Package org.apache.lucene.analysis.Analyzer

Examples of org.apache.lucene.analysis.Analyzer.TokenStreamComponents

95
96
97
98
99
100
101
102
103
104
105
    Analyzer analyzer = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_43, reader) : factory.create(reader);
        TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_43, tokenizer) : tokenizer;
        return new TokenStreamComponents(tokenizer, stream);
      }
    };

    try {
      String formatClass = format;
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
    /* analyzer that uses whitespace + wdf */
    Analyzer a = new Analyzer() {
      @Override
      public TokenStreamComponents createComponents(String field, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new WordDelimiterFilter(
            tokenizer,
            flags, protWords));
      }
    };

    /* in this case, works as expected. */
    assertAnalyzesTo(a, "LUCENE / SOLR", new String[] { "LUCENE", "SOLR" },
        new int[] { 0, 9 },
        new int[] { 6, 13 },
        null,
        new int[] { 1, 1 },
        null,
        false);
   
    /* only in this case, posInc of 2 ?! */
    assertAnalyzesTo(a, "LUCENE / solR", new String[] { "LUCENE", "sol", "R", "solR" },
        new int[] { 0, 9, 12, 9 },
        new int[] { 6, 12, 13, 13 },
        null,
        new int[] { 1, 1, 1, 0 },
        null,
        false);
   
    assertAnalyzesTo(a, "LUCENE / NUTCH SOLR", new String[] { "LUCENE", "NUTCH", "SOLR" },
        new int[] { 0, 9, 15 },
        new int[] { 6, 14, 19 },
        null,
        new int[] { 1, 1, 1 },
        null,
        false);
   
    /* analyzer that will consume tokens with large position increments */
    Analyzer a2 = new Analyzer() {
      @Override
      public TokenStreamComponents createComponents(String field, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new WordDelimiterFilter(
            new LargePosIncTokenFilter(tokenizer),
            flags, protWords));
      }
    };
   
    /* increment of "largegap" is preserved */
    assertAnalyzesTo(a2, "LUCENE largegap SOLR", new String[] { "LUCENE", "largegap", "SOLR" },
        new int[] { 0, 7, 16 },
        new int[] { 6, 15, 20 },
        null,
        new int[] { 1, 10, 1 },
        null,
        false);
   
    /* the "/" had a position increment of 10, where did it go?!?!! */
    assertAnalyzesTo(a2, "LUCENE / SOLR", new String[] { "LUCENE", "SOLR" },
        new int[] { 0, 9 },
        new int[] { 6, 13 },
        null,
        new int[] { 1, 11 },
        null,
        false);
   
    /* in this case, the increment of 10 from the "/" is carried over */
    assertAnalyzesTo(a2, "LUCENE / solR", new String[] { "LUCENE", "sol", "R", "solR" },
        new int[] { 0, 9, 12, 9 },
        new int[] { 6, 12, 13, 13 },
        null,
        new int[] { 1, 11, 1, 0 },
        null,
        false);
   
    assertAnalyzesTo(a2, "LUCENE / NUTCH SOLR", new String[] { "LUCENE", "NUTCH", "SOLR" },
        new int[] { 0, 9, 15 },
        new int[] { 6, 14, 19 },
        null,
        new int[] { 1, 11, 1 },
        null,
        false);

    Analyzer a3 = new Analyzer() {
      @Override
      public TokenStreamComponents createComponents(String field, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        StopFilter filter = new StopFilter(TEST_VERSION_CURRENT,
            tokenizer, StandardAnalyzer.STOP_WORDS_SET);
        return new TokenStreamComponents(tokenizer, new WordDelimiterFilter(filter, flags, protWords));
      }
    };

    assertAnalyzesTo(a3, "lucene.solr",
        new String[] { "lucene", "solr", "lucenesolr" },
View Full Code Here
345
346
347
348
349
350
351
352
353
354
355
      Analyzer a = new Analyzer() {
       
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
          Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
          return new TokenStreamComponents(tokenizer, new WordDelimiterFilter(tokenizer, flags, protectedWords));
        }
      };
      checkRandomData(random(), a, 200, 20, false, false);
    }
  }
View Full Code Here
367
368
369
370
371
372
373
374
375
376
377
   
      Analyzer a = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
          Tokenizer tokenizer = new KeywordTokenizer(reader);
          return new TokenStreamComponents(tokenizer, new WordDelimiterFilter(tokenizer, flags, protectedWords));
        }
      };
      // depending upon options, this thing may or may not preserve the empty term
      checkAnalysisConsistency(random, a, random.nextBoolean(), "");
    }
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
  public void testRandomStrings() throws Exception {
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new PatternTokenizer(reader, Pattern.compile("a"), -1);
        return new TokenStreamComponents(tokenizer);
      }   
    };
    checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
   
    Analyzer b = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new PatternTokenizer(reader, Pattern.compile("a"), 0);
        return new TokenStreamComponents(tokenizer);
      }   
    };
    checkRandomData(random(), b, 1000*RANDOM_MULTIPLIER);
  }
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
    Analyzer analyzer = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_CURRENT, reader) : factory.create(reader);
        TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_CURRENT, tokenizer) : tokenizer;
        return new TokenStreamComponents(tokenizer, stream);
      }
    };

    try {
      String formatClass = format;
View Full Code Here
76
77
78
79
80
81
82
83
84
85
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new PortugueseMinimalStemFilter(sink));
      }
    };
    checkOneTerm(a, "quilométricas", "quilométricas");
  }
View Full Code Here
92
93
94
95
96
97
98
99
100
101
  public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new PortugueseMinimalStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        TokenStream sink = new KeywordMarkerFilter(source, exclusionSet);
        return new TokenStreamComponents(source, new PortugueseLightStemFilter(sink));
      }
    };
    checkOneTerm(a, "quilométricas", "quilométricas");
  }
View Full Code Here
118
119
120
121
122
123
124
125
126
127
  public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new PortugueseLightStemFilter(tokenizer));
      }
    };
    checkOneTermReuse(a, "", "");
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.Analyzer.TokenStreamComponents

  • org.apache.lucene.analysis.miscellaneous.TestWordDelimiterFilter
  • org.apache.lucene.analysis.ngram.EdgeNGramTokenizerTest
  • org.apache.lucene.analysis.path.TestReversePathHierarchyTokenizer
  • org.apache.lucene.analysis.pattern.TestPatternTokenizer
  • org.apache.lucene.analysis.pt.TestPortugueseLightStemFilter
  • org.apache.lucene.analysis.pt.TestPortugueseMinimalStemFilter
  • org.apache.lucene.analysis.snowball.TestSnowball
  • org.apache.lucene.analysis.synonym.FSTSynonymFilterFactory
  • org.apache.lucene.codecs.idversion.TestIDVersionPostingsFormat
  • org.apache.lucene.index.TestPostingsOffsets
    • 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.