Package org.apache.lucene.index

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

128
129
130
131
132
133
134
135
136
137
138
    {
      Term currTerm=te.term();
     
      while((currTerm!=null)&&(currTerm.field()==startTerm.field())) //term fieldnames are interned
      {
        if(te.docFreq()>1)
        {
          int lastDoc=-1;
          //unset potential duplicates
          TermDocs td = reader.termDocs(currTerm);
          td.next();
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
                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
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
267
268
269
270
271
272
273
274
275
276
277
      Term t = te.term();

      if (null == t || ! t.field().equals(field))
        break;

      if (0 < te.docFreq()) { /* all docs may be deleted */
        int count = searcher.numDocs(new TermQuery(t),
                                     docs);

        if (zeros || 0 < count)
          counts.add(new CountPair<String,Integer>
View Full Code Here
146
147
148
149
150
151
152
153
154
155
156
                  {
                     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
                     }
View Full Code Here
340
341
342
343
344
345
346
347
348
349
350
    while (terms.next()) {
      Term term = terms.term();
      //message(term.field() + ":" + term.text() + " freq:" + terms.docFreq());
      //if we're either not looking by field or we're matching the specific field
      if ((field == null) || field.equals(term.field()))
        termMap.put(term.field() + ":" + term.text(), new Integer((terms.docFreq())));
    }

    Iterator termIterator = termMap.keySet().iterator();
    for (int ii = 0; termIterator.hasNext() && ii < 100; ii++) {
      String termDetails = (String) termIterator.next();
View Full Code Here
362
363
364
365
366
367
368
369
370
371
372
      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
27
28
29
30
31
32
33
34
35
36
37
    while (terms.next()) {
      String field = terms.term().field();
      if (!"keywords".equals(field)) continue;

      int freq = terms.docFreq();

      String text = terms.term().text().trim();

      Tag tag = new Tag(text, freq);
     
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
    while (terms.next()) {
      String field = terms.term().field();
      if (!"keywords".equals(field)) continue;

      int freq = terms.docFreq();

      String text = terms.term().text().trim();

      Tag tag = new Tag(text, freq);
     
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
    termEnum = reader.terms();
    // go to the first term (aaa)
    termEnum.next();
    // assert that term is 'aaa'
    assertEquals("aaa", termEnum.term().text());
    assertEquals(200, termEnum.docFreq());
    // go to the second term (bbb)
    termEnum.next();
    // assert that term is 'bbb'
    assertEquals("bbb", termEnum.term().text());
    assertEquals(100, termEnum.docFreq());
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.