4], - ["adores", -1, 2], - ["antes", -1, 2], - ["icos", -1, 1], - ["ismos", -1, 1], - ["osos", -1, 1], - ["amientos", -1, 1], - ["imientos", -1, 1], - ["ivos", -1, 9] - ]; - - /** @const */ var a_7 = [ - ["ya", -1, 1], - ["ye", -1, 1], - ["yan", -1, 1], - ["yen", -1, 1], - ["yeron", -1, 1], - ["yendo", -1, 1], - ["yo", -1, 1], - ["yas", -1, 1], - ["yes", -1, 1], - ["yais", -1, 1], - ["yamos", -1, 1], - ["y\u00F3", -1, 1] - ]; - - /** @const */ var a_8 = [ - ["aba", -1, 2], - ["ada", -1, 2], - ["ida", -1, 2], - ["ara", -1, 2], - ["iera", -1, 2], - ["\u00EDa", -1, 2], - ["ar\u00EDa", 5, 2], - ["er\u00EDa", 5, 2], - ["ir\u00EDa", 5, 2], - ["ad", -1, 2], - ["ed", -1, 2], - ["id", -1, 2], - ["ase", -1, 2], - ["iese", -1, 2], - ["aste", -1, 2], - ["iste", -1, 2], - ["an", -1, 2], - ["aban", 16, 2], - ["aran", 16, 2], - ["ieran", 16, 2], - ["\u00EDan", 16, 2], - ["ar\u00EDan", 20, 2], - ["er\u00EDan", 20, 2], - ["ir\u00EDan", 20, 2], - ["en", -1, 1], - ["asen", 24, 2], - ["iesen", 24, 2], - ["aron", -1, 2], - ["ieron", -1, 2], - ["ar\u00E1n", -1, 2], - ["er\u00E1n", -1, 2], - ["ir\u00E1n", -1, 2], - ["ado", -1, 2], - ["ido", -1, 2], - ["ando", -1, 2], - ["iendo", -1, 2], - ["ar", -1, 2], - ["er", -1, 2], - ["ir", -1, 2], - ["as", -1, 2], - ["abas", 39, 2], - ["adas", 39, 2], - ["idas", 39, 2], - ["aras", 39, 2], - ["ieras", 39, 2], - ["\u00EDas", 39, 2], - ["ar\u00EDas", 45, 2], - ["er\u00EDas", 45, 2], - ["ir\u00EDas", 45, 2], - ["es", -1, 1], - ["ases", 49, 2], - ["ieses", 49, 2], - ["abais", -1, 2], - ["arais", -1, 2], - ["ierais", -1, 2], - ["\u00EDais", -1, 2], - ["ar\u00EDais", 55, 2], - ["er\u00EDais", 55, 2], - ["ir\u00EDais", 55, 2], - ["aseis", -1, 2], - ["ieseis", -1, 2], - ["asteis", -1, 2], - ["isteis", -1, 2], - ["\u00E1is", -1, 2], - ["\u00E9is", -1, 1], - ["ar\u00E9is", 64, 2], - ["er\u00E9is", 64, 2], - ["ir\u00E9is", 64, 2], - ["ados", -1, 2], - ["idos", -1, 2], - ["amos", -1, 2], - ["\u00E1bamos", 70, 2], - ["\u00E1ramos", 70, 2], - ["i\u00E9ramos", 70, 2], - ["\u00EDamos", 70, 2], - ["ar\u00EDamos", 74, 2], - ["er\u00EDamos", 74, 2], - ["ir\u00EDamos", 74, 2], - ["emos", -1, 1], - ["aremos", 78, 2], - ["eremos", 78, 2], - ["iremos", 78, 2], - ["\u00E1semos", 78, 2], - ["i\u00E9semos", 78, 2], - ["imos", -1, 2], - ["ar\u00E1s", -1, 2], - ["er\u00E1s", -1, 2], - ["ir\u00E1s", -1, 2], - ["\u00EDs", -1, 2], - ["ar\u00E1", -1, 2], - ["er\u00E1", -1, 2], - ["ir\u00E1", -1, 2], - ["ar\u00E9", -1, 2], - ["er\u00E9", -1, 2], - ["ir\u00E9", -1, 2], - ["i\u00F3", -1, 2] - ]; - - /** @const */ var a_9 = [ - ["a", -1, 1], - ["e", -1, 2], - ["o", -1, 1], - ["os", -1, 1], - ["\u00E1", -1, 1], - ["\u00E9", -1, 2], - ["\u00ED", -1, 1], - ["\u00F3", -1, 1] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 17, 4, 10]; - - var /** number */ I_p2 = 0; - var /** number */ I_p1 = 0; - var /** number */ I_pV = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_pV = base.limit; - I_p1 = base.limit; - I_p2 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - lab1: { - var /** number */ v_2 = base.cursor; - lab2: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab2; - } - lab3: { - var /** number */ v_3 = base.cursor; - lab4: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab4; - } - golab5: while(true) - { - lab6: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab6; - } - break golab5; - } - if (base.cursor >= base.limit) - { - break lab4; - } - base.cursor++; - } - break lab3; - } - base.cursor = v_3; - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab2; - } - golab7: while(true) - { - lab8: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab8; - } - break golab7; - } - if (base.cursor >= base.limit) - { - break lab2; - } - base.cursor++; - } - } - break lab1; - } - base.cursor = v_2; - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab0; - } - lab9: { - var /** number */ v_6 = base.cursor; - lab10: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab10; - } - golab11: while(true) - { - lab12: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab12; - } - break golab11; - } - if (base.cursor >= base.limit) - { - break lab10; - } - base.cursor++; - } - break lab9; - } - base.cursor = v_6; - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab0; - } - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - } - } - I_pV = base.cursor; - } - base.cursor = v_1; - var /** number */ v_8 = base.cursor; - lab13: { - golab14: while(true) - { - lab15: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab15; - } - break golab14; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab16: while(true) - { - lab17: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab17; - } - break golab16; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p1 = base.cursor; - golab18: while(true) - { - lab19: { - if (!(base.in_grouping(g_v, 97, 252))) - { - break lab19; - } - break golab18; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - golab20: while(true) - { - lab21: { - if (!(base.out_grouping(g_v, 97, 252))) - { - break lab21; - } - break golab20; - } - if (base.cursor >= base.limit) - { - break lab13; - } - base.cursor++; - } - I_p2 = base.cursor; - } - base.cursor = v_8; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - var /** number */ among_var; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("a")) - { - return false; - } - break; - case 2: - if (!base.slice_from("e")) - { - return false; - } - break; - case 3: - if (!base.slice_from("i")) - { - return false; - } - break; - case 4: - if (!base.slice_from("o")) - { - return false; - } - break; - case 5: - if (!base.slice_from("u")) - { - return false; - } - break; - case 6: - if (base.cursor >= base.limit) - { - break lab0; - } - base.cursor++; - break; - } - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_RV() { - return I_pV <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R2() { - return I_p2 <= base.cursor; - }; - - /** @return {boolean} */ - function r_attached_pronoun() { - var /** number */ among_var; - base.ket = base.cursor; - if (base.find_among_b(a_1) == 0) - { - return false; - } - base.bra = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - return false; - } - if (!r_RV()) - { - return false; - } - switch (among_var) { - case 1: - base.bra = base.cursor; - if (!base.slice_from("iendo")) - { - return false; - } - break; - case 2: - base.bra = base.cursor; - if (!base.slice_from("ando")) - { - return false; - } - break; - case 3: - base.bra = base.cursor; - if (!base.slice_from("ar")) - { - return false; - } - break; - case 4: - base.bra = base.cursor; - if (!base.slice_from("er")) - { - return false; - } - break; - case 5: - base.bra = base.cursor; - if (!base.slice_from("ir")) - { - return false; - } - break; - case 6: - if (!base.slice_del()) - { - return false; - } - break; - case 7: - if (!(base.eq_s_b("u"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("ic"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 3: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("log")) - { - return false; - } - break; - case 4: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("u")) - { - return false; - } - break; - case 5: - if (!r_R2()) - { - return false; - } - if (!base.slice_from("ente")) - { - return false; - } - break; - case 6: - if (!r_R1()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - switch (among_var) { - case 1: - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_2; - break lab1; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_2; - break lab1; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - break; - case 7: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - if (base.find_among_b(a_4) == 0) - { - base.cursor = base.limit - v_3; - break lab2; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_3; - break lab2; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 8: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - lab3: { - base.ket = base.cursor; - if (base.find_among_b(a_5) == 0) - { - base.cursor = base.limit - v_4; - break lab3; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_4; - break lab3; - } - if (!base.slice_del()) - { - return false; - } - } - break; - case 9: - if (!r_R2()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_5 = base.limit - base.cursor; - lab4: { - base.ket = base.cursor; - if (!(base.eq_s_b("at"))) - { - base.cursor = base.limit - v_5; - break lab4; - } - base.bra = base.cursor; - if (!r_R2()) - { - base.cursor = base.limit - v_5; - break lab4; - } - if (!base.slice_del()) - { - return false; - } - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_y_verb_suffix() { - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - if (base.find_among_b(a_7) == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - if (!(base.eq_s_b("u"))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_verb_suffix() { - var /** number */ among_var; - if (base.cursor < I_pV) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_pV; - base.ket = base.cursor; - among_var = base.find_among_b(a_8); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("u"))) - { - base.cursor = base.limit - v_3; - break lab0; - } - var /** number */ v_4 = base.limit - base.cursor; - if (!(base.eq_s_b("g"))) - { - base.cursor = base.limit - v_3; - break lab0; - } - base.cursor = base.limit - v_4; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_residual_suffix() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_9); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_RV()) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (!(base.eq_s_b("u"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.bra = base.cursor; - var /** number */ v_2 = base.limit - base.cursor; - if (!(base.eq_s_b("g"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - base.cursor = base.limit - v_2; - if (!r_RV()) - { - base.cursor = base.limit - v_1; - break lab0; - } - if (!base.slice_del()) - { - return false; - } - } - break; - } - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_mark_regions(); - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_attached_pronoun(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - lab0: { - lab1: { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - if (!r_standard_suffix()) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_4; - lab3: { - if (!r_y_verb_suffix()) - { - break lab3; - } - break lab1; - } - base.cursor = base.limit - v_4; - if (!r_verb_suffix()) - { - break lab0; - } - } - } - base.cursor = base.limit - v_3; - var /** number */ v_5 = base.limit - base.cursor; - r_residual_suffix(); - base.cursor = base.limit - v_5; - base.cursor = base.limit_backward; - var /** number */ v_6 = base.cursor; - r_postlude(); - base.cursor = v_6; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['SpanishStemmer'] = SpanishStemmer; diff --git a/js/swedish-stemmer.js b/js/swedish-stemmer.js deleted file mode 100644 index 1e636f7..0000000 --- a/js/swedish-stemmer.js +++ /dev/null @@ -1,267 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var SwedishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["a", -1, 1], - ["arna", 0, 1], - ["erna", 0, 1], - ["heterna", 2, 1], - ["orna", 0, 1], - ["ad", -1, 1], - ["e", -1, 1], - ["ade", 6, 1], - ["ande", 6, 1], - ["arne", 6, 1], - ["are", 6, 1], - ["aste", 6, 1], - ["en", -1, 1], - ["anden", 12, 1], - ["aren", 12, 1], - ["heten", 12, 1], - ["ern", -1, 1], - ["ar", -1, 1], - ["er", -1, 1], - ["heter", 18, 1], - ["or", -1, 1], - ["s", -1, 2], - ["as", 21, 1], - ["arnas", 22, 1], - ["ernas", 22, 1], - ["ornas", 22, 1], - ["es", 21, 1], - ["ades", 26, 1], - ["andes", 26, 1], - ["ens", 21, 1], - ["arens", 29, 1], - ["hetens", 29, 1], - ["erns", 21, 1], - ["at", -1, 1], - ["andet", -1, 1], - ["het", -1, 1], - ["ast", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["dd", -1, -1], - ["gd", -1, -1], - ["nn", -1, -1], - ["dt", -1, -1], - ["gt", -1, -1], - ["kt", -1, -1], - ["tt", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["ig", -1, 1], - ["lig", 0, 1], - ["els", -1, 1], - ["fullt", -1, 3], - ["l\u00F6st", -1, 2] - ]; - - /** @const */ var /** Array */ g_v = [17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 24, 0, 32]; - - /** @const */ var /** Array */ g_s_ending = [119, 127, 149]; - - var /** number */ I_x = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - var /** number */ v_1 = base.cursor; - { - var /** number */ c1 = base.cursor + 3; - if (c1 > base.limit) - { - return false; - } - base.cursor = c1; - } - I_x = base.cursor; - base.cursor = v_1; - golab0: while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - if (!(base.in_grouping(g_v, 97, 246))) - { - break lab1; - } - base.cursor = v_2; - break golab0; - } - base.cursor = v_2; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - golab2: while(true) - { - lab3: { - if (!(base.out_grouping(g_v, 97, 246))) - { - break lab3; - } - break golab2; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - I_p1 = base.cursor; - lab4: { - if (I_p1 >= I_x) - { - break lab4; - } - I_p1 = I_x; - } - return true; - }; - - /** @return {boolean} */ - function r_main_suffix() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_0); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - base.limit_backward = v_2; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!(base.in_grouping_b(g_s_ending, 98, 121))) - { - return false; - } - if (!base.slice_del()) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_consonant_pair() { - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - var /** number */ v_3 = base.limit - base.cursor; - if (base.find_among_b(a_1) == 0) - { - base.limit_backward = v_2; - return false; - } - base.cursor = base.limit - v_3; - base.ket = base.cursor; - if (base.cursor <= base.limit_backward) - { - base.limit_backward = v_2; - return false; - } - base.cursor--; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.limit_backward = v_2; - return true; - }; - - /** @return {boolean} */ - function r_other_suffix() { - var /** number */ among_var; - if (base.cursor < I_p1) - { - return false; - } - var /** number */ v_2 = base.limit_backward; - base.limit_backward = I_p1; - base.ket = base.cursor; - among_var = base.find_among_b(a_2); - if (among_var == 0) - { - base.limit_backward = v_2; - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("l\u00F6s")) - { - return false; - } - break; - case 3: - if (!base.slice_from("full")) - { - return false; - } - break; - } - base.limit_backward = v_2; - return true; - }; - - this.stem = /** @return {boolean} */ function() { - var /** number */ v_1 = base.cursor; - r_mark_regions(); - base.cursor = v_1; - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_2 = base.limit - base.cursor; - r_main_suffix(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_consonant_pair(); - base.cursor = base.limit - v_3; - var /** number */ v_4 = base.limit - base.cursor; - r_other_suffix(); - base.cursor = base.limit - v_4; - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['SwedishStemmer'] = SwedishStemmer; diff --git a/js/tamil-stemmer.js b/js/tamil-stemmer.js deleted file mode 100644 index 2cc4b12..0000000 --- a/js/tamil-stemmer.js +++ /dev/null @@ -1,1190 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var TamilStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u0BB5\u0BC1", -1, 3], - ["\u0BB5\u0BC2", -1, 4], - ["\u0BB5\u0BCA", -1, 2], - ["\u0BB5\u0BCB", -1, 1] - ]; - - /** @const */ var a_1 = [ - ["\u0B95", -1, -1], - ["\u0B99", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9E", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BA8", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BAE", -1, -1], - ["\u0BAF", -1, -1], - ["\u0BB5", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC8", -1, -1] - ]; - - /** @const */ var a_3 = [ - ["\u0BBE", -1, -1], - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC1", -1, -1], - ["\u0BC2", -1, -1], - ["\u0BC6", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BC8", -1, -1] - ]; - - /** @const */ var a_4 = [ - ["", -1, 2], - ["\u0BC8", 0, 1], - ["\u0BCD", 0, 1] - ]; - - /** @const */ var a_5 = [ - ["\u0BA8\u0BCD\u0BA4", -1, 1], - ["\u0BAF", -1, 1], - ["\u0BB5", -1, 1], - ["\u0BA9\u0BC1", -1, 8], - ["\u0BC1\u0B95\u0BCD", -1, 7], - ["\u0BC1\u0B95\u0BCD\u0B95\u0BCD", -1, 7], - ["\u0B9F\u0BCD\u0B95\u0BCD", -1, 3], - ["\u0BB1\u0BCD\u0B95\u0BCD", -1, 4], - ["\u0B99\u0BCD", -1, 9], - ["\u0B9F\u0BCD\u0B9F\u0BCD", -1, 5], - ["\u0BA4\u0BCD\u0BA4\u0BCD", -1, 6], - ["\u0BA8\u0BCD\u0BA4\u0BCD", -1, 1], - ["\u0BA8\u0BCD", -1, 1], - ["\u0B9F\u0BCD\u0BAA\u0BCD", -1, 3], - ["\u0BAF\u0BCD", -1, 2], - ["\u0BA9\u0BCD\u0BB1\u0BCD", -1, 4], - ["\u0BB5\u0BCD", -1, 1] - ]; - - /** @const */ var a_6 = [ - ["\u0B95", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9F", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BB1", -1, -1] - ]; - - /** @const */ var a_7 = [ - ["\u0B95", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9F", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BB1", -1, -1] - ]; - - /** @const */ var a_8 = [ - ["\u0B9E", -1, -1], - ["\u0BA3", -1, -1], - ["\u0BA8", -1, -1], - ["\u0BA9", -1, -1], - ["\u0BAE", -1, -1], - ["\u0BAF", -1, -1], - ["\u0BB0", -1, -1], - ["\u0BB2", -1, -1], - ["\u0BB3", -1, -1], - ["\u0BB4", -1, -1], - ["\u0BB5", -1, -1] - ]; - - /** @const */ var a_9 = [ - ["\u0BBE", -1, -1], - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC1", -1, -1], - ["\u0BC2", -1, -1], - ["\u0BC6", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BC8", -1, -1], - ["\u0BCD", -1, -1] - ]; - - /** @const */ var a_10 = [ - ["\u0B85", -1, -1], - ["\u0B87", -1, -1], - ["\u0B89", -1, -1] - ]; - - /** @const */ var a_11 = [ - ["\u0B95", -1, -1], - ["\u0B99", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9E", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BA8", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BAE", -1, -1], - ["\u0BAF", -1, -1], - ["\u0BB5", -1, -1] - ]; - - /** @const */ var a_12 = [ - ["\u0B95", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9F", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BB1", -1, -1] - ]; - - /** @const */ var a_13 = [ - ["\u0B95\u0BB3\u0BCD", -1, 4], - ["\u0BC1\u0B99\u0BCD\u0B95\u0BB3\u0BCD", 0, 1], - ["\u0B9F\u0BCD\u0B95\u0BB3\u0BCD", 0, 3], - ["\u0BB1\u0BCD\u0B95\u0BB3\u0BCD", 0, 2] - ]; - - /** @const */ var a_14 = [ - ["\u0BBE", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BCB", -1, -1] - ]; - - /** @const */ var a_15 = [ - ["\u0BAA\u0BBF", -1, -1], - ["\u0BB5\u0BBF", -1, -1] - ]; - - /** @const */ var a_16 = [ - ["\u0BBE", -1, -1], - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC1", -1, -1], - ["\u0BC2", -1, -1], - ["\u0BC6", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BC8", -1, -1] - ]; - - /** @const */ var a_17 = [ - ["\u0BAA\u0B9F\u0BCD\u0B9F", -1, 3], - ["\u0BAA\u0B9F\u0BCD\u0B9F\u0BA3", -1, 3], - ["\u0BA4\u0BBE\u0BA9", -1, 3], - ["\u0BAA\u0B9F\u0BBF\u0BA4\u0BBE\u0BA9", 2, 3], - ["\u0BC6\u0BA9", -1, 1], - ["\u0BBE\u0B95\u0BBF\u0BAF", -1, 1], - ["\u0B95\u0BC1\u0BB0\u0BBF\u0BAF", -1, 3], - ["\u0BC1\u0B9F\u0BC8\u0BAF", -1, 1], - ["\u0BB2\u0BCD\u0BB2", -1, 2], - ["\u0BC1\u0BB3\u0BCD\u0BB3", -1, 1], - ["\u0BBE\u0B95\u0BBF", -1, 1], - ["\u0BAA\u0B9F\u0BBF", -1, 3], - ["\u0BBF\u0BA9\u0BCD\u0BB1\u0BBF", -1, 1], - ["\u0BAA\u0BB1\u0BCD\u0BB1\u0BBF", -1, 3], - ["\u0BAA\u0B9F\u0BC1", -1, 3], - ["\u0BB5\u0BBF\u0B9F\u0BC1", -1, 3], - ["\u0BAA\u0B9F\u0BCD\u0B9F\u0BC1", -1, 3], - ["\u0BB5\u0BBF\u0B9F\u0BCD\u0B9F\u0BC1", -1, 3], - ["\u0BAA\u0B9F\u0BCD\u0B9F\u0BA4\u0BC1", -1, 3], - ["\u0BC6\u0BA9\u0BCD\u0BB1\u0BC1", -1, 1], - ["\u0BC1\u0B9F\u0BC8", -1, 1], - ["\u0BBF\u0BB2\u0BCD\u0BB2\u0BC8", -1, 1], - ["\u0BC1\u0B9F\u0BA9\u0BCD", -1, 1], - ["\u0BBF\u0B9F\u0BAE\u0BCD", -1, 1], - ["\u0BC6\u0BB2\u0BCD\u0BB2\u0BBE\u0BAE\u0BCD", -1, 3], - ["\u0BC6\u0BA9\u0BC1\u0BAE\u0BCD", -1, 1] - ]; - - /** @const */ var a_18 = [ - ["\u0BBE", -1, -1], - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC1", -1, -1], - ["\u0BC2", -1, -1], - ["\u0BC6", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BC8", -1, -1] - ]; - - /** @const */ var a_19 = [ - ["\u0BBE", -1, -1], - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC1", -1, -1], - ["\u0BC2", -1, -1], - ["\u0BC6", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BC8", -1, -1] - ]; - - /** @const */ var a_20 = [ - ["\u0BB5\u0BBF\u0B9F", -1, 2], - ["\u0BC0", -1, 7], - ["\u0BCA\u0B9F\u0BC1", -1, 2], - ["\u0BCB\u0B9F\u0BC1", -1, 2], - ["\u0BA4\u0BC1", -1, 6], - ["\u0BBF\u0BB0\u0BC1\u0BA8\u0BCD\u0BA4\u0BC1", 4, 2], - ["\u0BBF\u0BA9\u0BCD\u0BB1\u0BC1", -1, 2], - ["\u0BC1\u0B9F\u0BC8", -1, 2], - ["\u0BA9\u0BC8", -1, 1], - ["\u0B95\u0BA3\u0BCD", -1, 1], - ["\u0BBF\u0BA9\u0BCD", -1, 3], - ["\u0BAE\u0BC1\u0BA9\u0BCD", -1, 1], - ["\u0BBF\u0B9F\u0BAE\u0BCD", -1, 4], - ["\u0BBF\u0BB1\u0BCD", -1, 2], - ["\u0BAE\u0BC7\u0BB1\u0BCD", -1, 1], - ["\u0BB2\u0BCD", -1, 5], - ["\u0BBE\u0BAE\u0BB2\u0BCD", 15, 2], - ["\u0BBE\u0BB2\u0BCD", 15, 2], - ["\u0BBF\u0BB2\u0BCD", 15, 2], - ["\u0BAE\u0BC7\u0BB2\u0BCD", 15, 1], - ["\u0BC1\u0BB3\u0BCD", -1, 2], - ["\u0B95\u0BC0\u0BB4\u0BCD", -1, 1] - ]; - - /** @const */ var a_21 = [ - ["\u0B95", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9F", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BB1", -1, -1] - ]; - - /** @const */ var a_22 = [ - ["\u0B95", -1, -1], - ["\u0B9A", -1, -1], - ["\u0B9F", -1, -1], - ["\u0BA4", -1, -1], - ["\u0BAA", -1, -1], - ["\u0BB1", -1, -1] - ]; - - /** @const */ var a_23 = [ - ["\u0B85", -1, -1], - ["\u0B86", -1, -1], - ["\u0B87", -1, -1], - ["\u0B88", -1, -1], - ["\u0B89", -1, -1], - ["\u0B8A", -1, -1], - ["\u0B8E", -1, -1], - ["\u0B8F", -1, -1], - ["\u0B90", -1, -1], - ["\u0B92", -1, -1], - ["\u0B93", -1, -1], - ["\u0B94", -1, -1] - ]; - - /** @const */ var a_24 = [ - ["\u0BBE", -1, -1], - ["\u0BBF", -1, -1], - ["\u0BC0", -1, -1], - ["\u0BC1", -1, -1], - ["\u0BC2", -1, -1], - ["\u0BC6", -1, -1], - ["\u0BC7", -1, -1], - ["\u0BC8", -1, -1] - ]; - - /** @const */ var a_25 = [ - ["\u0B95", -1, 1], - ["\u0BA4", -1, 1], - ["\u0BA9", -1, 1], - ["\u0BAA", -1, 1], - ["\u0BAF", -1, 1], - ["\u0BBE", -1, 5], - ["\u0B95\u0BC1", -1, 6], - ["\u0BAA\u0B9F\u0BC1", -1, 1], - ["\u0BA4\u0BC1", -1, 3], - ["\u0BBF\u0BB1\u0BCD\u0BB1\u0BC1", -1, 1], - ["\u0BA9\u0BC8", -1, 1], - ["\u0BB5\u0BC8", -1, 1], - ["\u0BA9\u0BA9\u0BCD", -1, 1], - ["\u0BAA\u0BA9\u0BCD", -1, 1], - ["\u0BB5\u0BA9\u0BCD", -1, 2], - ["\u0BBE\u0BA9\u0BCD", -1, 4], - ["\u0BA9\u0BBE\u0BA9\u0BCD", 15, 1], - ["\u0BAE\u0BBF\u0BA9\u0BCD", -1, 1], - ["\u0BA9\u0BC6\u0BA9\u0BCD", -1, 1], - ["\u0BC7\u0BA9\u0BCD", -1, 5], - ["\u0BA9\u0BAE\u0BCD", -1, 1], - ["\u0BAA\u0BAE\u0BCD", -1, 1], - ["\u0BBE\u0BAE\u0BCD", -1, 5], - ["\u0B95\u0BC1\u0BAE\u0BCD", -1, 1], - ["\u0B9F\u0BC1\u0BAE\u0BCD", -1, 5], - ["\u0BA4\u0BC1\u0BAE\u0BCD", -1, 1], - ["\u0BB1\u0BC1\u0BAE\u0BCD", -1, 1], - ["\u0BC6\u0BAE\u0BCD", -1, 5], - ["\u0BC7\u0BAE\u0BCD", -1, 5], - ["\u0BCB\u0BAE\u0BCD", -1, 5], - ["\u0BBE\u0BAF\u0BCD", -1, 5], - ["\u0BA9\u0BB0\u0BCD", -1, 1], - ["\u0BAA\u0BB0\u0BCD", -1, 1], - ["\u0BC0\u0BAF\u0BB0\u0BCD", -1, 5], - ["\u0BB5\u0BB0\u0BCD", -1, 1], - ["\u0BBE\u0BB0\u0BCD", -1, 5], - ["\u0BA9\u0BBE\u0BB0\u0BCD", 35, 1], - ["\u0BAE\u0BBE\u0BB0\u0BCD", 35, 1], - ["\u0B95\u0BCA\u0BA3\u0BCD\u0B9F\u0BBF\u0BB0\u0BCD", -1, 1], - ["\u0BA9\u0BBF\u0BB0\u0BCD", -1, 5], - ["\u0BC0\u0BB0\u0BCD", -1, 5], - ["\u0BA9\u0BB3\u0BCD", -1, 1], - ["\u0BAA\u0BB3\u0BCD", -1, 1], - ["\u0BB5\u0BB3\u0BCD", -1, 1], - ["\u0BBE\u0BB3\u0BCD", -1, 5], - ["\u0BA9\u0BBE\u0BB3\u0BCD", 44, 1] - ]; - - /** @const */ var a_26 = [ - ["\u0B95\u0BBF\u0BB1", -1, -1], - ["\u0B95\u0BBF\u0BA9\u0BCD\u0BB1", -1, -1], - ["\u0BBE\u0BA8\u0BBF\u0BA9\u0BCD\u0BB1", -1, -1], - ["\u0B95\u0BBF\u0BB1\u0BCD", -1, -1], - ["\u0B95\u0BBF\u0BA9\u0BCD\u0BB1\u0BCD", -1, -1], - ["\u0BBE\u0BA8\u0BBF\u0BA9\u0BCD\u0BB1\u0BCD", -1, -1] - ]; - - var /** boolean */ B_found_vetrumai_urupu = false; - var /** boolean */ B_found_a_match = false; - - - /** @return {boolean} */ - function r_has_min_length() { - return base.current.length > 4; - }; - - /** @return {boolean} */ - function r_fix_va_start() { - var /** number */ among_var; - base.bra = base.cursor; - among_var = base.find_among(a_0); - if (among_var == 0) - { - return false; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u0B93")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u0B92")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u0B89")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u0B8A")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_fix_endings() { - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - if (!r_fix_ending()) - { - break lab1; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_remove_question_prefixes() { - base.bra = base.cursor; - if (!(base.eq_s("\u0B8E"))) - { - return false; - } - if (base.find_among(a_1) == 0) - { - return false; - } - if (!(base.eq_s("\u0BCD"))) - { - return false; - } - base.ket = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.cursor; - r_fix_va_start(); - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_fix_ending() { - var /** number */ among_var; - if (base.current.length <= 3) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - break lab1; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - var /** number */ v_2 = base.limit - base.cursor; - if (base.find_among_b(a_2) == 0) - { - break lab1; - } - base.cursor = base.limit - v_2; - if (!base.slice_del()) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u0BB3\u0BCD")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u0BB2\u0BCD")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u0B9F\u0BC1")) - { - return false; - } - break; - case 6: - if (!B_found_vetrumai_urupu) - { - break lab1; - } - { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - if (!(base.eq_s_b("\u0BC8"))) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_3; - } - if (!base.slice_from("\u0BAE\u0BCD")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 8: - { - var /** number */ v_4 = base.limit - base.cursor; - lab3: { - if (base.find_among_b(a_3) == 0) - { - break lab3; - } - break lab1; - } - base.cursor = base.limit - v_4; - } - if (!base.slice_del()) - { - return false; - } - break; - case 9: - among_var = base.find_among_b(a_4); - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u0BAE\u0BCD")) - { - return false; - } - break; - } - break; - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - if (!(base.eq_s_b("\u0BCD"))) - { - return false; - } - lab4: { - var /** number */ v_5 = base.limit - base.cursor; - lab5: { - if (base.find_among_b(a_6) == 0) - { - break lab5; - } - var /** number */ v_6 = base.limit - base.cursor; - lab6: { - if (!(base.eq_s_b("\u0BCD"))) - { - base.cursor = base.limit - v_6; - break lab6; - } - if (base.find_among_b(a_7) == 0) - { - base.cursor = base.limit - v_6; - break lab6; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_5; - lab7: { - if (base.find_among_b(a_8) == 0) - { - break lab7; - } - base.bra = base.cursor; - if (!(base.eq_s_b("\u0BCD"))) - { - break lab7; - } - if (!base.slice_del()) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_5; - var /** number */ v_7 = base.limit - base.cursor; - if (base.find_among_b(a_9) == 0) - { - return false; - } - base.cursor = base.limit - v_7; - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - } - } - base.cursor = base.limit_backward; - return true; - }; - - /** @return {boolean} */ - function r_remove_pronoun_prefixes() { - base.bra = base.cursor; - if (base.find_among(a_10) == 0) - { - return false; - } - if (base.find_among(a_11) == 0) - { - return false; - } - if (!(base.eq_s("\u0BCD"))) - { - return false; - } - base.ket = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_1 = base.cursor; - r_fix_va_start(); - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_remove_plural_suffix() { - var /** number */ among_var; - base.limit_backward = base.cursor; base.cursor = base.limit; - base.ket = base.cursor; - among_var = base.find_among_b(a_13); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (base.find_among_b(a_12) == 0) - { - break lab1; - } - if (!base.slice_from("\u0BC1\u0B99\u0BCD")) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!base.slice_from("\u0BCD")) - { - return false; - } - } - break; - case 2: - if (!base.slice_from("\u0BB2\u0BCD")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u0BB3\u0BCD")) - { - return false; - } - break; - case 4: - if (!base.slice_del()) - { - return false; - } - break; - } - base.cursor = base.limit_backward; - return true; - }; - - /** @return {boolean} */ - function r_remove_question_suffixes() { - if (!r_has_min_length()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - if (base.find_among_b(a_14) == 0) - { - break lab0; - } - base.bra = base.cursor; - if (!base.slice_from("\u0BCD")) - { - return false; - } - } - base.cursor = base.limit - v_1; - base.cursor = base.limit_backward; - r_fix_endings(); - return true; - }; - - /** @return {boolean} */ - function r_remove_command_suffixes() { - if (!r_has_min_length()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - base.ket = base.cursor; - if (base.find_among_b(a_15) == 0) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.cursor = base.limit_backward; - return true; - }; - - /** @return {boolean} */ - function r_remove_um() { - if (!r_has_min_length()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - base.ket = base.cursor; - if (!(base.eq_s_b("\u0BC1\u0BAE\u0BCD"))) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_from("\u0BCD")) - { - return false; - } - base.cursor = base.limit_backward; - var /** number */ v_1 = base.cursor; - r_fix_ending(); - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_remove_common_word_endings() { - var /** number */ among_var; - if (!r_has_min_length()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - base.ket = base.cursor; - among_var = base.find_among_b(a_17); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 2: - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (base.find_among_b(a_16) == 0) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_1; - } - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 3: - if (!base.slice_del()) - { - return false; - } - break; - } - base.cursor = base.limit_backward; - r_fix_endings(); - return true; - }; - - /** @return {boolean} */ - function r_remove_vetrumai_urupukal() { - var /** number */ among_var; - B_found_vetrumai_urupu = false; - if (!r_has_min_length()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - base.ket = base.cursor; - among_var = base.find_among_b(a_20); - if (among_var == 0) - { - break lab1; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 3: - { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - if (!(base.eq_s_b("\u0BAE"))) - { - break lab2; - } - break lab1; - } - base.cursor = base.limit - v_3; - } - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 4: - if (base.current.length < 7) - { - break lab1; - } - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 5: - { - var /** number */ v_4 = base.limit - base.cursor; - lab3: { - if (base.find_among_b(a_18) == 0) - { - break lab3; - } - break lab1; - } - base.cursor = base.limit - v_4; - } - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 6: - { - var /** number */ v_5 = base.limit - base.cursor; - lab4: { - if (base.find_among_b(a_19) == 0) - { - break lab4; - } - break lab1; - } - base.cursor = base.limit - v_5; - } - if (!base.slice_del()) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u0BBF")) - { - return false; - } - break; - } - base.cursor = base.limit - v_2; - break lab0; - } - base.cursor = base.limit - v_1; - var /** number */ v_6 = base.limit - base.cursor; - base.ket = base.cursor; - if (!(base.eq_s_b("\u0BC8"))) - { - return false; - } - lab5: { - var /** number */ v_7 = base.limit - base.cursor; - lab6: { - { - var /** number */ v_8 = base.limit - base.cursor; - lab7: { - if (base.find_among_b(a_21) == 0) - { - break lab7; - } - break lab6; - } - base.cursor = base.limit - v_8; - } - break lab5; - } - base.cursor = base.limit - v_7; - var /** number */ v_9 = base.limit - base.cursor; - if (base.find_among_b(a_22) == 0) - { - return false; - } - if (!(base.eq_s_b("\u0BCD"))) - { - return false; - } - base.cursor = base.limit - v_9; - } - base.bra = base.cursor; - if (!base.slice_from("\u0BCD")) - { - return false; - } - base.cursor = base.limit - v_6; - } - B_found_vetrumai_urupu = true; - var /** number */ v_10 = base.limit - base.cursor; - lab8: { - base.ket = base.cursor; - if (!(base.eq_s_b("\u0BBF\u0BA9\u0BCD"))) - { - break lab8; - } - base.bra = base.cursor; - if (!base.slice_from("\u0BCD")) - { - return false; - } - } - base.cursor = base.limit - v_10; - base.cursor = base.limit_backward; - r_fix_endings(); - return true; - }; - - /** @return {boolean} */ - function r_remove_tense_suffixes() { - B_found_a_match = true; - while(true) - { - var /** number */ v_1 = base.cursor; - lab0: { - if (!B_found_a_match) - { - break lab0; - } - var /** number */ v_2 = base.cursor; - r_remove_tense_suffix(); - base.cursor = v_2; - continue; - } - base.cursor = v_1; - break; - } - return true; - }; - - /** @return {boolean} */ - function r_remove_tense_suffix() { - var /** number */ among_var; - B_found_a_match = false; - if (!r_has_min_length()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - var /** number */ v_2 = base.limit - base.cursor; - base.ket = base.cursor; - among_var = base.find_among_b(a_25); - if (among_var == 0) - { - break lab0; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_del()) - { - return false; - } - break; - case 2: - { - var /** number */ v_3 = base.limit - base.cursor; - lab1: { - if (base.find_among_b(a_23) == 0) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_3; - } - if (!base.slice_del()) - { - return false; - } - break; - case 3: - { - var /** number */ v_4 = base.limit - base.cursor; - lab2: { - if (base.find_among_b(a_24) == 0) - { - break lab2; - } - break lab0; - } - base.cursor = base.limit - v_4; - } - if (!base.slice_del()) - { - return false; - } - break; - case 4: - { - var /** number */ v_5 = base.limit - base.cursor; - lab3: { - if (!(base.eq_s_b("\u0B9A"))) - { - break lab3; - } - break lab0; - } - base.cursor = base.limit - v_5; - } - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u0BCD")) - { - return false; - } - break; - case 6: - var /** number */ v_6 = base.limit - base.cursor; - if (!(base.eq_s_b("\u0BCD"))) - { - break lab0; - } - base.cursor = base.limit - v_6; - if (!base.slice_del()) - { - return false; - } - break; - } - B_found_a_match = true; - base.cursor = base.limit - v_2; - } - base.cursor = base.limit - v_1; - var /** number */ v_7 = base.limit - base.cursor; - lab4: { - base.ket = base.cursor; - if (base.find_among_b(a_26) == 0) - { - break lab4; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - B_found_a_match = true; - } - base.cursor = base.limit - v_7; - base.cursor = base.limit_backward; - r_fix_endings(); - return true; - }; - - this.stem = /** @return {boolean} */ function() { - B_found_vetrumai_urupu = false; - var /** number */ v_1 = base.cursor; - r_fix_ending(); - base.cursor = v_1; - if (!r_has_min_length()) - { - return false; - } - var /** number */ v_2 = base.cursor; - r_remove_question_prefixes(); - base.cursor = v_2; - var /** number */ v_3 = base.cursor; - r_remove_pronoun_prefixes(); - base.cursor = v_3; - var /** number */ v_4 = base.cursor; - r_remove_question_suffixes(); - base.cursor = v_4; - var /** number */ v_5 = base.cursor; - r_remove_um(); - base.cursor = v_5; - var /** number */ v_6 = base.cursor; - r_remove_common_word_endings(); - base.cursor = v_6; - var /** number */ v_7 = base.cursor; - r_remove_vetrumai_urupukal(); - base.cursor = v_7; - var /** number */ v_8 = base.cursor; - r_remove_plural_suffix(); - base.cursor = v_8; - var /** number */ v_9 = base.cursor; - r_remove_command_suffixes(); - base.cursor = v_9; - var /** number */ v_10 = base.cursor; - r_remove_tense_suffixes(); - base.cursor = v_10; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['TamilStemmer'] = TamilStemmer; diff --git a/js/turkish-stemmer.js b/js/turkish-stemmer.js deleted file mode 100644 index 84f6255..0000000 --- a/js/turkish-stemmer.js +++ /dev/null @@ -1,2361 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var TurkishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["m", -1, -1], - ["n", -1, -1], - ["miz", -1, -1], - ["niz", -1, -1], - ["muz", -1, -1], - ["nuz", -1, -1], - ["m\u00FCz", -1, -1], - ["n\u00FCz", -1, -1], - ["m\u0131z", -1, -1], - ["n\u0131z", -1, -1] - ]; - - /** @const */ var a_1 = [ - ["leri", -1, -1], - ["lar\u0131", -1, -1] - ]; - - /** @const */ var a_2 = [ - ["ni", -1, -1], - ["nu", -1, -1], - ["n\u00FC", -1, -1], - ["n\u0131", -1, -1] - ]; - - /** @const */ var a_3 = [ - ["in", -1, -1], - ["un", -1, -1], - ["\u00FCn", -1, -1], - ["\u0131n", -1, -1] - ]; - - /** @const */ var a_4 = [ - ["a", -1, -1], - ["e", -1, -1] - ]; - - /** @const */ var a_5 = [ - ["na", -1, -1], - ["ne", -1, -1] - ]; - - /** @const */ var a_6 = [ - ["da", -1, -1], - ["ta", -1, -1], - ["de", -1, -1], - ["te", -1, -1] - ]; - - /** @const */ var a_7 = [ - ["nda", -1, -1], - ["nde", -1, -1] - ]; - - /** @const */ var a_8 = [ - ["dan", -1, -1], - ["tan", -1, -1], - ["den", -1, -1], - ["ten", -1, -1] - ]; - - /** @const */ var a_9 = [ - ["ndan", -1, -1], - ["nden", -1, -1] - ]; - - /** @const */ var a_10 = [ - ["la", -1, -1], - ["le", -1, -1] - ]; - - /** @const */ var a_11 = [ - ["ca", -1, -1], - ["ce", -1, -1] - ]; - - /** @const */ var a_12 = [ - ["im", -1, -1], - ["um", -1, -1], - ["\u00FCm", -1, -1], - ["\u0131m", -1, -1] - ]; - - /** @const */ var a_13 = [ - ["sin", -1, -1], - ["sun", -1, -1], - ["s\u00FCn", -1, -1], - ["s\u0131n", -1, -1] - ]; - - /** @const */ var a_14 = [ - ["iz", -1, -1], - ["uz", -1, -1], - ["\u00FCz", -1, -1], - ["\u0131z", -1, -1] - ]; - - /** @const */ var a_15 = [ - ["siniz", -1, -1], - ["sunuz", -1, -1], - ["s\u00FCn\u00FCz", -1, -1], - ["s\u0131n\u0131z", -1, -1] - ]; - - /** @const */ var a_16 = [ - ["lar", -1, -1], - ["ler", -1, -1] - ]; - - /** @const */ var a_17 = [ - ["niz", -1, -1], - ["nuz", -1, -1], - ["n\u00FCz", -1, -1], - ["n\u0131z", -1, -1] - ]; - - /** @const */ var a_18 = [ - ["dir", -1, -1], - ["tir", -1, -1], - ["dur", -1, -1], - ["tur", -1, -1], - ["d\u00FCr", -1, -1], - ["t\u00FCr", -1, -1], - ["d\u0131r", -1, -1], - ["t\u0131r", -1, -1] - ]; - - /** @const */ var a_19 = [ - ["cas\u0131na", -1, -1], - ["cesine", -1, -1] - ]; - - /** @const */ var a_20 = [ - ["di", -1, -1], - ["ti", -1, -1], - ["dik", -1, -1], - ["tik", -1, -1], - ["duk", -1, -1], - ["tuk", -1, -1], - ["d\u00FCk", -1, -1], - ["t\u00FCk", -1, -1], - ["d\u0131k", -1, -1], - ["t\u0131k", -1, -1], - ["dim", -1, -1], - ["tim", -1, -1], - ["dum", -1, -1], - ["tum", -1, -1], - ["d\u00FCm", -1, -1], - ["t\u00FCm", -1, -1], - ["d\u0131m", -1, -1], - ["t\u0131m", -1, -1], - ["din", -1, -1], - ["tin", -1, -1], - ["dun", -1, -1], - ["tun", -1, -1], - ["d\u00FCn", -1, -1], - ["t\u00FCn", -1, -1], - ["d\u0131n", -1, -1], - ["t\u0131n", -1, -1], - ["du", -1, -1], - ["tu", -1, -1], - ["d\u00FC", -1, -1], - ["t\u00FC", -1, -1], - ["d\u0131", -1, -1], - ["t\u0131", -1, -1] - ]; - - /** @const */ var a_21 = [ - ["sa", -1, -1], - ["se", -1, -1], - ["sak", -1, -1], - ["sek", -1, -1], - ["sam", -1, -1], - ["sem", -1, -1], - ["san", -1, -1], - ["sen", -1, -1] - ]; - - /** @const */ var a_22 = [ - ["mi\u015F", -1, -1], - ["mu\u015F", -1, -1], - ["m\u00FC\u015F", -1, -1], - ["m\u0131\u015F", -1, -1] - ]; - - /** @const */ var a_23 = [ - ["b", -1, 1], - ["c", -1, 2], - ["d", -1, 3], - ["\u011F", -1, 4] - ]; - - /** @const */ var /** Array */ g_vowel = [17, 65, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 32, 8, 0, 0, 0, 0, 0, 0, 1]; - - /** @const */ var /** Array */ g_U = [1, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 1]; - - /** @const */ var /** Array */ g_vowel1 = [1, 64, 16, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1]; - - /** @const */ var /** Array */ g_vowel2 = [17, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 130]; - - /** @const */ var /** Array */ g_vowel3 = [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1]; - - /** @const */ var /** Array */ g_vowel4 = [17]; - - /** @const */ var /** Array */ g_vowel5 = [65]; - - /** @const */ var /** Array */ g_vowel6 = [65]; - - var /** boolean */ B_continue_stemming_noun_suffixes = false; - - - /** @return {boolean} */ - function r_check_vowel_harmony() { - var /** number */ v_1 = base.limit - base.cursor; - golab0: while(true) - { - var /** number */ v_2 = base.limit - base.cursor; - lab1: { - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - break lab1; - } - base.cursor = base.limit - v_2; - break golab0; - } - base.cursor = base.limit - v_2; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - lab2: { - var /** number */ v_3 = base.limit - base.cursor; - lab3: { - if (!(base.eq_s_b("a"))) - { - break lab3; - } - golab4: while(true) - { - var /** number */ v_4 = base.limit - base.cursor; - lab5: { - if (!(base.in_grouping_b(g_vowel1, 97, 305))) - { - break lab5; - } - base.cursor = base.limit - v_4; - break golab4; - } - base.cursor = base.limit - v_4; - if (base.cursor <= base.limit_backward) - { - break lab3; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - lab6: { - if (!(base.eq_s_b("e"))) - { - break lab6; - } - golab7: while(true) - { - var /** number */ v_5 = base.limit - base.cursor; - lab8: { - if (!(base.in_grouping_b(g_vowel2, 101, 252))) - { - break lab8; - } - base.cursor = base.limit - v_5; - break golab7; - } - base.cursor = base.limit - v_5; - if (base.cursor <= base.limit_backward) - { - break lab6; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - lab9: { - if (!(base.eq_s_b("\u0131"))) - { - break lab9; - } - golab10: while(true) - { - var /** number */ v_6 = base.limit - base.cursor; - lab11: { - if (!(base.in_grouping_b(g_vowel3, 97, 305))) - { - break lab11; - } - base.cursor = base.limit - v_6; - break golab10; - } - base.cursor = base.limit - v_6; - if (base.cursor <= base.limit_backward) - { - break lab9; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - lab12: { - if (!(base.eq_s_b("i"))) - { - break lab12; - } - golab13: while(true) - { - var /** number */ v_7 = base.limit - base.cursor; - lab14: { - if (!(base.in_grouping_b(g_vowel4, 101, 105))) - { - break lab14; - } - base.cursor = base.limit - v_7; - break golab13; - } - base.cursor = base.limit - v_7; - if (base.cursor <= base.limit_backward) - { - break lab12; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - lab15: { - if (!(base.eq_s_b("o"))) - { - break lab15; - } - golab16: while(true) - { - var /** number */ v_8 = base.limit - base.cursor; - lab17: { - if (!(base.in_grouping_b(g_vowel5, 111, 117))) - { - break lab17; - } - base.cursor = base.limit - v_8; - break golab16; - } - base.cursor = base.limit - v_8; - if (base.cursor <= base.limit_backward) - { - break lab15; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - lab18: { - if (!(base.eq_s_b("\u00F6"))) - { - break lab18; - } - golab19: while(true) - { - var /** number */ v_9 = base.limit - base.cursor; - lab20: { - if (!(base.in_grouping_b(g_vowel6, 246, 252))) - { - break lab20; - } - base.cursor = base.limit - v_9; - break golab19; - } - base.cursor = base.limit - v_9; - if (base.cursor <= base.limit_backward) - { - break lab18; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - lab21: { - if (!(base.eq_s_b("u"))) - { - break lab21; - } - golab22: while(true) - { - var /** number */ v_10 = base.limit - base.cursor; - lab23: { - if (!(base.in_grouping_b(g_vowel5, 111, 117))) - { - break lab23; - } - base.cursor = base.limit - v_10; - break golab22; - } - base.cursor = base.limit - v_10; - if (base.cursor <= base.limit_backward) - { - break lab21; - } - base.cursor--; - } - break lab2; - } - base.cursor = base.limit - v_3; - if (!(base.eq_s_b("\u00FC"))) - { - return false; - } - golab24: while(true) - { - var /** number */ v_11 = base.limit - base.cursor; - lab25: { - if (!(base.in_grouping_b(g_vowel6, 246, 252))) - { - break lab25; - } - base.cursor = base.limit - v_11; - break golab24; - } - base.cursor = base.limit - v_11; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - } - base.cursor = base.limit - v_1; - return true; - }; - - /** @return {boolean} */ - function r_mark_suffix_with_optional_n_consonant() { - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("n"))) - { - break lab1; - } - var /** number */ v_2 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - break lab1; - } - base.cursor = base.limit - v_2; - break lab0; - } - base.cursor = base.limit - v_1; - { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - var /** number */ v_4 = base.limit - base.cursor; - if (!(base.eq_s_b("n"))) - { - break lab2; - } - base.cursor = base.limit - v_4; - return false; - } - base.cursor = base.limit - v_3; - } - var /** number */ v_5 = base.limit - base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - return false; - } - base.cursor = base.limit - v_5; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_suffix_with_optional_s_consonant() { - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("s"))) - { - break lab1; - } - var /** number */ v_2 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - break lab1; - } - base.cursor = base.limit - v_2; - break lab0; - } - base.cursor = base.limit - v_1; - { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - var /** number */ v_4 = base.limit - base.cursor; - if (!(base.eq_s_b("s"))) - { - break lab2; - } - base.cursor = base.limit - v_4; - return false; - } - base.cursor = base.limit - v_3; - } - var /** number */ v_5 = base.limit - base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - return false; - } - base.cursor = base.limit - v_5; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_suffix_with_optional_y_consonant() { - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("y"))) - { - break lab1; - } - var /** number */ v_2 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - break lab1; - } - base.cursor = base.limit - v_2; - break lab0; - } - base.cursor = base.limit - v_1; - { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - var /** number */ v_4 = base.limit - base.cursor; - if (!(base.eq_s_b("y"))) - { - break lab2; - } - base.cursor = base.limit - v_4; - return false; - } - base.cursor = base.limit - v_3; - } - var /** number */ v_5 = base.limit - base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - return false; - } - base.cursor = base.limit - v_5; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_suffix_with_optional_U_vowel() { - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.in_grouping_b(g_U, 105, 305))) - { - break lab1; - } - var /** number */ v_2 = base.limit - base.cursor; - if (!(base.out_grouping_b(g_vowel, 97, 305))) - { - break lab1; - } - base.cursor = base.limit - v_2; - break lab0; - } - base.cursor = base.limit - v_1; - { - var /** number */ v_3 = base.limit - base.cursor; - lab2: { - var /** number */ v_4 = base.limit - base.cursor; - if (!(base.in_grouping_b(g_U, 105, 305))) - { - break lab2; - } - base.cursor = base.limit - v_4; - return false; - } - base.cursor = base.limit - v_3; - } - var /** number */ v_5 = base.limit - base.cursor; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - if (!(base.out_grouping_b(g_vowel, 97, 305))) - { - return false; - } - base.cursor = base.limit - v_5; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_possessives() { - if (base.find_among_b(a_0) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_U_vowel()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_sU() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (!(base.in_grouping_b(g_U, 105, 305))) - { - return false; - } - if (!r_mark_suffix_with_optional_s_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_lArI() { - if (base.find_among_b(a_1) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_yU() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (!(base.in_grouping_b(g_U, 105, 305))) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_nU() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_2) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_nUn() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_3) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_n_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_yA() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_4) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_nA() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_5) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_DA() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_6) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ndA() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_7) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_DAn() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_8) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ndAn() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_9) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ylA() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_10) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ki() { - if (!(base.eq_s_b("ki"))) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ncA() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_11) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_n_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_yUm() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_12) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_sUn() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_13) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_yUz() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_14) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_sUnUz() { - if (base.find_among_b(a_15) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_lAr() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_16) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_nUz() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_17) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_DUr() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_18) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_cAsInA() { - if (base.find_among_b(a_19) == 0) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_yDU() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_20) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ysA() { - if (base.find_among_b(a_21) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_ymUs_() { - if (!r_check_vowel_harmony()) - { - return false; - } - if (base.find_among_b(a_22) == 0) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_mark_yken() { - if (!(base.eq_s_b("ken"))) - { - return false; - } - if (!r_mark_suffix_with_optional_y_consonant()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_stem_nominal_verb_suffixes() { - base.ket = base.cursor; - B_continue_stemming_noun_suffixes = true; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - lab2: { - var /** number */ v_2 = base.limit - base.cursor; - lab3: { - if (!r_mark_ymUs_()) - { - break lab3; - } - break lab2; - } - base.cursor = base.limit - v_2; - lab4: { - if (!r_mark_yDU()) - { - break lab4; - } - break lab2; - } - base.cursor = base.limit - v_2; - lab5: { - if (!r_mark_ysA()) - { - break lab5; - } - break lab2; - } - base.cursor = base.limit - v_2; - if (!r_mark_yken()) - { - break lab1; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab6: { - if (!r_mark_cAsInA()) - { - break lab6; - } - lab7: { - var /** number */ v_3 = base.limit - base.cursor; - lab8: { - if (!r_mark_sUnUz()) - { - break lab8; - } - break lab7; - } - base.cursor = base.limit - v_3; - lab9: { - if (!r_mark_lAr()) - { - break lab9; - } - break lab7; - } - base.cursor = base.limit - v_3; - lab10: { - if (!r_mark_yUm()) - { - break lab10; - } - break lab7; - } - base.cursor = base.limit - v_3; - lab11: { - if (!r_mark_sUn()) - { - break lab11; - } - break lab7; - } - base.cursor = base.limit - v_3; - lab12: { - if (!r_mark_yUz()) - { - break lab12; - } - break lab7; - } - base.cursor = base.limit - v_3; - } - if (!r_mark_ymUs_()) - { - break lab6; - } - break lab0; - } - base.cursor = base.limit - v_1; - lab13: { - if (!r_mark_lAr()) - { - break lab13; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - lab14: { - base.ket = base.cursor; - lab15: { - var /** number */ v_5 = base.limit - base.cursor; - lab16: { - if (!r_mark_DUr()) - { - break lab16; - } - break lab15; - } - base.cursor = base.limit - v_5; - lab17: { - if (!r_mark_yDU()) - { - break lab17; - } - break lab15; - } - base.cursor = base.limit - v_5; - lab18: { - if (!r_mark_ysA()) - { - break lab18; - } - break lab15; - } - base.cursor = base.limit - v_5; - if (!r_mark_ymUs_()) - { - base.cursor = base.limit - v_4; - break lab14; - } - } - } - B_continue_stemming_noun_suffixes = false; - break lab0; - } - base.cursor = base.limit - v_1; - lab19: { - if (!r_mark_nUz()) - { - break lab19; - } - lab20: { - var /** number */ v_6 = base.limit - base.cursor; - lab21: { - if (!r_mark_yDU()) - { - break lab21; - } - break lab20; - } - base.cursor = base.limit - v_6; - if (!r_mark_ysA()) - { - break lab19; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab22: { - lab23: { - var /** number */ v_7 = base.limit - base.cursor; - lab24: { - if (!r_mark_sUnUz()) - { - break lab24; - } - break lab23; - } - base.cursor = base.limit - v_7; - lab25: { - if (!r_mark_yUz()) - { - break lab25; - } - break lab23; - } - base.cursor = base.limit - v_7; - lab26: { - if (!r_mark_sUn()) - { - break lab26; - } - break lab23; - } - base.cursor = base.limit - v_7; - if (!r_mark_yUm()) - { - break lab22; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_8 = base.limit - base.cursor; - lab27: { - base.ket = base.cursor; - if (!r_mark_ymUs_()) - { - base.cursor = base.limit - v_8; - break lab27; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!r_mark_DUr()) - { - return false; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_9 = base.limit - base.cursor; - lab28: { - base.ket = base.cursor; - lab29: { - var /** number */ v_10 = base.limit - base.cursor; - lab30: { - if (!r_mark_sUnUz()) - { - break lab30; - } - break lab29; - } - base.cursor = base.limit - v_10; - lab31: { - if (!r_mark_lAr()) - { - break lab31; - } - break lab29; - } - base.cursor = base.limit - v_10; - lab32: { - if (!r_mark_yUm()) - { - break lab32; - } - break lab29; - } - base.cursor = base.limit - v_10; - lab33: { - if (!r_mark_sUn()) - { - break lab33; - } - break lab29; - } - base.cursor = base.limit - v_10; - lab34: { - if (!r_mark_yUz()) - { - break lab34; - } - break lab29; - } - base.cursor = base.limit - v_10; - } - if (!r_mark_ymUs_()) - { - base.cursor = base.limit - v_9; - break lab28; - } - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_stem_suffix_chain_before_ki() { - base.ket = base.cursor; - if (!r_mark_ki()) - { - return false; - } - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!r_mark_DA()) - { - break lab1; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - base.ket = base.cursor; - lab3: { - var /** number */ v_3 = base.limit - base.cursor; - lab4: { - if (!r_mark_lAr()) - { - break lab4; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_4 = base.limit - base.cursor; - lab5: { - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_4; - break lab5; - } - } - break lab3; - } - base.cursor = base.limit - v_3; - if (!r_mark_possessives()) - { - base.cursor = base.limit - v_2; - break lab2; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_5 = base.limit - base.cursor; - lab6: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_5; - break lab6; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_5; - break lab6; - } - } - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab7: { - if (!r_mark_nUn()) - { - break lab7; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_6 = base.limit - base.cursor; - lab8: { - base.ket = base.cursor; - lab9: { - var /** number */ v_7 = base.limit - base.cursor; - lab10: { - if (!r_mark_lArI()) - { - break lab10; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break lab9; - } - base.cursor = base.limit - v_7; - lab11: { - base.ket = base.cursor; - lab12: { - var /** number */ v_8 = base.limit - base.cursor; - lab13: { - if (!r_mark_possessives()) - { - break lab13; - } - break lab12; - } - base.cursor = base.limit - v_8; - if (!r_mark_sU()) - { - break lab11; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_9 = base.limit - base.cursor; - lab14: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_9; - break lab14; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_9; - break lab14; - } - } - break lab9; - } - base.cursor = base.limit - v_7; - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_6; - break lab8; - } - } - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!r_mark_ndA()) - { - return false; - } - lab15: { - var /** number */ v_10 = base.limit - base.cursor; - lab16: { - if (!r_mark_lArI()) - { - break lab16; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break lab15; - } - base.cursor = base.limit - v_10; - lab17: { - if (!r_mark_sU()) - { - break lab17; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_11 = base.limit - base.cursor; - lab18: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_11; - break lab18; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_11; - break lab18; - } - } - break lab15; - } - base.cursor = base.limit - v_10; - if (!r_stem_suffix_chain_before_ki()) - { - return false; - } - } - } - return true; - }; - - /** @return {boolean} */ - function r_stem_noun_suffixes() { - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - break lab1; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_2; - break lab2; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab3: { - base.ket = base.cursor; - if (!r_mark_ncA()) - { - break lab3; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_3 = base.limit - base.cursor; - lab4: { - lab5: { - var /** number */ v_4 = base.limit - base.cursor; - lab6: { - base.ket = base.cursor; - if (!r_mark_lArI()) - { - break lab6; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break lab5; - } - base.cursor = base.limit - v_4; - lab7: { - base.ket = base.cursor; - lab8: { - var /** number */ v_5 = base.limit - base.cursor; - lab9: { - if (!r_mark_possessives()) - { - break lab9; - } - break lab8; - } - base.cursor = base.limit - v_5; - if (!r_mark_sU()) - { - break lab7; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_6 = base.limit - base.cursor; - lab10: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_6; - break lab10; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_6; - break lab10; - } - } - break lab5; - } - base.cursor = base.limit - v_4; - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_3; - break lab4; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_3; - break lab4; - } - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab11: { - base.ket = base.cursor; - lab12: { - var /** number */ v_7 = base.limit - base.cursor; - lab13: { - if (!r_mark_ndA()) - { - break lab13; - } - break lab12; - } - base.cursor = base.limit - v_7; - if (!r_mark_nA()) - { - break lab11; - } - } - lab14: { - var /** number */ v_8 = base.limit - base.cursor; - lab15: { - if (!r_mark_lArI()) - { - break lab15; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break lab14; - } - base.cursor = base.limit - v_8; - lab16: { - if (!r_mark_sU()) - { - break lab16; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_9 = base.limit - base.cursor; - lab17: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_9; - break lab17; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_9; - break lab17; - } - } - break lab14; - } - base.cursor = base.limit - v_8; - if (!r_stem_suffix_chain_before_ki()) - { - break lab11; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab18: { - base.ket = base.cursor; - lab19: { - var /** number */ v_10 = base.limit - base.cursor; - lab20: { - if (!r_mark_ndAn()) - { - break lab20; - } - break lab19; - } - base.cursor = base.limit - v_10; - if (!r_mark_nU()) - { - break lab18; - } - } - lab21: { - var /** number */ v_11 = base.limit - base.cursor; - lab22: { - if (!r_mark_sU()) - { - break lab22; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_12 = base.limit - base.cursor; - lab23: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_12; - break lab23; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_12; - break lab23; - } - } - break lab21; - } - base.cursor = base.limit - v_11; - if (!r_mark_lArI()) - { - break lab18; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab24: { - base.ket = base.cursor; - if (!r_mark_DAn()) - { - break lab24; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_13 = base.limit - base.cursor; - lab25: { - base.ket = base.cursor; - lab26: { - var /** number */ v_14 = base.limit - base.cursor; - lab27: { - if (!r_mark_possessives()) - { - break lab27; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_15 = base.limit - base.cursor; - lab28: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_15; - break lab28; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_15; - break lab28; - } - } - break lab26; - } - base.cursor = base.limit - v_14; - lab29: { - if (!r_mark_lAr()) - { - break lab29; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_16 = base.limit - base.cursor; - lab30: { - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_16; - break lab30; - } - } - break lab26; - } - base.cursor = base.limit - v_14; - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_13; - break lab25; - } - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab31: { - base.ket = base.cursor; - lab32: { - var /** number */ v_17 = base.limit - base.cursor; - lab33: { - if (!r_mark_nUn()) - { - break lab33; - } - break lab32; - } - base.cursor = base.limit - v_17; - if (!r_mark_ylA()) - { - break lab31; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_18 = base.limit - base.cursor; - lab34: { - lab35: { - var /** number */ v_19 = base.limit - base.cursor; - lab36: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - break lab36; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - break lab36; - } - break lab35; - } - base.cursor = base.limit - v_19; - lab37: { - base.ket = base.cursor; - lab38: { - var /** number */ v_20 = base.limit - base.cursor; - lab39: { - if (!r_mark_possessives()) - { - break lab39; - } - break lab38; - } - base.cursor = base.limit - v_20; - if (!r_mark_sU()) - { - break lab37; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_21 = base.limit - base.cursor; - lab40: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_21; - break lab40; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_21; - break lab40; - } - } - break lab35; - } - base.cursor = base.limit - v_19; - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_18; - break lab34; - } - } - } - break lab0; - } - base.cursor = base.limit - v_1; - lab41: { - base.ket = base.cursor; - if (!r_mark_lArI()) - { - break lab41; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - break lab0; - } - base.cursor = base.limit - v_1; - lab42: { - if (!r_stem_suffix_chain_before_ki()) - { - break lab42; - } - break lab0; - } - base.cursor = base.limit - v_1; - lab43: { - base.ket = base.cursor; - lab44: { - var /** number */ v_22 = base.limit - base.cursor; - lab45: { - if (!r_mark_DA()) - { - break lab45; - } - break lab44; - } - base.cursor = base.limit - v_22; - lab46: { - if (!r_mark_yU()) - { - break lab46; - } - break lab44; - } - base.cursor = base.limit - v_22; - if (!r_mark_yA()) - { - break lab43; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_23 = base.limit - base.cursor; - lab47: { - base.ket = base.cursor; - lab48: { - var /** number */ v_24 = base.limit - base.cursor; - lab49: { - if (!r_mark_possessives()) - { - break lab49; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_25 = base.limit - base.cursor; - lab50: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_25; - break lab50; - } - } - break lab48; - } - base.cursor = base.limit - v_24; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_23; - break lab47; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_23; - break lab47; - } - } - break lab0; - } - base.cursor = base.limit - v_1; - base.ket = base.cursor; - lab51: { - var /** number */ v_26 = base.limit - base.cursor; - lab52: { - if (!r_mark_possessives()) - { - break lab52; - } - break lab51; - } - base.cursor = base.limit - v_26; - if (!r_mark_sU()) - { - return false; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - var /** number */ v_27 = base.limit - base.cursor; - lab53: { - base.ket = base.cursor; - if (!r_mark_lAr()) - { - base.cursor = base.limit - v_27; - break lab53; - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - if (!r_stem_suffix_chain_before_ki()) - { - base.cursor = base.limit - v_27; - break lab53; - } - } - } - return true; - }; - - /** @return {boolean} */ - function r_post_process_last_consonants() { - var /** number */ among_var; - base.ket = base.cursor; - among_var = base.find_among_b(a_23); - if (among_var == 0) - { - return false; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("p")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u00E7")) - { - return false; - } - break; - case 3: - if (!base.slice_from("t")) - { - return false; - } - break; - case 4: - if (!base.slice_from("k")) - { - return false; - } - break; - } - return true; - }; - - /** @return {boolean} */ - function r_append_U_to_stems_ending_with_d_or_g() { - base.ket = base.cursor; - base.bra = base.cursor; - lab0: { - var /** number */ v_1 = base.limit - base.cursor; - lab1: { - if (!(base.eq_s_b("d"))) - { - break lab1; - } - break lab0; - } - base.cursor = base.limit - v_1; - if (!(base.eq_s_b("g"))) - { - return false; - } - } - golab2: while(true) - { - var /** number */ v_2 = base.limit - base.cursor; - lab3: { - if (!(base.in_grouping_b(g_vowel, 97, 305))) - { - break lab3; - } - base.cursor = base.limit - v_2; - break golab2; - } - base.cursor = base.limit - v_2; - if (base.cursor <= base.limit_backward) - { - return false; - } - base.cursor--; - } - lab4: { - var /** number */ v_3 = base.limit - base.cursor; - lab5: { - lab6: { - var /** number */ v_4 = base.limit - base.cursor; - lab7: { - if (!(base.eq_s_b("a"))) - { - break lab7; - } - break lab6; - } - base.cursor = base.limit - v_4; - if (!(base.eq_s_b("\u0131"))) - { - break lab5; - } - } - if (!base.slice_from("\u0131")) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_3; - lab8: { - lab9: { - var /** number */ v_5 = base.limit - base.cursor; - lab10: { - if (!(base.eq_s_b("e"))) - { - break lab10; - } - break lab9; - } - base.cursor = base.limit - v_5; - if (!(base.eq_s_b("i"))) - { - break lab8; - } - } - if (!base.slice_from("i")) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_3; - lab11: { - lab12: { - var /** number */ v_6 = base.limit - base.cursor; - lab13: { - if (!(base.eq_s_b("o"))) - { - break lab13; - } - break lab12; - } - base.cursor = base.limit - v_6; - if (!(base.eq_s_b("u"))) - { - break lab11; - } - } - if (!base.slice_from("u")) - { - return false; - } - break lab4; - } - base.cursor = base.limit - v_3; - lab14: { - var /** number */ v_7 = base.limit - base.cursor; - lab15: { - if (!(base.eq_s_b("\u00F6"))) - { - break lab15; - } - break lab14; - } - base.cursor = base.limit - v_7; - if (!(base.eq_s_b("\u00FC"))) - { - return false; - } - } - if (!base.slice_from("\u00FC")) - { - return false; - } - } - return true; - }; - - /** @return {boolean} */ - function r_is_reserved_word() { - if (!(base.eq_s_b("ad"))) - { - return false; - } - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (!(base.eq_s_b("soy"))) - { - base.cursor = base.limit - v_1; - break lab0; - } - } - if (base.cursor > base.limit_backward) - { - return false; - } - return true; - }; - - /** @return {boolean} */ - function r_more_than_one_syllable_word() { - var /** number */ v_1 = base.cursor; - for (var /** number */ v_2 = 2; v_2 > 0; v_2--) - { - golab0: while(true) - { - lab1: { - if (!(base.in_grouping(g_vowel, 97, 305))) - { - break lab1; - } - break golab0; - } - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - } - base.cursor = v_1; - return true; - }; - - /** @return {boolean} */ - function r_postlude() { - base.limit_backward = base.cursor; base.cursor = base.limit; - { - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - if (!r_is_reserved_word()) - { - break lab0; - } - return false; - } - base.cursor = base.limit - v_1; - } - var /** number */ v_2 = base.limit - base.cursor; - r_append_U_to_stems_ending_with_d_or_g(); - base.cursor = base.limit - v_2; - var /** number */ v_3 = base.limit - base.cursor; - r_post_process_last_consonants(); - base.cursor = base.limit - v_3; - base.cursor = base.limit_backward; - return true; - }; - - this.stem = /** @return {boolean} */ function() { - if (!r_more_than_one_syllable_word()) - { - return false; - } - base.limit_backward = base.cursor; base.cursor = base.limit; - var /** number */ v_1 = base.limit - base.cursor; - r_stem_nominal_verb_suffixes(); - base.cursor = base.limit - v_1; - if (!B_continue_stemming_noun_suffixes) - { - return false; - } - var /** number */ v_2 = base.limit - base.cursor; - r_stem_noun_suffixes(); - base.cursor = base.limit - v_2; - base.cursor = base.limit_backward; - if (!r_postlude()) - { - return false; - } - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['TurkishStemmer'] = TurkishStemmer; diff --git a/js/yiddish-stemmer.js b/js/yiddish-stemmer.js deleted file mode 100644 index f21669d..0000000 --- a/js/yiddish-stemmer.js +++ /dev/null @@ -1,1173 +0,0 @@ -// Generated by Snowball 2.2.0 - https://snowballstem.org/ - -/**@constructor*/ -var YiddishStemmer = function() { - var base = new BaseStemmer(); - /** @const */ var a_0 = [ - ["\u05D5\u05D5", -1, 1], - ["\u05D5\u05D9", -1, 2], - ["\u05D9\u05D9", -1, 3], - ["\u05DA", -1, 4], - ["\u05DD", -1, 5], - ["\u05DF", -1, 6], - ["\u05E3", -1, 7], - ["\u05E5", -1, 8] - ]; - - /** @const */ var a_1 = [ - ["\u05D0\u05D3\u05D5\u05E8\u05DB", -1, 1], - ["\u05D0\u05D4\u05D9\u05E0", -1, 1], - ["\u05D0\u05D4\u05E2\u05E8", -1, 1], - ["\u05D0\u05D4\u05F2\u05DE", -1, 1], - ["\u05D0\u05D5\u05DE", -1, 1], - ["\u05D0\u05D5\u05E0\u05D8\u05E2\u05E8", -1, 1], - ["\u05D0\u05D9\u05D1\u05E2\u05E8", -1, 1], - ["\u05D0\u05E0", -1, 1], - ["\u05D0\u05E0\u05D8", 7, 1], - ["\u05D0\u05E0\u05D8\u05E7\u05E2\u05D2\u05E0", 8, 1], - ["\u05D0\u05E0\u05D9\u05D3\u05E2\u05E8", 7, 1], - ["\u05D0\u05E4", -1, 1], - ["\u05D0\u05E4\u05D9\u05E8", 11, 1], - ["\u05D0\u05E7\u05E2\u05D2\u05E0", -1, 1], - ["\u05D0\u05E8\u05D0\u05E4", -1, 1], - ["\u05D0\u05E8\u05D5\u05DE", -1, 1], - ["\u05D0\u05E8\u05D5\u05E0\u05D8\u05E2\u05E8", -1, 1], - ["\u05D0\u05E8\u05D9\u05D1\u05E2\u05E8", -1, 1], - ["\u05D0\u05E8\u05F1\u05E1", -1, 1], - ["\u05D0\u05E8\u05F1\u05E4", -1, 1], - ["\u05D0\u05E8\u05F2\u05E0", -1, 1], - ["\u05D0\u05F0\u05E2\u05E7", -1, 1], - ["\u05D0\u05F1\u05E1", -1, 1], - ["\u05D0\u05F1\u05E4", -1, 1], - ["\u05D0\u05F2\u05E0", -1, 1], - ["\u05D1\u05D0", -1, 1], - ["\u05D1\u05F2", -1, 1], - ["\u05D3\u05D5\u05E8\u05DB", -1, 1], - ["\u05D3\u05E2\u05E8", -1, 1], - ["\u05DE\u05D9\u05D8", -1, 1], - ["\u05E0\u05D0\u05DB", -1, 1], - ["\u05E4\u05D0\u05E8", -1, 1], - ["\u05E4\u05D0\u05E8\u05D1\u05F2", 31, 1], - ["\u05E4\u05D0\u05E8\u05F1\u05E1", 31, 1], - ["\u05E4\u05D5\u05E0\u05D0\u05E0\u05D3\u05E2\u05E8", -1, 1], - ["\u05E6\u05D5", -1, 1], - ["\u05E6\u05D5\u05D6\u05D0\u05DE\u05E2\u05E0", 35, 1], - ["\u05E6\u05D5\u05E0\u05F1\u05E4", 35, 1], - ["\u05E6\u05D5\u05E8\u05D9\u05E7", 35, 1], - ["\u05E6\u05E2", -1, 1] - ]; - - /** @const */ var a_2 = [ - ["\u05D3\u05D6\u05E9", -1, -1], - ["\u05E9\u05D8\u05E8", -1, -1], - ["\u05E9\u05D8\u05E9", -1, -1], - ["\u05E9\u05E4\u05E8", -1, -1] - ]; - - /** @const */ var a_3 = [ - ["\u05E7\u05DC\u05D9\u05D1", -1, 9], - ["\u05E8\u05D9\u05D1", -1, 10], - ["\u05D8\u05E8\u05D9\u05D1", 1, 7], - ["\u05E9\u05E8\u05D9\u05D1", 1, 15], - ["\u05D4\u05F1\u05D1", -1, 23], - ["\u05E9\u05F0\u05D9\u05D2", -1, 12], - ["\u05D2\u05D0\u05E0\u05D2", -1, 1], - ["\u05D6\u05D5\u05E0\u05D2", -1, 18], - ["\u05E9\u05DC\u05D5\u05E0\u05D2", -1, 21], - ["\u05E6\u05F0\u05D5\u05E0\u05D2", -1, 20], - ["\u05D1\u05F1\u05D2", -1, 22], - ["\u05D1\u05D5\u05E0\u05D3", -1, 16], - ["\u05F0\u05D9\u05D6", -1, 6], - ["\u05D1\u05D9\u05D8", -1, 4], - ["\u05DC\u05D9\u05D8", -1, 8], - ["\u05DE\u05D9\u05D8", -1, 3], - ["\u05E9\u05E0\u05D9\u05D8", -1, 14], - ["\u05E0\u05D5\u05DE", -1, 2], - ["\u05E9\u05D8\u05D0\u05E0", -1, 25], - ["\u05D1\u05D9\u05E1", -1, 5], - ["\u05E9\u05DE\u05D9\u05E1", -1, 13], - ["\u05E8\u05D9\u05E1", -1, 11], - ["\u05D8\u05E8\u05D5\u05E0\u05E7", -1, 19], - ["\u05E4\u05D0\u05E8\u05DC\u05F1\u05E8", -1, 24], - ["\u05E9\u05F0\u05F1\u05E8", -1, 26], - ["\u05F0\u05D5\u05D8\u05E9", -1, 17] - ]; - - /** @const */ var a_4 = [ - ["\u05D5\u05E0\u05D2", -1, 1], - ["\u05E1\u05D8\u05D5", -1, 1], - ["\u05D8", -1, 1], - ["\u05D1\u05E8\u05D0\u05DB\u05D8", 2, 31], - ["\u05E1\u05D8", 2, 1], - ["\u05D9\u05E1\u05D8", 4, 33], - ["\u05E2\u05D8", 2, 1], - ["\u05E9\u05D0\u05E4\u05D8", 2, 1], - ["\u05D4\u05F2\u05D8", 2, 1], - ["\u05E7\u05F2\u05D8", 2, 1], - ["\u05D9\u05E7\u05F2\u05D8", 9, 1], - ["\u05DC\u05E2\u05DB", -1, 1], - ["\u05E2\u05DC\u05E2\u05DB", 11, 1], - ["\u05D9\u05D6\u05DE", -1, 1], - ["\u05D9\u05DE", -1, 1], - ["\u05E2\u05DE", -1, 1], - ["\u05E2\u05E0\u05E2\u05DE", 15, 3], - ["\u05D8\u05E2\u05E0\u05E2\u05DE", 16, 4], - ["\u05E0", -1, 1], - ["\u05E7\u05DC\u05D9\u05D1\u05E0", 18, 14], - ["\u05E8\u05D9\u05D1\u05E0", 18, 15], - ["\u05D8\u05E8\u05D9\u05D1\u05E0", 20, 12], - ["\u05E9\u05E8\u05D9\u05D1\u05E0", 20, 7], - ["\u05D4\u05F1\u05D1\u05E0", 18, 27], - ["\u05E9\u05F0\u05D9\u05D2\u05E0", 18, 17], - ["\u05D6\u05D5\u05E0\u05D2\u05E0", 18, 22], - ["\u05E9\u05DC\u05D5\u05E0\u05D2\u05E0", 18, 25], - ["\u05E6\u05F0\u05D5\u05E0\u05D2\u05E0", 18, 24], - ["\u05D1\u05F1\u05D2\u05E0", 18, 26], - ["\u05D1\u05D5\u05E0\u05D3\u05E0", 18, 20], - ["\u05F0\u05D9\u05D6\u05E0", 18, 11], - ["\u05D8\u05E0", 18, 4], - ["GE\u05D1\u05D9\u05D8\u05E0", 31, 9], - ["GE\u05DC\u05D9\u05D8\u05E0", 31, 13], - ["GE\u05DE\u05D9\u05D8\u05E0", 31, 8], - ["\u05E9\u05E0\u05D9\u05D8\u05E0", 31, 19], - ["\u05E1\u05D8\u05E0", 31, 1], - ["\u05D9\u05E1\u05D8\u05E0", 36, 1], - ["\u05E2\u05D8\u05E0", 31, 1], - ["GE\u05D1\u05D9\u05E1\u05E0", 18, 10], - ["\u05E9\u05DE\u05D9\u05E1\u05E0", 18, 18], - ["GE\u05E8\u05D9\u05E1\u05E0", 18, 16], - ["\u05E2\u05E0", 18, 1], - ["\u05D2\u05D0\u05E0\u05D2\u05E2\u05E0", 42, 5], - ["\u05E2\u05DC\u05E2\u05E0", 42, 1], - ["\u05E0\u05D5\u05DE\u05E2\u05E0", 42, 6], - ["\u05D9\u05D6\u05DE\u05E2\u05E0", 42, 1], - ["\u05E9\u05D8\u05D0\u05E0\u05E2\u05E0", 42, 29], - ["\u05D8\u05E8\u05D5\u05E0\u05E7\u05E0", 18, 23], - ["\u05E4\u05D0\u05E8\u05DC\u05F1\u05E8\u05E0", 18, 28], - ["\u05E9\u05F0\u05F1\u05E8\u05E0", 18, 30], - ["\u05F0\u05D5\u05D8\u05E9\u05E0", 18, 21], - ["\u05D2\u05F2\u05E0", 18, 5], - ["\u05E1", -1, 1], - ["\u05D8\u05E1", 53, 4], - ["\u05E2\u05D8\u05E1", 54, 1], - ["\u05E0\u05E1", 53, 1], - ["\u05D8\u05E0\u05E1", 56, 4], - ["\u05E2\u05E0\u05E1", 56, 3], - ["\u05E2\u05E1", 53, 1], - ["\u05D9\u05E2\u05E1", 59, 2], - ["\u05E2\u05DC\u05E2\u05E1", 59, 1], - ["\u05E2\u05E8\u05E1", 53, 1], - ["\u05E2\u05E0\u05E2\u05E8\u05E1", 62, 1], - ["\u05E2", -1, 1], - ["\u05D8\u05E2", 64, 4], - ["\u05E1\u05D8\u05E2", 65, 1], - ["\u05E2\u05D8\u05E2", 65, 1], - ["\u05D9\u05E2", 64, -1], - ["\u05E2\u05DC\u05E2", 64, 1], - ["\u05E2\u05E0\u05E2", 64, 3], - ["\u05D8\u05E2\u05E0\u05E2", 70, 4], - ["\u05E2\u05E8", -1, 1], - ["\u05D8\u05E2\u05E8", 72, 4], - ["\u05E1\u05D8\u05E2\u05E8", 73, 1], - ["\u05E2\u05D8\u05E2\u05E8", 73, 1], - ["\u05E2\u05E0\u05E2\u05E8", 72, 3], - ["\u05D8\u05E2\u05E0\u05E2\u05E8", 76, 4], - ["\u05D5\u05EA", -1, 32] - ]; - - /** @const */ var a_5 = [ - ["\u05D5\u05E0\u05D2", -1, 1], - ["\u05E9\u05D0\u05E4\u05D8", -1, 1], - ["\u05D4\u05F2\u05D8", -1, 1], - ["\u05E7\u05F2\u05D8", -1, 1], - ["\u05D9\u05E7\u05F2\u05D8", 3, 1], - ["\u05DC", -1, 2] - ]; - - /** @const */ var a_6 = [ - ["\u05D9\u05D2", -1, 1], - ["\u05D9\u05E7", -1, 1], - ["\u05D3\u05D9\u05E7", 1, 1], - ["\u05E0\u05D3\u05D9\u05E7", 2, 1], - ["\u05E2\u05E0\u05D3\u05D9\u05E7", 3, 1], - ["\u05D1\u05DC\u05D9\u05E7", 1, -1], - ["\u05D2\u05DC\u05D9\u05E7", 1, -1], - ["\u05E0\u05D9\u05E7", 1, 1], - ["\u05D9\u05E9", -1, 1] - ]; - - /** @const */ var /** Array */ g_niked = [255, 155, 6]; - - /** @const */ var /** Array */ g_vowel = [33, 2, 4, 0, 6]; - - /** @const */ var /** Array */ g_consonant = [239, 254, 253, 131]; - - var /** number */ I_x = 0; - var /** number */ I_p1 = 0; - - - /** @return {boolean} */ - function r_prelude() { - var /** number */ among_var; - var /** number */ v_1 = base.cursor; - lab0: { - while(true) - { - var /** number */ v_2 = base.cursor; - lab1: { - golab2: while(true) - { - var /** number */ v_3 = base.cursor; - lab3: { - base.bra = base.cursor; - among_var = base.find_among(a_0); - if (among_var == 0) - { - break lab3; - } - base.ket = base.cursor; - switch (among_var) { - case 1: - { - var /** number */ v_4 = base.cursor; - lab4: { - if (!(base.eq_s("\u05BC"))) - { - break lab4; - } - break lab3; - } - base.cursor = v_4; - } - if (!base.slice_from("\u05F0")) - { - return false; - } - break; - case 2: - { - var /** number */ v_5 = base.cursor; - lab5: { - if (!(base.eq_s("\u05B4"))) - { - break lab5; - } - break lab3; - } - base.cursor = v_5; - } - if (!base.slice_from("\u05F1")) - { - return false; - } - break; - case 3: - { - var /** number */ v_6 = base.cursor; - lab6: { - if (!(base.eq_s("\u05B4"))) - { - break lab6; - } - break lab3; - } - base.cursor = v_6; - } - if (!base.slice_from("\u05F2")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u05DB")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u05DE")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u05E0")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u05E4")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u05E6")) - { - return false; - } - break; - } - base.cursor = v_3; - break golab2; - } - base.cursor = v_3; - if (base.cursor >= base.limit) - { - break lab1; - } - base.cursor++; - } - continue; - } - base.cursor = v_2; - break; - } - } - base.cursor = v_1; - var /** number */ v_7 = base.cursor; - lab7: { - while(true) - { - var /** number */ v_8 = base.cursor; - lab8: { - golab9: while(true) - { - var /** number */ v_9 = base.cursor; - lab10: { - base.bra = base.cursor; - if (!(base.in_grouping(g_niked, 1456, 1474))) - { - break lab10; - } - base.ket = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.cursor = v_9; - break golab9; - } - base.cursor = v_9; - if (base.cursor >= base.limit) - { - break lab8; - } - base.cursor++; - } - continue; - } - base.cursor = v_8; - break; - } - } - base.cursor = v_7; - return true; - }; - - /** @return {boolean} */ - function r_mark_regions() { - I_p1 = base.limit; - var /** number */ v_1 = base.cursor; - lab0: { - base.bra = base.cursor; - if (!(base.eq_s("\u05D2\u05E2"))) - { - base.cursor = v_1; - break lab0; - } - base.ket = base.cursor; - { - var /** number */ v_2 = base.cursor; - lab1: { - lab2: { - var /** number */ v_3 = base.cursor; - lab3: { - if (!(base.eq_s("\u05DC\u05D8"))) - { - break lab3; - } - break lab2; - } - base.cursor = v_3; - if (!(base.eq_s("\u05D1\u05E0"))) - { - break lab1; - } - } - base.cursor = v_1; - break lab0; - } - base.cursor = v_2; - } - if (!base.slice_from("GE")) - { - return false; - } - } - var /** number */ v_4 = base.cursor; - lab4: { - if (base.find_among(a_1) == 0) - { - base.cursor = v_4; - break lab4; - } - lab5: { - var /** number */ v_5 = base.cursor; - lab6: { - var /** number */ v_6 = base.cursor; - lab7: { - var /** number */ v_7 = base.cursor; - lab8: { - if (!(base.eq_s("\u05E6\u05D5\u05D2\u05E0"))) - { - break lab8; - } - break lab7; - } - base.cursor = v_7; - lab9: { - if (!(base.eq_s("\u05E6\u05D5\u05E7\u05D8"))) - { - break lab9; - } - break lab7; - } - base.cursor = v_7; - if (!(base.eq_s("\u05E6\u05D5\u05E7\u05E0"))) - { - break lab6; - } - } - if (base.cursor < base.limit) - { - break lab6; - } - base.cursor = v_6; - break lab5; - } - base.cursor = v_5; - lab10: { - var /** number */ v_8 = base.cursor; - if (!(base.eq_s("\u05D2\u05E2\u05D1\u05E0"))) - { - break lab10; - } - base.cursor = v_8; - break lab5; - } - base.cursor = v_5; - lab11: { - base.bra = base.cursor; - if (!(base.eq_s("\u05D2\u05E2"))) - { - break lab11; - } - base.ket = base.cursor; - if (!base.slice_from("GE")) - { - return false; - } - break lab5; - } - base.cursor = v_5; - base.bra = base.cursor; - if (!(base.eq_s("\u05E6\u05D5"))) - { - base.cursor = v_4; - break lab4; - } - base.ket = base.cursor; - if (!base.slice_from("TSU")) - { - return false; - } - } - } - var /** number */ v_9 = base.cursor; - { - var /** number */ c1 = base.cursor + 3; - if (c1 > base.limit) - { - return false; - } - base.cursor = c1; - } - I_x = base.cursor; - base.cursor = v_9; - var /** number */ v_10 = base.cursor; - lab12: { - if (base.find_among(a_2) == 0) - { - base.cursor = v_10; - break lab12; - } - } - { - var /** number */ v_11 = base.cursor; - lab13: { - if (!(base.in_grouping(g_consonant, 1489, 1520))) - { - break lab13; - } - if (!(base.in_grouping(g_consonant, 1489, 1520))) - { - break lab13; - } - if (!(base.in_grouping(g_consonant, 1489, 1520))) - { - break lab13; - } - I_p1 = base.cursor; - return false; - } - base.cursor = v_11; - } - golab14: while(true) - { - var /** number */ v_12 = base.cursor; - lab15: { - if (!(base.in_grouping(g_vowel, 1488, 1522))) - { - break lab15; - } - base.cursor = v_12; - break golab14; - } - base.cursor = v_12; - if (base.cursor >= base.limit) - { - return false; - } - base.cursor++; - } - while(true) - { - lab16: { - if (!(base.in_grouping(g_vowel, 1488, 1522))) - { - break lab16; - } - continue; - } - break; - } - I_p1 = base.cursor; - lab17: { - if (I_p1 >= I_x) - { - break lab17; - } - I_p1 = I_x; - } - return true; - }; - - /** @return {boolean} */ - function r_R1() { - return I_p1 <= base.cursor; - }; - - /** @return {boolean} */ - function r_R1plus3() { - return I_p1 <= (base.cursor + 3); - }; - - /** @return {boolean} */ - function r_standard_suffix() { - var /** number */ among_var; - var /** number */ v_1 = base.limit - base.cursor; - lab0: { - base.ket = base.cursor; - among_var = base.find_among_b(a_4); - if (among_var == 0) - { - break lab0; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - break lab0; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R1()) - { - break lab0; - } - if (!base.slice_from("\u05D9\u05E2")) - { - return false; - } - break; - case 3: - if (!r_R1()) - { - break lab0; - } - if (!base.slice_del()) - { - return false; - } - base.ket = base.cursor; - among_var = base.find_among_b(a_3); - if (among_var == 0) - { - break lab0; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!base.slice_from("\u05D2\u05F2")) - { - return false; - } - break; - case 2: - if (!base.slice_from("\u05E0\u05E2\u05DE")) - { - return false; - } - break; - case 3: - if (!base.slice_from("\u05DE\u05F2\u05D3")) - { - return false; - } - break; - case 4: - if (!base.slice_from("\u05D1\u05F2\u05D8")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u05D1\u05F2\u05E1")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u05F0\u05F2\u05D6")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u05D8\u05E8\u05F2\u05D1")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u05DC\u05F2\u05D8")) - { - return false; - } - break; - case 9: - if (!base.slice_from("\u05E7\u05DC\u05F2\u05D1")) - { - return false; - } - break; - case 10: - if (!base.slice_from("\u05E8\u05F2\u05D1")) - { - return false; - } - break; - case 11: - if (!base.slice_from("\u05E8\u05F2\u05E1")) - { - return false; - } - break; - case 12: - if (!base.slice_from("\u05E9\u05F0\u05F2\u05D2")) - { - return false; - } - break; - case 13: - if (!base.slice_from("\u05E9\u05DE\u05F2\u05E1")) - { - return false; - } - break; - case 14: - if (!base.slice_from("\u05E9\u05E0\u05F2\u05D3")) - { - return false; - } - break; - case 15: - if (!base.slice_from("\u05E9\u05E8\u05F2\u05D1")) - { - return false; - } - break; - case 16: - if (!base.slice_from("\u05D1\u05D9\u05E0\u05D3")) - { - return false; - } - break; - case 17: - if (!base.slice_from("\u05F0\u05D9\u05D8\u05E9")) - { - return false; - } - break; - case 18: - if (!base.slice_from("\u05D6\u05D9\u05E0\u05D2")) - { - return false; - } - break; - case 19: - if (!base.slice_from("\u05D8\u05E8\u05D9\u05E0\u05E7")) - { - return false; - } - break; - case 20: - if (!base.slice_from("\u05E6\u05F0\u05D9\u05E0\u05D2")) - { - return false; - } - break; - case 21: - if (!base.slice_from("\u05E9\u05DC\u05D9\u05E0\u05D2")) - { - return false; - } - break; - case 22: - if (!base.slice_from("\u05D1\u05F2\u05D2")) - { - return false; - } - break; - case 23: - if (!base.slice_from("\u05D4\u05F2\u05D1")) - { - return false; - } - break; - case 24: - if (!base.slice_from("\u05E4\u05D0\u05E8\u05DC\u05D9\u05E8")) - { - return false; - } - break; - case 25: - if (!base.slice_from("\u05E9\u05D8\u05F2")) - { - return false; - } - break; - case 26: - if (!base.slice_from("\u05E9\u05F0\u05E2\u05E8")) - { - return false; - } - break; - } - break; - case 4: - lab1: { - var /** number */ v_2 = base.limit - base.cursor; - lab2: { - if (!r_R1()) - { - break lab2; - } - if (!base.slice_del()) - { - return false; - } - break lab1; - } - base.cursor = base.limit - v_2; - if (!base.slice_from("\u05D8")) - { - return false; - } - } - base.ket = base.cursor; - if (!(base.eq_s_b("\u05D1\u05E8\u05D0\u05DB"))) - { - break lab0; - } - var /** number */ v_3 = base.limit - base.cursor; - lab3: { - if (!(base.eq_s_b("\u05D2\u05E2"))) - { - base.cursor = base.limit - v_3; - break lab3; - } - } - base.bra = base.cursor; - if (!base.slice_from("\u05D1\u05E8\u05E2\u05E0\u05D2")) - { - return false; - } - break; - case 5: - if (!base.slice_from("\u05D2\u05F2")) - { - return false; - } - break; - case 6: - if (!base.slice_from("\u05E0\u05E2\u05DE")) - { - return false; - } - break; - case 7: - if (!base.slice_from("\u05E9\u05E8\u05F2\u05D1")) - { - return false; - } - break; - case 8: - if (!base.slice_from("\u05DE\u05F2\u05D3")) - { - return false; - } - break; - case 9: - if (!base.slice_from("\u05D1\u05F2\u05D8")) - { - return false; - } - break; - case 10: - if (!base.slice_from("\u05D1\u05F2\u05E1")) - { - return false; - } - break; - case 11: - if (!base.slice_from("\u05F0\u05F2\u05D6")) - { - return false; - } - break; - case 12: - if (!base.slice_from("\u05D8\u05E8\u05F2\u05D1")) - { - return false; - } - break; - case 13: - if (!base.slice_from("\u05DC\u05F2\u05D8")) - { - return false; - } - break; - case 14: - if (!base.slice_from("\u05E7\u05DC\u05F2\u05D1")) - { - return false; - } - break; - case 15: - if (!base.slice_from("\u05E8\u05F2\u05D1")) - { - return false; - } - break; - case 16: - if (!base.slice_from("\u05E8\u05F2\u05E1")) - { - return false; - } - break; - case 17: - if (!base.slice_from("\u05E9\u05F0\u05F2\u05D2")) - { - return false; - } - break; - case 18: - if (!base.slice_from("\u05E9\u05DE\u05F2\u05E1")) - { - return false; - } - break; - case 19: - if (!base.slice_from("\u05E9\u05E0\u05F2\u05D3")) - { - return false; - } - break; - case 20: - if (!base.slice_from("\u05D1\u05D9\u05E0\u05D3")) - { - return false; - } - break; - case 21: - if (!base.slice_from("\u05F0\u05D9\u05D8\u05E9")) - { - return false; - } - break; - case 22: - if (!base.slice_from("\u05D6\u05D9\u05E0\u05D2")) - { - return false; - } - break; - case 23: - if (!base.slice_from("\u05D8\u05E8\u05D9\u05E0\u05E7")) - { - return false; - } - break; - case 24: - if (!base.slice_from("\u05E6\u05F0\u05D9\u05E0\u05D2")) - { - return false; - } - break; - case 25: - if (!base.slice_from("\u05E9\u05DC\u05D9\u05E0\u05D2")) - { - return false; - } - break; - case 26: - if (!base.slice_from("\u05D1\u05F2\u05D2")) - { - return false; - } - break; - case 27: - if (!base.slice_from("\u05D4\u05F2\u05D1")) - { - return false; - } - break; - case 28: - if (!base.slice_from("\u05E4\u05D0\u05E8\u05DC\u05D9\u05E8")) - { - return false; - } - break; - case 29: - if (!base.slice_from("\u05E9\u05D8\u05F2")) - { - return false; - } - break; - case 30: - if (!base.slice_from("\u05E9\u05F0\u05E2\u05E8")) - { - return false; - } - break; - case 31: - if (!base.slice_from("\u05D1\u05E8\u05E2\u05E0\u05D2")) - { - return false; - } - break; - case 32: - if (!r_R1()) - { - break lab0; - } - if (!base.slice_from("\u05D4")) - { - return false; - } - break; - case 33: - lab4: { - var /** number */ v_4 = base.limit - base.cursor; - lab5: { - lab6: { - var /** number */ v_5 = base.limit - base.cursor; - lab7: { - if (!(base.eq_s_b("\u05D2"))) - { - break lab7; - } - break lab6; - } - base.cursor = base.limit - v_5; - if (!(base.eq_s_b("\u05E9"))) - { - break lab5; - } - } - var /** number */ v_6 = base.limit - base.cursor; - lab8: { - if (!r_R1plus3()) - { - base.cursor = base.limit - v_6; - break lab8; - } - if (!base.slice_from("\u05D9\u05E1")) - { - return false; - } - } - break lab4; - } - base.cursor = base.limit - v_4; - if (!r_R1()) - { - break lab0; - } - if (!base.slice_del()) - { - return false; - } - } - break; - } - } - base.cursor = base.limit - v_1; - var /** number */ v_7 = base.limit - base.cursor; - lab9: { - base.ket = base.cursor; - among_var = base.find_among_b(a_5); - if (among_var == 0) - { - break lab9; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - break lab9; - } - if (!base.slice_del()) - { - return false; - } - break; - case 2: - if (!r_R1()) - { - break lab9; - } - if (!(base.in_grouping_b(g_consonant, 1489, 1520))) - { - break lab9; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - base.cursor = base.limit - v_7; - var /** number */ v_8 = base.limit - base.cursor; - lab10: { - base.ket = base.cursor; - among_var = base.find_among_b(a_6); - if (among_var == 0) - { - break lab10; - } - base.bra = base.cursor; - switch (among_var) { - case 1: - if (!r_R1()) - { - break lab10; - } - if (!base.slice_del()) - { - return false; - } - break; - } - } - base.cursor = base.limit - v_8; - var /** number */ v_9 = base.limit - base.cursor; - lab11: { - while(true) - { - var /** number */ v_10 = base.limit - base.cursor; - lab12: { - golab13: while(true) - { - var /** number */ v_11 = base.limit - base.cursor; - lab14: { - base.ket = base.cursor; - lab15: { - var /** number */ v_12 = base.limit - base.cursor; - lab16: { - if (!(base.eq_s_b("GE"))) - { - break lab16; - } - break lab15; - } - base.cursor = base.limit - v_12; - if (!(base.eq_s_b("TSU"))) - { - break lab14; - } - } - base.bra = base.cursor; - if (!base.slice_del()) - { - return false; - } - base.cursor = base.limit - v_11; - break golab13; - } - base.cursor = base.limit - v_11; - if (base.cursor <= base.limit_backward) - { - break lab12; - } - base.cursor--; - } - continue; - } - base.cursor = base.limit - v_10; - break; - } - } - base.cursor = base.limit - v_9; - return true; - }; - - this.stem = /** @return {boolean} */ function() { - r_prelude(); - var /** number */ v_2 = base.cursor; - r_mark_regions(); - base.cursor = v_2; - base.limit_backward = base.cursor; base.cursor = base.limit; - r_standard_suffix(); - base.cursor = base.limit_backward; - return true; - }; - - /**@return{string}*/ - this['stemWord'] = function(/**string*/word) { - base.setCurrent(word); - this.stem(); - return base.getCurrent(); - }; -}; - -window['YiddishStemmer'] = YiddishStemmer; diff --git a/otherapps/romanian/index.tt b/otherapps/romanian/index.tt deleted file mode 100644 index 95e66ea..0000000 --- a/otherapps/romanian/index.tt +++ /dev/null @@ -1,180 +0,0 @@ -[% header('Two Romanian stemmers') %] - -

Links to resources

- - - -

-In swift succession, we received in 2006 two stemmers for Romanian -written in Snowball. -Here is the original correspondence, -

- -
-From: Erwin Glockner <eglockne@ix.urz.uni-heidelberg.de>
-To: snowball-discuss
-Date: Wed, 07 Jun 2006 00:06:30 +0200
-Subject: [Snowball-discuss] romanian stemmer
-
-Hello everyone,
-
-my name is Erwn Glockner, I'm a student of computational linguistics in
-Heidelberg, Germany. Together with my fellow students Doina Gliga and
-Marina Stegarescu we started to write a romanian stemmer in Snowball.
-We planned to finish the stemmer until end of this month. We would be
-happy if the stemmer would be accepted as part of the Snowball-distribution.
-There is still some work to do, e.g. evaluating the stemmer, making a
-stopwords-list, unicode support, etc. After finishing this we will send
-you our stemmer with the corresponding files, but I couldn't find any
-email address to whom the stemmer should be sent to.
-Could please someone tell me the address(es)?
-
-With kind regards,
-E. Glockner, D. Gliga, M. Stegarescu.
-
- -
-From: Erwin Glockner <eglockne@ix.urz.uni-heidelberg.de>
-To: richard@lemurconsulting.com,
-    martin.porter@grapeshot.co.uk
-Date: Tue Jul 18 19:43:39 2006
-Subject: romanian stemmer
-
-Dear Mr. Porter, dear Mr. Boulton,
-
-we finally finished the Romanian stemmer. Unfortunately evaluation took
-more time than expected.
-However, it was an interesting experience creating the stemmer, and we
-are happy to send you the result of our work.
-The attachment-file is a Tarball-zipped file with (hopefully) all files
-needed. The files and the stemmer as well are encoded in UTF-8. Please
-inform us if something is missing.
-
-We would be happy if the Romanian stemmer would be accepted and
-integrated into the official Snowball distribution. We agree of course
-to license the stemmer under the same terms as the existing snowball
-software.
-
-We're looking forward to hear from you soon.
-
-
-With kind regards,
-
-Marina, Doina and Erwin.
-
-Attachment: [romanian1.tgz]
-
- -
-From: Irina Tirdea <irina.tirdea@gmail.com>
-To: richard@lemurconsulting.com,
-    martin.porter@grapeshot.co.uk
-Date: Mon Jul 31 10:19:51 2006
-Subject: Romanian stemmer
-
-Hello,
-
-My name is Irina Tirdea and I have developed a Romanian stemmer in Snowball
-as part of my bachelor thesis, in Bucharest, Romania. I am sending you the
-code attached (with vocabulary and stop word list files) and I hope you will
-accept and integrate it as a part of the Snowball project. I am ready to
-release the stemmer under the BSD license, just as the Snowball software.
-The files have been written in UTF-8 encoding (on a Linux system).
-
-Looking forward to hear from you.
-
-Kind regards,
-Irina Tirdea
-
-Attachment: [romanian2.tgz]
-
- -
-From: martin.porter@grapeshot.co.uk (Martin Porter)
-To: snowball-discuss
-Cc: atordai@science.uva.nl,
-    eglockne@ix.urz.uni-heidelberg.de,
-    irina.tirdea@gmail.com
-Date: Mon Jul 31 10:43:05 BST 2006
-Subject: Tardy response to submissions to Snowball
-
-I am sending this general email as a kind of apology, for having done nothing
-so far on the following generously sent Snowball submissions:
-
-7 June, from E. Glockner: a Romanian stemmer
-8 June, from A. Tordai: a Hungarian stemmer
-
-and this morning another Romanian stemmer arrived,
-
-31 July, from I. Tirdea, a Romanian stemmer
-
-After the first submission I promised to look at it "next week", so Mr Glockner
-has probably been wondering what has happened. [. . .] I will make a point of
-looking at these submissions this week,
-
-More soon,
-
-Martin
-
- -
-From: martin.porter@grapeshot.co.uk (Martin Porter)
-To: snowball-discuss
-Cc: irina.tirdea@gmail.com,
-    eglockne@ix.urz.uni-heidelberg.de,
-    mstegare@hotmail.com,
-    doina_gliga@yahoo.co.uk,
-    eglockner@hotmail.com
-Date: Wed Sep 06 12:39:16 BST 2006
-Subject: Romanian stemmer
-
-To the originators of the Romanian stemmers,
-
-I have now found time to do some preliminary work on the Romanian stemmer. I
-should explain that part of the complication has been the receipt, no more
-than ten days apart, of two Romanian stemmers in Snowball, the first
-(romanian1) from [Glockner, Gliga, and Stegarescu] in Heidelberg, the second
-(romanian2) from Tirdea in Bucharest.
-
-[. . . .]
-
-I have put together a vocabulary by combining the vocabularies provided with
-romanian1 and romanian2. This appears in column 1. Column 2 is the stemmed
-form produced by romanian1, and column 3 the stemmed form produced by
-romanian2. If the entry in column 3 is blank, both stemmers are producing the
-same result.
-
-You might care to compare the two approaches.
-
-My own feeling is that romanian1 does a more thorough job of ending removal,
-but unlike romanian2 has a habit of discarding too much from short words.
-aberant->ab, abatere->ab, aburi->ab are examples of this. In romanian1 the R2
-test is rarely used (it seems to me that 'R1 or R2' is equivalent to 'R1',
-since p2 is never to the left of p1.)
-
-I might have a go at making some modifications here. Needless to say, I am
-not familiar with Romanian, but the similarity to the other Romance
-languages, especially Italian, enables one to grasp the essential features of
-the morphology.
-
-What we would like to do is to have a single stemmer for release from the
-snowball site, if that is possible, and giving all necessary credits, along
-the lines of the recent addition,
-
-http://snowballstem.org/algorithms/hungarian/stemmer.html
-
-Hope to hear from you,
-
-Martin Porter
-
- -

-Finally we decided to produce our own Romanian stemmer as described on the -Romanian stemmer page. The submitted stemmers both contain stop word lists, -available inside the tarballs. -

- -[% footer %] diff --git a/otherapps/schinke/index.tt b/otherapps/schinke/index.tt deleted file mode 100644 index 6589bf4..0000000 --- a/otherapps/schinke/index.tt +++ /dev/null @@ -1,168 +0,0 @@ -[% header('The Schinke Latin stemming algorithm') %] - -

Links to resources

- - - -

-(A note by Martin Porter.) -

- -

-The Schinke Latin stemming algorithm is described in, -

- -
- Schinke R, Greengrass M, Robertson AM and Willett P (1996) A stemming algorithm for Latin text - databases. Journal of Documentation, 52: 172-187. -
- -

-It has the feature that it stems each word to two forms, noun and verb. For example, -

- -
-                NOUN        VERB
-                ----        ----
-    aquila      aquil       aquila
-    portat      portat      porta
-    portis      port        por
-
- -

-Here (slightly reformatted) are the rules of the stemmer, -

- -
-1. (start)
-
-2.  Convert all occurrences of the letters 'j' or 'v' to 'i' or 'u',
-    respectively.
-
-3.  If the word ends in '-que' then
-        if the word is on the list shown in Figure 4, then
-            write the original word to both the noun-based and verb-based
-            stem dictionaries and go to 8.
-        else remove '-que'
-
-    [Figure 4 was
-
-        atque quoque neque itaque absque apsque abusque adaeque adusque denique
-        deque susque oblique peraeque plenisque quandoque quisque quaeque
-        cuiusque cuique quemque quamque quaque quique quorumque quarumque
-        quibusque quosque quasque quotusquisque quousque ubique undique usque
-        uterque utique utroque utribique torque coque concoque contorque
-        detorque decoque excoque extorque obtorque optorque retorque recoque
-        attorque incoque intorque praetorque]
-
-4.  Match the end of the word against the suffix list show in Figure 6(a),
-    removing the longest matching suffix, (if any).
-
-    [Figure 6(a) was
-
-        -ibus -ius  -ae   -am   -as   -em   -es   -ia
-        -is   -nt   -os   -ud   -um   -us   -a    -e
-        -i    -o    -u]
-
-5.  If the resulting stem contains at least two characters then write this stem
-    to the noun-based stem dictionary.
-
-6.  Match the end of the word against the suffix list show in Figure 6(b),
-    identifying the longest matching suffix, (if any).
-
-    [Figure 6(b) was
-
-    -iuntur-beris -erunt -untur -iunt  -mini  -ntur  -stis
-    -bor   -ero   -mur   -mus   -ris   -sti   -tis   -tur
-    -unt   -bo    -ns    -nt    -ri    -m     -r     -s
-    -t]
-
-    If any of the following suffixes are found then convert them as shown:
-
-        '-iuntur', '-erunt', '-untur', '-iunt', and '-unt', to '-i';
-        '-beris', '-bor', and '-bo' to '-bi';
-        '-ero' to '-eri'
-
-    else remove the suffix in the normal way.
-
-7.  If the resulting stem contains at least two characters then write this stem
-    to the verb-based stem dictionary.
-
-8.  (end)
-
- -

-Unfortunately I was not able to make the rules match the examples given, which -led to the following email correspondence, -

- -
-From: Martin Porter
-To: Peter Willett
-Date: Mon Sep 10 15:11:51 2001
-Subject: Re: Stemming algorithms
-
-> ... I'm no longer working in the IR area,
->spending all of my time on computational chemistry/drug discovery
->research but I guess that Mark Sanderson would be interested in
->Snowball - do you mind if I pass your email onto him?
-
-Peter,
-
-Well, actually, I do have a question, if you can cast your mind back. I've
-implemented the Latin Stemmer in Snowball (see below: you'll have to guess the
-semantics, but I'm sure you'll agree the syntax looks nice), and find that Fig
-5 of the 1996 Schinke paper doesn't correspond to the algorithm of fig 7, but to
-the algorithm with the extra rules concerning -ba-, -bi-, -sse- mentioned on
-page 182. Which is the "correct" algorithm - with or without those rules? If
-with, what is the exact criterion for their removal? A bigger problem is why
-the -nt is not removed from 'Apparebunt', given -nt as an ending in 6(a). Is
--nt a misprint?
-
-Sorry to bother you with this, but the paper says you are the one "to whom all
-correspondence should be addressed" :-)
-
-Martin
-
-
- Here is your algorithm in Snowball. The generated code will do about 1 million
- Latin word in 5 seconds:
-
- -------
-
-
-[% highlight_file('schinke') %] -
- -
-From: Peter Willett
-To: Martin Porter
-Date: Mon Sep 10 20:25:24 2001
-Subject: Re: Stemming algorithms
-
-Martin
-
-Sorry - I just cannot answer.  Robertson has retired to Dorset while
-Schinke is now in - I think - Canada
-
-Peter
-
- -

-Following this, I was unable to contact Schinke, and so the problems have -remained unresolved. -

- -

-The linked zip file contains the stemmer, -generated C version, and sample data. -(The stemmer differs slightly from the version in the email above in that -it assembles the noun- and verb-forms of the stem in a single string with -space separation.) -voc.txt is a sample vocabulary, and joined.txt the vocabulary -joined with the two stemmed forms as three column output. -

- -[% footer %] diff --git a/runtime/use.tt b/runtime/use.tt deleted file mode 100644 index 1a00df1..0000000 --- a/runtime/use.tt +++ /dev/null @@ -1,381 +0,0 @@ -[% header('Using Snowball') %] - -

Links to resources

- - - -

Compiling Snowball

- -

-When you download Snowball, -it already contains a make file to allow you to build it, like so: -

- -
-    make
-
- -

-You can confirm it's working with a simple test like so: -

- -
-    echo "running" | ./stemwords -l en
-
- -

-which should output: run -

- -

-There's no built in way to install snowball currently - you can either copy -the snowball binary to somewhere that's on your PATH -(e.g. on a typical Linux machine: sudo cp snowball /usr/local/bin) -or just run it from the source tree with ./snowball). -

- -

Running Snowball

- -

-The snowball compiler has the following command line syntax, -

- -
-[% snowball_help | html %]
-
- -

-For example, -

- -
-    snowball danish.sbl -o q/danish
-    snowball danish.sbl -syntax
-    snowball danish.sbl -output q/danish -ep danish_
-
- -

-The first argument,  SOURCE_FILE, is the name of the Snowball file to be compiled. Unless you specify a different programming language to -generate code for, the default is to generate ISO C which results in two output -files, a C source in  OUTPUT_BASE.c  and a corresponding header file in  OUTPUT_BASE.h. This is similar for other -programming languages, e.g. if option  -java  is -present, Java output is produced in  OUTPUT_BASE.java. -

- -

-Some options are only valid when generating code for particular programming -languages. For example, the  -widechars, - -utf8,  -eprefix  and - -vprefix  options are specific to C and C++. -

- -

ISO C generation

- -

-In the absence of the  -eprefix  and  -vprefix  options, the list of -declared externals in the Snowball program, for example, -

- -[% highlight(" - externals ( stem_1 stem_2 moderate ) -") %] - -

-gives rise to a header file containing, -

- -[% highlight(" - extern struct SN_env * create_env(void); - extern void close_env(struct SN_env * z); - - extern int moderate(struct SN_env * z); - extern int stem_2(struct SN_env * z); - extern int stem_1(struct SN_env * z); -", "c") %] - -

-If  -eprefix  is used, its string,  S1, is prefixed to each external -name, for example -

- -
-    -eprefix Khotanese_
-
- -

-would give rise to the header file, -

- -[% highlight(" - extern struct SN_env * Khotanese_create_env(void); - extern void Khotanese_close_env(struct SN_env * z); - - extern int Khotanese_moderate(struct SN_env * z); - extern int Khotanese_stem_2(struct SN_env * z); - extern int Khotanese_stem_1(struct SN_env * z); -", "c") %] - -

-If  -vprefix  is used, all Snowball strings, integers and booleans give -rise to a  #define  line in the header file. For example -

- -
-    -eprefix Khotanese_ -vprefix Khotanese_variable
-
- -

-would give rise the header file, -

- -[% highlight(" - extern struct SN_env * Khotanese_create_env(void); - extern void Khotanese_close_env(struct SN_env * z); - - #define Khotanese_variable_ch (S[0]) - #define Khotanese_variable_Y_found (B[0]) - #define Khotanese_variable_p2 (I[1]) - #define Khotanese_variable_p1 (I[0]) - extern int Khotanese_stem(struct SN_env * z); -", "c") %] - -

-The -utf8 and -widechars  options affects how -the generated C/C++ code expects strings to be represented - UTF-8 or -wide-character Unicode (stored using 2 bytes per codepoint), or if neither is -specified, one byte per codepoint using either ISO-8859-1 or another encoding. -

- -

-For other programming languages, one of these three options is effectively -implicitly hard-coded (except wide-characters may be wider) - e.g. C#, Java, -Javascript and Python use wide characters; Ada, Go and Rust use UTF-8; Pascal -uses ISO-8859-1. Since Snowball 2.0 it's possible with a little care to write -Snowball code that works regardless of how characters are represented. See -section 12 of the Snowball manual for -more details. -

- -

-The  -runtime  option is used to prepend a path to any  #include -lines in the generated code, and is useful when the runtime header files (i.e. -those files in the runtime directory in the standard distribution) are not -in the same location as the generated source files. It is used when -building the libstemmer library, and may be useful for other projects. -

- - - -

Other options

- -

-If  -syntax  is used the other options are ignored, and the syntax tree -of the Snowball program is directed to  stdout. This can be a handy way -of checking that you have got the bracketing right in the program you have -written. -

- -

-Any number of  -include  options may be present, for example, -

- -
-    snowball testfile -output test -ep danish_  \
-             -include /home/martin/Snowball/codesets  \
-             -include extras
-
- -

-Each  -include  is followed by a directory name. With a chain of -directories  D1,  D2  ...  Dn, a Snowball  get  directive, -

- -[% highlight(" - get 'F' -") %] - -

-causes  F  to be searched for in the successive locations, -

- -
-    F
-    D1/F
-    D2/F
-    ...
-    Dn/F
-
- -

-— that is, the current directory, followed in turn by directories  D1  to -Dn. -

- -

The Snowball API

- -

-To access Snowball from C, include the header  api.h, and any headers -generated from the Snowball scripts you wish to use.  api.h  declares -

- -[% highlight(" - struct SN_env { /* ... */ }; - extern void SN_set_current(struct SN_env * z, int size, char * s); -", "c") %] - -

-Continuing the previous example, you set up an environment to call the -resources of the Khotanese module with -

- -[% highlight(" - struct SN_env * z; - z = Khotanese_create_env(); -", "c") %] - -

-Snowball has the concept of a ‘current string’. -This can be set up by, -

- -[% highlight(" - SN_set_current(z, i, b); -", "c") %] - -

-This defines the current string as the  i  bytes of data starting at -address  b. The externals can then be called, -

- -[% highlight(" - Khotanese_moderate(z); - /* ... */ - Khotanese_stem_1(z); -", "c") %] - -

-They give a 1 or 0 result, corresponding to the t or f result of -the Snowball routine. -

- -

-And later, -

- -[% highlight(" - Khotanese_close_env(z); -", "c") %] - -

-To release the space raised by z back to the system. You can do this for a -number of Snowball modules at the same time: you will need a separate -struct SN_env * z;  for each module. -

- -

-The current string is given by the  z->l  bytes of data starting at  z->p. -The string is not zero-terminated, but you can zero terminate it yourself with -

- -[% highlight(" - z->p[z->l] = 0; -", "c") %] - -

-(There is always room for this last zero byte.) For example, -

- -[% highlight(' - SN_set_current(z, strlen(s), s); - Khotanese_stem_1(z); - z->p[z->l] = 0; - printf("Khotanese-1' _ " stems '%s' to '%s'" _ '\n", s, z->p); -', "c") %] - -

-The values of the other variables can be accessed via the  #define -settings that result from the  -vprefix  option, although this should not -usually be necessary: -

- -[% highlight(' - printf("p1 is %d\n", z->Khotanese_variable_p1); -', "c") %] - -

-The stemming scripts on this Web site use Snowball very simply. --vprefix  is left unset, and  -eprefix  is set to the name of the -script (usually the language the script is for). -

- - - -

Debugging snowball scripts

- -

-In the rare event that your Snowball script does not run perfectly the first time: -

- -

-Remember that the option  -syntax  prints out the syntax tree. A question -mark can be included in Snowball as a command, and it will generate a call -debug(...). The defined  debug  in  runtime/utilities.c  (usually -commented out) can then be used. It causes the -current string to sent to  stdout, with square brackets marking the -slice and vertical bar the position of c. Curly brackets mark the -end-limits of the string, which may be less than the whole string because -of the action of  setlimit. -

- -

-At present there is no way of reporting the value of an integer or boolean. -

- -

-If desperate, you can put debugging lines into the generated C program. -You can pass -comments to the snowball compiler to get it to -generate comments showing the correspondence with the Snowball source which -makes it easier to find where to add such debugging code. -

- -

Compiler bugs

- -

-If you hit a snowball compiler bug, try to -capture it in a small script before notifying us. -

- -

Known problems in Snowball

- -

-The main one is that it is possible to ‘pull the rug from under your own feet’ in -constructions like this: -

- -[% highlight(' - [ do something ] - do something_else - ( C1 delete C2 ) or ( C3 ) -') %] - -

-Suppose  C1  gives t, the delete removes the slice established on the first -line, and  C2  gives f, so C3 is done with c set back to the value it had -before  C1  was obeyed — but this old value does not take account of the byte shift -caused by the delete. This problem was foreseen from the beginning when designing -Snowball, and recognised as a minor issue because it is an unnatural thing to want to -do. (C3  should not be an alternative to something which has deletion as an -occasional side-effect.) It may be addressed in the future. -

- -[% footer %] diff --git a/texts/apostrophe.tt b/texts/apostrophe.tt deleted file mode 100644 index 3948dce..0000000 --- a/texts/apostrophe.tt +++ /dev/null @@ -1,75 +0,0 @@ -[% header('The apostrophe character') %] - -

-Representing apostrophe is problematical for various reasons, -

- -
    -

  1. There are two Unicode characters for apostrophe, U+0027 (also ASCII hex -27), and U+2019. Compare, -

    - -
    -        Hamlet's father's ghost (U+0027)
-        Hamlet’s father’s ghost (U+2019)
-
    - -

  2. Although conceptually different from an apostrophe, a single closing -quote is also represented by character U+2019. -

    - -

  3. Character U+0027 is used for apostrophe, single closing quote and -single opening quote (U+2018). -

    - -

  4. A fourth character, U+201B, like U+2018 but with the tail ‘rising’ -instead of ‘descending’, is also sometimes used as apostrophe (in the -house style of certain publishers, for surnames like M’Coy and so on.) -

    -
- -

-In the English stemming algorithm, it is assumed that apostrophe is -represented by U+0027. This makes it ASCII compatible. Clearly other codes -for apostrophe can be mapped to this code prior to stemming. -

- -

-In English orthography, apostrophe has one of three functions. -

- -
    -

  1. It indicates a contraction in what is now accepted as a single word: -o’clock, O’Reilly, M’Coy. Except in proper names such forms -are rare: the apostrophe in Hallowe’en is disappearing, and in -’bus has disappeared. -

    - -

  2. It indicates a standard contraction with auxiliary or modal verbs: -you’re, isn’t, we’d. There are about forty of these forms in -contemporary English, and their use is increasing as they displace the full -forms that were at one time used in formal documents. Although they can be -reduced to word pairs, it is more convenient to treat them as single items -(usually stopwords) in IR work. And then preserving the apostrophe is -important, so that he’ll, she’ll, we’ll are not equated with -hell, shell, well etc. -

    - -

  3. It is used to form the ‘English genitive’, John's book, the horses’ -hooves etc. This is a development of (1), where historically the apostrophe -stood for an elided e. (Similarly the printed form ’d for ed was -very common before the nineteenth century.) Although in decline (witness pigs -trotters, Girls School Trust), its use continues in contemporary -English, where it is fiercely promoted as correct grammar, despite (or it might -be closer to the truth to say because of) its complete semantic redundancy. -

    -
- -

-For these reasons, the English stemmer treats apostrophe as a letter, removing -it from the beginning of a word, where it might have stood for an opening -quote, from the end of the word, where it might have stood for a closing quote, -or been an apostrophe following s. The form ’s is also treated as an ending. -

- -[% footer %] diff --git a/texts/earlyenglish.tt b/texts/earlyenglish.tt deleted file mode 100644 index 827a911..0000000 --- a/texts/earlyenglish.tt +++ /dev/null @@ -1,135 +0,0 @@ -[% header('Stemming early English') %] - -

Links to resources

- - - -

-The question occasionally arises of how far the English (or earlier Porter) -stemming algorithm can be adapted to handle older forms of the English -language. -

- -

-Historically, English is usually divided into three periods of development, -

- -
    -
  1. Old English (or Anglo-Saxon), the language of Beowulf, -
  2. Middle English, the language of Chaucer, -
  3. Modern English, the language of Shakespeare, Dickens, and people today. -
- -

-Old English is so different from Modern English that it may be regarded as a -distinct language. -

- -

-Middle English is problematical for a number of reasons. There is no standard -spelling in the original texts, and the grammatical differences between Middle -and Modern English prevent the spelling from being simply ‘modernised’. It is -however possible to normalise the spelling according to some modern scheme, but -again there is no standard modern scheme. Middle -English itself had great regional variations, so that for example the -English of Chaucer and his contemporary the Gawain poet (both late 14th century) -are strikingly different. Finally, grammar was fluid even for one writer, so -Chaucer might use they love or they loven, he -sitteth or he sit. -

- -

-We may take Modern English to mean English which can be cast into a modern -spelling form without too much damage being done to the original. From this -point of view Shakespeare and the Authorised Version of the Bible are in Modern -English. The ending structure of words in early Modern English differ from -contemporary English in the est and eth endings of verbs in the present -indicative, -

- -
- I bring
- thou bringest
- he bringeth
- we bring
- you bring
- they bring -
- -

-Both of these endings underwent rapid decline. The eth form occurs in -Shakespeare, but is much rarer than the modern s form. The language of the -Authorised Version, -in which both forms abound, -seemed archaic even on its first publication. Consequently -the eth form survives now only in the language of the traditional Bible and -Book of Common Prayer. The est form disappeared more slowly, as the use of -thou became displaced by you in conversation. -

- -

-To put the endings into the -Porter stemmer, -the rules -

- -
-Step 1b -
-
(m>0) EED → EE -
(*v*) ED → -
(*v*) ING → -
-
- -

-should be extended to -

- -
-Step 1b -
-
(m>0) EED → EE -
(*v*) ED → -
(*v*) ING → -
(*v*) EST → -
(*v*) ETH → -
-
- -

-And to put the endings into the -English stemmer, -the list -

- -
-ed   edly   ing   ingly -
-of Step 1b should be extended to -
-ed   edly   ing   ingly   est   eth -
- -

-As far as the Snowball scripts are concerned, the endings  'est' 'eth'  must -be added against ending  'ing'. -

- -

-The inclusion of these endings does produce certain ‘side effects’. est is -the ending of adjectival superlatives (greatest, unkindest), where it -will also be removed. Words like brandreth, deforest will be mis-stemmed. -Nevertheless, for the vocabulary of the Bible, the inclusion of these extra -endings is not harmful (see -this demonstration — -for example, search for the text love in 1000 verses). - -[% footer %] diff --git a/texts/glossary.tt b/texts/glossary.tt deleted file mode 100644 index 0860abb..0000000 --- a/texts/glossary.tt +++ /dev/null @@ -1,106 +0,0 @@ -[% header('Glossary') %] - -

a-suffix

-
-

-An a-suffix, or attached suffix, is a particle word attached to another -word. (In the stemming literature they sometimes get referred to as -‘enclitics’.) In Italian, for example, personal pronouns attach to -certain verb forms: -

- -
-
mandargli = mandare + gli = to send + to him -
mandarglielo = mandare + gli + lo = to send + it + to him -
- -

-a-suffixes appear in Italian and Spanish, and also in Portuguese, although -in Portuguese they are separated by hyphen from the preceding word, which -makes them easy to eliminate. -

-
- -

i-suffix

-
-

-An i-suffix, or inflectional suffix, forms part of the basic grammar of a -language, and is applicable to all words of a certain grammatical type, -with perhaps a small number of exceptions. In English for example, the past -of a verb is formed by adding ed. Certain modifications may be required -in the stem: -

- -
-
fit + ed → fitted (double t) -
love + ed → loved (drop the final e of love) -
-
- -

d-suffix

- -
-

-A d-suffix, or derivational suffix, enables a new word, often with a -different grammatical category, or with a different sense, to be built from -another word. Whether a d-suffix can be attached is discovered not from -the rules of grammar, but by referring to a dictionary. So in English, -ness can be added to certain adjectives to form corresponding nouns -(littleness, kindness, foolishness ...) but not to all adjectives (not for -example, to big, cruel, wise ...) d-suffixes can be used to change -meaning, often in rather exotic ways. So in italian astro means a sham -form of something else: -

- -
-
medico + astro = medicastro = quack doctor -
poeta + astro = poetastro = poetaster -
-
- -

Indo-European languages

- -
-

-Most European and many Asian languages belong to the Indo-European language -group. Historically, it includes the Latin, Greek, Persian and Sanskrit of -the ancient world, and with the rise of the European empires, languages of -this group are now dominant in the Americas, Australia and large parts of -Africa. Indo-European languages are therefore the main languages of modern -Western culture, and they are all similarly amenable to stemming. -

- -

-The Indo-European group has many recognisable sub-groups, for example -Romance (Italian, French, Spanish ...), Slavonic (Russian, Polish, -Czech ...), Celtic (Irish Gaelic, Scottish Gaelic, Welsh ...). The -Germanic sub-group includes German and Dutch, and the Scandinavian -languages are also usually classed as Germanic, although for convenience we -have made a separate grouping of them on the Snowball site. English is also -classed as Germanic, although it has been classed separately by us. This is -not for reasons of narrow chauvinism, but because the suffix structure of -English clearly lies mid-way between the Germanic and Romance groups, and it -therefore requires separate treatment. -

-
- -

Uralic languages

- -
-

-The Uralic languages are spoken mainly in Northern Russia and Europe. They -are divided into Samoyed, spoken mainly in the Siberian region, and -Finno-Ugric, spoken mainly in Europe. Although the number of languages in -the group is substantial, the total number of speakers is relatively small. -The best known Uralic languages are perhaps Hungarian, Finnish and -Estonian. Finnish and Estonian are in fact fairly similar. On the other -hand Hungarian and Finnish are as different as are, say, French and Persian -in the Indo-European group. -

- -

-Like the Indo-European languages, the Uralic languages are amenable to -stemming. -

- -[% footer %] diff --git a/texts/howtohelp.tt b/texts/howtohelp.tt deleted file mode 100644 index 5231d72..0000000 --- a/texts/howtohelp.tt +++ /dev/null @@ -1,65 +0,0 @@ -[% header('Snowball: How You Can Help') %] - -

-For the work on this site there are two possible lines of development, one is -Snowball itself — the language and compiler — and the other is the -stemmers which are written in Snowball. At the moment it is the latter that -is the real area of interest. -

- -

-It is useful to have suggestions about improvements to the existing -stemmers, especially for the ones which are not English. However, the -process of piecemeal improvement can be taken too far, and it is important -in making these suggestions to recognise the inevitable limitations of -accuracy of algorithmic stemmers. But more importantly: — -

- -

-Stemming algorithms have a well-understood place in IR (Information -Retrieval), and as language-specific tools in an IR system, they have an -extremely useful part to play. It is therefore something of a scandal that -there are so very few stemming algorithms which are readily available, so -if you want to make a contribution to Snowball, the best thing you can do -is to create a good quality stemmer for a new language. This must -include an algorithmic description of the stemmer, an implementation in -Snowball, and a representative language vocabulary of about 30,000 words -that can be used as part of a standard test. -

- -

-Alternatively, you might come up with the algorithm and be able to provide -representative texts from which to derive the vocabulary, but hesitate -about the Snowball implementation. If so, get in touch, and we might be -able to complete the work collaboratively. -

- -

-We are also interested in: -

- -
    -
  • Significant applications developed with the Snowball stemmers - -
  • Stemmers held on other sites that derive from Snowball work - -
  • Other useful stemming resources -
- -

-It may seem like stating the obvious, but if you do hit a technical -problem, please, please send in a full notice of the system being used, -the activity you were engaged on, and the errors that you encounter. -

- -

-Finally, if you want to contribute to this site, you must be prepared to -release under the BSD license (i.e. to make your work free). -

- -

-Martin Porter
-Richard Boulton -

- -[% footer %] diff --git a/texts/introduction.tt b/texts/introduction.tt deleted file mode 100644 index 16b7727..0000000 --- a/texts/introduction.tt +++ /dev/null @@ -1,923 +0,0 @@ -[% header('Snowball: A language for stemming algorithms') %] - -

Links

- - - -

-M.F. Porter
-October 2001 -

- -

Summary

- -

- Algorithmic stemmers continue to have great utility in IR, despite the - promise of out-performance by dictionary-based stemmers. Nevertheless, - there are few algorithmic descriptions of stemmers, and even when they - exist they are liable to misinterpretation. Here we look at the ideas - underlying stemming, and on this website define a language, Snowball, - in which stemmers can be exactly defined, and from which fast stemmer - programs in ANSI C or Java can be generated. A range of stemmers is presented - in parallel algorithmic and Snowball form, including the original - Porter stemmer for English. -

- -

1 Introduction

- -

-There are two main reasons for creating Snowball. One is the lack of -readily available stemming algorithms for languages -other than English. The other is the consciousness of a certain failure on -my part in promoting exact implementations of the stemming -algorithm described in (Porter 1980), which has come to be called the -Porter stemming algorithm. The first point needs some qualification: a -great deal of work has been done on stemmers in a wide range of natural -languages, both in their development and evaluation, (a complete -bibliography cannot be attempted here). But it is rare to see a stemmer -laid out in an unambiguous algorithmic form from which encodings in C, -Java, Perl etc might easily be made. When exact descriptions are -attempted, it is often with approaches to stemming that are -relatively simple, for example the Latin stemmer of Schinke (Schinke 1996), -or the Slovene stemmer of Popovic (Popovic 1990). A more complex, and -therefore more characteristic stemmer is the Kraaij-Pohlmann stemmer for -Dutch (Kraaij 1994), which is presented as open source code in ANSI C. To -extract an algorithmic description of their stemmer from the source code -proves to be quite hard. -

- -

-The disparity between the Porter stemmer definition and many of its -purported implementations is much wider than is generally realised in the -IR community. Three problems seem to compound: one is a misunderstanding -of the meaning of the original algorithm, another is bugs in the -encodings, and a third is the almost irresistible urge of programmers -to add improvements. -

- -

-For example, a Perl script advertised on the Web as an -implementation of the Porter algorithm was tested in October 2001, and it was -found that 14 percent of words were stemmed incorrectly when given a large sample -vocabulary. Most words of English have -very simple endings, so this means that it was effectively getting everything -wrong. At certain points on the Web are demonstrations of the Porter stemmer. -You type some English into a box and the stemmed words are displayed. These -are frequently faulty. (A good test is to type in agreement. It should stem -to agreement — the same word. If it stems to agreem there is an -error.) Researchers frequently pick up faulty versions of the stemmer and -report that they have applied ‘Porter stemming’, with the result that their -experiments are not quite repeatable. Researchers who work on stemming will -sometimes give incorrect examples of the behaviour of the Porter stemmer in -their published works. -

- -

-To address all these problems I have tried to develop a rigorous system -for defining stemming algorithms. A language, Snowball, has been invented, -in which the rules of stemming algorithms can be expressed in a natural -way. Snowball is quite small, and can be learned by an experienced -programmer in an hour or so. On this website a number of foreign language -stemmers is presented (a) in Snowball, and (b) in a less formal -English-language description. (b) can be thought of as the program -comments for (a). A Snowball compiler translates each Snowball -definition into (c) an equivalent program in ANSI C or Java. Finally (d) -standard vocabularies of words and their stemmed equivalents are provided -for each stemmer. The combination of (a), (b), (c) and (d) -can be used to pin down the definition of a stemmer exactly, and it is -hoped that Snowball itself will be a useful resource in creating stemmers -in the future. -

- -

2 Some ideas underlying stemming

- -

-Work in stemming has produced a number of different approaches, albeit tied -together by a number of common assumptions. It is worthwhile looking at some -of them to see exactly where Snowball fits into the whole picture. -

- -

-A point tacitly assumed in almost all of the stemming literature is that -stemmers are based upon the written, and not the spoken, form of the -language. This is also the assumption here. Historically, -grammarians often regarded the written language as the real language and -the spoken as a mere derivative form. Almost in reaction, many modern -linguists have taken a precisely opposite view (Palmer, 1965 pp 2-3). A -more balanced position is that the two languages are distinct though -connected, and require separate treatment. One can in fact imagine parallel -stemming algorithms for the spoken language, or rather for the phoneme -sequence into which the spoken language is transformed. Stress and -intonation could be used as clues for an indexing process in the same way -that punctuation and capitalisation are used as clues in the written -language. But currently stemmers work on the written language for the good -reason that there is so much of it available in machine readable form from -which to build our IR systems. Inevitably therefore the stemmers get -caught up in accidental details of orthography. In English, removing the -ing from rotting should be followed by undoubling the tt, -whereas in rolling we do not undouble the ll. In French, removing -the er from ennuyer should be followed by changing the y to -i, so that the resulting word conflates with ennui, and so on. -

- -

-The idea of stemming is to improve IR performance generally by bringing -under one heading variant forms of a word which share a common meaning. -Harman (1991) was first to present compelling evidence that it may not do -so, when her experiments discovered no significant improvement with the -use of stemming. -Similarly Lennon (1981) discovered no appreciable difference between different -stemmers running on a constant collection. -Later work has modified this position however. Krovetz -(1995) found significant, although sometimes small, improvements across a -range of test collections. What he did discover is that the degree of -improvement varies considerably between different collections. -These tests were however done on collections in -English, and the reasonable assumption of IR researchers has always been that for -languages that are more highly inflected than English (and nearly all -are), greater improvements will be observed when stemming is applied. My -own view is that stemming helps regularise the -vocabulary of an IR system, and this leads to advantages that are not -easily quantifiable through standard IR experiments. For example, it helps -in presenting lists of terms associated with the query back to the IR user -in a relevance feedback cycle, which is one of the underlying ideas of the -probabilistic model. More will be said on the use of a stemmed vocabulary -in section 5. -

- -

-Stemming is not a concept applicable to all languages. It is not, for -example, applicable in Chinese. But to languages of the Indo-European (*) -group (and most of the stemmers on this site are for Indo-European -languages), a common -pattern of word structure does emerge. Assuming words are written left to -right, the stem, or root of a word is on the left, and zero or more -suffixes may be added on the right. If the root is modified by this -process it will normally be at its right hand end. And also prefixes may -be added on the left. So unhappiness has a prefix un, a suffix -ness, and the y of happy has become i with the addition of -the suffix. Usually, prefixes alter meaning radically, so they are best -left in place (German and Dutch ge is an exception here). But suffixes -can, in certain circumstances, be removed. So for example happy and -happiness have closely related meanings, and we may wish to stem both -forms to happy, or happi. Infixes can occur, although rarely: -ge in German and Dutch, and zu in German. -

- -

-One can make some distinction between root and stem. Lovins (1968) -sees the root as the stem minus any prefixes. But here we will -think of the stem as the residue of the stemming process, and the root as the -inner word from which the stemmed word derives, so we think of root to -some extent in an etymological way. It must be admitted that when you -start thinking hard about these concepts root, stem, suffix, -prefix ... they turn out to be very difficult indeed to define. -Nor do definitions, even if we arrive at them, help us much. After all, suffix -stripping is a practical aid in IR, not an exercise in linguistics or -etymology. This is especially true of the central concept of root. We -think of the etymological root of a word as something we can discover with -certainty from a dictionary, forgetting that etymology itself is a subject -with its own doubts and controversies (Jesperson 1922, Chapter XVI). -Indeed, Jesperson goes so far as to say that -

- -
-

- ‘It is of course impossible to say how great a proportion of the - etymologies given in dictionaries should strictly be classed under - each of the following heads: (1) certain, (2) probable, (3) - possible, (4) improbable, (5) impossible — but I am afraid the - first two classes would be the least numerous.’ -

-
- -

-Here we will simply assume a common sense understanding of -the basic idea of stem and suffix, and hope that this proves sufficient -for designing and discussing stemming algorithms. -

- -

-We can separate suffixes out into three basic classes, which will be -called d-, i- and a-suffixes. -

- -

-An a-suffix, or attached suffix, is a particle word attached to another -word. (In the stemming literature they sometimes get referred to as -‘enclitics’.) In Italian, for example, personal pronouns attach to -certain verb forms: -

- -
-
mandargli = mandare + gli = to send + to him -
mandarglielo = mandare + gli + lo = to send + it + to him -
- -

-a-suffixes appear in Italian and Spanish, and also in Portuguese, although -in Portuguese they are separated by hyphen from the preceding word, which -makes them easy to eliminate. -

- -

-An i-suffix, or inflectional suffix, forms part of the basic grammar of a -language, and is applicable to all words of a certain grammatical type, -with perhaps a small number of exceptions. In English for example, the past -of a verb is formed by adding ed. Certain modifications may be required -in the stem: -

- -
-
fit + ed → fitted (double t) -
love + ed → loved (drop the final e of love) -
- -

-but otherwise the rule applies in a regular way to all verbs in -contemporary English, with about 150 (Palmer, 1965) exceptional forms, -

- -
-
bear beat become begin bend .... -
bore beat became began bent -
- -

-A d-suffix, or derivational suffix, enables a new word, often with a -different grammatical category, or with a different sense, to be built from -another word. Whether a d-suffix can be attached is discovered not from -the rules of grammar, but by referring to a dictionary. So in English, -ness can be added to certain adjectives to form corresponding nouns -(littleness, kindness, foolishness ...) but not to all adjectives (not for -example, to big, cruel, wise ...) d-suffixes can be used to change -meaning, often in rather exotic ways. So in Italian astro means a sham -form of something else: -

- -
-
medico + astro = medicastro = quack doctor -
poeta + astro = poetastro = poetaster -
- -

-Generally i-suffixes follow d-suffixes. i-suffixes can precede d-suffixes, -for example lovingly, devotedness, but such cases are exceptional. To -be a little more precise, d-suffixes can sometimes be added to -participles. devoted, used adjectivally, is a participle derived from the -verb devote, and ly can be added to turn the adjective into an adverb, -or ness to turn it into a noun. The same feature occurs in other -Indo-European languages. -

- -

-Sometimes it is hard to say whether a suffix is a d-suffix or i-suffix, -the comparative and superlative endings er, est of English for example. -

- -

-A d-suffix can serve more than one function. In English, for example, -ly standardly turns an adjective into an adverb (greatly), but it -can also turn a noun into an adjective (kingly). In French, ement -also standardly turns an adjective into an adverb (grandement), but it -can also turn a verb into a noun (rapprochement). (Referring to the -French stemmer, this double use is ultimately why ement is tested for -being in the RV rather than the R2 region of the word being -stemmed.) -

- -

-It is quite common for an i-suffix to serve more than one function. -In English, s can either be (1) a verb ending attached to third person -singular forms (runs, sings), (2) a noun ending indicating the plural -(dogs, cats) or (3) a noun ending indicating the possessive -(boy’s, girls’). By an orthographic convention now several hundred -years old, the possessive is written with an apostrophe, but -nowadays this is -frequently omitted in familiar phrases (a girls school). (Usage (3) is -relatively rare compared with (1) and (2): there are only nine uses of -’s in this document.) -

- -

-Since the normal order of suffixes is d, i and a, we -can expect them to be removed -from the right in the order a, i and d. Usually we want to remove -all a- and i-suffixes, and some of the d-suffixes. -

- -

-If the stemming process reduces two words to the same stem, they are said -to be conflated. -

- -

3 Stemming errors, and the use of dictionaries

- -

-One way of thinking of the relation between terms and documents in an IR -system is to see the documents as being about concepts, and the terms as -words that describe the concepts. Then, of course, one word can cover many -concepts, so pound can mean a unit of currency, a weight, an enclosure, -or a beating. Pound is a homonym. And one concept can be described by -many words, as with money, capital, cash, currency. These words -are synonyms. There is a many-many mapping therefore between the set of -terms and the set of concepts. Stemming is a process that transforms this -mapping to advantage, on the whole reducing the number of synonyms, but -occasionally creating new homonyms. It is worth remembering that what are -called stemming errors are usually just the introduction of new homonyms into -vocabularies that already contain very large numbers of homonyms. -

- -

-Words which have no place in this term-concept mapping are those which -describe no concepts. The particle words of grammar, the, of, -and -..., known in IR as stopwords, fall into this category. Stopwords can be -useful for retrieval but only in searching for phrases, ‘to be or not to -be’, ‘do as you would be done by’ etc. This suggests that stemming -stopwords is not useful. More will be said on stopwords in section 7. -

- -

-In the literature, a distinction is often made between -under-stemming, which is the error of taking off too small a suffix, and -over-stemming, which is the error of taking off too much. In French, for -example, croûtons is the plural of croûton, ‘a crust’, so to remove -ons would be over-stemming, while croulons is a verb form of crouler, -‘to totter’, so to remove s would be under-stemming. We would like to -introduce a further distinction between mis-stemming and over-stemming. -Mis-stemming is taking off what looks like an ending, but is really part -of the stem. Over-stemming is taking off a true ending which results in -the conflation of words of different meanings. -

- -

-So for example ly can be removed from cheaply, but not from reply, -because in reply ly is not a suffix. If it was removed, reply would -conflate with rep, (the commonly used short form of representative). -Here we have a case of mis-stemming. -

- -

-To illustrate over-stemming, look at these four words, -

- -
-
verb adjective - -
First pair: prove provable -
Second pair: probe probable -
- -

-Morphologically, the two pairs are exactly parallel (in the written, if not -the spoken language). They also have a common etymology. All four words -derive from the Latin probare, ‘to prove or to test’, and the idea of -testing connects the meanings of the words. But the meanings are not parallel. -provable means ‘able to be proved’; probable does not mean ‘able to be -probed’. Most people would judge conflation of the first pair as correct, -and of the second pair, incorrect. In other words, to remove able from -probable is a case of over-stemming. -

- -

-We can try to avoid mis-stemming and over-stemming by using a dictionary. -The dictionary can tell us that reply does not derive from rep, and -that the meanings of probe and probable are well separated in modern -English. It is important to realise however that a dictionary does not give -a complete solution here, but can be a tool to improve the conflation -process. -

- -

-In Krovetz’s dictionary experiments (Krovetz 1995), he noted that in -looking up a past participle like suited, one is led either to suit or -to suite as plausible infinitive forms. suite can be rejected, -however, because the dictionary tells us that -although it is a word of English -it is not a verb form. Cases -like this (and Krovetz found about 60) had to be treated as exceptions. But -the form routed could -either derive from the verb rout or the verb route: -

- -

- At Waterloo Napoleon’s forces were routed
- The cars were routed off the motorway -

- -

-Such cases in English are extremely rare, but they are commoner in more -highly inflected languages. In French for example, affiliez can either be -the verb affiler, to sharpen, with imperfect ending iez, or the verb -affilier, to affiliate, with present indicative ending ez: -

- -
-
vous affiliez = vous affil-iez = you sharpened -
vous affiliez = vous affili-ez = you affiliate -
- -

-If the second is intended, removal of iez is mis-stemming. -

- -

-With over-stemming we must rely upon the dictionary to separate meanings. -There are different ways of doing this, but all involve some degree of -reliance upon the lexicographers. Krovetz’s methods are no doubt best, -because the most objective: he uses several measures, but they are based on -the idea of measuring the similarity in -meaning of two words by the degree of overlap among the words used to define -them, and this is at a good remove from a lexicographer’s subjective -judgement about semantic similarity. -

- -

-There is an interesting difference between mis-stemming and over-stemming -to do with language history. The morphology of a language changes less -rapidly than the meanings of the words in it. When extended to include a -few archaic endings, such as ick as an alternative to ic, a stemmer for -contemporary English can be applied to the English of 300 years ago. -Mis-stemmings will be roughly the same, but the pattern of over-stemming will -be different because of the changing meaning of words in the language. For -example, relativity in the 19th century merely meant ‘the condition of -being relative to’. With that meaning, it is acceptable to conflate it -with relative. -But with the 20th century meaning brought to it by -Einstein, stemming to relativ is over-stemming. -Here we see the word with the suffix changing its meaning, but it can happen -the other way round. transpire has come to mean ‘happen’, and its old -meaning of ’exhalation’ or ‘breathing out’ is now effectively lost. -(That is the bitter reality, although dictionaries still try to persuade us -otherwise). But transpiration still carries the earlier meaning. -So what was formerly an acceptable stemming may be judged now as -an over-stemming, not because the word being stemmed has changed its meaning, -but because some cognate word has changed its meaning. -

- -

-In these examples we are presenting words as if they had single meanings, but -the true picture is more complicated. Krovetz uses a model of word -meanings which is extremely helpful here. He makes a distinction between -homonyms and polysemes. The meaning of homonyms are quite unrelated. -For example, ground in the sense of ‘earth’, and ‘ground’ as the past -participle of ‘grind’ are homonyms. Etymologically homonyms have different -stories, and they usually have separate entries in a dictionary. But each -homonym form can have a range of polysemic forms, corresponding to different -shades of meaning. So ground can mean the earth’s surface, or the bottom -of the sea, or soil, or any base, and so the basis of an argument, and so on. -Over time new polysemes appear and old ones die. At any moment, the use of a -word will be common in some polysemic forms and rare in others. If a suffix is -attached to a word the new word will get a different set of polysemes. For -example, grounds = ground + s acquires the sense of ‘dregs’ and -‘estate lands’, loses the sense of ‘earth’, and shares the sense of -‘basis’. -

- -

-Consider the conflation of mobility with mobile. mobile has -acquired two new polysemes not shared with mobility. One is the ‘mobile -art object’, common in the nursery. This arrived in the 1960s, and is -still in use. The other is the ‘mobile phone’ which is now very dominant, -although it may decline in the future when it has been replaced by some new -gadget with a different name. We might draw a graph of the degree of -separation of the meanings of mobility and mobile against time, -which would depend upon the number of polysemes and the intensity of their -use. What seemed like a valid conflation of the two words in 1940 may seem -to be invalid today. -

- -

-In general therefore one can say that judgements about whether words are -over-stemmed change with time as the meanings of words in the language -change. -

- -

-The use of a dictionary should reduce errors of mis-stemming and errors of -over-stemming. And, for English at least, the mis-stemming errors should -reduce well, even if there are problems with over-stemming errors. Of -course, it depends on the quality of the dictionary. A dictionary will need -to be very comprehensive, fully up-to-date, and with good word definitions -to achieve the best results. -

- -

-Historically, stemmers have often been thought of as either -dictionary-based or algorithmic. The presentation of studies of stemming -in the literature has perhaps helped to create this division. In the -Lovins’ stemmer the algorithmic description is central. In accounts of -dictionary-based stemmers the emphasis tends to be on dictionary content -and structure, and IR effectiveness. Savoy’s French stemmer (Savoy, 1993) -is a good example of this. But the two approaches are not really distinct. -An algorithmic stemmer can include long exception lists that are -effectively mini-dictionaries, and a dictionary-based stemmer usually -needs a process for removing at least i-suffixes to make the look-up -in the dictionary possible. In fact in a language in which proper names -are inflected (Latin, Finnish, Russian ...), a dictionary-based stemmer -will need to remove i-suffixes independently of dictionary look-up, -because the proper names will not of course be in the dictionary. -

- -

-The stemmers available on the Snowball website are all purely -algorithmic. They can be extended to include built-in exception lists, they -could be used in combination with a full dictionary, but they are still -presented here in their simplest possible form. Being purely algorithmic, -they are, or ought to be, inferior to the performance of well-constructed -dictionary-based stemmers. But they are still very useful, for the -following reasons: -

- -
    -

  1. Algorithmic stemmers are (or can be made) very lean and very fast. The -stemmers presented here generate code that will process about a million -words in six seconds on a conventional 500MHz PC. Nowadays we can generate -very large IR systems with quite modest resources, and tools that assist in -this have value. -

    - -

  2. Despite the errors they can be seen to make, algorithmic stemmers still -give good practical results. As Krovetz (1995) says in surprise of the -algorithmic stemmer, ‘Why does it do so well?’ (page 89). -

    - -

  3. Dictionary-based stemmers require dictionary maintenance, to keep up -with an ever-changing language, and this is actually quite a problem. It -is not just that a dictionary created to assist stemming today will -probably require major updating in a few years time, but that a dictionary -in use for this purpose today may already be several years out of date. -

    -
- -

-We can hazard an answer to Krovetz’s question, as to why algorithmic -stemmers perform as well as they do, when they reveal so many cases of -under-, over- and mis-stemming. Under-stemming is a fault, but by itself -it will not degrade the performance of an IR system. Because of -under-stemming words may fail -to conflate that ought to have conflated, but you are, in a sense, no -worse off than you were before. Mis-stemming is more serious, but again -mis-stemming does not really matter unless it leads to false conflations, -and that frequently does not happen. For example, removing the ate -ending in English, can result in useful conflations (luxury, -luxuriate; affection, affectionate), but very often produces -stems that are not English words -(enerv-ate, accommod-ate, -deliber-ate etc). In the literature, these are normally -classed as stemming errors — overstemming — although in our nomenclature -they are examples of mis-stemming. -However these residual stems, -enerv, accommod, -deliber ... do not conflate with other word forms, and so behave in -an IR system in the same way as if they still retained their ate -ending. No false conflations arise, and so there is no over-stemming here. -

- -

-To summarise, one can say that just as a word can be over-stemmed -but not mis-stemmed (relativity → relative), so it can be -mis-stemmed but not over-stemmed (enervate → enerv). And, of -course, even over-stemming does not matter, if the over-stemmed word falsely -conflates with other words that exist in the language, but are not -encountered in the IR -system which is being used. -

- -

-Of the three types of error, -over-stemming is the most important, and -using a dictionary does not eliminate all over-stemmings, but does reduce their -incidence. -

- -

4 Stemming as part of an indexing process

- -

-Stemming is part of a composite process of extracting words from text and -turning them into index terms in an IR system. Because stemming is somewhat -complex and specialised, it is usually studied in isolation. Even so, it -cannot really be separated from other aspect of the indexing process: -

- -
    -

  1. What is a word? For indexing purposes, a word in a European language is -a sequence of letters bounded by non-letters. But in English, an internal -apostrophe does not split a word, although it is not classed as a letter. -The treatment of these word boundary characters affects the stemmer. For -example, the Kraaij Pohlmann stemmer for Dutch (Kraaij, 1994, 1995) removes hyphen and -treats apostrophe as part of the alphabet (so ’s, ’tje and ’je are three -of their endings). The Dutch stemmer presented here assumes hyphen and -apostrophe have already been removed from the word to be stemmed. -

    - -

  2. What is a letter? Clearly letters define words, but different languages -use different letters, much confusion coming from the varied use of -accented Roman letters. -

    - -

    -English speakers, perhaps influenced by the ASCII character set, typically regard -their alphabet of a to z as the norm, and other forms (for example, Danish -å and ø, or German ß) as somewhat abnormal. But this is -an insular point of view. In Italian, for example, the letters -j, k, w, x and y are not part of the alphabet, and are -only seen in foreign words. We also tend to regard other alphabets as only -used for isolated languages, and that is not strictly true. Cyrillic is -used for a range of languages other than Russian, among which additional -letters and accented forms abound. -

    - -

    -In English, a broad definition of letter would be anything that could be -accepted as a pronounceable element of a word. This would include -accented Roman letters (naïve, Fauré), and certain ligature -forms (encyclopædia). It would exclude letters -of foreign alphabets, such as Greek and Cyrillic. -The a to z alphabet is one of those where letters come in -two styles, upper and lower case, which historically correspond (very roughly) to the -shapes you get if you use a chisel or a pen. Across all languages, the -exact relation of upper to lower case is not so easy to define. In Italian, -for example, an accented lower case letter is sometimes represented in -upper case by the unaccented letter followed by an apostrophe. (I have -seen this convention used in modern Italian news stories in machine -readable form.) -

    - -

    -In fact the Porter stemmer (which is for English) assumes the word being stemmed is -unaccented and in lower case. More exactly, a, e, i, o, -u, -and sometimes y, are -treated as vowels, and any other character gets treated as a consonant. -Each stemmer presented here assumes some degree of normalisation before it -receives the word, which is roughly (a) put all letters into lower case, -and (b) remove accents from letter-accent combinations that do not form -part of the alphabet of the language. Each stemmer declares the -letter-accent combinations for its language, and this can be used as a -guide for the normalisation, but even so, we can see from -the discussion above that (a) and (b) are not trivial -operations, and need to be done with care. -

    - -

    -(Incidentally, because the stemmers work on lower case words, turning -letters to upper case is sometimes used internally for flagging purposes.) -

    - -

  3. Identifying stopwords. Invariant stopwords are more easily found before -stemming is applied, but inflecting stopwords (for example, German kein, keine, keinem, -keinen ... ) may be easier to find after — because there are fewer forms. -There is a case for building stopword identification into the stemming -process. See section 7. -

    - -

  4. Conflating irregular forms. More will be said on this in section 6. -

    -
- -

5 The use of stemmed words

- -

-The idea of how stemmed words might be employed in an IR system has -evolved slightly over the years. The Lovins stemmer (Lovins 1968) was -developed not for indexing document texts, but the subject terms attached -to them. With queries stemmed in the same way, the user needed no special -knowledge of the form of the subject terms. Rijsbergen (1979, Chapter 2) -assumes document text analysis: stopwords are removed, the remaining words -are stemmed, and the resulting set of stemmed word constitute the IR index -(and this style of use is widespread today). More flexibility however is -obtained by indexing all words in a text in an unstemmed form, and -keeping a separate two-column relation which connects the words to their -stemmed equivalents. The relation can be denoted by R(s, w), which means -that s is the stemmed form of word w. From the relation we can get, for -any word w, its unique stemmed form, stem(w), and for any stem s, the set -of words, words(s), that stem to s. -

- -

-The user should not have to see the stemmed form of a word. If a list of -stems is to be presented back for query expansion, in place of -a stem, s, the user should be shown a single representative from the set -words(s), the one of highest frequency perhaps. The user should also -be able to choose for the whole query, or at a lower level for each word -in a query, whether or not it should be stemmed. In the absence of such -choices, the system can make its own -decisions. -Perhaps single word queries would not undergo -stemming; long queries would; stopwords would be removed -except in phrases. In query expansion, the system would work with stemmed -forms, ignoring stopwords. -

- -

-Query expansion with stemming results in a much cleaner vocabulary list -than without, and this is a main strength of using a stemming process. -

- -

-A question arises: if the user never sees the stemmed form, does its -appearance matter? The answer must be no, although -the Porter stemmer tries to make the unstemmed forms guessable from the stemmed -forms. For example, from appropri you can guess appropriate. At least, -trying to achieve this effect acts as a useful control. Similarly with the -other stemmers presented here, an attempt has been made to keep the -appearance of the stemmed forms as familiar as possible. -

- -

6 Irregular grammatical forms

- -

-All languages contain irregularities, but to what extent should they be -accommodated in a stemming algorithm? An English stemmer, for example, can -convert regular plurals to singular form without difficulty (boys, girls, -hands ...). Should it do the same with irregular plurals (men, children, -feet, ...)? Here we have irregular cases with i-suffixes, but there are -irregularities with d-suffixes, which Lovins calls ‘spelling exceptions’. -absorb/absorption and conceive/conception are examples of this. -Etymologically, the explanation of the first is that the Latin root, -sorbere, is an irregular verb, and of the second that the word -conceive comes to us from the French rather than straight from the Latin. -It is interesting that, even with no knowledge of the etymology, we do -recognise the connection between the words. -

- -

-Lovins tries to solve spelling exceptions by formulating general respelling -rules (turn rpt into rb for example), but it might be easier to have -simply a list of exceptional stems. -

- -

-The Porter stemmer does not handle irregularities at all, but from the -author’s own experience, this has never been an area of complaint. -Complaints in fact are always about false conflations, for example new -and news. -

- -

-Possibly Lovins was right in wanting to resolve d-suffix irregularities, -and not being concerned about i-suffix irregularities. i-suffix -irregularities in English go with short, old words, that are either in very -common use (man/men, woman/women, see/saw ...) or are used only rarely -(ox/oxen, louse/lice, forsake/forsook ...). The latter class can be -ignored, and the former has its own problems which are not always solved -by stemming. For example man is a verb, and saw can mean a cutting -instrument, or, as a verb, can mean to use such an instrument. Conflation -of these forms frequently leads to an error like mis-stemming therefore. -

- -

-An algorithmic stemmer really needs holes where the irregular forms can be -plugged in as necessary. This is more serviceable than attempting to -embed special lists of these irregular forms into software. -

- -

7 Stopwords

- -

-We have suggested that stemming stopwords is not useful. There is a -grammatical connection between being and be, but conflation of the two -forms has little use in IR because they have no shared meaning that would -entitle us to think of them as synonyms. being and be have a -morphological connection as well, but that is not true of am and was, -although they have a grammatical connection. Generally speaking, -inflectional stopwords exhibit many irregularities, which means that -stemming is not only not useful, but not possible, unless one builds into -the stemmer tables of exceptions. -

- -

-Switching from English to French, consider être, the equivalent form -of be. It has about 40 different forms, including, -

- -
- suis   es   sommes   serez   étaient   fus   furent   sois   été -
- -

-(and suis incidentally is a homonym, as part of the verb suivre.) -Passing all forms through a rule-based stemmer creates something of a -mess. An alternative approach is to recognise this group of words, and -other groups, and take special action. The recognition could take place -inside the stemmer, or be done before the stemmer is called. One special -action would be to stem (perhaps one should say ‘map’) all the forms to a -standard form, ETRE, to indicate that they are parts of the verb être. -Deciding what to do with the term ETRE, and it would probably be to -discard it, would be done outside the stemming process. Another special -action would be to recognize a whole class of stopwords and simply discard -them. -

- -

-The strategy adopted will depend upon the underlying IR model, so what one -needs is the flexibility to create modified forms of a standard stemmer. -Usually we present Snowball stemmers in their unadorned form. Thereafter, -the addition of stopword tables is quite easy. -

- -

8 Rare forms

- -

-Stemmers do not need to handle linguistic forms that turn up only very -rarely, but in practice it is hard to design a stemmer with all rare forms -eliminated without there appearing to be some gaps in the thinking. For -this reason one should not worry too much about their occasional presence. -For example, in contemporary Portuguese, use of the second person plural -form of verbs has almost completely disappeared. Even so, endings for -those forms are included in the Portuguese stemmer. They appear in all the -grammar books, and will in any case be found in older texts. The habit of -putting in rare forms to ‘complete the picture’ is well established, and -usually passes unnoticed. An example is the list of English stopwords in -van Rijsbergen (1979). This includes yourselves, by analogy with -himself, herself etc., although yourselves is actually quite a rare -word in English. -

- -

References

- -

-Farber DJ, Griswold RE and Polonsky IP (1964) SNOBOL, a string manipulation -language. Journal of the Association for Computing Machinery, 11: 21-30. -

- -

-Griswold RE, Poage JF and Polonsky IP (1968) The SNOBOL4 programming -language. Prentice-Hall, New Jersey. -

- -

-Harman D (1991) How effective is suffixing? Journal of the American -Society for Information Science, 42: 7-15. -

- -

-Jesperson O (1921) Language, its nature, origin and development. George -Allen & Unwin, London. -

- -

-Kraaij W and Pohlmann R. (1994) Porter’s stemming algorithm for Dutch. In -Noordman LGM and de Vroomen WAM, eds. Informatiewetenschap 1994: -Wetenschappelijke bijdragen aan de derde STINFON Conferentie, Tilburg, -1994. pp. 167-180. -

- -

-Kraaij W and Pohlmann R (1995) Evaluation of a Dutch stemming algorithm. -Rowley J, ed. The New Review of Document and Text Management, volume 1, -Taylor Graham, London, 1995. pp. 25-43, -

- -

-Krovetz B (1995) Word sense disambiguation for large text databases. PhD -Thesis. Department of Computer Science, University of Massachusetts -Amherst. -

- -

-Lennon M, Pierce DS, Tarry BD and Willett P (1981) An evaluation of some -conflation algorithms for information retrieval. Journal of Information -Science, 3: 177-183. -

- -

-Lovins JB (1968) Development of a stemming algorithm. Mechanical -Translation and Computational Linguistics, 11: 22-31. -

- -

-Palmer FR (1965) A linguistic study of the English verb. Longmans, London. -

- -

-Popovic M and Willett P (1990) Processing of documents and queries in a -Slovene language free text retrieval system. Literary and Linguistic -Computing, 5: 182-190. -

- -

-Porter MF (1980) An algorithm for suffix stripping. Program, 14: 130-137. -

- -

-Rijsbergen CJ (1979) Information retrieval. Second edition. Butterworths, -London. -

- -

-Savoy J (1993) Stemming of French words based on grammatical categories. -Journal of the American Society for Information Science, 44: 1-9. -

- -

-Schinke R, Greengrass M, Robertson AM and Willett P (1996) A stemming -algorithm for Latin text databases. Journal of Documentation, 52: -172-187. -

- -[% footer %] diff --git a/texts/r1r2.tt b/texts/r1r2.tt deleted file mode 100644 index 6b2df04..0000000 --- a/texts/r1r2.tt +++ /dev/null @@ -1,78 +0,0 @@ -[% header('Defining R1 and R2') %] - -

-Most of the stemmers make use of at least one of the region definitions R1 and -R2. They are defined as follows: -

- -

-R1 is the region after the first non-vowel following a vowel, or is the null -region at the end of the word if there is no such non-vowel. -

- -

-R2 is the region after the first non-vowel following a vowel in R1, or is -the null region at the end of the word if there is no such non-vowel. -

- -

-The definition of vowel varies from language to language. In French, for -example, é is a vowel, and in Italian i between two other vowels is not a -vowel. The class of letters that constitute vowels is made clear in each stemmer. -

- -

-Below, R1 and R2 are shown for a number of English words, -

- -
-    b   e   a   u   t   i   f   u   l
-                      |<------------->|    R1
-                              |<----->|    R2
-
- -

-Letter t is the first non-vowel following a vowel in beautiful, so R1 -is iful. In iful, the letter f is the first non-vowel following a -vowel, so R2 is ul. -

- -
-    b   e   a   u   t   y
-                      |<->|    R1
-                        ->|<-  R2
-
- -

-In beauty, the last letter y is classed as a vowel. Again, letter t is -the first non-vowel following a vowel, so R1 is just the last letter, y. -R1 contains no non-vowel, so R2 is the null region at the end of the word. -

- -
-    b   e   a   u
-                ->|<-  R1
-                ->|<-  R2
-
-In beau, R1 and R2 are both null. -

- -

-Other examples: -

- -
-    a   n   i   m   a   d   v   e   r   s   i   o   n
-          |<----------------------------------------->|    R1
-                  |<--------------------------------->|    R2
-
-    s   p   r   i   n   k   l   e   d
-                      |<------------->|    R1
-                                    ->|<-  R2
-
-    e   u   c   h   a   r   i   s   t
-              |<--------------------->|    R1
-                          |<--------->|    R2
-
- -[% footer %] diff --git a/texts/vowelmarking.tt b/texts/vowelmarking.tt deleted file mode 100644 index 13a24d2..0000000 --- a/texts/vowelmarking.tt +++ /dev/null @@ -1,74 +0,0 @@ -[% header('Marking vowels as consonants') %] - -

-Some of the algorithms begin with a step which puts letters which are -normally classed as vowels into upper case to indicate that they are are to be -treated as consonants (the assumption being that the words are presented to -the stemmers in lower case). Upper case therefore acts as a flag indicating a -consonant. -

- -

-For example, the English stemmer begins with the step -

- Set initial y, or y after a vowel, to Y, -
-giving rise to the following changes, -

- -
-
youth   →   Youth -
boy   →   boY -
boyish   →   boYish -
fly   →   fly -
flying   →   flying -
syzygy   →   syzygy -
- -

-This process works from left to right, and -if a word contains Vyy, where V is a vowel, the first y is put -into upper case, but the second y is left alone, since it is preceded by -upper case Y which is a consonant. A sequence Vyyyyy... would be -changed to VYyYyY.... -

- -

-The combination yy never occurs in English, although it might appear in -foreign words: -

- -
-
sayyid   →   saYyid -
- -

-(A sayyid, my dictionary tells me, is a descendant of Mohammed's daughter -Fatima.) But the left-to-right process is significant in other languages, for -example French. In French the rule for marking vowels as consonants is, -

- -
- Put into upper case u or i preceded and followed by a vowel, and - y preceded or followed by a vowel. Put u after q into upper - case. -
- -

-which gives rise to, -

- -
-
ennuie   →   ennuIe -
inquiétude   →   inqUiétude -
- -

-In the first word, i is put into upper case since it has a vowel on both -sides of it. -In the second word, u after q is put into upper case, and again the -following i is left alone, since it is preceded by upper case U which -is a consonant. -

- -[% footer %]