List of usage examples for org.apache.lucene.analysis.id IndonesianAnalyzer getDefaultStopSet
public static CharArraySet getDefaultStopSet()
From source file:org.elasticsearch.analysis.common.IndonesianAnalyzerProvider.java
License:Apache License
IndonesianAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
super(indexSettings, name, settings);
analyzer = new IndonesianAnalyzer(
Analysis.parseStopWords(env, settings, IndonesianAnalyzer.getDefaultStopSet()),
Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET));
analyzer.setVersion(version);/*from w w w. ja va 2 s. co m*/
}
From source file:org.elasticsearch.index.analysis.IndonesianAnalyzerProvider.java
License:Apache License
@Inject public IndonesianAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) { super(index, indexSettings, name, settings); analyzer = new IndonesianAnalyzer(version, Analysis.parseStopWords(env, settings, IndonesianAnalyzer.getDefaultStopSet(), version), Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET, version)); }
From source file:org.omegat.tokenizer.LuceneIndonesianTokenizer.java
License:Open Source License
@Override protected TokenStream getTokenStream(final String strOrig, final boolean stemsAllowed, final boolean stopWordsAllowed) { if (stemsAllowed) { Set<?> stopWords = stopWordsAllowed ? IndonesianAnalyzer.getDefaultStopSet() : Collections.EMPTY_SET; return new IndonesianAnalyzer(getBehavior(), stopWords).tokenStream("", new StringReader(strOrig)); } else {//from www .ja v a 2 s. c o m return new StandardTokenizer(getBehavior(), new StringReader(strOrig)); } }