Java Language.getShortCode方法代码示例

import org.languagetool.Language; //导入方法依赖的package包/类
/**
 * Get the string to begin the XML. After this, use {@link #ruleMatchesToXmlSnippet} and then {@link #getXmlEnd()}
 * or better, simply use {@link #ruleMatchesToXml}.
 */
public String getXmlStart(Language lang, Language motherTongue) {
  StringBuilder xml = new StringBuilder(CAPACITY);
  xml.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n")
          .append("<!-- THIS OUTPUT IS DEPRECATED, PLEASE SEE http://wiki.languagetool.org/http-server FOR A BETTER APPROACH -->\n")
          .append("<matches software=\"LanguageTool\" version=\"" + JLanguageTool.VERSION + "\"" + " buildDate=\"")
          .append(JLanguageTool.BUILD_DATE).append("\">\n");
  if (lang != null || motherTongue != null) {
    String languageXml = "<language ";
    String warning = "";
    if (lang != null) {
      languageXml += "shortname=\"" + lang.getShortCodeWithCountryAndVariant() + "\" name=\"" + lang.getName() + "\"";
      String longCode = lang.getShortCodeWithCountryAndVariant();
      if ("en".equals(longCode) || "de".equals(longCode)) {
        xml.append("<!-- NOTE: The language code you selected ('").append(longCode).append("') doesn't support spell checking. Consider using a code with a variant like 'en-US'. -->\n");
      }
    }
    if (motherTongue != null && (lang == null || !motherTongue.getShortCode().equals(lang.getShortCodeWithCountryAndVariant()))) {
      languageXml += " mothertongueshortname=\"" + motherTongue.getShortCode() + "\" mothertonguename=\"" + motherTongue.getName() + "\"";
    }
    languageXml += "/>\n";
    xml.append(languageXml);
    xml.append(warning);
  }
  return xml.toString();
}
 

import org.languagetool.Language; //导入方法依赖的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.Language; //导入方法依赖的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.Language; //导入方法依赖的package包/类
private void activateLanguageModelRules(Language language) {
  if (config.getNgramDirectory() != null) {
    File ngramLangDir = new File(config.getNgramDirectory(), language.getShortCode());
    if (ngramLangDir.exists()) {
      try {
        languageTool.activateLanguageModelRules(config.getNgramDirectory());
      } catch (Exception e) {
        JOptionPane.showMessageDialog(null, "Error while loading ngram database.\n" + e.getMessage());
      }
    } else {
      // user might have set ngram directory to use it for e.g. English, but they
      // might not have the data for other languages that supports ngram, so don't
      // annoy them with an error dialog:
      System.err.println("Not loading ngram data, directory does not exist: " + ngramLangDir);
    }
  }
}
 

import org.languagetool.Language; //导入方法依赖的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.Language; //导入方法依赖的package包/类
private void run(Language lang) throws IOException {
  File basePath = new File("/lt/git/languagetool/languagetool-language-modules");
  if (!basePath.exists()) {
    throw new RuntimeException("basePath does not exist: " + basePath);
  }
  String langCode = lang.getShortCode();
  File xml = new File(basePath, "/" + langCode + "/src/main/resources/org/languagetool/rules/" + langCode + "/grammar.xml");
  List<String> xmlLines = IOUtils.readLines(new FileReader(xml));
  JLanguageTool tool = new JLanguageTool(lang);
  for (Rule rule : tool.getAllRules()) {
    if (!(rule instanceof PatternRule)) {
      continue;
    }
    List<IncorrectExample> incorrectExamples = rule.getIncorrectExamples();
    for (IncorrectExample incorrectExample : incorrectExamples) {
      checkCorrections(rule, incorrectExample, xmlLines, tool);
    }
  }
  System.err.println("Added corrections: " + addedCorrectionsCount);
  for (String xmlLine : xmlLines) {
    System.out.println(xmlLine);
  }
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
private void run(Language lang) throws IOException {
  File basePath = new File("/lt/git/languagetool/languagetool-language-modules");
  if (!basePath.exists()) {
    throw new RuntimeException("basePath does not exist: " + basePath);
  }
  String langCode = lang.getShortCode();
  File xml = new File(basePath, "/" + langCode + "/src/main/resources/org/languagetool/rules/" + langCode + "/grammar.xml");
  List<String> xmlLines = IOUtils.readLines(new FileReader(xml));
  JLanguageTool tool = new JLanguageTool(lang);
  for (Rule rule : tool.getAllActiveRules()) {
    if (!(rule instanceof PatternRule)) {
      continue;
    }
    List<CorrectExample> correctExamples = rule.getCorrectExamples();
    List<IncorrectExample> incorrectExamples = rule.getIncorrectExamples();
    for (IncorrectExample incorrectExample : incorrectExamples) {
      checkCorrections(rule, correctExamples, incorrectExample, xmlLines);
    }
  }
  System.err.println("Useless examples: " + uselessExampleCount);
  System.err.println("Removed lines: " + removedLinesCount);
  for (String xmlLine : xmlLines) {
    System.out.println(xmlLine);
  }
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
private int getShortestCorrectDetection(String line, Language expectedLanguage) {
  totalInputs++;
  String[] tokens = line.split("\\s+");
  for (int i = tokens.length; i > 0; i--) {
    String text = String.join(" ", Arrays.asList(tokens).subList(0, i));
    Language detectedLangObj = languageIdentifier.detectLanguage(text);
    String detectedLang = null;
    if (detectedLangObj != null) {
      detectedLang = detectedLangObj.getShortCode();
    }
    if (detectedLang == null && i == tokens.length) {
      throw new DetectionException("Detection failed for '" + line + "', detected <null>");
    } else if (detectedLang != null && !expectedLanguage.getShortCode().equals(detectedLang)) {
      if (i == tokens.length) {
        throw new DetectionException("Detection failed for '" + line + "', detected " + detectedLang);
      } else {
        int textLength = getTextLength(tokens, i + 1);
        //System.out.println("TEXT     : " + line);
        //System.out.println("TOO SHORT: " + text + " => " + detectedLang + " (" + textLength + ")");
        return textLength;
      }
    }
  }
  return tokens[0].length();
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
public XmlRuleDisambiguator(Language language) {
  Objects.requireNonNull(language);
  String disambiguationFile = language.getShortCode() + "/" + DISAMBIGUATION_FILE;
  try {
    disambiguationRules = loadPatternRules(disambiguationFile);
  } catch (Exception e) {
    throw new RuntimeException("Problems with loading disambiguation file: " + disambiguationFile, e);
  }
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
public ConfusionProbabilityRule(ResourceBundle messages, LanguageModel languageModel, Language language, int grams) {
  super(messages);
  setCategory(Categories.TYPOS.getCategory(messages));
  setLocQualityIssueType(ITSIssueType.NonConformance);
  for (String filename : getFilenames()) {
    String path = "/" + language.getShortCode() + "/" + filename;
    this.wordToSets.putAll(confSetCache.getUnchecked(path));
  }
  this.lm = Objects.requireNonNull(languageModel);
  this.language = Objects.requireNonNull(language);
  if (grams < 1 || grams > 5) {
    throw new IllegalArgumentException("grams must be between 1 and 5: " + grams);
  }
  this.grams = grams;
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
/**
 * Gets default bitext rules for a given pair of languages
 * @param source  Source language.
 * @param target  Target language.
 * @param externalBitextRuleFile external file with bitext rules
 * @return  List of Bitext rules
 * @since 2.9
 */
public static List<BitextRule> getBitextRules(Language source,
    Language target, File externalBitextRuleFile) throws IOException, ParserConfigurationException, SAXException {
  List<BitextRule> bRules = new ArrayList<>();
  //try to load the bitext pattern rules for the language...
  BitextPatternRuleLoader ruleLoader = new BitextPatternRuleLoader();          
  String name = "/" + target.getShortCode() + "/bitext.xml";
  if (JLanguageTool.getDataBroker().ruleFileExists(name)) {
    InputStream is = JLanguageTool.getDataBroker().getFromRulesDirAsStream(name);
    if (is != null) {
      bRules.addAll(ruleLoader.getRules(is, name));
    }
  }
  if (externalBitextRuleFile != null) {
    bRules.addAll(ruleLoader.getRules(new FileInputStream(externalBitextRuleFile), externalBitextRuleFile.getAbsolutePath()));
  }
  
  //load the false friend rules in the bitext mode:
  FalseFriendsAsBitextLoader fRuleLoader = new FalseFriendsAsBitextLoader();
  String falseFriendsFile = "/false-friends.xml";
  List<BitextPatternRule> rules = fRuleLoader.getFalseFriendsAsBitext(falseFriendsFile, source, target);
  bRules.addAll(rules);

  //load Java bitext rules:
  bRules.addAll(getAllBuiltinBitextRules(source, null));
  return bRules;
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
@Test
@Override
public void testHTTPServer() throws Exception {
  File dir = new File(DATA_PATH);
  List<Language> languages = new ArrayList<>();
  //languages.add(new German());
  languages.addAll(Languages.get());
  for (Language language : languages) {
    File file = new File(dir, "tatoeba-" + language.getShortCode() + ".txt");
    if (!file.exists()) {
      System.err.println("No data found for " + language + ", language will not be tested");
    } else {
      String content = StringTools.readerToString(new FileReader(file));
      int fromPos = random.nextInt(content.length());
      int toPos = fromPos + random.nextInt(MAX_TEXT_LENGTH) + MIN_TEXT_LENGTH;
      String textSubstring = content.substring(fromPos, Math.min(toPos, content.length()));
      langCodeToText.put(language, textSubstring);
      String response = checkByPOST(language, textSubstring);
      textToResult.put(language, response);
      System.err.println("Using " + content.length() + " bytes of data for " + language);
    }
  }
  if (langCodeToText.size() == 0) {
    throw new RuntimeException("No input data found in " + dir);
  }
  System.out.println("Testing " + langCodeToText.keySet().size() + " languages and variants");
  //super.testHTTPServer();  // start server in this JVM
  super.doTest();  // assume server has been started manually in its own JVM
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
@Test
@Ignore("for interactive use only")
public void testExportPosDictAndCreateSynth() throws Exception {
  for (Language language : Languages.get()) {
    String langCode = language.getShortCode();
    File dir = new File("./languagetool-language-modules/" + langCode + "/src/main/resources/org/languagetool/resource/" + langCode);
    File oldBinarySynthFile = new File(dir, language.getName().toLowerCase() + "_synth.dict");
    if (!oldBinarySynthFile.exists()) {
      System.out.println("Ignoring " + language + ", no synth file found");
      continue;
    }
    File oldBinaryFile = new File(dir, language.getName().toLowerCase() + ".dict");
    File infoFile = new File(dir, language.getName().toLowerCase() + "_synth.info");
    File exportFile = exportDictionaryContents(oldBinaryFile);
    if (exportFile.length() == 0) {
      System.out.println("Zero-size output for " + language + ", skipping dictionary generation");
      exportFile.delete();
      continue;
    }
    SynthDictionaryBuilder builder = new SynthDictionaryBuilder(infoFile);
    File newBinarySynthFile = builder.build(exportFile, infoFile);
    exportFile.delete();
    System.out.println(language + " old binary file size: " + oldBinarySynthFile.length() + " bytes (" + oldBinarySynthFile.getName() + ")");
    System.out.println(language + " new binary file size: " + newBinarySynthFile.length() + " bytes (" + newBinarySynthFile.getAbsolutePath() + ")");
    // comment in to copy the new files over the old ones:
    /*boolean b = newBinarySynthFile.renameTo(oldBinarySynthFile);
    if (!b) {
      throw new RuntimeException("Could not rename " + newBinarySynthFile.getAbsolutePath() + " to " + oldBinarySynthFile.getCanonicalPath());
    }*/
    System.out.println("");
  }
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
private void activateWord2VecModelRules(Language language) {
  if (config.getWord2VecDirectory() != null) {
    File word2vecDir = new File(config.getWord2VecDirectory(), language.getShortCode());
    if (word2vecDir.exists()) {
      try {
        languageTool.activateWord2VecModelRules(config.getWord2VecDirectory());
      } catch (Exception e) {
        JOptionPane.showMessageDialog(null, "Error while loading word2vec model.\n" + e.getMessage());
      }
    } else {
      System.err.println("Not loading word2vec data, directory does not exist: " + word2vecDir);
    }
  }
}
 

import org.languagetool.Language; //导入方法依赖的package包/类
private void run(Language lang) throws IOException {
  File basePath = new File("/lt/git/languagetool/languagetool-language-modules");
  if (!basePath.exists()) {
    throw new RuntimeException("basePath does not exist: " + basePath);
  }
  String langCode = lang.getShortCode();
  File xml = new File(basePath, "/" + langCode + "/src/main/resources/org/languagetool/rules/" + langCode + "/grammar.xml");
  List<String> xmlLines = IOUtils.readLines(new FileReader(xml));
  JLanguageTool tool = new JLanguageTool(lang);
  int totalRules = 0;
  for (Rule rule : tool.getAllActiveRules()) {
    if (!(rule instanceof PatternRule)) {
      continue;
    }
    PatternRule patternRule = (PatternRule) rule;
    String id = patternRule.getFullId();
    if (isSimple((PatternRule)rule)) {
      System.err.println("Simplifying: " + id);
      simplify(patternRule, xmlLines);
    } else {
      System.err.println("Can't simplify: " + id);
    }
    totalRules++;
  }
  System.err.println("touchedRulesCount: " + touchedRulesCount + " out of " + totalRules);
  for (String xmlLine : xmlLines) {
    System.out.println(xmlLine);
  }
}