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

org.apache.lucene.index.TermsEnum.docFreq()
Returns the number of documents containing the current term. Do not call this when the enum is unpositioned. {@link SeekStatus#END}.

        
        if (termsEnum == TermsEnum.EMPTY) continue;
        if (termsEnum.seekExact(term.bytes())) {
          if (termContext == null) {
            contextArray[i] = new TermContext(reader.getContext(),
                termsEnum.termState(), context.ord, termsEnum.docFreq(),
                termsEnum.totalTermFreq());
          } else {
            termContext.register(termsEnum.termState(), context.ord,
                termsEnum.docFreq(), termsEnum.totalTermFreq());
          }

View Full Code Here

            contextArray[i] = new TermContext(reader.getContext(),
                termsEnum.termState(), context.ord, termsEnum.docFreq(),
                termsEnum.totalTermFreq());
          } else {
            termContext.register(termsEnum.termState(), context.ord,
                termsEnum.docFreq(), termsEnum.totalTermFreq());
          }
          
        }
        
      }

View Full Code Here

      // if (DEBUG) {
      //   System.out.println("\nLOAD terms seg=" + state.segmentInfo.name + " field=" + field + " hasOffsets=" + hasOffsets + " hasFreq=" + hasFreq + " hasPos=" + hasPos + " hasPayloads=" + hasPayloads);
      // }


      while ((term = termsEnum.next()) != null) {
        final int docFreq = termsEnum.docFreq();
        final long totalTermFreq = termsEnum.totalTermFreq();


        // if (DEBUG) {
        //   System.out.println("  term=" + term.utf8ToString());
        // }

View Full Code Here

        if (postingsEnum == null) {
          assert te.seekExact(t.bytes()) : "termstate found but no term exists in reader";
          // term does exist, but has no positions
          throw new IllegalStateException("field \"" + t.field() + "\" was indexed without position data; cannot run PhraseQuery (term=" + t.text() + ")");
        }
        postingsFreqs[i] = new PostingsAndFreq(postingsEnum, te.docFreq(), positions.get(i).intValue(), t);
      }


      // sort by increasing docFreq order
      if (slop == 0) {
        ArrayUtil.timSort(postingsFreqs);

View Full Code Here

            if (termState == null) {
              // Term not in reader
              continue;
            }
            termsEnum.seekExact(term.bytes(), termState);
            docFreq += termsEnum.docFreq();
          }


          if (docFreq == 0) {
            // None of the terms are in this reader
            return null;

View Full Code Here

            // term does exist, but has no positions
            assert termsEnum.docs(liveDocs, null, DocsEnum.FLAG_NONE) != null: "termstate found but no term exists in reader";
            throw new IllegalStateException("field \"" + term.field() + "\" was indexed without position data; cannot run PhraseQuery (term=" + term.text() + ")");
          }


          docFreq = termsEnum.docFreq();
        }


        postingsFreqs[pos] = new PhraseQuery.PostingsAndFreq(postingsEnum, docFreq, positions.get(pos).intValue(), terms);
      }

View Full Code Here

        if (postingsEnum == null) {
          assert te.seekExact(t.bytes()) : "termstate found but no term exists in reader";
          // term does exist, but has no positions
          throw new IllegalStateException("field \"" + t.field() + "\" was indexed without position data; cannot run PhraseQuery (term=" + t.text() + ")");
        }
        postingsFreqs[i] = new PostingsAndFreq(postingsEnum, te.docFreq(), positions.get(i).intValue(), t);
      }


      // sort by increasing docFreq order
      if (slop == 0) {
        ArrayUtil.timSort(postingsFreqs);

View Full Code Here

          // too much ram)


          int numUniqueTerms = 0;
          while (te.next() != null) {
            numUniqueTerms++;
            int df = te.docFreq();
            if (df <= longTailDfEnd) {
              int i = df - longTailDfStart;
              longTailTermDfCounts[i]++;
            } else {
              terms.add(new TermCount(new Term(field, te.term().utf8ToString()), df));

View Full Code Here

    try {
      TermsEnum iterator = terms.iterator(null);
      while (iterator.next() != null) {
        if (highFreqQueue.size() < 5) {
          highFreqQueue.add(new TermAndFreq(
              BytesRef.deepCopyOf(iterator.term()), iterator.docFreq()));
          lowFreqQueue.add(new TermAndFreq(
              BytesRef.deepCopyOf(iterator.term()), iterator.docFreq()));
        } else {
          if (highFreqQueue.top().freq < iterator.docFreq()) {
            highFreqQueue.top().freq = iterator.docFreq();

View Full Code Here

      while (iterator.next() != null) {
        if (highFreqQueue.size() < 5) {
          highFreqQueue.add(new TermAndFreq(
              BytesRef.deepCopyOf(iterator.term()), iterator.docFreq()));
          lowFreqQueue.add(new TermAndFreq(
              BytesRef.deepCopyOf(iterator.term()), iterator.docFreq()));
        } else {
          if (highFreqQueue.top().freq < iterator.docFreq()) {
            highFreqQueue.top().freq = iterator.docFreq();
            highFreqQueue.top().term = BytesRef.deepCopyOf(iterator.term());
            highFreqQueue.updateTop();

View Full Code Here

0 1 2 3 4 5 6 7 8

TOP

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.