Package org.apache.lucene.analysis.tokenattributes

Examples of org.apache.lucene.analysis.tokenattributes.CharTermAttribute

117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
  }
 
  private void doTestStopPositons(StopFilter stpf, boolean enableIcrements) throws IOException {
    log("---> test with enable-increments-"+(enableIcrements?"enabled":"disabled"));
    stpf.setEnablePositionIncrements(enableIcrements);
    CharTermAttribute termAtt = stpf.getAttribute(CharTermAttribute.class);
    PositionIncrementAttribute posIncrAtt = stpf.getAttribute(PositionIncrementAttribute.class);
    stpf.reset();
    for (int i=0; i<20; i+=3) {
      assertTrue(stpf.incrementToken());
      log("Token "+i+": "+stpf);
      String w = English.intToEnglish(i).trim();
      assertEquals("expecting token "+i+" to be "+w,w,termAtt.toString());
      assertEquals("all but first token must have position increment of 3",enableIcrements?(i==0?1:3):1,posIncrAtt.getPositionIncrement());
    }
    assertFalse(stpf.incrementToken());
    stpf.end();
    stpf.close();
View Full Code Here
778
779
780
781
782
783
784
785
786
787
788
789
790
791
    }
    TokenStream ts = analyzer.tokenStream(fieldName, r);
    try {
      int tokenCount = 0;
      // for every token
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      ts.reset();
      while (ts.incrementToken()) {
        String word = termAtt.toString();
        tokenCount++;
        if (tokenCount > maxNumTokensParsed) {
          break;
        }
        if (isNoiseWord(word)) {
View Full Code Here
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
     *  reuse and its chars must not be null. */
    public CharsRef analyze(String text, CharsRef reuse) throws IOException {
      IOException priorException = null;
      TokenStream ts = analyzer.tokenStream("", text);
      try {
        CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
        PositionIncrementAttribute posIncAtt = ts.addAttribute(PositionIncrementAttribute.class);
        ts.reset();
        reuse.length = 0;
        while (ts.incrementToken()) {
          int length = termAtt.length();
          if (length == 0) {
            throw new IllegalArgumentException("term: " + text + " analyzed to a zero-length token");
          }
          if (posIncAtt.getPositionIncrement() != 1) {
            throw new IllegalArgumentException("term: " + text + " analyzed to a token with posinc != 1");
          }
          reuse.grow(reuse.length + length + 1); /* current + word + separator */
          int end = reuse.offset + reuse.length;
          if (reuse.length > 0) {
            reuse.chars[end++] = SynonymMap.WORD_SEPARATOR;
            reuse.length++;
          }
          System.arraycopy(termAtt.buffer(), 0, reuse.chars, end, length);
          reuse.length += length;
        }
        ts.end();
      } catch (IOException e) {
        priorException = e;
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
129
130
131
  private String[] tokenizeDoc(String doc) throws IOException {
    Collection<String> result = new LinkedList<String>();
    for (String textFieldName : textFieldNames) {
      TokenStream tokenStream = analyzer.tokenStream(textFieldName, doc);
      try {
        CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
        tokenStream.reset();
        while (tokenStream.incrementToken()) {
          result.add(charTermAttribute.toString());
        }
        tokenStream.end();
      } finally {
        IOUtils.closeWhileHandlingException(tokenStream);
      }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
  public void testDefaults() throws IOException {
    assertTrue(stop != null);
    TokenStream stream = stop.tokenStream("test", "This is a test of the english stop analyzer");
    try {
      assertTrue(stream != null);
      CharTermAttribute termAtt = stream.getAttribute(CharTermAttribute.class);
      stream.reset();
   
      while (stream.incrementToken()) {
        assertFalse(inValidTokens.contains(termAtt.toString()));
      }
      stream.end();
    } finally {
      IOUtils.closeWhileHandlingException(stream);
    }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
    CharArraySet stopWordsSet = new CharArraySet(TEST_VERSION_CURRENT, asSet("good", "test", "analyzer"), false);
    StopAnalyzer newStop = new StopAnalyzer(Version.LUCENE_40, stopWordsSet);
    TokenStream stream = newStop.tokenStream("test", "This is a good test of the english stop analyzer");
    try {
      assertNotNull(stream);
      CharTermAttribute termAtt = stream.getAttribute(CharTermAttribute.class);
   
      stream.reset();
      while (stream.incrementToken()) {
        String text = termAtt.toString();
        assertFalse(stopWordsSet.contains(text));
      }
      stream.end();
    } finally {
      IOUtils.closeWhileHandlingException(stream);
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
    int expectedIncr[] =  { 1,   1, 1,          3, 1,  1,      1,            2,   1};
    TokenStream stream = newStop.tokenStream("test", s);
    try {
      assertNotNull(stream);
      int i = 0;
      CharTermAttribute termAtt = stream.getAttribute(CharTermAttribute.class);
      PositionIncrementAttribute posIncrAtt = stream.addAttribute(PositionIncrementAttribute.class);

      stream.reset();
      while (stream.incrementToken()) {
        String text = termAtt.toString();
        assertFalse(stopWordsSet.contains(text));
        assertEquals(expectedIncr[i++],posIncrAtt.getPositionIncrement());
      }
      stream.end();
    } finally {
View Full Code Here
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
        @Override
        protected Object highlight(String text, Set<String> matchedTokens, String prefixToken) throws IOException {
          TokenStream ts = queryAnalyzer.tokenStream("text", new StringReader(text));
          try {
            CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
            OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
            ts.reset();
            List<LookupHighlightFragment> fragments = new ArrayList<LookupHighlightFragment>();
            int upto = 0;
            while (ts.incrementToken()) {
              String token = termAtt.toString();
              int startOffset = offsetAtt.startOffset();
              int endOffset = offsetAtt.endOffset();
              if (upto < startOffset) {
                fragments.add(new LookupHighlightFragment(text.substring(upto, startOffset), false));
                upto = startOffset;
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
  /**
   * TODO: rewrite tests not to use string comparison.
   */
  private static String tsToString(TokenStream in) throws IOException {
    StringBuilder out = new StringBuilder();
    CharTermAttribute termAtt = in.addAttribute(CharTermAttribute.class);
    // extra safety to enforce, that the state is not preserved and also
    // assign bogus values
    in.clearAttributes();
    termAtt.setEmpty().append("bogusTerm");
    in.reset();
    while (in.incrementToken()) {
      if (out.length() > 0)
        out.append(' ');
      out.append(termAtt.toString());
      in.clearAttributes();
      termAtt.setEmpty().append("bogusTerm");
    }

    in.close();
    return out.toString();
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
    PerFieldAnalyzerWrapper analyzer =
              new PerFieldAnalyzerWrapper(new WhitespaceAnalyzer(TEST_VERSION_CURRENT), analyzerPerField);

    TokenStream tokenStream = analyzer.tokenStream("field", text);
    try {
      CharTermAttribute termAtt = tokenStream.getAttribute(CharTermAttribute.class);
      tokenStream.reset();

      assertTrue(tokenStream.incrementToken());
      assertEquals("WhitespaceAnalyzer does not lowercase",
                 "Qwerty",
                 termAtt.toString());
      assertFalse(tokenStream.incrementToken());
      tokenStream.end();
    } finally {
      IOUtils.closeWhileHandlingException(tokenStream);
    }

    tokenStream = analyzer.tokenStream("special", text);
    try {
      CharTermAttribute termAtt = tokenStream.getAttribute(CharTermAttribute.class);
      tokenStream.reset();

      assertTrue(tokenStream.incrementToken());
      assertEquals("SimpleAnalyzer lowercases",
                 "qwerty",
                 termAtt.toString());
      assertFalse(tokenStream.incrementToken());
      tokenStream.end();
    } finally {
      IOUtils.closeWhileHandlingException(tokenStream);
    }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.tokenattributes.CharTermAttribute

  • com.chenlb.mmseg4j.analysis.TokenUtils
  • com.code972.elasticsearch.rest.action.RestHebrewAnalyzerCheckWordAction
  • com.digitalpebble.behemoth.mahout.LuceneTokenizerMapper
  • com.gentics.cr.lucene.analysis.CustomPatternAnalyzerTest
  • com.ikanow.infinit.e.api.knowledge.SearchHandler
  • com.livingsocial.hive.udf.Tokenize
  • com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer
  • com.mozilla.grouperfish.pig.eval.text.NGramTokenize
  • com.mozilla.grouperfish.pig.eval.text.Tokenize
  • ivory.core.tokenize.LuceneArabicAnalyzer
    • 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.