Package org.apache.lucene.analysis.tokenattributes

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

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
    BooleanQuery bq=new BooleanQuery(DOMUtils.getAttribute(e,"disableCoord",false));
    bq.setMinimumNumberShouldMatch(DOMUtils.getAttribute(e,"minimumNumberShouldMatch",0));
    try
    {
      TokenStream ts = analyzer.reusableTokenStream(fieldName, new StringReader(text));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      Term term = null;
      ts.reset();
      while (ts.incrementToken()) {
        if (term == null)
        {
          term = new Term(fieldName, termAtt.toString());
        } else
        {
//           create from previous to save fieldName.intern overhead
          term = term.createTerm(termAtt.toString());
        }
        bq.add(new BooleanClause(new TermQuery(term),BooleanClause.Occur.SHOULD));
      }
      ts.end();
      ts.close();
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
    String fieldName = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
   
    try
    {
      TokenStream ts = analyzer.reusableTokenStream(fieldName, new StringReader(text));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      Term term = null;
      ts.reset();
        while (ts.incrementToken()) {
        if (term == null)
        {
          term = new Term(fieldName, termAtt.toString());
        } else
        {
//           create from previous to save fieldName.intern overhead
          term = term.createTerm(termAtt.toString());
        }
        tf.addTerm(term);
      }
      ts.end();
      ts.close();
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
        for (int i = 0; i < fields.length; i++)
            {
                try
                {
                  TokenStream ts = analyzer.reusableTokenStream(fields[i],new StringReader(stopWords));
                  CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
                  ts.reset();
                  while(ts.incrementToken()) {
                      stopWordsSet.add(termAtt.toString());
                  }
                  ts.end();
                  ts.close();
                }
                catch(IOException ioe)
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
   
    private void addTerms(IndexReader reader,FieldVals f) throws IOException
    {
        if(f.queryString==null) return;
        TokenStream ts=analyzer.reusableTokenStream(f.fieldName,new StringReader(f.queryString));
        CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
       
        int corpusNumDocs=reader.numDocs();
        Term internSavingTemplateTerm =new Term(f.fieldName); //optimization to avoid constructing new Term() objects
        HashSet<String> processedTerms=new HashSet<String>();
        ts.reset();
        while (ts.incrementToken())
        {
                String term = termAtt.toString();
          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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
   
    try
    {
      ArrayList<SpanQuery> clausesList=new ArrayList<SpanQuery>();
      TokenStream ts=analyzer.reusableTokenStream(fieldName,new StringReader(value));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
     
      ts.reset();
      while (ts.incrementToken()) {
          SpanTermQuery stq=new SpanTermQuery(new Term(fieldName, termAtt.toString()));
          clausesList.add(stq);
      }
      ts.end();
      ts.close();
      SpanOrQuery soq=new SpanOrQuery(clausesList.toArray(new SpanQuery[clausesList.size()]));
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
  }
 
  private void doTestStopPositons(StopFilter stpf, boolean enableIcrements) throws IOException {
    log("---> test with enable-increments-"+(enableIcrements?"enabled":"disabled"));
    stpf.setEnablePositionIncrements(enableIcrements);
    CharTermAttribute termAtt = stpf.getAttribute(CharTermAttribute.class);
    PositionIncrementAttribute posIncrAtt = stpf.getAttribute(PositionIncrementAttribute.class);
    stpf.reset();
    for (int i=0; i<20; i+=3) {
      assertTrue(stpf.incrementToken());
      log("Token "+i+": "+stpf);
      String w = English.intToEnglish(i).trim();
      assertEquals("expecting token "+i+" to be "+w,w,termAtt.toString());
      assertEquals("all but first token must have position increment of 3",enableIcrements?(i==0?1:3):1,posIncrAtt.getPositionIncrement());
    }
    assertFalse(stpf.incrementToken());
    stpf.end();
    stpf.close();
View Full Code Here
891
892
893
894
895
896
897
898
899
900
901
902
903
904
    throws IOException
  {
       TokenStream ts = analyzer.reusableTokenStream(fieldName, r);
      int tokenCount=0;
      // for every token
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      ts.reset();
      while (ts.incrementToken()) {
        String word = termAtt.toString();
        tokenCount++;
        if(tokenCount>maxNumTokensParsed)
        {
          break;
        }
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
                      String field,
                      Set<?> stop)
                      throws IOException
  { 
    TokenStream ts = a.reusableTokenStream( field, new StringReader( body));
    CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
   
    BooleanQuery tmp = new BooleanQuery();
    Set<String> already = new HashSet<String>(); // ignore dups
    while (ts.incrementToken()) {
      String word = termAtt.toString();
      // ignore opt stop words
      if ( stop != null &&
         stop.contains( word)) continue;
      // ignore dups
      if ( ! already.add( word)) continue;
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
        List<String> terms = new ArrayList<String>();
        try {
          boolean hasMoreTokens = false;
         
          stream.reset();
          final CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);

          hasMoreTokens = stream.incrementToken();
          while (hasMoreTokens) {
            terms.add(termAtt.toString());
            hasMoreTokens = stream.incrementToken();
          }
          processTerms(terms.toArray(new String[terms.size()]));
        } catch (IOException e) {
        }
View Full Code Here
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
      HashMap<String,ArrayIntList> terms = new HashMap<String,ArrayIntList>();
      int numTokens = 0;
      int numOverlapTokens = 0;
      int pos = -1;
     
      CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
      PositionIncrementAttribute posIncrAttribute = stream.addAttribute(PositionIncrementAttribute.class);
      OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
      stream.reset();
      while (stream.incrementToken()) {
        String term = termAtt.toString();
        if (term.length() == 0) continue; // nothing to do
//        if (DEBUG) System.err.println("token='" + term + "'");
        numTokens++;
        final int posIncr = posIncrAttribute.getPositionIncrement();
        if (posIncr == 0)
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.