Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.ReusableAnalyzerBase

104
105
106
107
108
109
110
111
112
113
114
  // LUCENE-3642
  // EdgeNgram blindly adds term length to offset, but this can take things out of bounds
  // wrt original text if a previous filter increases the length of the word (in this case æ -> ae)
  // so in this case we behave like WDF, and preserve any modified offsets
  public void testInvalidOffsets() throws Exception {
    Analyzer analyzer = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenFilter filters = new ASCIIFoldingFilter(tokenizer);
        filters = new NGramTokenFilter(filters, 2, 2);
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
        new int[]    {   11,   11,   11,   11,   11,   11,   11,   11,   11,   11,   11 });
  }
 
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer,
            new NGramTokenFilter(tokenizer, 2, 15));
View Full Code Here
133
134
135
136
137
138
139
140
141
142
143
    };
    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws Exception {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer,
            new NGramTokenFilter(tokenizer, 2, 15));
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
  public void testRandomStrings() throws Exception {
    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new GermanLightStemFilter(tokenizer));
      }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
    TokenFilter tf = new HindiStemFilter(tokenizer);
    assertTokenStreamContents(tf, new String[] { output });
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new HindiStemFilter(tokenizer));
      }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
  public void testRandomStrings() throws Exception {
    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new GermanMinimalStemFilter(tokenizer));
      }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
    assertTokenStreamContents(tokenizer, new String[]{"a","ab","abc"}, new int[]{0,0,0}, new int[]{1,2,3}, 5 /* abcde */);
  }
 
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new EdgeNGramTokenizer(reader, EdgeNGramTokenizer.Side.FRONT, 2, 15);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
    };
    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
    checkRandomData(random, a, 200*RANDOM_MULTIPLIER, 8192);
   
    Analyzer b = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new EdgeNGramTokenizer(reader, EdgeNGramTokenizer.Side.BACK, 2, 15);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
View Full Code Here
226
227
228
229
230
231
232
233
234
235
236
        new KeywordMarkerFilter(tokenStream, set));
    assertTokenStreamContents(filter, new String[] { "строй", "строеве" });
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new BulgarianStemFilter(tokenizer));
      }
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
    assertTokenStreamContents(tokenizer, new String[]{"a","b","c","d","e"}, new int[]{0,1,2,3,4}, new int[]{1,2,3,4,5}, 5 /* abcde */);
  }
 
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new NGramTokenizer(reader, 2, 15);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
  public void testRandomStrings() throws Exception {
    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
  }
 
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new GermanStemFilter(tokenizer));
      }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.ReusableAnalyzerBase

  • com.tigertext.lucene.LuceneServer
  • org.apache.lucene.analysis.ar.TestArabicNormalizationFilter
  • org.apache.lucene.analysis.ar.TestArabicStemFilter
  • org.apache.lucene.analysis.bg.TestBulgarianStemmer
  • org.apache.lucene.analysis.br.TestBrazilianStemmer
  • org.apache.lucene.analysis.charfilter.HTMLStripCharFilterTest
  • org.apache.lucene.analysis.cjk.TestCJKAnalyzer
  • org.apache.lucene.analysis.cjk.TestCJKWidthFilter
  • org.apache.lucene.analysis.cn.smart.TestSmartChineseAnalyzer
  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
    • Copyright © 2018 www.massapicom. 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.