Example usage for org.apache.lucene.analysis.tr TurkishLowerCaseFilter TurkishLowerCaseFilter

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.tr TurkishLowerCaseFilter TurkishLowerCaseFilter.

Prototype

public TurkishLowerCaseFilter(TokenStream in) 

Source Link

Document

Create a new TurkishLowerCaseFilter, that normalizes Turkish token text to lower case.

Usage

From source file:com.hourglassapps.cpi_ii.stem.snowball.lucene.SnowballAnalyzer.java

License:Apache License

/** Constructs a {@link StandardTokenizer} filtered by a {@link
    StandardFilter}, a {@link LowerCaseFilter}, a {@link StopFilter},
    and a {@link SnowballFilter} */
@Override/*from  w w w. ja  v  a  2s.  com*/
public TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer tokenizer = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, tokenizer);
    // remove the possessive 's for english stemmers
    if (matchVersion.onOrAfter(Version.LUCENE_3_1)
            && (name.equals("English") || name.equals("Porter") || name.equals("Lovins")))
        result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (matchVersion.onOrAfter(Version.LUCENE_3_1) && name.equals("Turkish"))
        result = new TurkishLowerCaseFilter(result);
    else
        result = new LowerCaseFilter(matchVersion, result);
    if (stopSet != null)
        result = new StopFilter(matchVersion, result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
}

---

From source file:org.apache.solr.analysis.TurkishLowerCaseFilterFactory.java

License:Apache License

public TokenStream create(TokenStream input) {
    return new TurkishLowerCaseFilter(input);
}

---

From source file:org.codelibs.elasticsearch.index.analysis.SnowballAnalyzer.java

License:Apache License

/** Constructs a {StandardTokenizer} filtered by a {@link
    StandardFilter}, a {LowerCaseFilter}, a {StopFilter},
    and a {SnowballFilter} *//*from  w  ww. j a v a2  s .com*/
@Override
public TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer tokenizer = new StandardTokenizer();
    TokenStream result = tokenizer;
    // remove the possessive 's for english stemmers
    if (name.equals("English") || name.equals("Porter") || name.equals("Lovins")) {
        result = new EnglishPossessiveFilter(result);
    }
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (name.equals("Turkish")) {
        result = new TurkishLowerCaseFilter(result);
    } else {
        result = new LowerCaseFilter(result);
    }
    if (stopSet != null) {
        result = new StopFilter(result, stopSet);
    }
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
}

---

From source file:org.elasticsearch.analysis.common.LowerCaseTokenFilterFactory.java

License:Apache License

@Override
public TokenStream create(TokenStream tokenStream) {
    if (lang == null) {
        return new LowerCaseFilter(tokenStream);
    } else if (lang.equalsIgnoreCase("greek")) {
        return new GreekLowerCaseFilter(tokenStream);
    } else if (lang.equalsIgnoreCase("irish")) {
        return new IrishLowerCaseFilter(tokenStream);
    } else if (lang.equalsIgnoreCase("turkish")) {
        return new TurkishLowerCaseFilter(tokenStream);
    } else {/*  www . j  a va 2 s  .  c om*/
        throw new IllegalArgumentException("language [" + lang + "] not support for lower case");
    }
}

---

From source file:org.elasticsearch.analysis.common.SnowballAnalyzer.java

License:Apache License

/** Constructs a {@link StandardTokenizer} filtered by a {@link
    StandardFilter}, a {@link LowerCaseFilter}, a {@link StopFilter},
    and a {@link SnowballFilter} */
@Override/*ww w . ja  va  2 s.  c om*/
public TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer tokenizer = new StandardTokenizer();
    TokenStream result = tokenizer;
    // remove the possessive 's for english stemmers
    if (name.equals("English") || name.equals("Porter") || name.equals("Lovins"))
        result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (name.equals("Turkish"))
        result = new TurkishLowerCaseFilter(result);
    else
        result = new LowerCaseFilter(result);
    if (stopSet != null)
        result = new StopFilter(result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
}

---

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

License:Apache License

@Override
public TokenStream create(TokenStream tokenStream) {
    if (lang == null) {
        return new LowerCaseFilter(version, tokenStream);
    } else if (lang.equalsIgnoreCase("greek")) {
        return new GreekLowerCaseFilter(version, tokenStream);
    } else if (lang.equalsIgnoreCase("turkish")) {
        return new TurkishLowerCaseFilter(tokenStream);
    } else {/*  w  w w.j av a 2  s .c o m*/
        throw new ElasticsearchIllegalArgumentException("language [" + lang + "] not support for lower case");
    }
}

---

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

License:Apache License

/** Constructs a {@link StandardTokenizer} filtered by a {@link
    StandardFilter}, a {@link LowerCaseFilter}, a {@link StopFilter},
    and a {@link SnowballFilter} */
@Override/*from w  w  w .  ja v a 2 s .  c o m*/
public TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer tokenizer;
    if (getVersion().onOrAfter(Version.LUCENE_4_7_0)) {
        tokenizer = new StandardTokenizer();
    } else {
        tokenizer = new StandardTokenizer40();
    }
    TokenStream result = tokenizer;
    // remove the possessive 's for english stemmers
    if (name.equals("English") || name.equals("Porter") || name.equals("Lovins"))
        result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (name.equals("Turkish"))
        result = new TurkishLowerCaseFilter(result);
    else
        result = new LowerCaseFilter(result);
    if (stopSet != null)
        result = new StopFilter(result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
}

---