Revert "[pt] Update dictionary to v1.1.0 (#10609)"

This reverts commit e466962.
languagetool-org · Jun 13, 2024 · 4f288eb · 4f288eb
1 parent be211b8
commit 4f288eb
Show file tree

Hide file tree

Showing 12 changed files with 59 additions and 366 deletions.
diff --git a/languagetool-language-modules/pt/src/main/java/org/languagetool/language/Portuguese.java b/languagetool-language-modules/pt/src/main/java/org/languagetool/language/Portuguese.java
@@ -134,7 +134,6 @@ public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfi
             //Specific to Portuguese:
             new PostReformPortugueseCompoundRule(messages, this, userConfig),
             new PortugueseColourHyphenationRule(messages, this, userConfig),
-            new PortugueseOrthographyReplaceRule(messages, this),
             new PortugueseReplaceRule(messages, this),
             new PortugueseBarbarismsRule(messages, "/pt/barbarisms.txt", this),
             //new PortugueseArchaismsRule(messages, "/pt/archaisms-pt.txt"),   // see https://github.com/languagetool-org/languagetool/issues/3095
@@ -289,24 +288,18 @@ public Map<String, Integer> getPriorityMap() {
 
   @Override
   protected int getPriorityForId(String id) {
-    // generic spelling rule
     if (id.startsWith("MORFOLOGIK_RULE")) {
       return -50;
     }
-    // simple replace spelling rule
-    if (id.startsWith("PT_SIMPLE_REPLACE_ORTHOGRAPHY")) {
-      return -49;
-    }
-    // AI spelling rule
     if (id.startsWith("AI_PT_GGEC_REPLACEMENT_ORTHOGRAPHY_SPELL")) {
-      return -48;
-    }
-    if (id.startsWith("PT_MULTITOKEN_SPELLING")) {
-      return -48;
+      return -49;
     }
     if (id.startsWith("AI_PT_GGEC_REPLACEMENT_OTHER")) {
       return -4;
     }
+    if (id.startsWith("PT_MULTITOKEN_SPELLING")) {
+      return -49;
+    }
     // enclitic diacritics always take precedence over pronoun placement
     if (id.startsWith("ACENTUAÇÃO_VOGAL_ÊNCLISE")) {
       return -51;

diff --git a/...e-modules/pt/src/main/java/org/languagetool/rules/pt/MorfologikPortugueseSpellerRule.java b/...e-modules/pt/src/main/java/org/languagetool/rules/pt/MorfologikPortugueseSpellerRule.java
@@ -18,7 +18,6 @@
  */
 package org.languagetool.rules.pt;
 
-import com.google.errorprone.annotations.concurrent.LazyInit;
 import org.languagetool.*;
 import org.languagetool.rules.RuleMatch;
 import org.languagetool.rules.SuggestedReplacement;
@@ -39,8 +38,6 @@
 public class MorfologikPortugueseSpellerRule extends MorfologikSpellerRule {
 
   private final Language spellerLanguage;
-  // Used for suggestions to words tagged as _english_ignore_. This should be lazy-initialised or memoised somehow.
-  private static final MorfologikSpellerRule englishSpeller = loadEnglishSpeller();
   private final String dictFilepath;
   // Path, in pt/resources, where the list of words to be removed from the suggestion list is to be found.
   private static final String doNotSuggestWordsFilepath = "/pt/do_not_suggest.txt";
@@ -237,17 +234,6 @@ public MorfologikPortugueseSpellerRule(ResourceBundle messages, Language languag
     dialectAlternationMapping = getDialectAlternationMapping();
   }
 
-  @Nullable
-  private static MorfologikSpellerRule loadEnglishSpeller() {
-    try {
-      Language english = Languages.getLanguageForShortCode("en");
-      return (MorfologikSpellerRule) english.getDefaultSpellingRule();
-    } catch (IllegalArgumentException e) {
-      System.err.println("English is not available, so we can't use it for suggestions in the Portuguese speller.");
-      return null;
-    }
-  }
-
   @Override
   protected List<SuggestedReplacement> filterNoSuggestWords(List<SuggestedReplacement> suggestedReplacements) {
     return suggestedReplacements.stream().filter(
@@ -314,15 +300,7 @@ 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 (englishSpeller != null && tokens[idx].hasPosTag("_english_ignore_")) {
-      if (englishSpeller.isMisspelled(word)) {
-        List<String> englishSuggestions = englishSpeller.getSpellingSuggestions(word);
-        String msg = "Este parece ser um termo em inglês. Se for o caso, há um erro de ortografia.";
-        RuleMatch match = ruleMatches.get(0);
-        match.setSuggestedReplacements(englishSuggestions);
-        match.setMessage(msg);
-        return Collections.singletonList(match);
-      }
+    if (tokens[idx].hasPosTag("_english_ignore_")) {
       return Collections.emptyList();
     }
     if (!ruleMatches.isEmpty()) {

diff --git a/...-modules/pt/src/main/java/org/languagetool/rules/pt/PortugueseOrthographyReplaceRule.java b/...-modules/pt/src/main/java/org/languagetool/rules/pt/PortugueseOrthographyReplaceRule.java
diff --git a/...ol-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml b/...ol-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml
@@ -3530,13 +3530,6 @@
           </pattern>
           <disambig action="ignore_spelling"/>
       </rule>
-
-      <rule id="IGNORE_SPELLING_RS_LAUGHTER">
-          <pattern>
-              <token regexp="yes">(rs){2,15}</token>
-          </pattern>
-          <disambig action="ignore_spelling"/>
-      </rule>
   </rulegroup>
 
   <rulegroup name="Add interjection tag to common laughter onomatopoeia" id="INTERJ_LAUGHTER">
@@ -4026,55 +4019,23 @@
                   </token>
               </marker>
           </pattern>
-          <!-- <filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:2"/> -->
+          <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}+|'s
+                  <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:2"/> -->
+          <filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1"/>
           <disambig action="add"><wd pos="_english_ignore_"/></disambig>
       </rule>
-      <rule> <!-- #3 -->
-          <pattern>
-              <marker>
-                  <token regexp="yes" postag="UNKNOWN">\p{L}+
-                      <exception regexp="yes">&english_no;|&english_forward;</exception>
-                      <exception postag="_english_ignore_"/>
-                  </token>
-                  <token regexp="yes">&english_common;</token>
-              </marker>
-          </pattern>
-          <!-- <filter class="org.languagetool.rules.IsEnglishWordFilter" args="formPositions:1"/> -->
-          <disambig action="add">
-              <wd pos="_english_ignore_"/>
-              <wd pos="_english_ignore_"/>
-          </disambig>
-      </rule>
-      <rule> <!-- #4 -->
-          <pattern>
-              <marker>
-                  <token regexp="yes">&english_common;</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:1"/> -->
-          <disambig action="add">
-              <wd pos="_english_ignore_"/>
-              <wd pos="_english_ignore_"/>
-          </disambig>
-      </rule>
-      <rule> <!-- #5, unknown single-word parenthetical -->
+      <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>

diff --git a/...-language-modules/pt/src/main/resources/org/languagetool/resource/pt/entities/english.ent b/...-language-modules/pt/src/main/resources/org/languagetool/resource/pt/entities/english.ent
@@ -34,7 +34,7 @@
   during|going|such|many|then|year|became|later|well|including|area|both|make|name|
   called|until|while|against|may|number|season|several|team|work|born|
   early|family|now|based|life|released|since|began|century|each|end|
-  following|found|located|town|around|government|named|
+  following|found|located|town|around|day|government|named|
   often|three|too|up|along|built|career|include|left|own|still|
   took|held|last|members|much|than|within|another|company|death|
   down|even|five|however|published|received|served|become|best|died|history|
@@ -56,7 +56,7 @@
   success|successful|track|units|white|added|attack|below|brought|census|changed|
   county|decided|ever|fact|generally|hand|households|instead|introduced|least|
   mid|mother|outside|private|professional|provide|provided|saw|seven|soon|space|
-  study|systems?|teams|thus|women|september|allowed|battle|beginning|
+  study|systems|teams|thus|women|september|allowed|battle|beginning|
   books|director|eight|female|find|ground|higher|industry|interest|
   league|lived|market|night|owned|placed|previous|primary|reached|related|
   reported|runs|strong|winning|august|january|july|march|always|approximately|
@@ -106,7 +106,7 @@
   agreement|allowing|applied|attacks|ball|bank|birth|claim|compared|
   conducted|connected|critical|dead|designated|develop|enemy|
   entitled|estate|estimated|existing|expanded|expected|fellow|fighting|
-  floor|follow|forward|founder|fully?|goes|granted|hands|hour|
+  floor|follow|forward|founder|fully|goes|granted|hands|hour|
   ice|leaves|literature|necessary|newly|occupied|occur|occurred|
   oldest|organizations|organized|owner|paid|parish|powers|promoted|providing|
   read|receive|reduced|refers|refused|respectively|say|settled|settlement|
@@ -175,7 +175,7 @@
   advertising|animated|anyone|appeal|apply|appointment|artillery|
   asks|assault|assembly|attributed|benefits|blocks|buy|championships|
   chapter|circumstances|claiming|closer|colony|colors|continuous|corporate|
-  crowd|crown|customers?|dated|daughters|debuted|defeating|departure|
+  crowd|crown|customers|dated|daughters|debuted|defeating|departure|
   destroy|detailed|drawing|drugs|electrical|eleven|else|encouraged|
   essentially|everyone|evil|expensive|facing|fighter|generated|governments|
   identical|infantry|integrated|journey|junction|latest|lawyer|
@@ -200,13 +200,7 @@
   spending|spoke|stream|studying|submarine|sufficient|suggest|suitable|
   supposed|surgery|survey|swimming|team's|anyway|anyhow|anywhere|
   somewhere|somebody|somehow|whatever|whoever|whosever|whomever|
-  whichever|whenever|wherever|however|art|miss|mister|whats|theyre|
-  weve|theyve|shes|im|Im|youre|whos|wouldve|couldve|whens|wheres|hows|
-  dictionary|cards?|services?|kids?|groups?|skills?|news?|news?|
-  tomorrow|yesterday|(sun|mon|tues|wednes|thurs|fri|satur)?days?|
-  thanks?|welcome|black|yellow|orange|green|purple|gr[ae]y|blue|express|
-  coffee|academy|gold|golden|tech|clean|dirty|users?|sellers?|buyers?|
-  release|headlines?|points?|transfers?|foot|feet
+  whichever|whenever|wherever|however|art|miss|mister
 ">
 
 <!ENTITY english_common "&english_wh_words;|&english_prepositions;|&english_adverbs;|&english_pronouns;|&english_determiners;|&english_common_verbs;|&english_conjunctions;|&english_word_list;|&english_suffixed_word;">
diff --git a/...getool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/multiwords.txt b/...getool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/multiwords.txt
@@ -12044,9 +12044,4 @@ touch screens	NCFP000_
 José Luiz	NPMSS00_
 Sofia Kovalevskaya	NPFSS00_
 Maya Plisetskaia	NPFSS00_
-Campos Elísios	NPMP000
-
-QR code	NCMS000_
-QR codes	NCMP000_
-code review	NCCS000_
-code reviews	NCCP000_
+Campos Elísios	NPMP000