Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[pt] Dictionary update to v1.0.1 #10559

Merged
merged 12 commits into from
May 6, 2024
Merged

[pt] Dictionary update to v1.0.1 #10559

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
2d65ff5
[pt] Add Γ©ons/Γ©ones dialect alternation
p-goulart Apr 24, 2024
d968e2a
[pt] Check English words in speller
p-goulart Apr 23, 2024
edce1a6
[pt] Add English tests to JLTool tests
p-goulart Apr 24, 2024
3c51c4d
[pt] Move EMAIL_SEM_HIFEN to style
p-goulart Apr 24, 2024
ecf9454
[pt] Fix typo πŸ₯΄
p-goulart Apr 24, 2024
ce0d127
[pt] Move EMAIL_SEM_HIFEN back to grammar
p-goulart Apr 24, 2024
a3d0d7c
[pt] Add new word tests for dict v1.0.0
p-goulart May 2, 2024
7202d3b
[pt] Bump dict to v1.0.0
p-goulart May 2, 2024
4835934
[pt] Add test for 'mesmo' and 'mesmΓ­ssimo' tagging
p-goulart May 2, 2024
be3d768
[pt] Bump dict to v1.0.1
p-goulart May 2, 2024
41070c9
[pt] Fix disambiguation of 'a'
p-goulart May 2, 2024
43ece3d
[pt] Test GENERAL_GENDER_AGREEMENT_ERRORS for mesmo/mesmΓ­ssimo
p-goulart May 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions ...e-modules/pt/src/main/java/org/languagetool/rules/pt/MorfologikPortugueseSpellerRule.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -300,6 +300,9 @@ public List<RuleMatch> getRuleMatches(String word, int startPos, AnalyzedSentenc
List<RuleMatch> ruleMatchesSoFar, int idx,
AnalyzedTokenReadings[] tokens) throws IOException {
List<RuleMatch> ruleMatches = super.getRuleMatches(word, startPos, sentence, ruleMatchesSoFar, idx, tokens);
if (tokens[idx].hasPosTag("_english_ignore_")) {
return Collections.emptyList();
}
if (!ruleMatches.isEmpty()) {
if (isValidCliticVerb(word)) {
ruleMatches = Collections.emptyList();
Expand Down
1 change: 1 addition & 0 deletions ...guage-modules/pt/src/main/resources/org/languagetool/resource/pt/dialect_alternations.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7559,3 +7559,4 @@ fato=facto
fatos=factos
pΓ­tons=pΓ­tones
pΓ­tons-da-birmΓ’nia=pΓ­tones-da-birmΓ’nia
Γ©ons=Γ©ones
309 changes: 298 additions & 11 deletions ...ol-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@
<!ENTITY % languages SYSTEM "../../resource/pt/entities/languages.ent">
<!ENTITY % postal SYSTEM "../../resource/pt/entities/postal.ent" >
<!ENTITY % chars SYSTEM "../../resource/pt/entities/chars.ent" >
<!ENTITY % english SYSTEM "../../resource/pt/entities/english.ent" >
%datetime;
%misc;
%abbrev;
Expand All @@ -41,6 +42,7 @@
%languages;
%postal;
%chars;
%english;
]>

<rules lang="pt" xsi:noNamespaceSchemaLocation="../../../../../../../../../languagetool-core/src/main/resources/org/languagetool/resource/disambiguation.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xs="http://www.w3.org/2001/XMLSchema">
Expand Down Expand Up @@ -1745,7 +1747,10 @@
<token inflected='yes' regexp='yes'>caminhar|correr|explicar|inaugurar|ver|comprar</token>
<token min='0' postag='R.' postag_regexp='yes'/>
<marker>
<token>a</token>
<and> <!-- only when the determiner reading has not already been dismissed -->
<token postag_regexp="yes" postag="S.+">a</token>
<token postag_regexp="yes" postag="[^S].+">a</token>
</and>
</marker>
</pattern>
<disambig action="remove" postag="S.+"/>
Expand Down Expand Up @@ -3729,14 +3734,296 @@
</rule>
</rulegroup>

<!-- p-goulart@2024-03-07 - DESC: all tags that contain verbs *and* pronouns come from our tagger and need to be accepted...
the only exception being -Γ‘mos verbs in pt-BR, but I feel like this is a super edge case...-->
<!-- <rulegroup id="VERBS_WITH_CLITICS" name="Ignore spelling issues in verbs tagged with clitics"> -->
<!-- <rule> -->
<!-- <pattern> -->
<!-- <token postag_regexp="yes" postag="V.+:P.+"/> -->
<!-- </pattern> -->
<!-- <disambig action="ignore_spelling"/> -->
<!-- </rule> -->
<!-- </rulegroup> -->
<rulegroup id="IGNORE_ENGLISH_WORDS" name="Label English words">
<rule> <!-- #1 -->
<pattern>
<token regexp="yes">&english_common;</token>
<token regexp="yes">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
</token>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1,2"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #2 -->
<pattern>
<token postag="_english_ignore_"/>
<marker>
<token regexp="yes">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
<exception postag="_english_ignore_"/>
</token>
</marker>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:2"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #3 -->
<pattern>
<token regexp="yes">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
</token>
<token regexp="yes">&english_common;</token>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1,2"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #4 -->
<pattern>
<marker>
<token regexp="yes">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
<exception postag="_english_ignore_"/>
</token>
</marker>
<token postag="_english_ignore_|allow_saxon_genitive" postag_regexp="yes"/>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #5 -->
<pattern>
<token>to</token>
<token regexp="yes" postag="UNKNOWN">\p{L}+</token>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:2 postags:VB"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #6 -->
<pattern>
<token case_sensitive="yes">I</token>
<token regexp="yes" postag="UNKNOWN">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
</token>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:2 postags:VB[PD]"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<!--<rule>
<pattern>
<token postag="_english_ignore_|UNKNOWN" postag_regexp="yes" regexp="yes">[a-z]+<exception regexp="yes">saint|anti|&english_no;</exception></token>
<token spacebefore="no">-</token>
<token spacebefore="no" regexp="yes">[a-z]+<exception regexp="yes">&english_no;|&english_forward;</exception></token>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1,3"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule>
<pattern>
<token regexp="yes">[a-z]+<exception regexp="yes">saint|anti|&english_no;</exception></token>
<token spacebefore="no">-</token>
<token postag="_english_ignore_|UNKNOWN" postag_regexp="yes" spacebefore="no" regexp="yes">[a-z]+<exception regexp="yes">&english_no;|&english_forward;</exception></token>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1,3"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>-->
<rule> <!-- #7 -->
<pattern>
<token postag="_english_ignore_"/>
<marker>
<token regexp="yes">to</token>
<token regexp="yes" postag="UNKNOWN">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
<exception postag="_english_ignore_"/>
</token>
</marker>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:3"/>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #8 -->
<pattern>
<token postag="_english_ignore_"/>
<marker>
<token regexp="yes">to</token>
</marker>
<token postag="_english_ignore_"/>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #9 -->
<pattern>
<token>from</token>
<token/>
<marker>
<token>to</token>
</marker>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #10, contractions -->
<pattern>
<token regexp="yes">&english_contracted_not;</token>
<token regexp="yes">&apostrophes;</token>
<token>t</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #11, contractions -->
<pattern>
<token regexp="yes">&english_contracted_is;</token>
<token regexp="yes">&apostrophes;</token>
<token>s</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #12, contractions -->
<pattern>
<token regexp="yes">&english_contracted_are;</token>
<token regexp="yes">&apostrophes;</token>
<token>re</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #13, contractions -->
<pattern>
<token regexp="yes">&english_contracted_have;</token>
<token regexp="yes">&apostrophes;</token>
<token>ve</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #14, contractions -->
<pattern>
<token regexp="yes">&english_contracted_will;</token>
<token regexp="yes">&apostrophes;</token>
<token>ll</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #15, contractions -->
<pattern>
<token regexp="yes">&english_contracted_would;</token>
<token regexp="yes">&apostrophes;</token>
<token>d</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>

<rule> <!-- #16, risky -->
<pattern>
<token regexp="yes">&english_forward;
<exception postag="_english_ignore_"/>
</token>
<token regexp="yes" negate_pos="yes" postag="_english_ignore_">&english_common;</token>
</pattern>
<disambig action="add">
<wd pos="_english_ignore_"/>
<wd pos="_english_ignore_"/>
</disambig>
</rule>
<rule> <!-- #17, risky -->
<pattern>
<marker>
<token regexp="yes">&english_forward;
<exception postag="_english_ignore_"/>
</token>
</marker>
<token postag="_english_ignore_"/>
</pattern>
<disambig action="add"><wd pos="_english_ignore_"/></disambig>
</rule>
</rulegroup>

<rulegroup id="IGNORE_WORDS_AROUND_ENGLISH_WORDS" name="Label unknown words as English when adjacent to English-labelled words">
<rule> <!-- #1 -->
<pattern>
<token postag="_english_ignore_"/>
<marker>
<token regexp="yes" postag="UNKNOWN">\p{L}+|'s
<exception regexp="yes">&english_no;|&english_forward;</exception>
<exception postag="_english_ignore_"/>
</token>
</marker>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:2"/>
<disambig action="add"><wd pos="_english_ignore_"/></disambig>
</rule>
<rule> <!-- #2 -->
<pattern>
<marker>
<token regexp="yes" postag="UNKNOWN">\p{L}+
<exception regexp="yes">&english_no;|&english_forward;</exception>
<exception postag="_english_ignore_"/>
</token>
</marker>
<token postag="_english_ignore_"/>
</pattern>
<filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1"/>
<disambig action="add"><wd pos="_english_ignore_"/></disambig>
</rule>
<rule> <!-- #3, unknown single-word parenthetical -->
<!-- This is for when we have a bunch of English words and then a single word in parenthesis,
99% of the time it's also English or it's some kind of English acronym. -->
<pattern>
<token postag="_english_ignore_"/> <!-- refused to work with min="3", idk why -->
<token postag="_english_ignore_"/>
<token postag="_english_ignore_"/>
<token>(</token>
<marker>
<token spacebefore="no" postag="UNKNOWN">
<exception postag="_english_ignore_"/>
</token>
</marker>
<token spacebefore="no">)</token>
</pattern>
<disambig action="add"><wd pos="_english_ignore_"/></disambig>
</rule>
</rulegroup>

</rules>
1 change: 1 addition & 0 deletions ...ol-language-modules/pt/src/main/resources/org/languagetool/resource/pt/entities/chars.ent
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
<!ENTITY separadores_de_oracoes "(?:[,;:…–—\(\)Β«β€œ]|\-|\[\]\{\})">
<!ENTITY tracos_de_separacao "(?:[-‑]|–|β€”|γ…‘)">
<!ENTITY minus_sign "βˆ’">
<!ENTITY apostrophes "['’]">

<!-- ORDINALS, SUPERSCRIPTS, DEGREE SIGNS, AND OTHER NONSENSE 😩 -->
<!-- For some reason, entities with special characters do NOT work in the disambiguation.xml file
Expand Down
Loading
Loading