@Test public void testRule() throws IOException { DoublePunctuationRule rule = new DoublePunctuationRule(TestTools.getEnglishMessages()); RuleMatch[] matches; JLanguageTool langTool = new JLanguageTool(TestTools.getDemoLanguage()); // correct sentences: matches = rule.match(langTool.getAnalyzedSentence("This is a test sentence...")); assertEquals(0, matches.length); matches = rule.match(langTool.getAnalyzedSentence("Это тестовое предложение?..")); assertEquals(0, matches.length); matches = rule.match(langTool.getAnalyzedSentence("Это тестовое предложение!.. ")); assertEquals(0, matches.length); matches = rule.match(langTool.getAnalyzedSentence("This is a test sentence... More stuff....")); assertEquals(0, matches.length); matches = rule.match(langTool.getAnalyzedSentence("This is a test sentence..... More stuff....")); assertEquals(0, matches.length); matches = rule.match(langTool.getAnalyzedSentence("This, is, a test sentence.")); assertEquals(0, matches.length); // errors: matches = rule.match(langTool.getAnalyzedSentence("This,, is a test sentence.")); assertEquals(1, matches.length); assertEquals(4, matches[0].getFromPos()); assertEquals(6, matches[0].getToPos()); matches = rule.match(langTool.getAnalyzedSentence("This is a test sentence.. Another sentence")); assertEquals(1, matches.length); assertEquals(23, matches[0].getFromPos()); assertEquals(25, matches[0].getToPos()); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) { return Arrays.asList( new DoublePunctuationRule(messages), new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) { return Arrays.asList( new DoublePunctuationRule(messages), new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "\"", "”"), Arrays.asList("]", ")", "}", "\"", "”")), new HunspellNoSuggestionRule(messages, this, userConfig, altLanguages), new UppercaseSentenceStartRule(messages, this), // abbreviation exceptions, done in DanishSentenceTokenizer // "WORD_REPEAT_RULE" implemented in grammar.xml new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new MultipleWhitespaceRule(messages, this), new LongSentenceRule(messages, userConfig), new SentenceWhitespaceRule(messages) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages), new MorfologikAsturianSpellerRule(messages, this, userConfig, altLanguages), new UppercaseSentenceStartRule(messages, this), new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages), new UppercaseSentenceStartRule(messages, this), new MultipleWhitespaceRule(messages, this), // specific to Tagalog: new MorfologikTagalogSpellerRule(messages, this, userConfig, altLanguages) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages), new MorfologikLithuanianSpellerRule(messages, this), new UppercaseSentenceStartRule(messages, this), new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "“", "«", "»", "¿", "¡"), Arrays.asList("]", ")", "}", "”", "»", "«", "?", "!")), new MorfologikSpanishSpellerRule(messages, this, userConfig, altLanguages), new UppercaseSentenceStartRule(messages, this), new WordRepeatRule(messages, this), new MultipleWhitespaceRule(messages, this), new SpanishWikipediaRule(messages) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{" /*"«", "‘"*/), Arrays.asList("]", ")", "}" /*"»", French dialog can contain multiple sentences. */ /*"’" used in "d’arm" and many other words */)), new MorfologikYourLanguageSpellerRule(messages, this), new UppercaseSentenceStartRule(messages, this), new MultipleWhitespaceRule(messages, this), new SentenceWhitespaceRule(messages), // specific to French: new CompoundRule(messages), new QuestionWhitespaceRule(messages) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new WhitespaceBeforePunctuationRule(messages), new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "»", "«" /*"‘"*/), Arrays.asList("]", ")", "}", "«", "»" /*"’"*/)), new MorfologikItalianSpellerRule(messages, this, userConfig, altLanguages), new UppercaseSentenceStartRule(messages, this), new ItalianWordRepeatRule(messages, this), new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages), new MorfologikMalayalamSpellerRule(messages, this), new UppercaseSentenceStartRule(messages, this), new WordRepeatRule(messages, this), new MultipleWhitespaceRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "„", "»", "«", "\""), Arrays.asList("]", ")", "}", "“", "«", "»", "\"")), new UppercaseSentenceStartRule(messages, this), new WordRepeatRule(messages, this), new MultipleWhitespaceRule(messages, this), // specific to Slovak: new CompoundRule(messages), new MorfologikSlovakSpellerRule(messages, this, userConfig, altLanguages) //new SlovakVesRule(messages) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages), new HunspellNoSuggestionRule(messages, this, userConfig, altLanguages), new UppercaseSentenceStartRule(messages, this), new WordRepeatRule(messages, this), new MultipleWhitespaceRule(messages, this), new SentenceWhitespaceRule(messages) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages), new HunspellRule(messages, this, userConfig, altLanguages), new UppercaseSentenceStartRule(messages, this), new WordRepeatRule(messages, this), new MultipleWhitespaceRule(messages, this), new CompoundRule(messages) ); }
protected List<Rule> getBasicRules(ResourceBundle messages) { return Arrays.asList( new CommaWhitespaceRule(messages, Example.wrong("Није шија<marker> ,</marker> него врат."), Example.fixed("Није шија<marker>,</marker> него врат.")), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "„", "„", "\""), Arrays.asList("]", ")", "}", "”", "“", "\"")), new UppercaseSentenceStartRule(messages, this, Example.wrong("Почела је школа. <marker>ђаци</marker> су поново сели у клупе."), Example.fixed("Почела је школа. <marker>Ђаци</marker> су поново сели у клупе.")), new MultipleWhitespaceRule(messages, this), new SentenceWhitespaceRule(messages), new WordRepeatRule(messages, this) ); }
@Override public List<Rule> getRelevantRules(ResourceBundle messages, UserConfig userConfig, List<Language> altLanguages) throws IOException { return Arrays.asList( new CommaWhitespaceRule(messages), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "“", "‹", "“", "„", "\""), Arrays.asList("]", ")", "}", "”", "›", "”", "”", "\"")), new UppercaseSentenceStartRule(messages, this), new MorfologikDutchSpellerRule(messages, this, userConfig, altLanguages), new MultipleWhitespaceRule(messages, this), new CompoundRule(messages), new DutchWrongWordInContextRule(messages), new WordCoherencyRule(messages), new SimpleReplaceRule(messages), new LongSentenceRule(messages, userConfig, -1, true), new PreferredWordRule(messages) ); }
Example.wrong("Tomamos café<marker> ,</marker> queixo, bolachas e uvas."), Example.fixed("Tomamos café<marker>,</marker> queixo, bolachas e uvas.")), new DoublePunctuationRule(messages), new GenericUnpairedBracketsRule(messages, Arrays.asList("[", "(", "{", "“", "«", "»", "‘", "\"", "'"),