Package org.apache.lucene.analysis.Analyzer

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

133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
        try {
          tokenizer = new PatternTokenizer(reader, Pattern.compile("a"), -1);
        } catch (IOException e) {
          throw new RuntimeException(e);
        }
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
    };
    checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER);
   
    Analyzer b = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = null;
        try {
          tokenizer = new PatternTokenizer(reader, Pattern.compile("a"), 0);
        } catch (IOException e) {
          throw new RuntimeException(e);
        }
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
    };
    checkRandomData(random(), b, 1000*RANDOM_MULTIPLIER);
  }
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
  public void testRandomStrings() throws Exception {
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new ReversePathHierarchyTokenizer(newAttributeFactory(), reader, DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
    };
    // TODO: properly support positionLengthAttribute
    checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER, 20, false, false);
  }
View Full Code Here
181
182
183
184
185
186
187
188
189
190
191
    Random random = random();
    Analyzer a = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new ReversePathHierarchyTokenizer(newAttributeFactory(), reader, DEFAULT_DELIMITER, DEFAULT_DELIMITER, DEFAULT_SKIP);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }   
    };
    // TODO: properly support positionLengthAttribute
    checkRandomData(random, a, 100*RANDOM_MULTIPLIER, 1027, false, false);
  }
View Full Code Here
454
455
456
457
458
459
460
461
462
463
464
  public void testCrazyOffsetGap() throws Exception {
    Directory dir = newDirectory();
    Analyzer analyzer = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        return new TokenStreamComponents(new MockTokenizer(reader, MockTokenizer.KEYWORD, false));
      }

      @Override
      public int getOffsetGap(String fieldName) {
        return -10;
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(newAttributeFactory(), 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(newAttributeFactory(), reader, Pattern.compile("a"), 0);
        return new TokenStreamComponents(tokenizer);
      }   
    };
    checkRandomData(random(), b, 1000*RANDOM_MULTIPLIER);
  }
View Full Code Here
217
218
219
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
    /* 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(TEST_VERSION_CURRENT,
            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 },
        new int[] { 1, 1 });
   
    /* only in this case, posInc of 2 ?! */
    assertAnalyzesTo(a, "LUCENE / solR", new String[] { "LUCENE", "sol", "solR", "R" },
        new int[] { 0, 9, 9, 12 },
        new int[] { 6, 12, 13, 13 },
        new int[] { 1, 1, 0, 1 });
   
    assertAnalyzesTo(a, "LUCENE / NUTCH SOLR", new String[] { "LUCENE", "NUTCH", "SOLR" },
        new int[] { 0, 9, 15 },
        new int[] { 6, 14, 19 },
        new int[] { 1, 1, 1 });
   
    /* 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(TEST_VERSION_CURRENT,
            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 },
        new int[] { 1, 10, 1 });
   
    /* 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 },
        new int[] { 1, 11 });
   
    /* in this case, the increment of 10 from the "/" is carried over */
    assertAnalyzesTo(a2, "LUCENE / solR", new String[] { "LUCENE", "sol", "solR", "R" },
        new int[] { 0, 9, 9, 12 },
        new int[] { 6, 12, 13, 13 },
        new int[] { 1, 11, 0, 1 });
   
    assertAnalyzesTo(a2, "LUCENE / NUTCH SOLR", new String[] { "LUCENE", "NUTCH", "SOLR" },
        new int[] { 0, 9, 15 },
        new int[] { 6, 14, 19 },
        new int[] { 1, 11, 1 });

    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(TEST_VERSION_CURRENT, filter, flags, protWords));
      }
    };

    assertAnalyzesTo(a3, "lucene.solr",
        new String[] { "lucene", "lucenesolr", "solr" },
View Full Code Here
307
308
309
310
311
312
313
314
315
316
317
    /* 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(TEST_VERSION_CURRENT, tokenizer, flags, null));
      }
    };
   
    assertAnalyzesTo(a, "abc-def-123-456",
        new String[] { "abc", "abcdef", "abcdef123456", "def", "123", "123456", "456" },
View Full Code Here
327
328
329
330
331
332
333
334
335
336
337
    /* 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(TEST_VERSION_CURRENT, tokenizer, flags, null));
      }
    };
   
    assertAnalyzesTo(a, "abc-def-123-456",
        new String[] { "abc-def-123-456", "abc", "abcdef", "abcdef123456", "def", "123", "123456", "456" },
View Full Code Here
355
356
357
358
359
360
361
362
363
364
365
      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(TEST_VERSION_CURRENT, tokenizer, flags, protectedWords));
        }
      };
      // TODO: properly support positionLengthAttribute
      checkRandomData(random(), a, 1000*RANDOM_MULTIPLIER, 20, false, false);
    }
View Full Code Here
380
381
382
383
384
385
386
387
388
389
390
      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(TEST_VERSION_CURRENT, tokenizer, flags, protectedWords));
        }
      };
      // TODO: properly support positionLengthAttribute
      checkRandomData(random(), a, 100*RANDOM_MULTIPLIER, 8192, false, false);
    }
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.