Examples of ArabicNormalizationFilter

Examples of org.apache.lucene.analysis.ar.ArabicNormalizationFilter

36
37
38
39
40
41
42
        super(index, indexSettings, name, settings);
    }

    @Override
    public TokenStream create(TokenStream tokenStream) {
        return new ArabicNormalizationFilter(tokenStream);
    }
View Full Code Here

Examples of org.apache.lucene.analysis.ar.ArabicNormalizationFilter

155
156
157
158
159
160
161
162
163
164
165
      source = new StandardTokenizer(matchVersion, reader);
    } else {
      source = new ArabicLetterTokenizer(matchVersion, reader);
    }
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    result = new ArabicNormalizationFilter(result);
    /* additional persian-specific normalization */
    result = new PersianNormalizationFilter(result);
    /*
     * the order here is important: the stopword list is normalized with the
     * above!
 
View Full Code Here

Examples of org.apache.lucene.analysis.ar.ArabicNormalizationFilter

81
82
83
84
85
86
87
88
89
90
91
  }

  @Override
  public String stem(String token) {
    tokenizer = new StandardTokenizer(Version.LUCENE_35, new StringReader(token));
    TokenStream tokenStream = new ArabicStemFilter(new ArabicNormalizationFilter(tokenizer));
    CharTermAttribute termAtt = tokenStream.getAttribute(CharTermAttribute.class);
    tokenStream.clearAttributes();
    StringBuilder stemmed = new StringBuilder();
    try {
      while (tokenStream.incrementToken()) {
View Full Code Here

Examples of org.apache.lucene.analysis.ar.ArabicNormalizationFilter

124
125
126
127
128
129
130
131
132
133
134
      }
    }
   
    if (isStemming()) {
      tokenizer = new StandardTokenizer(Version.LUCENE_35, new StringReader(finalTokenized.toString().trim()));
      tokenStream = new ArabicStemFilter(new ArabicNormalizationFilter(tokenizer));
      CharTermAttribute termAtt = tokenStream.getAttribute(CharTermAttribute.class);
      tokenStream.clearAttributes();
      try {
        while (tokenStream.incrementToken()) {
          String curToken = termAtt.toString();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.