[en] improve rules

languagetool-org · May 2, 2024 · f5f3fbe · f5f3fbe
1 parent 0446d1b
commit f5f3fbe
Show file tree

Hide file tree

Showing 6 changed files with 59 additions and 3 deletions.
diff --git a/...agetool-language-modules/en/src/main/resources/org/languagetool/resource/en/compounds.txt b/...agetool-language-modules/en/src/main/resources/org/languagetool/resource/en/compounds.txt
@@ -9047,4 +9047,5 @@ gang-banger?
 gang-bangers?
 trench-coat?
 trench-coats?
+sub-par*
 star-spangled*
diff --git a/...language-modules/en/src/main/resources/org/languagetool/resource/en/hunspell/spelling.txt b/...language-modules/en/src/main/resources/org/languagetool/resource/en/hunspell/spelling.txt
@@ -269,6 +269,10 @@ seismicity
 nanocatalyst/S
 metalorganic
 opto-electronic
+backport
+backports
+backported
+backporting
 popup
 popups
 share-out
@@ -281,4 +285,4 @@ trackability
 heterorganic
 optoelectronic
 optoelectronics
-derogative
+derogative
diff --git a/...getool-language-modules/en/src/main/resources/org/languagetool/resource/en/multiwords.txt b/...getool-language-modules/en/src/main/resources/org/languagetool/resource/en/multiwords.txt
@@ -7952,4 +7952,5 @@ Mount Erebus	NNP
 GE Appliances	NNP
 Neuer Markt	NNP
 Belle Isle	NNP
-cyt c	NN:U
+cyt c	NN:U
+caffe latte	NN:UN
diff --git a/languagetool-language-modules/en/src/main/resources/org/languagetool/rules/en/diacritics.txt b/languagetool-language-modules/en/src/main/resources/org/languagetool/rules/en/diacritics.txt
@@ -1377,4 +1377,5 @@ Adam Hlozek=Adam Hložek
 Peter Magyar=Péter Magyar
 Ekrem Imamoglu=Ekrem İmamoğlu
 Ryoyu Kobayashi=Ryōyū Kobayashi
+Planeta Corporacion=Planeta Corporación
 Tadej Pogacar=Tadej Pogačar
diff --git a/languagetool-language-modules/en/src/main/resources/org/languagetool/rules/en/grammar.xml b/languagetool-language-modules/en/src/main/resources/org/languagetool/rules/en/grammar.xml
@@ -68079,6 +68079,30 @@ USA
                     <token>less</token>
                     <token postag="NN.*" postag_regexp="yes" />
                 </antipattern>
+                <antipattern>
+                    <token>the</token>
+                    <token skip="-1">less</token>
+                    <token>the</token>
+                    <token>more</token>
+                </antipattern>
+                <antipattern>
+                    <token>the</token>
+                    <token skip="-1">less</token>
+                    <token>the</token>
+                    <token postag="JJR" />
+                </antipattern>
+                <antipattern>
+                    <token>the</token>
+                    <token skip="-1">more</token>
+                    <token>the</token>
+                    <token>less</token>
+                </antipattern>
+                <antipattern>
+                    <token>the</token>
+                    <token skip="-1" postag="JJR" />
+                    <token>the</token>
+                    <token>less</token>
+                </antipattern>
                 <pattern>
                     <marker>
                         <token postag="JJR|RBR" postag_regexp="yes">less<exception scope="previous" regexp="yes">\d+%</exception></token>
@@ -68087,7 +68111,7 @@ USA
                     Causes false alarms like: "Less dramatic improvements are possible"
                     <token min="0" postag="JJ"/>
                     -->
-                    <token postag="NNS"><exception postag="JJ"/><exception regexp="yes">brains|taxes|resources</exception></token>
+                    <token postag="NNS"><exception postag="JJ|NN:UN?" postag_regexp="yes"/><exception regexp="yes">data|brains|taxes|fruit|resources</exception></token>
                 </pattern>
                 <message>Did you mean <suggestion>fewer</suggestion>? The noun "\2" is countable.</message>
                 <short>Grammatical error</short>
@@ -94983,6 +95007,28 @@ USA
                 <token postag="DT|CD" postag_regexp="yes" skip="1" />
                 <token regexp="yes">dozen|hundred|thousand|[bm]illion</token>
             </antipattern>
+            <antipattern>
+                <token regexp="yes">dozen|hundred|thousand|[bm]illion</token>
+                <token>of</token>
+                <token chunk_re=".-NP-plural" />
+            </antipattern>
+            <antipattern>
+                <token regexp="yes">mrs?|miss|dr|professor|doctor|[$€£¥฿₹₿]?\d+</token>
+                <token min="0">.</token>
+                <token regexp="yes">dozen|hundred|thousand|[bm]illion</token>
+            </antipattern>
+            <antipattern>
+                <token regexp="yes">dozen|hundred|thousand|[bm]illion</token>
+                <token>'s</token>
+            </antipattern>
+            <antipattern>
+                <token>Coleridge</token>
+                <token>Hundred</token>
+            </antipattern>
+            <antipattern>
+                <token>Thousand</token>
+                <token>Island</token>
+            </antipattern>
             <pattern>
                 <token regexp="yes">dozen|hundred|thousand|[bm]illion
                     <exception scope="previous" postag_regexp="yes" postag="UNKNOWN|CD|W?DT|PRP\$|JJ"/>

diff --git a/languagetool-language-modules/en/src/main/resources/org/languagetool/rules/en/replace.txt b/languagetool-language-modules/en/src/main/resources/org/languagetool/rules/en/replace.txt
@@ -157,5 +157,8 @@ Phillip Morris=Philip Morris
 untied Ireland=united Ireland
 Downtown Abbey=Downton Abbey
 Sascha Baron Cohen=Sacha Baron Cohen
+cafe latte=caffe latte  Did you mean the espresso mixed with milk?
+café latte=caffe latte  Did you mean the espresso mixed with milk?
+cafè latte=caffe latte  Did you mean the espresso mixed with milk?
 derogative=derogatory	'Derogative' is less common than 'derogatory', and replacing it could make your writing clearer.
 running nose=runny nose