Package org.apache.lucene.index

Examples of org.apache.lucene.index.TermEnum.docFreq()

74
75
76
77
78
79
80
81
82
83
84
    TermEnum terms = reader.terms();
     
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = ((TermFreq)tiq.top()).docFreq; // reset minFreq
        }
      }
View Full Code Here
501
502
503
504
505
506
507
508
509
510
511
                    break;

                if (prefix != null && !t.text().startsWith(prefix))
                    break;

                int df = te.docFreq();

                // If we are sorting, we can use df>min (rather than >=) since we
                // are going in index order. For certain term distributions this can
                // make a large difference (for example, many terms with df=1).
                if (df > 0 && df > min) {
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
    TermFreqQueue tiq = new TermFreqQueue(count);
    TermEnum terms = reader.terms();
     
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = ((TermFreq)tiq.top()).docFreq; // reset minFreq
        }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
    TermEnum terms = reader.terms();
     
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = ((TermFreq)tiq.top()).docFreq; // reset minFreq
        }
      }
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
    TermFreqQueue tiq = new TermFreqQueue(count);
    TermEnum terms = reader.terms();
     
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = ((TermFreq)tiq.top()).docFreq; // reset minFreq
        }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
    TermEnum terms = reader.terms();
     
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = ((TermFreq)tiq.top()).docFreq; // reset minFreq
        }
      }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
    long time = System.currentTimeMillis();
    IndexReader ir = lis.getIndexReader();
    TermEnum termEnum = ir.terms();
    while(termEnum.next()) {
      Term t = termEnum.term();
      if(t.field().equals("txt") && termEnum.docFreq() > 20) queryList.add(t.text());
    }
    //queryList.addAll(lis.termsFromQuery(new TermQuery(new Term("txt", queryTerm))));
    System.out.println("All terms loaded: " + (System.currentTimeMillis() - time));
   
    time = System.currentTimeMillis();
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
    do {
      Term term = te.term();
      if (term == null || !term.field().equals(field)) {
        break;
      }
      int df = te.docFreq();
      if (df < minDf || df > percent) {
        continue;
      }
      TermEntry entry = new TermEntry(term.text(), count++, df);
      termEntries.put(entry.term, entry);
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
              // if we are past the upper term, or equal to it (when don't include upper) then stop.
              if (upperCmp>0 || (upperCmp==0 && !upperIncl)) break;
            }

            // This is a good term in the range.  Check if mincount/maxcount conditions are satisfied.
            int docFreq = termEnum.docFreq();
            if (docFreq >= freqmin && docFreq <= freqmax) {
              // add the term to the list
              String label = raw ? indexedText : ft.indexedToReadable(indexedText);
              if (sort) {
                queue.add(new CountPair<String, Integer>(label, docFreq));
View Full Code Here
252
253
254
255
256
257
258
259
260
261
262
      int result = 1;
      currentTerm = currentTerm.createTerm(term);
      try {
        TermEnum termEnum = reader.terms(currentTerm);
        if (termEnum != null && termEnum.term().equals(currentTerm)) {
          result = termEnum.docFreq();
        }
      } catch (IOException e) {
        throw new RuntimeException(e);
      }
      return result;
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.