List of usage examples for org.apache.lucene.analysis.ja JapaneseReadingFormFilter JapaneseReadingFormFilter
public JapaneseReadingFormFilter(TokenStream input, boolean useRomaji)
From source file:org.apache.solr.analysis.JapaneseReadingFormFilterFactory.java
License:Apache License
public TokenStream create(TokenStream input) { return new JapaneseReadingFormFilter(input, useRomaji); }
From source file:org.codelibs.elasticsearch.ja.analysis.KuromojiReadingFormFilterFactory.java
License:Apache License
@Override public TokenStream create(TokenStream tokenStream) { return new JapaneseReadingFormFilter(tokenStream, useRomaji); }
From source file:org.elasticsearch.indices.analysis.KuromojiIndicesAnalysis.java
License:Apache License
@Inject public KuromojiIndicesAnalysis(Settings settings, IndicesAnalysisService indicesAnalysisService) { super(settings); indicesAnalysisService.analyzerProviderFactories().put("kuromoji", new PreBuiltAnalyzerProviderFactory("kuromoji", AnalyzerScope.INDICES, new JapaneseAnalyzer())); indicesAnalysisService.charFilterFactories().put("kuromoji_iteration_mark", new PreBuiltCharFilterFactoryFactory(new CharFilterFactory() { @Override//w w w. j av a 2 s .c om public String name() { return "kuromoji_iteration_mark"; } @Override public Reader create(Reader reader) { return new JapaneseIterationMarkCharFilter(reader, JapaneseIterationMarkCharFilter.NORMALIZE_KANJI_DEFAULT, JapaneseIterationMarkCharFilter.NORMALIZE_KANA_DEFAULT); } })); indicesAnalysisService.tokenizerFactories().put("kuromoji_tokenizer", new PreBuiltTokenizerFactoryFactory(new TokenizerFactory() { @Override public String name() { return "kuromoji_tokenizer"; } @Override public Tokenizer create() { return new JapaneseTokenizer(null, true, Mode.SEARCH); } })); indicesAnalysisService.tokenFilterFactories().put("kuromoji_baseform", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() { @Override public String name() { return "kuromoji_baseform"; } @Override public TokenStream create(TokenStream tokenStream) { return new JapaneseBaseFormFilter(tokenStream); } })); indicesAnalysisService.tokenFilterFactories().put("kuromoji_part_of_speech", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() { @Override public String name() { return "kuromoji_part_of_speech"; } @Override public TokenStream create(TokenStream tokenStream) { return new JapanesePartOfSpeechStopFilter(tokenStream, JapaneseAnalyzer.getDefaultStopTags()); } })); indicesAnalysisService.tokenFilterFactories().put("kuromoji_readingform", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() { @Override public String name() { return "kuromoji_readingform"; } @Override public TokenStream create(TokenStream tokenStream) { return new JapaneseReadingFormFilter(tokenStream, true); } })); indicesAnalysisService.tokenFilterFactories().put("kuromoji_stemmer", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() { @Override public String name() { return "kuromoji_stemmer"; } @Override public TokenStream create(TokenStream tokenStream) { return new JapaneseKatakanaStemFilter(tokenStream); } })); }