Package org.apache.lucene.index

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

167
168
169
170
171
172
173
174
175
176
177
    do {
      Term term = te.term();
      if (term == null || term.field().equals(field) == false) {
        break;
      }
      out.printf("%s %d\n", term.text(), te.docFreq());
    } while (te.next());
    te.close();
  }
 
  /** dump the values stored in the specified field for each document.
View Full Code Here
338
339
340
341
342
343
344
345
346
347
348
  protected float calculateWeight(Term term, IndexReader reader) throws IOException {
    //if a term is not in the index, then it's weight is 0
    TermEnum termEnum = reader.terms(term);
    if (termEnum != null && termEnum.term() != null && termEnum.term().equals(term)) {
      return 1.0f / termEnum.docFreq();
    } else {
      log.warn("Couldn't find doc freq for term {}", term);
      return 0;
    }
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
    do {
      Term term = te.term();
      if (term == null || term.field().equals(field) == false) {
        break;
      }
      System.err.printf("%s %d\n", term.text(), te.docFreq());
    } while (te.next());
    te.close();
  }
 
  public static void emitTextForTags(File file, File output) throws IOException {
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
      Term term = te.term();
      if (term == null || term.field().equals(field) == false) {
        break;
      }
     
      if (te.docFreq() > 30) {
        File f = new File(output, term.text() + ".txt");
        PrintWriter pw = new PrintWriter(new FileWriter(f));
        System.err.printf("%s %d\n", term.text(), te.docFreq());
       
        TermDocs td = reader.termDocs(term);
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
      }
     
      if (te.docFreq() > 30) {
        File f = new File(output, term.text() + ".txt");
        PrintWriter pw = new PrintWriter(new FileWriter(f));
        System.err.printf("%s %d\n", term.text(), te.docFreq());
       
        TermDocs td = reader.termDocs(term);
        while (td.next()) {
          int doc = td.doc();
          buf.setLength(0);
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
      if (terms != null && terms.term() != null) {
        do {
          if (!terms.term().field().equals(field)) {
            break;
          }
          tiq.insertWithOverflow(new TermStats(terms.term(), terms.docFreq()));
        } while (terms.next());
      } else {
        System.out.println("No terms for field \"" + field + "\"");
      }
    } else {
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
        System.out.println("No terms for field \"" + field + "\"");
      }
    } else {
      TermEnum terms = reader.terms();
      while (terms.next()) {
        tiq.insertWithOverflow(new TermStats(terms.term(), terms.docFreq()));
      }
    }

    TermStats[] result = new TermStats[tiq.size()];
View Full Code Here
223
224
225
226
227
228
229
230
231
232
233
      if (fields == null || fields.contains(termEnum.term().field())) { // todo skipto if not using field
        InstantiatedTerm instantiatedTerm = new InstantiatedTerm(termEnum.term().field(), termEnum.term().text());
        getTermsByFieldAndText().get(termEnum.term().field()).put(termEnum.term().text(), instantiatedTerm);
        instantiatedTerm.setTermIndex(terms.size());
        terms.add(instantiatedTerm);
        instantiatedTerm.setAssociatedDocuments(new InstantiatedTermDocumentInformation[termEnum.docFreq()]);
      }
    }
    termEnum.close();
    orderedTerms = terms.toArray(new InstantiatedTerm[terms.size()]);
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
                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
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
      */
      final int output;
      if (storeOrd) {
        output = ord;
      } else {
        output = termEnum.docFreq();
      }
      //System.out.println("ADD: " + term.text() + " ch[0]=" + (term.text().length() == 0 ? -1 : term.text().charAt(0)));
      builder.add(toIntsRef(term.text()), outputs.get(output));
      ord++;
      if (ord % 100000 == 0 && LuceneTestCase.TEST_NIGHTLY) {
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.