Package org.apache.lucene.index

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

48
49
50
51
52
53
54
55
56
57
58
    do {
      Term term = te.term();
      if (term == null || term.field().equals(field) == false){
        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
137
138
139
140
141
142
143
144
145
146
147
                        Term t = terms.term();
                        if (t != null) {
                            currentTerm.setBase(t.text());
                            int compare = currentTerm.compareTo(termText);
                            if (compare == 0) {
                                orderedTerms.put(t, new Integer(terms.docFreq()));
                            } else if (compare < 0) {
                                // try next one
                            } else {
                                // compare > 0
                            }
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
    TermFreqQueue tiq = new TermFreqQueue(count);
    TermEnum terms = reader.terms();
     
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        TermFreq top = tiq.add(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = top.docFreq; // reset minFreq
        }
View Full Code Here
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) {
        TermFreq top = tiq.add(new TermFreq(terms.term(), terms.docFreq()));
        if (tiq.size() >= count) {                 // if tiq overfull
          tiq.pop();                              // remove lowest in tiq
          minFreq = top.docFreq; // reset minFreq
        }
      }
View Full Code Here
304
305
306
307
308
309
310
311
312
313
314
        }

        public int docFreq() {
            TermEnum terms = queue.peek();
            if (terms != null) {
                return terms.docFreq();
            }
            return 0;
        }

        public void close() throws IOException {
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
    Term term = te.term();
    while (term != null) {
      if (term.field() != internedFieldName) {
        break;
      }
      if (te.docFreq() > maxDocFreq) {
        stopWords.add(term.text());
      }
      if (!te.next()) {
        break;
      }
View Full Code Here
312
313
314
315
316
317
318
319
320
321
322
        break;
      }
      assertTrue(testTermEnum.next());

      assertEquals(aprioriTermEnum.term(), testTermEnum.term());
      assertTrue(aprioriTermEnum.docFreq() == testTermEnum.docFreq());

      // compare termDocs seeking

      TermDocs aprioriTermDocsSeeker = aprioriReader.termDocs(aprioriTermEnum.term());
      TermDocs testTermDocsSeeker = testReader.termDocs(testTermEnum.term());
View Full Code Here
202
203
204
205
206
207
208
209
210
211
212
                FuzzyTermEnum fe=new FuzzyTermEnum(reader,startTerm,f.minSimilarity,f.prefixLength);
                TermEnum origEnum = reader.terms(startTerm);
                int df=0;
                if(startTerm.equals(origEnum.term()))
                {
                    df=origEnum.docFreq(); //store the df so all variants use same idf
                }
                int numVariants=0;
                int totalVariantDocFreqs=0;
                do
                {
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
    TermEnum terms = reader.terms();

    if (field != null) {
      while (terms.next()) {
        if (terms.term().field().equals(field)) {
          tiq.insertWithOverflow(new TermInfo(terms.term(), terms.docFreq()));
        }
      }
    }
    else {
      while (terms.next()) {
View Full Code Here
518
519
520
521
522
523
524
525
526
527
528
      if (null == t || ! t.field().equals(field))
        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
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.