Java Languages类代码示例

import org.languagetool.Languages; //导入依赖的package包/类
@Override
public void startElement(String namespaceURI, String lName,
    String qName, Attributes attrs) throws SAXException {
  switch (qName) {
    case RULES:
      String languageStr = attrs.getValue("targetLang");
      language = Languages.getLanguageForShortCode(languageStr);
      break;
    case RULE:
      super.startElement(namespaceURI, lName, qName, attrs);
      correctExamples = new ArrayList<>();
      incorrectExamples = new ArrayList<>();
      break;
    case TARGET:
      startPattern(attrs);
      break;
    case SOURCE:
      srcLang = Languages.getLanguageForShortCode(attrs.getValue("lang"));
      break;
    default:
      super.startElement(namespaceURI, lName, qName, attrs);
      break;
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
private static List<String> getLanguageCodes() {
  List<String> langCodes = new ArrayList<>();
  for (Language lang : Languages.get()) {
    String langCode = lang.getShortCode();
    boolean ignore = lang.isVariant() || ignoreLangCodes.contains(langCode) || externalLangCodes.contains(langCode);
    if (ignore) {
      continue;
    }
    if ("zh".equals(langCode)) {
      langCodes.add("zh-CN");
      langCodes.add("zh-TW");
    } else {
      langCodes.add(langCode);
    }
  }
  return langCodes;
}
 

import org.languagetool.Languages; //导入依赖的package包/类
private List<String> getGrammarFileNames(Language lang) {
  String shortNameWithVariant = lang.getShortCodeWithCountryAndVariant();
  List<String> fileNames = new ArrayList<>();
  for (String ruleFile : lang.getRuleFileNames()) {
    String nameOnly = new File(ruleFile).getName();
    String fileName;
    if (shortNameWithVariant.contains("-x-")) {
      fileName = lang.getShortCode() + "/" + nameOnly;
    } else if (shortNameWithVariant.contains("-") && !shortNameWithVariant.equals("xx-XX")
            && !shortNameWithVariant.endsWith("-ANY") && Languages.get().size() > 1) {
      fileName = lang.getShortCode() + "/" + shortNameWithVariant + "/" + nameOnly;
    } else {
      fileName = lang.getShortCode() + "/" + nameOnly;
    }
    if (!fileNames.contains(fileName)) {
      fileNames.add(fileName);
    }
  }
  return fileNames;
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Test
public void testJson() {
  String json = serializer.ruleMatchesToJson(matches, "This is an text.", 5, Languages.getLanguageForShortCode("xx-XX"));
  // Software:
  assertContains("\"LanguageTool\"", json);
  assertContains(JLanguageTool.VERSION, json);
  // Language:
  assertContains("\"Testlanguage\"", json);
  assertContains("\"xx-XX\"", json);
  // Matches:
  assertContains("\"My Message, use \\\"foo\\\" instead\"", json);
  assertContains("\"My rule description\"", json);
  assertContains("\"FAKE_ID\"", json);
  assertContains("\"This is ...\"", json);
  assertContains("\"http://foobar.org/blah\"", json);
  assertContains("\"addition\"", json);
  assertContains("\"short message\"", json);
  assertContains("\"sentence\":\"This is an test sentence.\"", json);
}
 

import org.languagetool.Languages; //导入依赖的package包/类
/**
 * @return true if LT supports the language of a given locale
 * @param locale The Locale to check
 */
@Override
public final boolean hasLocale(Locale locale) {
  try {
    for (Language element : Languages.get()) {
      if (locale.Language.equalsIgnoreCase(LIBREOFFICE_SPECIAL_LANGUAGE_TAG)
          && element.getShortCodeWithCountryAndVariant().equals(locale.Variant)) {
        return true;
      }
      if (element.getShortCode().equals(locale.Language)) {
        return true;
      }
    }
  } catch (Throwable t) {
    showError(t);
  }
  return false;
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Test
@Ignore("for interactive use only")
public void test() throws Exception {
  List<Language> languages1 = new ArrayList<>(Languages.get());
  initExpectedResults(languages1);
  List<Language> languages2 = new ArrayList<>(Languages.get());
  ExecutorService executor = Executors.newFixedThreadPool(THREADS);
  for (int i = 0; i < RUNS; i++) {
    System.out.println("Run #" + i);
    Collections.shuffle(languages1, rnd);
    Collections.shuffle(languages2, rnd);
    List<Future> futures = new ArrayList<>();
    for (int j = 0; j < languages1.size(); j++) {
      Language lang1 = languages1.get(j);
      Language lang2 = languages2.get(j);
      //System.out.println("Checking " + lang1 + " and " + lang2);
      futures.add(executor.submit(new Handler(lang1)));
      futures.add(executor.submit(new Handler(lang2)));
    }
    for (Future future : futures) {
      future.get();  // wait for all results or exception
    }
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Test
public void testOfficeFootnoteTokenize() {
  int count = 0;
  for (Language language : Languages.get()) {
    if (language.getSentenceTokenizer().getClass() != SRXSentenceTokenizer.class) {
      continue;
    }
    if (language.getShortCode().equals("km") || language.getShortCode().equals("ml")) {
      // TODO: I don't know about these...
      continue;
    }
    String input = "A sentence.\u0002 And another one.";
    SentenceTokenizer tokenizer = new SRXSentenceTokenizer(language);
    assertEquals("Sentence not split correctly for " + language + ": '" + input + "'",
            "[A sentence.\u0002 , And another one.]", tokenizer.tokenize(input).toString());
    count++;
  }
  if (count == 0) {
    fail("No languages found for testing");
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Test
public void testConfusionSetLoading() throws IOException {
  int count = 0;
  for (Language language : Languages.get()) {
    List<Rule> rules;
    try {
      rules = language.getRelevantLanguageModelRules(JLanguageTool.getMessageBundle(), new FakeLanguageModel());
    } catch (Exception e) {
      throw new RuntimeException("Could not load confusion pairs for " + language.getName(), e);
    }
    if (rules.size() > 0) {
      String path = "/" + language.getShortCode() + "/confusion_sets.txt";
      try (InputStream confusionSetStream = JLanguageTool.getDataBroker().getFromResourceDirAsStream(path)) {
        ConfusionSetLoader confusionSetLoader = new ConfusionSetLoader();
        Map<String, List<ConfusionSet>> set = confusionSetLoader.loadConfusionSet(confusionSetStream);
        count += set.size();
      }
    }
  }
  int minCount = 1000;
  assertTrue("Only got " + count + " confusion pairs for all languages, expected > " + minCount, count > minCount);
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Test
public void testJavaRules() throws IOException {
  Map<String,String> idsToClassName = new HashMap<>();
  Set<Class> ruleClasses = new HashSet<>();
  if (Languages.getWithDemoLanguage().size() <= 1) {
    System.err.println("***************************************************************************");
    System.err.println("WARNING: found only these languages - the tests might not be complete:");
    System.err.println(Languages.getWithDemoLanguage());
    System.err.println("***************************************************************************");
  }
  for (Language language : Languages.getWithDemoLanguage()) {
    JLanguageTool lt = new JLanguageTool(language);
    List<Rule> allRules = lt.getAllRules();
    for (Rule rule : allRules) {
      if (!(rule instanceof AbstractPatternRule)) {
        assertIdUniqueness(idsToClassName, ruleClasses, language, rule);
        assertIdValidity(language, rule);
        assertTrue(rule.supportsLanguage(language));
        testExamples(rule, lt);
      }
    }
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Test
public void testWordListValidity() throws IOException {
  Set<String> checked = new HashSet<>();
  for (Language lang : Languages.get()) {
    if (lang.getShortCode().equals("ru")) {
      // skipping, Cyrillic chars not part of the validation yet
      continue;
    }
    JLanguageTool lt = new JLanguageTool(lang);
    List<Rule> rules = lt.getAllActiveRules();
    for (Rule rule : rules) {
      if (rule instanceof SpellingCheckRule) {
        SpellingCheckRule sRule = (SpellingCheckRule) rule;
        String file = sRule.getSpellingFileName();
        if (JLanguageTool.getDataBroker().resourceExists(file) && !checked.contains(file)) {
          System.out.println("Checking " + file);
          CachingWordListLoader loader = new CachingWordListLoader();
          List<String> words = loader.loadWords(file);
          validateWords(words, file);
          checked.add(file);
        }
      }
    }
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
OldSpellingData(String ruleDesc) {
  String filePath = "/de/alt_neu.csv";
  try (InputStream inputStream = JLanguageTool.getDataBroker().getFromResourceDirAsStream(filePath);
       Scanner scanner = new Scanner(inputStream, "utf-8")) {
    Language german = Languages.getLanguageForShortCode("de");
    String message = "Diese Schreibweise war nur in der alten Rechtschreibung korrekt.";
    String shortMessage = "alte Rechtschreibung";
    while (scanner.hasNextLine()) {
      String line = scanner.nextLine();
      if (line.startsWith("#")) {
        continue;
      }
      String[] parts = line.split(";");
      if (parts.length != 2) {
        throw new RuntimeException("Unexpected format in file " + filePath + ": " + line);
      }
      String oldSpelling = parts[0];
      String newSpelling = parts[1];
      List<PatternToken> patternTokens = getTokens(oldSpelling, german);
      PatternRule rule = new PatternRule("OLD_SPELLING_INTERNAL", german, patternTokens, ruleDesc, message, shortMessage);
      spellingRules.add(new OldSpellingRuleWithSuggestion(rule, oldSpelling, newSpelling));
    }
  } catch (IOException e) {
    throw new RuntimeException(e);
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
@Ignore("just for internal performance testing, thus ignored by default")
@Test
public void testPerformance() throws Exception {
  List<Language> allLanguages = Languages.get();
  for (Language language : allLanguages) {
    JLanguageTool langTool = new JLanguageTool(language);
    //HunspellRule rule = new HunspellRule(TestTools.getMessages("German"), language);
    langTool.check("warmup");  // make sure everything is initialized when actually testing
    langTool.check("anotherwarmup");
    long startTime = System.currentTimeMillis();
    langTool.check("fdfds fdfdsa fdfdsb fdfdsc fdfdsd fdfdse fdfdsf fdfds fdfdsa fdfdsb fdfdsc fdfdsd fdfdse fdfdsf");
    //String[] w = {"foo", "warmup", "Rechtschreipreform", "Theatrekasse", "Zoobesuck", "Handselvertreter", "Mückenstick", "gewönlich", "Traprennen", "Autoverkehrr"};
    //AnalyzedSentence analyzedSentence = langTool.getAnalyzedSentence("fdfds fdfdsa fdfdsb fdfdsc fdfdsd fdfdse fdfdsf");
    //rule.match(analyzedSentence);
    long endTime = System.currentTimeMillis();
    System.out.println((endTime-startTime) + "ms for " + language);
  }
}
 

import org.languagetool.Languages; //导入依赖的package包/类
public static void main(String[] args) throws XMLStreamException {
  XmlUsageCounter counter = new XmlUsageCounter();
  Set<String> countedFiles = new HashSet<>();
  for (Language language : Languages.get()) {
    List<String> ruleFileNames = language.getRuleFileNames();
    //comment in this to count disambiguation files instead:
    //List<String> ruleFileNames = Collections.singletonList(ResourceDataBroker.RESOURCE_DIR + "/" +
    //        language.getShortCode() + "/" + "disambiguation.xml");
    for (String ruleFileName : ruleFileNames) {
      if (countedFiles.contains(ruleFileName)) {
        continue;
      }
      System.err.println("Counting elements for " + ruleFileName);
      InputStream ruleStream = XmlUsageCounter.class.getResourceAsStream(ruleFileName);
      if (ruleStream == null) {
        System.err.println("Not found, ignoring: " + ruleFileName);
        continue;
      }
      counter.countElementsAndAttributes(ruleStream);
      countedFiles.add(ruleFileName);
    }
  }
  counter.printResult();
}
 

import org.languagetool.Languages; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
  if (args.length < 4) {
    System.err.println("Usage: " + NeuralNetworkRuleEvaluator.class.getSimpleName()
            + " <langCode> <word2vecDir> <ruleId> <wikipediaXml|tatoebaFile|plainTextFile|dir>...");
    System.err.println("   <word2vecDir> is a directory with sub-directories 'en' etc. with dictionary.txt and final_embeddings.txt");
    System.err.println("   <ruleId> id of a NeuralNetworkRule or ALL for evaluating all NeuralNetworkRules");
    System.err.println("   <wikipediaXml|tatoebaFile|plainTextFile> either a Wikipedia XML dump, or a Tatoeba file, or");
    System.err.println("                      a plain text file with one sentence per line, a Wikipedia or Tatoeba file");
    System.exit(1);
  }
  long startTime = System.currentTimeMillis();
  String langCode = args[0];
  File word2vecDir = new File(args[1]);
  String ruleId = args[2];
  Language lang;
  lang = Languages.getLanguageForShortCode(langCode);
  List<String> inputsFiles = Arrays.stream(args).skip(3).collect(toList());
  NeuralNetworkRuleEvaluator generator = new NeuralNetworkRuleEvaluator(lang, word2vecDir, ruleId);
  List<Map<Double, EvalResult>> evaluationResults = generator.runAll(inputsFiles, MAX_SENTENCES, EVAL_MIN_SCORES);
  long endTime = System.currentTimeMillis();
  System.out.println("\nTime: " + (endTime - startTime) + "ms");

  System.out.println("Recommended configuration:");
  System.out.println(ConfusionFileIndenter.indent(confusionSetConfig(evaluationResults, RECOMMENDED_MIN_PRECISION)));
}
 

import org.languagetool.Languages; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
  if (args.length < 4) {
    System.out.println("Usage: " + AfterTheDeadlineChecker.class.getSimpleName() + " <langCode> <atdUrlPrefix> <file...>");
    System.out.println("   <langCode>      a language code like 'en' for English");
    System.out.println("   <atdUrlPrefix>  URL prefix of After the Deadline server, like 'http://localhost:1059/checkDocument?data='");
    System.out.println("   <sentenceLimit> Maximum number of sentences to check, or 0 for no limit");
    System.out.println("   <file...>       Wikipedia and/or Tatoeba file(s)");
    System.exit(1);
  }
  Language language = Languages.getLanguageForShortCode(args[0]);
  String urlPrefix = args[1];
  int maxSentenceCount = Integer.parseInt(args[2]);
  List<String> files = Arrays.asList(args).subList(3, args.length);
  AfterTheDeadlineChecker atdChecker = new AfterTheDeadlineChecker(urlPrefix, maxSentenceCount);
  atdChecker.run(language, files);
}