Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.KeywordTokenizer.reset()

191
192
193
194
195
196
197
198
199
200
201
    final int maxGram = _TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new NGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int start = 0; start < codePointCount; ++start) {
      for (int end = start + minGram; end <= Math.min(codePointCount, start + maxGram); ++end) {
        assertTrue(tk.incrementToken());
        assertEquals(0, offsetAtt.startOffset());
        assertEquals(s.length(), offsetAtt.endOffset());
View Full Code Here
279
280
281
282
283
284
285
286
287
288
289
    final int maxGram = _TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int i = minGram; i <= Math.min(codePointCount, maxGram); ++i) {
      assertTrue(tk.incrementToken());
      assertEquals(0, offsetAtt.startOffset());
      assertEquals(s.length(), offsetAtt.endOffset());
      final int end = Character.offsetByCodePoints(s, 0, i);
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
      int max = _TestUtil.nextInt(random(), 0, 100);
      int count = text.codePointCount(0, text.length());
      boolean expected = count >= min && count <= max;
      TokenStream stream = new KeywordTokenizer(new StringReader(text));
      stream = new CodepointCountFilter(TEST_VERSION_CURRENT, stream, min, max);
      stream.reset();
      assertEquals(expected, stream.incrementToken());
      stream.end();
      stream.close();
    }
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
        max = temp;
      }
      boolean expected = count >= min && count <= max;
      TokenStream stream = new KeywordTokenizer(new StringReader(text));
      stream = new CodepointCountFilter(TEST_VERSION_CURRENT, stream, min, max);
      stream.reset();
      assertEquals(expected, stream.incrementToken());
      stream.end();
      stream.close();
    }
  }
View Full Code Here
279
280
281
282
283
284
285
286
287
288
289
    final int maxGram = TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int i = minGram; i <= Math.min(codePointCount, maxGram); ++i) {
      assertTrue(tk.incrementToken());
      assertEquals(0, offsetAtt.startOffset());
      assertEquals(s.length(), offsetAtt.endOffset());
      final int end = Character.offsetByCodePoints(s, 0, i);
View Full Code Here
191
192
193
194
195
196
197
198
199
200
201
    final int maxGram = TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new NGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int start = 0; start < codePointCount; ++start) {
      for (int end = start + minGram; end <= Math.min(codePointCount, start + maxGram); ++end) {
        assertTrue(tk.incrementToken());
        assertEquals(0, offsetAtt.startOffset());
        assertEquals(s.length(), offsetAtt.endOffset());
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
  public void testCustomAttribute() throws IOException {
    TokenStream stream = new KeywordTokenizer(new StringReader("D'Angelo"));
    stream = new PatternKeywordMarkerFilter(stream, Pattern.compile(".*"));
    stream = new BeiderMorseFilter(stream, new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true));
    KeywordAttribute keyAtt = stream.addAttribute(KeywordAttribute.class);
    stream.reset();
    int i = 0;
    while(stream.incrementToken()) {
      assertTrue(keyAtt.isKeyword());
      i++;
    }
View Full Code Here
275
276
277
278
279
280
281
282
283
284
285
    final int maxGram = _TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int i = minGram; i <= Math.min(codePointCount, maxGram); ++i) {
      assertTrue(tk.incrementToken());
      assertEquals(0, offsetAtt.startOffset());
      assertEquals(s.length(), offsetAtt.endOffset());
      final int end = Character.offsetByCodePoints(s, 0, i);
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
    final int maxGram = _TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new NGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int start = 0; start < codePointCount; ++start) {
      for (int end = start + minGram; end <= Math.min(codePointCount, start + maxGram); ++end) {
        assertTrue(tk.incrementToken());
        assertEquals(0, offsetAtt.startOffset());
        assertEquals(s.length(), offsetAtt.endOffset());
View Full Code Here
280
281
282
283
284
285
286
287
288
289
290
    final int maxGram = _TestUtil.nextInt(random(), minGram, 10);
    TokenStream tk = new KeywordTokenizer(new StringReader(s));
    tk = new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, tk, minGram, maxGram);
    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int i = minGram; i <= Math.min(codePointCount, maxGram); ++i) {
      assertTrue(tk.incrementToken());
      assertEquals(0, offsetAtt.startOffset());
      assertEquals(s.length(), offsetAtt.endOffset());
      final int end = Character.offsetByCodePoints(s, 0, i);
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.