Java 类org.apache.lucene.analysis.ru.RussianAnalyzer 实例源码

public RussianAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new RussianAnalyzer(
        Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, RussianAnalyzer.getDefaultStopSet()),
        Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)
    );
    analyzer.setVersion(version);
}

@Inject
public RussianAnalyzerProvider(Index index, IndexSettingsService indexSettingsService, Environment env, @Assisted String name, @Assisted Settings settings) {
    super(index, indexSettingsService.getSettings(), name, settings);
    analyzer = new RussianAnalyzer(Analysis.parseStopWords(env, settings, RussianAnalyzer.getDefaultStopSet()),
                                   Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET));
    analyzer.setVersion(version);
}

/**
 * Search in body using QueryParser
 * @param toSearch string to search
 * @param limit how many results to return
 * @throws IOException
 * @throws ParseException
 */
public void searchInBody(final String toSearch, final int limit) throws IOException, ParseException {
    final IndexSearcher indexSearcher = new IndexSearcher(reader);

    final QueryParser queryParser = new QueryParser("body", new RussianAnalyzer());
    final Query query = queryParser.parse(toSearch);
    System.out.println("Type of query: " + query.getClass().getSimpleName());

    final TopDocs search = indexSearcher.search(query, limit);
    final ScoreDoc[] hits = search.scoreDocs;
    showHits(hits);
}

WebPageIndexer() {
  if (!shouldIndex()) return;
  try {
    dir = FSDirectory.open(new File(Play.tmpDir, "web-index"));
    analyzer = new RussianAnalyzer(version);
  }
  catch (IOException e) {
    throw new RuntimeException(e);
  }

  try {
    reopenIndex();
  }
  catch (IOException ignore) {}
}

@Override
public RussianAnalyzer get() {
    return this.analyzer;
}

@Override
public RussianAnalyzer get() {
    return this.analyzer;
}

protected void configureLucene() {
    bind(Stemmer.class).to(LuceneStemmer.class);
    bind(TextNormalizer.class).to(LuceneNormalizer.class);
    bind(CharArraySet.class).annotatedWith(Models.named(LuceneNormalizer.LUCENE_STOP_WORDS_MODEL)).toInstance(RussianAnalyzer.getDefaultStopSet());
}

@Provides
@Singleton
@NoStopWordFiltering
public Analyzer getRussianWithStopWordsAnalyzer() {
    return new RussianAnalyzer(CharArraySet.EMPTY_SET);
}

@Singleton
@Provides
public Analyzer getRussianAnalyzer() {
    return new RussianAnalyzer();
}

/**
 * Returns the default stopwords set used by Lucene language analyzer for the specified language.
 *
 * @param language The language for which the stopwords are. The supported languages are English, French, Spanish,
 *                 Portuguese, Italian, Romanian, German, Dutch, Swedish, Norwegian, Danish, Russian, Finnish,
 *                 Irish, Hungarian, Turkish, Armenian, Basque and Catalan.
 * @return The default stopwords set used by Lucene language analyzers.
 */
private static CharArraySet getDefaultStopwords(String language) {
    switch (language) {
        case "English":
            return EnglishAnalyzer.getDefaultStopSet();
        case "French":
            return FrenchAnalyzer.getDefaultStopSet();
        case "Spanish":
            return SpanishAnalyzer.getDefaultStopSet();
        case "Portuguese":
            return PortugueseAnalyzer.getDefaultStopSet();
        case "Italian":
            return ItalianAnalyzer.getDefaultStopSet();
        case "Romanian":
            return RomanianAnalyzer.getDefaultStopSet();
        case "German":
            return GermanAnalyzer.getDefaultStopSet();
        case "Dutch":
            return DutchAnalyzer.getDefaultStopSet();
        case "Swedish":
            return SwedishAnalyzer.getDefaultStopSet();
        case "Norwegian":
            return NorwegianAnalyzer.getDefaultStopSet();
        case "Danish":
            return DanishAnalyzer.getDefaultStopSet();
        case "Russian":
            return RussianAnalyzer.getDefaultStopSet();
        case "Finnish":
            return FinnishAnalyzer.getDefaultStopSet();
        case "Irish":
            return IrishAnalyzer.getDefaultStopSet();
        case "Hungarian":
            return HungarianAnalyzer.getDefaultStopSet();
        case "Turkish":
            return SpanishAnalyzer.getDefaultStopSet();
        case "Armenian":
            return SpanishAnalyzer.getDefaultStopSet();
        case "Basque":
            return BasqueAnalyzer.getDefaultStopSet();
        case "Catalan":
            return CatalanAnalyzer.getDefaultStopSet();
        default:
            return CharArraySet.EMPTY_SET;
    }
}

public Tokenizer() {

    Analyzer en_analyzer = new EnglishAnalyzer(Version.LUCENE_44);
    Analyzer es_analyzer = new SpanishAnalyzer(Version.LUCENE_44);
    Analyzer de_analyzer = new GermanAnalyzer(Version.LUCENE_44);
    Analyzer da_analyzer = new DanishAnalyzer(Version.LUCENE_44);
    Analyzer el_analyzer = new GreekAnalyzer(Version.LUCENE_44);
    Analyzer fr_analyzer = new FrenchAnalyzer(Version.LUCENE_44);
    Analyzer it_analyzer = new ItalianAnalyzer(Version.LUCENE_44);
    Analyzer pt_analyzer = new PortugueseAnalyzer(Version.LUCENE_44);
    Analyzer ru_analyzer = new RussianAnalyzer(Version.LUCENE_44);
    Analyzer fa_analyzer = new PersianAnalyzer(Version.LUCENE_44);  
    Analyzer ar_analyzer = new ArabicAnalyzer(Version.LUCENE_44);
    Analyzer id_analyzer = new IndonesianAnalyzer(Version.LUCENE_44);
    Analyzer pl_analyzer = new MorfologikAnalyzer(Version.LUCENE_44);
    Analyzer nl_analyzer = new DutchAnalyzer(Version.LUCENE_44);
    Analyzer no_analyzer = new NorwegianAnalyzer(Version.LUCENE_44);
    Analyzer ro_analyzer = new RomanianAnalyzer(Version.LUCENE_44);
    Analyzer sv_analyzer = new SwedishAnalyzer(Version.LUCENE_44);
    Analyzer fi_analyzer = new FinnishAnalyzer(Version.LUCENE_44);
    Analyzer tr_analyzer = new TurkishAnalyzer(Version.LUCENE_44);
    Analyzer hu_analyzer = new HungarianAnalyzer(Version.LUCENE_44);
    Analyzer bg_analyzer = new BulgarianAnalyzer(Version.LUCENE_44);

    analyzers.put("en", en_analyzer);
    analyzers.put("es", es_analyzer);
    analyzers.put("de", de_analyzer);
    analyzers.put("da", da_analyzer);
    analyzers.put("el", el_analyzer);
    analyzers.put("fr", fr_analyzer);
    analyzers.put("it", it_analyzer);
    analyzers.put("pt", pt_analyzer);
    analyzers.put("ru", ru_analyzer);
    analyzers.put("fa", fa_analyzer);
    analyzers.put("ar", ar_analyzer);
    analyzers.put("id", id_analyzer);
    analyzers.put("pl", pl_analyzer);
    analyzers.put("nl", nl_analyzer);
    analyzers.put("no", no_analyzer);
    analyzers.put("ro", ro_analyzer);
    analyzers.put("sv", sv_analyzer);
    analyzers.put("fi", fi_analyzer);
    analyzers.put("tr", tr_analyzer);
    analyzers.put("hu", hu_analyzer);
    analyzers.put("bg", bg_analyzer);
}

/**
 * Indexing documents with RussianAnalyzer as analyzer
 *
 * @param create to decide create new or append to previous one
 * @throws IOException
 */
public void index(final Boolean create, List<Document> documents) throws IOException {
    final Analyzer analyzer = new RussianAnalyzer();
    index(create, documents, analyzer);
}