Java 类org.apache.lucene.analysis.pattern.PatternTokenizerFactory 实例源码

public SimpleAnalyzer(boolean lowerCase) {
    Map<String, String> parameters = new HashMap<String, String>();
    parameters.put(PatternTokenizerFactory.PATTERN, PATTERN);
    parameters.put(PatternTokenizerFactory.GROUP, "0");
    parameters.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM,
            version.name());
    tokenizerFactory = new PatternTokenizerFactory(parameters);
    if (lowerCase) {
        parameters = new HashMap<String, String>();
        parameters.put(AbstractAnalysisFactory.LUCENE_MATCH_VERSION_PARAM,
                version.name());
        lowerCaseFilterFactory = new LowerCaseFilterFactory(parameters);
    } else {
        lowerCaseFilterFactory = null;
    }
}

@Factory
public SearchMapping getSearchMapping() {
    SearchMapping mapping = new SearchMapping();

    mapping.analyzerDef("autocompleteEdgeAnalyzer", PatternTokenizerFactory.class)
            .tokenizerParam("pattern", "(.*)")
            .tokenizerParam("group", "1")
            .filter(LowerCaseFilterFactory.class)
            .filter(StopFilterFactory.class)
            .filter(EdgeNGramFilterFactory.class)
            .param("minGramSize", "3")
            .param("maxGramSize", "50")
        .analyzerDef("autocompletePhoneticAnalyzer", StandardTokenizerFactory.class)
            .filter(StandardFilterFactory.class)
            .filter(StopFilterFactory.class)
            .filter(PhoneticFilterFactory.class)
            .param("encoder", "DoubleMetaphone")
            .filter(SnowballPorterFilterFactory.class)
            .param("language", "English")
        .analyzerDef("autocompleteNGramAnalyzer", StandardTokenizerFactory.class)
            .filter(WordDelimiterFilterFactory.class)
            .filter(LowerCaseFilterFactory.class)
            .filter(NGramFilterFactory.class)
            .param("minGramSize", "3")
            .param("maxGramSize", "20")
        .analyzerDef("standardAnalyzer", StandardTokenizerFactory.class)
            .filter(LowerCaseFilterFactory.class)
        .analyzerDef("exactAnalyzer", StandardTokenizerFactory.class)
        .analyzerDef("conceptParentPidsAnalyzer", WhitespaceTokenizerFactory.class);

    return mapping;
}