Package org.apache.lucene.analysis.tokenattributes

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

43
44
45
46
47
48
49
50
51
52
53
54
55
    assertFalse(ts.incrementToken());
  }


  private void assertNext(TokenStream ts, String text, int startOffset, int endOffset) throws IOException {
    TermAttribute termAtt = (TermAttribute) ts.addAttribute(TermAttribute.class);
    OffsetAttribute offsetAtt = (OffsetAttribute) ts.addAttribute(OffsetAttribute.class);

    assertTrue(ts.incrementToken());
    assertEquals(text, termAtt.term());
    assertEquals(startOffset, offsetAtt.startOffset());
    assertEquals(endOffset, offsetAtt.endOffset());
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
    assertFalse(ts.incrementToken());
  }


  private void assertNext(TokenStream ts, String text, int startOffset, int endOffset) throws IOException {
    TermAttribute termAtt = (TermAttribute) ts.addAttribute(TermAttribute.class);
    OffsetAttribute offsetAtt = (OffsetAttribute) ts.addAttribute(OffsetAttribute.class);

    assertTrue(ts.incrementToken());
    assertEquals(text, termAtt.term());
    assertEquals(startOffset, offsetAtt.startOffset());
    assertEquals(endOffset, offsetAtt.endOffset());
  }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
      wlist.add(tmpBuffer.toString());
    }

    // get Analyzer from superclass and tokenize the term
    TokenStream source = getAnalyzer().tokenStream(field, new StringReader(termStr));
    TermAttribute termAtt = (TermAttribute) source.addAttribute(TermAttribute.class);
   
    int countTokens = 0;
    while (true) {
      try {
        if (!source.incrementToken()) break;
      } catch (IOException e) {
        break;
      }
      String term = termAtt.term();
      if (!"".equals(term)) {
        try {
          tlist.set(countTokens++, term);
        } catch (IndexOutOfBoundsException ioobe) {
          countTokens = -1;
View Full Code Here
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
   */
  protected Query getPrefixQuery(String field, String termStr) throws ParseException {
    // get Analyzer from superclass and tokenize the term
    TokenStream source = getAnalyzer().tokenStream(field, new StringReader(termStr));
    List tlist = new ArrayList();
    TermAttribute termAtt = (TermAttribute) source.addAttribute(TermAttribute.class);
   
    while (true) {
      try {
        if (!source.incrementToken()) break;
      } catch (IOException e) {
        break;
      }
      tlist.add(termAtt.term());
    }

    try {
      source.close();
    } catch (IOException e) {
View Full Code Here
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
   */
  protected Query getFuzzyQuery(String field, String termStr, float minSimilarity)
      throws ParseException {
    // get Analyzer from superclass and tokenize the term
    TokenStream source = getAnalyzer().tokenStream(field, new StringReader(termStr));
    TermAttribute termAtt = (TermAttribute) source.addAttribute(TermAttribute.class);
    String nextToken = null;
    boolean multipleTokens = false;
   
    try {
      if (source.incrementToken()) {
        nextToken = termAtt.term();
      }
      multipleTokens = source.incrementToken();
    } catch (IOException e) {
      nextToken = null;
    }
View Full Code Here
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
   */
  protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive)
      throws ParseException {
    // get Analyzer from superclass and tokenize the terms
    TokenStream source = getAnalyzer().tokenStream(field, new StringReader(part1));
    TermAttribute termAtt = (TermAttribute) source.addAttribute(TermAttribute.class);
    boolean multipleTokens = false;

    // part1
    try {
      if (source.incrementToken()) {
        part1 = termAtt.term();
      }
      multipleTokens = source.incrementToken();
    } catch (IOException e) {
      // ignore
    }
    try {
      source.close();
    } catch (IOException e) {
      // ignore
    }
    if (multipleTokens) {
      throw new ParseException("Cannot build RangeQuery with analyzer " + getAnalyzer().getClass()
          + " - tokens were added to part1");
    }

    // part2
    source = getAnalyzer().tokenStream(field, new StringReader(part2));
    termAtt = (TermAttribute) source.addAttribute(TermAttribute.class);
   
    try {
      if (source.incrementToken()) {
        part2 = termAtt.term();
      }
      multipleTokens = source.incrementToken();
    } catch (IOException e) {
      // ignore
    }
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
   
    private void addTerms(IndexReader reader,FieldVals f) throws IOException
    {
        if(f.queryString==null) return;
        TokenStream ts=analyzer.tokenStream(f.fieldName,new StringReader(f.queryString));
        TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
       
        int corpusNumDocs=reader.numDocs();
        Term internSavingTemplateTerm =new Term(f.fieldName); //optimization to avoid constructing new Term() objects
        HashSet<String> processedTerms=new HashSet<String>();
        while (ts.incrementToken())
        {
                String term = termAtt.term();
          if(!processedTerms.contains(term))
          {
            processedTerms.add(term);
                ScoreTermQueue variantsQ=new ScoreTermQueue(MAX_VARIANTS_PER_TERM); //maxNum variants considered for any one term
                float minScore=0;
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
    BooleanQuery bq=new BooleanQuery(DOMUtils.getAttribute(e,"disableCoord",false));
    bq.setMinimumNumberShouldMatch(DOMUtils.getAttribute(e,"minimumNumberShouldMatch",0));
    TokenStream ts = analyzer.tokenStream(fieldName, new StringReader(text));
    try
    {
      TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
      Term term = null;
      while (ts.incrementToken()) {
        if (term == null)
        {
          term = new Term(fieldName, termAtt.term());
        } else
        {
//           create from previous to save fieldName.intern overhead
          term = term.createTerm(termAtt.term());
        }
        bq.add(new BooleanClause(new TermQuery(term),BooleanClause.Occur.SHOULD));
      }
    }
    catch (IOException ioe)
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
      wlist.add(tmpBuffer.toString());
    }

    // get Analyzer from superclass and tokenize the term
    TokenStream source = getAnalyzer().tokenStream(field, new StringReader(termStr));
    TermAttribute termAtt = source.addAttribute(TermAttribute.class);
   
    int countTokens = 0;
    while (true) {
      try {
        if (!source.incrementToken()) break;
      } catch (IOException e) {
        break;
      }
      String term = termAtt.term();
      if (!"".equals(term)) {
        try {
          tlist.set(countTokens++, term);
        } catch (IndexOutOfBoundsException ioobe) {
          countTokens = -1;
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
  @Override
  protected Query getPrefixQuery(String field, String termStr) throws ParseException {
    // get Analyzer from superclass and tokenize the term
    TokenStream source = getAnalyzer().tokenStream(field, new StringReader(termStr));
    List<String> tlist = new ArrayList<String>();
    TermAttribute termAtt = source.addAttribute(TermAttribute.class);
   
    while (true) {
      try {
        if (!source.incrementToken()) break;
      } catch (IOException e) {
        break;
      }
      tlist.add(termAtt.term());
    }

    try {
      source.close();
    } catch (IOException e) {
View Full Code Here
TOP

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

  • com.alimama.mdrill.index.IndexReducer
  • com.flaptor.indextank.query.IndexEngineParser
  • com.jayway.mongodb.AnalyzedDBObject
  • com.senseidb.search.query.TextQueryConstructor
  • edu.wiki.search.ESASearcher
  • it.unibz.instasearch.indexing.StorageIndexer
  • lucli.LuceneMethods
  • mia.classifier.ch14.TokenizingAndVectorizingText
  • mia.clustering.ch09.MyAnalyzer
  • mia.clustering.ch12.TwitterAnalyzer
    • 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.