Package org.apache.lucene.analysis.tokenattributes

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

625
626
627
628
629
630
631
632
633
634
635
636
637
638
            }
          }
          IOException priorException = null;
          TokenStream ts = analyzer.tokenStream("ignore", term);
          try {
            CharTermAttribute termAttr = ts.addAttribute(CharTermAttribute.class);
            ts.reset();
            while(ts.incrementToken()) {
              String text = termAttr.toString();
              doc.add(text);
              sb.append(text).append(' ');
            }
            ts.end();
          } catch (IOException e) {
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
 
  private void assertCollatesToSame(TokenStream stream1, TokenStream stream2)
      throws IOException {
    stream1.reset();
    stream2.reset();
    CharTermAttribute term1 = stream1
        .addAttribute(CharTermAttribute.class);
    CharTermAttribute term2 = stream2
        .addAttribute(CharTermAttribute.class);
    assertTrue(stream1.incrementToken());
    assertTrue(stream2.incrementToken());
    assertEquals(term1.toString(), term2.toString());
    assertFalse(stream1.incrementToken());
    assertFalse(stream2.incrementToken());
    stream1.end();
    stream2.end();
    stream1.close();
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
      ("Des mot clés À LA CHAÎNE À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï IJ Ð Ñ"
      +" Ò Ó Ô Õ Ö Ø Œ Þ Ù Ú Û Ü Ý Ÿ à á â ã ä å æ ç è é ê ë ì í î ï ij"
      +" ð ñ ò ó ô õ ö ø œ ß þ ù ú û ü ý ÿ fi fl"), MockTokenizer.WHITESPACE, false);
    ASCIIFoldingFilter filter = new ASCIIFoldingFilter(stream);

    CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
    filter.reset();
    assertTermEquals("Des", filter, termAtt);
    assertTermEquals("mot", filter, termAtt);
    assertTermEquals("cles", filter, termAtt);
    assertTermEquals("A", filter, termAtt);
View Full Code Here
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
      expectedOutputTokens.add(expected.toString());
    }

    TokenStream stream = new MockTokenizer(new StringReader(inputText.toString()), MockTokenizer.WHITESPACE, false);
    ASCIIFoldingFilter filter = new ASCIIFoldingFilter(stream);
    CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
    Iterator<String> expectedIter = expectedOutputTokens.iterator();
    filter.reset();
    while (expectedIter.hasNext()) {
      assertTermEquals(expectedIter.next(), filter, termAtt);
    }
View Full Code Here
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
    TokenStream ts = null;
    try {
      ts = queryAnalyzer.tokenStream("", new StringReader(key.toString()));
      //long t0 = System.currentTimeMillis();
      ts.reset();
      final CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      final OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
      String lastToken = null;
      BooleanQuery query = new BooleanQuery();
      int maxEndOffset = -1;
      final Set<String> matchedTokens = new HashSet<String>();
      while (ts.incrementToken()) {
        if (lastToken != null) { 
          matchedTokens.add(lastToken);
          query.add(new TermQuery(new Term(TEXT_FIELD_NAME, lastToken)), occur);
        }
        lastToken = termAtt.toString();
        if (lastToken != null) {
          maxEndOffset = Math.max(maxEndOffset, offsetAtt.endOffset());
        }
      }
      ts.end();
View Full Code Here
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
   *  result is set on each {@link
   *  LookupResult#highlightKey} member. */
  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();
      StringBuilder sb = new StringBuilder();
      int upto = 0;
      while (ts.incrementToken()) {
        String token = termAtt.toString();
        int startOffset = offsetAtt.startOffset();
        int endOffset = offsetAtt.endOffset();
        if (upto < startOffset) {
          addNonMatch(sb, text.substring(upto, startOffset));
          upto = startOffset;
View Full Code Here
242
243
244
245
246
247
248
249
250
251
252
        System.out.println("\nTEST: iter=" + i);
      }
      String s = _TestUtil.randomUnicodeString(random(), 100);
      TokenStream ts = analyzer.tokenStream("foo", s);
      try {
        CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
        ts.reset();
        while (ts.incrementToken()) {
          assertTrue(UnicodeUtil.validUTF16String(termAtt));
        }
        ts.end();
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
  // we only check a few core attributes here.
  // TODO: test other things
  public void assertEquals(String s, TokenStream left, TokenStream right) throws Exception {
    left.reset();
    right.reset();
    CharTermAttribute leftTerm = left.addAttribute(CharTermAttribute.class);
    CharTermAttribute rightTerm = right.addAttribute(CharTermAttribute.class);
    OffsetAttribute leftOffset = left.addAttribute(OffsetAttribute.class);
    OffsetAttribute rightOffset = right.addAttribute(OffsetAttribute.class);
    PositionIncrementAttribute leftPos = left.addAttribute(PositionIncrementAttribute.class);
    PositionIncrementAttribute rightPos = right.addAttribute(PositionIncrementAttribute.class);
   
    while (left.incrementToken()) {
      assertTrue("wrong number of tokens for input: " + s, right.incrementToken());
      assertEquals("wrong term text for input: " + s, leftTerm.toString(), rightTerm.toString());
      assertEquals("wrong position for input: " + s, leftPos.getPositionIncrement(), rightPos.getPositionIncrement());
      assertEquals("wrong start offset for input: " + s, leftOffset.startOffset(), rightOffset.startOffset());
      assertEquals("wrong end offset for input: " + s, leftOffset.endOffset(), rightOffset.endOffset());
    };
    assertFalse("wrong number of tokens for input: " + s, right.incrementToken());
View Full Code Here
183
184
185
186
187
188
189
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
    throws IOException, InvalidTokenOffsetsException
  {
    ArrayList<TextFragment> docFrags = new ArrayList<TextFragment>();
    StringBuilder newText=new StringBuilder();

    CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
    tokenStream.reset();
    TextFragment currentFrag =  new TextFragment(newText,newText.length(), docFrags.size());

    if (fragmentScorer instanceof QueryScorer) {
      ((QueryScorer) fragmentScorer).setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
    }
   
    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.toString()
              +" exceeds length of provided text sized "+text.length());
        }
        if((tokenGroup.numTokens>0)&&(tokenGroup.isDistinct()))
        {
          //the current token is distinct from previous tokens -
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
    int numIterations = atLeast(1000);
    for (int i = 0; i < numIterations; i++) {
      String s = _TestUtil.randomUnicodeString(random(), 100);
      TokenStream ts = analyzer.tokenStream("foo", s);
      try {
        CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
        ts.reset();
        while (ts.incrementToken()) {
          assertTrue(UnicodeUtil.validUTF16String(termAtt));
        }
        ts.end();
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.