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

org.apache.lucene.index.TermsEnum.totalTermFreq()
Returns the total number of occurrences of this term across all documents (the sum of the freq() for each doc that has this term). This will be -1 if the codec doesn't support this measure. Note that, like other term measures, this measure does not take deleted documents into account.

    Terms termVector = reader.getTermVector( x, "content" );
    assertNotNull( termVector );
    TermsEnum iterator = termVector.iterator( null );
    BytesRef next = iterator.next(); //move to first Document: we expect it to exist
    assertNotNull( next );
    long totalTermFreq = iterator.totalTermFreq();


    assertEquals( "electrical", next.utf8ToString() );
    assertEquals( 2, totalTermFreq );


    final DocsAndPositionsEnum docsAndPositions = iterator.docsAndPositions( null, null );

View Full Code Here

      //   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


    // code to reconstruct the original sequence of Tokens
    TermsEnum termsEnum = tpv.iterator(null);
    int totalTokens = 0;
    while(termsEnum.next() != null) {
      totalTokens += (int) termsEnum.totalTermFreq();
    }
    Token tokensInOriginalOrder[] = new Token[totalTokens];
    ArrayList<Token> unsortedTokens = null;
    termsEnum = tpv.iterator(null);
    BytesRef text;

View Full Code Here


      int termCount = 0;
      while(termsEnum.next() != null) {
        termCount++;


        final int freq = (int) termsEnum.totalTermFreq();
        
        startTerm(termsEnum.term(), freq);


        if (hasPositions || hasOffsets) {
          docsAndPositionsEnum = termsEnum.docsAndPositions(null, docsAndPositionsEnum);

View Full Code Here

    assertNotNull(vector);
    assertEquals(1, vector.size());
    TermsEnum termsEnum = vector.iterator(null);
    assertNotNull(termsEnum.next());
    assertEquals("one", termsEnum.term().utf8ToString());
    assertEquals(5, termsEnum.totalTermFreq());
    DocsAndPositionsEnum dpEnum = termsEnum.docsAndPositions(null, null);
    assertNotNull(dpEnum);
    assertTrue(dpEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
    assertEquals(5, dpEnum.freq());
    for(int i=0;i<5;i++) {

View Full Code Here

        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

    TermsEnum termEnum = terms.iterator(null);
    TermsEnum memTermEnum = memTerms.iterator(null);


    while (termEnum.next() != null) {
      assertNotNull(memTermEnum.next());
      assertThat(termEnum.totalTermFreq(), equalTo(memTermEnum.totalTermFreq()));


      DocsAndPositionsEnum docsPosEnum = termEnum.docsAndPositions(null, null, 0);
      DocsAndPositionsEnum memDocsPosEnum = memTermEnum.docsAndPositions(null, null, 0);
      String currentTerm = termEnum.term().utf8ToString();

View Full Code Here

      while((term = termsEnum.next()) != null) {
        BytesRef term2 = termsEnum2.next();
        assertNotNull(term2);
        assertEquals(term, term2);
        assertEquals(termsEnum.docFreq(), termsEnum2.docFreq());
        assertEquals(termsEnum.totalTermFreq(), termsEnum2.totalTermFreq());


        if (ord == 0) {
          try {
            termsEnum.ord();
          } catch (UnsupportedOperationException uoe) {

View Full Code Here

        int ngramCount = countGrams(term);
        if (ngramCount > grams) {
          throw new IllegalArgumentException("tokens must not contain separator byte; got token=" + term + " but gramCount=" + ngramCount + ", which is greater than expected max ngram size=" + grams);
        }
        if (ngramCount == 1) {
          totTokens += termsEnum.totalTermFreq();
        }


        builder.add(Util.toIntsRef(term, scratchInts), encodeWeight(termsEnum.totalTermFreq()));
      }

View Full Code Here

0 1 2 3 4 5 6

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.