Example usage for org.apache.lucene.analysis.phonetic PhoneticFilter PhoneticFilter

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.phonetic PhoneticFilter PhoneticFilter.

Prototype

public PhoneticFilter(TokenStream in, Encoder encoder, boolean inject) 

Source Link

Document

Creates a PhoneticFilter with the specified encoder, and either adding encoded forms as synonyms (inject=true) or replacing them.

Usage

From source file:at.itbh.bev.index.TextAnalyzer.java

License:Open Source License

@Override
protected TokenStreamComponents createComponents(String fieldName) {
    Tokenizer source = new KeywordTokenizer();
    TokenStream filter = new LowerCaseFilter(source);
    filter = new PatternReplaceFilter(filter, RegexPatternCollection.addressLineStemmingPattern, "", true);
    filter = new PatternReplaceFilter(filter, RegexPatternCollection.nonAlphaCharPattern, "", true);
    filter = new PhoneticFilter(filter, new ColognePhonetic(), true);
    filter = new NGramTokenFilter(filter, 2, 6);
    return new TokenStreamComponents(source, filter);
}

---

From source file:com.example.PhoneticTokenFilterFactory.java

License:Apache License

@Override
public TokenStream create(TokenStream tokenStream) {
    if (encoder == null) {
        if (ruletype != null && nametype != null) {
            if (languageset != null) {
                final LanguageSet languages = LanguageSet.from(new HashSet<>(Arrays.asList(languageset)));
                return new BeiderMorseFilter(tokenStream, new PhoneticEngine(nametype, ruletype, true),
                        languages);/*from   ww w .  jav a2s.  c o  m*/
            }
            return new BeiderMorseFilter(tokenStream, new PhoneticEngine(nametype, ruletype, true));
        }
        if (maxcodelength > 0) {
            return new DoubleMetaphoneFilter(tokenStream, maxcodelength, !replace);
        }
    } else {
        return new PhoneticFilter(tokenStream, encoder, !replace);
    }
    throw new IllegalArgumentException("encoder error");
}

---

From source file:org.elasticsearch.index.analysis.PhoneticTokenFilterFactory.java

License:Apache License

@Override
public TokenStream create(TokenStream tokenStream) {
    if (encoder == null) {
        if (ruletype != null && nametype != null) {
            if (languageset != null) {
                final LanguageSet languages = LanguageSet.from(new HashSet(Arrays.asList(languageset)));
                return new BeiderMorseFilter(tokenStream, new PhoneticEngine(nametype, ruletype, true),
                        languages);/* w  w  w  . j  a v  a  2  s  .c o m*/
            }
            return new BeiderMorseFilter(tokenStream, new PhoneticEngine(nametype, ruletype, true));
        }
        if (maxcodelength > 0) {
            return new DoubleMetaphoneFilter(tokenStream, maxcodelength, !replace);
        }
    } else {
        return new PhoneticFilter(tokenStream, encoder, !replace);
    }
    throw new IllegalArgumentException("encoder error");
}

---