Package org.apache.lucene.analysis.tokenattributes

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

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
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
  }
 
  public void testFilterTokens() throws Exception {
    SnowballFilter filter = new SnowballFilter(new TestTokenStream(), "English");
    CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = filter.getAttribute(OffsetAttribute.class);
    TypeAttribute typeAtt = filter.getAttribute(TypeAttribute.class);
    PayloadAttribute payloadAtt = filter.getAttribute(PayloadAttribute.class);
    PositionIncrementAttribute posIncAtt = filter.getAttribute(PositionIncrementAttribute.class);
    FlagsAttribute flagsAtt = filter.getAttribute(FlagsAttribute.class);
   
    filter.incrementToken();

    assertEquals("accent", termAtt.toString());
    assertEquals(2, offsetAtt.startOffset());
    assertEquals(7, offsetAtt.endOffset());
    assertEquals("wrd", typeAtt.type());
    assertEquals(3, posIncAtt.getPositionIncrement());
    assertEquals(77, flagsAtt.getFlags());
    assertEquals(new BytesRef(new byte[]{0,1,2,3}), payloadAtt.getPayload());
  }
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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
  }

  private static void displayTokensWithFullDetails(TokenStream stream) throws IOException {
    final CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
    final PositionIncrementAttribute posIncr = stream.addAttribute(PositionIncrementAttribute.class);
    final OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
    final TypeAttribute type = stream.addAttribute(TypeAttribute.class);
    int position = 0;
    while (stream.incrementToken()) {
      final int increment = posIncr.getPositionIncrement();
      if (increment > 0) {
        position = position + increment;
        System.out.println();
        System.out.print(position + ": ");
      }
      System.out.print("[" + term.toString() + ":" + offset.startOffset() + "->"
          + offset.endOffset() + ":" + type.type() + "] ");
    }
    System.out.println();
  }
View Full Code Here
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
            new TreeMap<String, TermVectorOffsetInfo[]>();
        Reader r = new StringReader(text);
        TokenStream ts = index.getTextAnalyzer().tokenStream("", r);
        try {
            while (ts.incrementToken()) {
                OffsetAttribute offset = ts.getAttribute(OffsetAttribute.class);
                TermAttribute term = ts.getAttribute(TermAttribute.class);
                String termText = term.term();
                TermVectorOffsetInfo[] info = termMap.get(termText);
                if (info == null) {
                    info = new TermVectorOffsetInfo[1];
                } else {
                    TermVectorOffsetInfo[] tmp = info;
                    info = new TermVectorOffsetInfo[tmp.length + 1];
                    System.arraycopy(tmp, 0, info, 0, tmp.length);
                }
                info[info.length - 1] = new TermVectorOffsetInfo(
                    offset.startOffset(), offset.endOffset());
                termMap.put(termText, info);
            }
            ts.end();
            ts.close();
        } catch (IOException e) {
View Full Code Here
313
314
315
316
317
318
319
320
321
322
323
324
325
      record.put( "type", narrowedAttr.type() );
      return record;
    }
    else if ( attr instanceof OffsetAttribute ) {
      GenericRecord record = new GenericData.Record( protocol.getType( "OffsetAttribute" ) );
      OffsetAttribute narrowedAttr = (OffsetAttribute) attr;
      record.put( "startOffset", narrowedAttr.startOffset() );
      record.put( "endOffset", narrowedAttr.endOffset() );
      return record;
    }
    else if ( attr instanceof Serializable ) {
      return ByteBuffer.wrap( toByteArray( (Serializable) attr ) );
    }
View Full Code Here
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
            new TreeMap<String, TermVectorOffsetInfo[]>();
        Reader r = new StringReader(text);
        TokenStream ts = index.getTextAnalyzer().tokenStream("", r);
        try {
            while (ts.incrementToken()) {
                OffsetAttribute offset = ts.getAttribute(OffsetAttribute.class);
                TermAttribute term = ts.getAttribute(TermAttribute.class);
                String termText = term.term();
                TermVectorOffsetInfo[] info = termMap.get(termText);
                if (info == null) {
                    info = new TermVectorOffsetInfo[1];
                } else {
                    TermVectorOffsetInfo[] tmp = info;
                    info = new TermVectorOffsetInfo[tmp.length + 1];
                    System.arraycopy(tmp, 0, info, 0, tmp.length);
                }
                info[info.length - 1] = new TermVectorOffsetInfo(
                    offset.startOffset(), offset.endOffset());
                termMap.put(termText, info);
            }
            ts.end();
            ts.close();
        } catch (IOException e) {
View Full Code Here
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
        fieldInfos.put(fieldName,
            new FieldInfo(fieldName, true, fieldInfos.size(), false, false, false, this.storeOffsets ? IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS : IndexOptions.DOCS_AND_FREQS_AND_POSITIONS , null, null, null));
      }
      TermToBytesRefAttribute termAtt = stream.getAttribute(TermToBytesRefAttribute.class);
      PositionIncrementAttribute posIncrAttribute = stream.addAttribute(PositionIncrementAttribute.class);
      OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
      BytesRef ref = termAtt.getBytesRef();
      stream.reset();
     
      while (stream.incrementToken()) {
        termAtt.fillBytesRef();
//        if (DEBUG) System.err.println("token='" + term + "'");
        numTokens++;
        final int posIncr = posIncrAttribute.getPositionIncrement();
        if (posIncr == 0)
          numOverlapTokens++;
        pos += posIncr;
        int ord = terms.add(ref);
        if (ord < 0) {
          ord = (-ord) - 1;
          postingsWriter.reset(sliceArray.end[ord]);
        } else {
          sliceArray.start[ord] = postingsWriter.startNewSlice();
        }
        sliceArray.freq[ord]++;
        sumTotalTermFreq++;
        if (!storeOffsets) {
          postingsWriter.writeInt(pos);
        } else {
          postingsWriter.writeInt(pos);
          postingsWriter.writeInt(offsetAtt.startOffset());
          postingsWriter.writeInt(offsetAtt.endOffset());
        }
        sliceArray.end[ord] = postingsWriter.getCurrentOffset();
      }
      stream.end();
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
        String s = "a天b";
        ChineseTokenizer tokenizer = new ChineseTokenizer(new StringReader(s));

        int correctStartOffset = 0;
        int correctEndOffset = 1;
        OffsetAttribute offsetAtt = tokenizer.getAttribute(OffsetAttribute.class);
        while (tokenizer.incrementToken()) {
          assertEquals(correctStartOffset, offsetAtt.startOffset());
          assertEquals(correctEndOffset, offsetAtt.endOffset());
          correctStartOffset++;
          correctEndOffset++;
        }
    }
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.