Java 类org.apache.lucene.analysis.id.IndonesianAnalyzer 实例源码

private static List<String> getStopList(String path) {

List<String> stopwords = new ArrayList<String>();
   try {

    InputStream in = IndonesianAnalyzer.class.getResourceAsStream(path);
    BufferedReader input = new BufferedReader(
                new InputStreamReader(in));
     for(String line = input.readLine(); line != null; line = input.readLine()) {
      if (line.startsWith("#")) continue;
      stopwords.add(line);
     }
     input.close();

     return stopwords;

   } catch(IOException e) {
     e.printStackTrace();
     System.exit(1);
     return null;
   } 
 }

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

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

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

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

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);
}