Java 类org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilter 实例源码

public HyphenationCompoundWordTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, env, name, settings);

    String hyphenationPatternsPath = settings.get("hyphenation_patterns_path", null);
    if (hyphenationPatternsPath == null) {
        throw new IllegalArgumentException("hyphenation_patterns_path is a required setting.");
    }

    Path hyphenationPatternsFile = env.configFile().resolve(hyphenationPatternsPath);

    try {
        hyphenationTree = HyphenationCompoundWordTokenFilter.getHyphenationTree(new InputSource(Files.newInputStream(hyphenationPatternsFile)));
    } catch (Exception e) {
        throw new IllegalArgumentException("Exception while reading hyphenation_patterns_path.", e);
    }
}

@Inject
public HyphenationCompoundWordTokenFilterFactory(Index index, IndexSettingsService indexSettingsService, Environment env, @Assisted String name, @Assisted Settings settings) {
    super(index, indexSettingsService.getSettings(), env, name, settings);

    String hyphenationPatternsPath = settings.get("hyphenation_patterns_path", null);
    if (hyphenationPatternsPath == null) {
        throw new IllegalArgumentException("hyphenation_patterns_path is a required setting.");
    }

    Path hyphenationPatternsFile = env.configFile().resolve(hyphenationPatternsPath);

    try {
        hyphenationTree = HyphenationCompoundWordTokenFilter.getHyphenationTree(new InputSource(Files.newInputStream(hyphenationPatternsFile)));
    } catch (Exception e) {
        throw new IllegalArgumentException("Exception while reading hyphenation_patterns_path: " + e.getMessage());
    }
}

@Override
public void inform(ResourceLoader loader) throws IOException {
  InputStream stream = null;
  try {
    if (dictFile != null) // the dictionary can be empty.
      dictionary = getWordSet(loader, dictFile, false);
    // TODO: Broken, because we cannot resolve real system id
    // ResourceLoader should also supply method like ClassLoader to get resource URL
    stream = loader.openResource(hypFile);
    final InputSource is = new InputSource(stream);
    is.setEncoding(encoding); // if it's null let xml parser decide
    is.setSystemId(hypFile);
    hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
  } finally {
    IOUtils.closeWhileHandlingException(stream);
  }
}

@Override
public TokenStream create(TokenStream tokenStream) {
    if (version.onOrAfter(Version.LUCENE_4_4_0)) {
        return new HyphenationCompoundWordTokenFilter(tokenStream, hyphenationTree, wordList, minWordSize, 
                                                      minSubwordSize, maxSubwordSize, onlyLongestMatch);
    } else {
        return new Lucene43HyphenationCompoundWordTokenFilter(tokenStream, hyphenationTree, wordList, minWordSize, 
                minSubwordSize, maxSubwordSize, onlyLongestMatch);
    }
}

@Override public Object create(Random random) {
  // TODO: make nastier
  try {
    InputSource is = new InputSource(TestCompoundWordTokenFilter.class.getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
    return hyphenator;
  } catch (Exception ex) {
    Rethrow.rethrow(ex);
    return null; // unreachable code
  }
}

@Override public Object create(Random random) {
  // TODO: make nastier
  try {
    InputSource is = new InputSource(TestCompoundWordTokenFilter.class.getResource("da_UTF8.xml").toExternalForm());
    HyphenationTree hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
    return hyphenator;
  } catch (Exception ex) {
    Rethrow.rethrow(ex);
    return null; // unreachable code
  }
}

@Override
public TokenStream create(TokenStream tokenStream) {
    return new HyphenationCompoundWordTokenFilter(tokenStream, hyphenationTree, wordList, minWordSize,
                                                  minSubwordSize, maxSubwordSize, onlyLongestMatch);
}

@Override
public HyphenationCompoundWordTokenFilter create(TokenStream input) {
  return new HyphenationCompoundWordTokenFilter(luceneMatchVersion, input, hyphenator, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
}