Examples of TermDocs

org.apache.lucene.index.TermDocs
TermDocs provides an interface for enumerating <document, frequency> pairs for a term.
The document portion names each document containing the term. Documents are indicated by number. The frequency portion gives the number of times the term occurred in each document.
The pairs are ordered by document number. @see IndexReader#termDocs()
uk.ac.ucl.panda.utility.structure.TermDocs
TermDocs provides an interface for enumerating <document, frequency> pairs for a term.
The document portion names each document containing the term. Documents are indicated by number. The frequency portion gives the number of times the term occurred in each document.
The pairs are ordered by document number. @see IndexReader#termDocs()

Examples of org.apache.lucene.index.TermDocs

      value = queryWeight * idf;                  // idf for document
    }


    @Override
    public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, boolean topScorer) throws IOException {
      TermDocs termDocs = reader.termDocs(term);


      if (termDocs == null)
        return null;


      return new TermScorer(this, termDocs, similarity, reader.norms(term.field()));

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

      fieldExpl.setDescription("fieldWeight("+term+" in "+doc+
                               "), product of:");


      Explanation tfExplanation = new Explanation();
      int tf = 0;
      TermDocs termDocs = reader.termDocs(term);
      if (termDocs != null) {
        try {
          if (termDocs.skipTo(doc) && termDocs.doc() == doc) {
            tf = termDocs.freq();
          }
        } finally {
          termDocs.close();
        }
        tfExplanation.setValue(similarity.tf(tf));
        tfExplanation.setDescription("tf(termFreq("+term+")="+tf+")");
      } else {
        tfExplanation.setValue(0.0f);

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

    t = aprioriTermEnum.term();


    aprioriTermEnum.close();
    testTermEnum.close();


    TermDocs aprioriTermDocs = aprioriReader.termDocs(t);
    TermDocs testTermDocs = testReader.termDocs(t);


    assertEquals(aprioriTermDocs.next(), testTermDocs.next());
    assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
    assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());


    if (aprioriTermDocs.skipTo(4)) {
      assertTrue(testTermDocs.skipTo(4));
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.skipTo(4));
    }


    if (aprioriTermDocs.next()) {
      assertTrue(testTermDocs.next());
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.next());
    }




    // beyond this point all next and skipto will return false


    if (aprioriTermDocs.skipTo(100)) {
      assertTrue(testTermDocs.skipTo(100));
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.skipTo(100));
    }




    if (aprioriTermDocs.next()) {
      assertTrue(testTermDocs.next());
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.next());
    }


    if (aprioriTermDocs.skipTo(110)) {
      assertTrue(testTermDocs.skipTo(110));
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.skipTo(110));
    }


    if (aprioriTermDocs.skipTo(10)) {
      assertTrue(testTermDocs.skipTo(10));
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.skipTo(10));
    }




    if (aprioriTermDocs.skipTo(210)) {
      assertTrue(testTermDocs.skipTo(210));
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    } else {
      assertFalse(testTermDocs.skipTo(210));
    }


    aprioriTermDocs.close();
    testTermDocs.close();






    // test seek null (AllTermDocs)
    aprioriTermDocs = aprioriReader.termDocs(null);
    testTermDocs = testReader.termDocs(null);


    while (aprioriTermDocs.next()) {
      assertTrue(testTermDocs.next());
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    }
    assertFalse(testTermDocs.next());




    aprioriTermDocs.close();
    testTermDocs.close();




    // test seek default
    aprioriTermDocs = aprioriReader.termDocs();
    testTermDocs = testReader.termDocs();


    // this is invalid use of the API,
    // but if the response differs then it's an indication that something might have changed.
    // in 2.9 and 3.0 the two TermDocs-implementations returned different values at this point.
//    assertEquals("Descripency during invalid use of the TermDocs API, see comments in test code for details.",
//        aprioriTermDocs.next(), testTermDocs.next());


    // start using the API the way one is supposed to use it


    t = new Term("", "");
    aprioriTermDocs.seek(t);
    testTermDocs.seek(t);


    while (aprioriTermDocs.next()) {
      assertTrue(testTermDocs.next());
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
    }
    assertFalse(testTermDocs.next());


    aprioriTermDocs.close();
    testTermDocs.close();




    // clean up
    aprioriReader.close();
    testReader.close();

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

      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());


      while (aprioriTermDocsSeeker.next()) {
        assertTrue(testTermDocsSeeker.skipTo(aprioriTermDocsSeeker.doc()));
        assertEquals(aprioriTermDocsSeeker.doc(), testTermDocsSeeker.doc());
      }


      aprioriTermDocsSeeker.close();
      testTermDocsSeeker.close();


      // compare documents per term


      assertEquals(aprioriReader.docFreq(aprioriTermEnum.term()), testReader.docFreq(testTermEnum.term()));


      TermDocs aprioriTermDocs = aprioriReader.termDocs(aprioriTermEnum.term());
      TermDocs testTermDocs = testReader.termDocs(testTermEnum.term());


      while (true) {
        if (!aprioriTermDocs.next()) {
          assertFalse(testTermDocs.next());
          break;
        }
        assertTrue(testTermDocs.next());


        assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
        assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      }


      aprioriTermDocs.close();
      testTermDocs.close();


      // compare term positions


      TermPositions testTermPositions = testReader.termPositions(testTermEnum.term());
      TermPositions aprioriTermPositions = aprioriReader.termPositions(aprioriTermEnum.term());

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

    // Separately count how many tokens are actually in the index:
    IndexReader reader = IndexReader.open(benchmark.getRunData().getDirectory(), true);
    assertEquals(NUM_DOCS, reader.numDocs());


    TermEnum terms = reader.terms();
    TermDocs termDocs = reader.termDocs();
    int totalTokenCount2 = 0;
    while(terms.next()) {
      termDocs.seek(terms.term());
      while(termDocs.next())
        totalTokenCount2 += termDocs.freq();
    }
    reader.close();


    // Make sure they are the same
    assertEquals(totalTokenCount1, totalTokenCount2);

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

    doc.add(new Field("partnum", "Q37", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);
    writer.close();


    IndexReader reader = IndexReader.open(dir, true);
    TermDocs td = reader.termDocs(new Term("partnum", "Q36"));
    assertTrue(td.next());
    td = reader.termDocs(new Term("partnum", "Q37"));
    assertTrue(td.next());
  }

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

                    throw ex[0];
                }


                // filter out documents that do not match the name test
                if (nameTest != null) {
                    TermDocs tDocs = reader.termDocs(new Term(FieldNames.LABEL, nameTest));
                    try {
                        for (int i = hits.nextSetBit(0); i >= 0; i = hits.nextSetBit(i + 1)) {
                            if (!tDocs.skipTo(i)) {
                                hits.clear(i);
                            }
                        }
                    } finally {
                        tDocs.close();
                    }
                }
            }
        }

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

            for (Iterator it = startTerms.iterator(); it.hasNext(); ) {
                Term startTerm = (Term) it.next();


                TermEnum terms = reader.terms(startTerm);
                try {
                    TermDocs docs = reader.termDocs();
                    try {
                        do {
                            Term term = terms.term();
                            if (term != null
                                    && term.field() == testField
                                    && term.text().startsWith(namePrefix)) {
                                if (checkLower) {
                                    int compare = termCompare(term.text(), lowerTerm.text(), propNameLength);
                                    if (compare > 0 || compare == 0 && inclusive) {
                                        // do not check lower term anymore if no
                                        // transformation is done on the term enum
                                        checkLower = transform == TRANSFORM_NONE ? false : true;
                                    } else {
                                        // continue with next term
                                        continue;
                                    }
                                }
                                if (upperTerm != null) {
                                    int compare = termCompare(term.text(), upperTerm.text(), propNameLength);
                                    // if beyond the upper term, or is exclusive and
                                    // this is equal to the upper term
                                    if ((compare > 0) || (!inclusive && compare == 0)) {
                                        // only break out if no transformation
                                        // was done on the term from the enum
                                        if (transform == TRANSFORM_NONE) {
                                            break;
                                        } else {
                                            // because of the transformation
                                            // it is possible that the next
                                            // term will be included again if
                                            // we still enumerate on the same
                                            // property name
                                            if (term.text().startsWith(namePrefix)) {
                                                continue;
                                            } else {
                                                break;
                                            }
                                        }
                                    }
                                }


                                docs.seek(terms);
                                while (docs.next()) {
                                    hits.set(docs.doc());
                                }
                            } else {
                                break;
                            }
                        } while(terms.next());
                    } finally {
                        docs.close();
                    }
                } finally {
                    terms.close();
                }
            }

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

                return;
            }
            TermEnum terms = new WildcardTermEnum(reader, field, propName, pattern, transform);
            try {
                // use unpositioned TermDocs
                TermDocs docs = reader.termDocs();
                try {
                    while (terms.term() != null) {
                        docs.seek(terms);
                        while (docs.next()) {
                            hits.set(docs.doc());
                        }
                        if (!terms.next()) {
                            break;
                        }
                    }
                } finally {
                    docs.close();
                }
            } finally {
                terms.close();
            }
            hitsCalculated = true;

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

    private void calculateDocFilter() throws IOException {
        docFilter = new BitSet(reader.maxDoc());
        // we match all terms
        TermEnum terms = reader.terms(new Term(FieldNames.PROPERTIES, field));
        try {
            TermDocs docs = reader.termDocs();
            try {
                while (terms.term() != null
                        && terms.term().field() == FieldNames.PROPERTIES
                        && terms.term().text().startsWith(field)) {
                    docs.seek(terms);
                    while (docs.next()) {
                        docFilter.set(docs.doc());
                    }
                    terms.next();
                }
            } finally {
                docs.close();
            }
        } finally {
            terms.close();
        }
    }

View Full Code Here

0 1 2 3 4 5

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.