Package org.apache.lucene.analysis.tokenattributes

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

339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
      int numOverlapTokens = 0;
      int pos = -1;
     
      TermAttribute termAtt = stream.addAttribute(TermAttribute.class);
      PositionIncrementAttribute posIncrAttribute = stream.addAttribute(PositionIncrementAttribute.class);
      OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
     
      stream.reset();
      while (stream.incrementToken()) {
        String term = termAtt.term();
        if (term.length() == 0) continue; // nothing to do
//        if (DEBUG) System.err.println("token='" + term + "'");
        numTokens++;
        final int posIncr = posIncrAttribute.getPositionIncrement();
        if (posIncr == 0)
          numOverlapTokens++;
        pos += posIncr;
       
        ArrayIntList positions = terms.get(term);
        if (positions == null) { // term not seen before
          positions = new ArrayIntList(stride);
          terms.put(term, positions);
        }
        if (stride == 1) {
          positions.add(pos);
        } else {
          positions.add(pos, offsetAtt.startOffset(), offsetAtt.endOffset());
        }
      }
      stream.end();

      // ensure infos.numTokens > 0 invariant; needed for correct operation of terms()
View Full Code Here
88
89
90
91
92
93
94
95
96
97
  }

  // LUCENE-1441
  public void testOffsets() throws Exception {
    TokenStream stream = new KeywordAnalyzer().tokenStream("field", new StringReader("abcd"));
    OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
    assertTrue(stream.incrementToken());
    assertEquals(0, offsetAtt.startOffset());
    assertEquals(4, offsetAtt.endOffset());
  }
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
  {
    ArrayList<TextFragment> docFrags = new ArrayList<TextFragment>();
    StringBuilder newText=new StringBuilder();
   
      TermAttribute termAtt = tokenStream.addAttribute(TermAttribute.class);
      OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
      tokenStream.addAttribute(PositionIncrementAttribute.class);
      tokenStream.reset();
     
    TextFragment currentFrag =  new TextFragment(newText,newText.length(), docFrags.size());
    TokenStream newStream = fragmentScorer.init(tokenStream);
    if(newStream != null) {
      tokenStream = newStream;
    }
    fragmentScorer.startFragment(currentFrag);
    docFrags.add(currentFrag);

    FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);

    try
    {

      String tokenText;
      int startOffset;
      int endOffset;
      int lastEndOffset = 0;
      textFragmenter.start(text, tokenStream);

      TokenGroup tokenGroup=new TokenGroup(tokenStream);

      for (boolean next = tokenStream.incrementToken(); next && (offsetAtt.startOffset()< maxDocCharsToAnalyze);
            next = tokenStream.incrementToken())
      {
        if(  (offsetAtt.endOffset()>text.length())
          ||
          (offsetAtt.startOffset()>text.length())
          )           
        {
          throw new InvalidTokenOffsetsException("Token "+ termAtt.term()
              +" exceeds length of provided text sized "+text.length());
        }
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
    final int minGram = _TestUtil.nextInt(random(), 1, 3);
    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());
        final int startIndex = Character.offsetByCodePoints(s, 0, start);
        final int endIndex = Character.offsetByCodePoints(s, 0, end);
        assertEquals(s.substring(startIndex, endIndex), termAtt.toString());
      }
    }
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
      }
    };
    final CharTermAttribute termAtt = grams.addAttribute(CharTermAttribute.class);
    final PositionIncrementAttribute posIncAtt = grams.addAttribute(PositionIncrementAttribute.class);
    final PositionLengthAttribute posLenAtt = grams.addAttribute(PositionLengthAttribute.class);
    final OffsetAttribute offsetAtt = grams.addAttribute(OffsetAttribute.class);
    grams.reset();
    for (int start = 0; start < codePoints.length; ++start) {
      nextGram:
      for (int end = start + minGram; end <= start + maxGram && end <= codePoints.length; ++end) {
        if (edgesOnly && start > 0 && isTokenChar(nonTokenChars, codePoints[start - 1])) {
          // not on an edge
          continue nextGram;
        }
        for (int j = start; j < end; ++j) {
          if (!isTokenChar(nonTokenChars, codePoints[j])) {
            continue nextGram;
          }
        }
        assertTrue(grams.incrementToken());
        assertArrayEquals(Arrays.copyOfRange(codePoints, start, end), toCodePoints(termAtt));
        assertEquals(1, posIncAtt.getPositionIncrement());
        assertEquals(1, posLenAtt.getPositionLength());
        assertEquals(offsets[start], offsetAtt.startOffset());
        assertEquals(offsets[end], offsetAtt.endOffset());
      }
    }
    assertFalse(grams.incrementToken());
    grams.end();
    assertEquals(s.length(), offsetAtt.startOffset());
    assertEquals(s.length(), offsetAtt.endOffset());
  }
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
136
137
    for (int i = 0; i < num; i++) {
      String s = _TestUtil.randomUnicodeString(random());
      TokenStream ts = analyzer.tokenStream("foo", s);
      try {
        ts.reset();
        OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
        while (ts.incrementToken()) {
          String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
          for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
            cp = highlightedText.codePointAt(j);
            assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
          }
        }
View Full Code Here
166
167
168
169
170
171
172
173
174
175
176
177
178
    for (int i = 0; i < num; i++) {
      String s = _TestUtil.randomUnicodeString(random());
      TokenStream ts = analyzer.tokenStream("foo", s);
      try {
        ts.reset();
        OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
        while (ts.incrementToken()) {
          String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
          for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
            cp = highlightedText.codePointAt(j);
            assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
          }
        }
View Full Code Here
172
173
174
175
176
177
178
179
      return start + 31 * end;
    }

    @Override
    public void copyTo(AttributeImpl target) {
      OffsetAttribute t = (OffsetAttribute) target;
      t.setOffset(start, end);
    }
View Full Code Here
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
    final int minGram = _TestUtil.nextInt(random(), 1, 3);
    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);
      assertEquals(s.substring(0, end), termAtt.toString());
    }
    assertFalse(tk.incrementToken());
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
  @Test
  public void baseUIMAAnalyzerStreamTest() {
    try {
      TokenStream ts = analyzer.tokenStream("text", new StringReader("the big brown fox jumped on the wood"));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
      while (ts.incrementToken()) {
        assertNotNull(offsetAtt);
        assertNotNull(termAtt);
        System.out.println("token '" + termAtt.toString() + "' has offset " + offsetAtt.startOffset() + "," + offsetAtt.endOffset());
      }
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.getLocalizedMessage());
    }
View Full Code Here
TOP

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

  • com.chenlb.mmseg4j.analysis.TokenUtils
  • com.flaptor.indextank.query.IndexEngineParser
  • com.github.le11.nls.lucene.UIMABaseAnalyzerTest
  • com.github.le11.nls.lucene.UIMATypeAwareAnalyzerTest
  • com.o19s.RegexPathHierarchyTokenizerTest
  • com.tamingtext.texttamer.solr.NameFilterTest
  • com.tamingtext.texttamer.solr.SentenceTokenizerTest
  • com.tistory.devyongsik.crescent.admin.service.MorphServiceImpl
  • it.unibz.instasearch.indexing.StorageIndexer
  • me.shenfeng.mmseg.HashSetDictionaryTest
    • 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.