package org.wikibrain.lucene.tokenizers; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.Tokenizer; import org.apache.lucene.analysis.core.LowerCaseFilter; import org.apache.lucene.analysis.core.StopFilter; import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter; import org.apache.lucene.analysis.standard.StandardFilter; import org.apache.lucene.analysis.th.ThaiAnalyzer; import org.apache.lucene.analysis.util.CharArraySet; import org.apache.lucene.util.Version; import org.wikibrain.core.lang.Language; import org.wikibrain.lucene.TokenizerOptions; /** * * This Tokenizer is more questionable than most, * and is not currently added to LanguageTokenizer * * @author Ari Weiland */ public class ThaiTokenizer extends LanguageTokenizer { protected ThaiTokenizer(Version version, TokenizerOptions tokenizerOptions, Language language) { super(version, tokenizerOptions, language); } @Override public TokenStream getTokenStream(Tokenizer tokenizer, CharArraySet stemExclusionSet) { TokenStream stream = new StandardFilter(matchVersion, tokenizer); if (caseInsensitive) stream = new LowerCaseFilter(matchVersion, stream); if (useStopWords) stream = new StopFilter(matchVersion, stream, ThaiAnalyzer.getDefaultStopSet()); if (useStem) { if (!stemExclusionSet.isEmpty()) stream = new SetKeywordMarkerFilter(stream, stemExclusionSet); } return stream; } }