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

        } catch (NumberFormatException ne) {
          return wrapper.getLongs(reader, field, NUMERIC_UTILS_LONG_PARSER);      
        }
      }
      long[] retArray = null;
      TermDocs termDocs = reader.termDocs();
      TermEnum termEnum = reader.terms (new Term(field));
      try {
        do {
          Term term = termEnum.term();
          if (term==null || term.field() != field) break;
          long termval = parser.parseLong(term.text());
          if (retArray == null) // late init
            retArray = new long[reader.maxDoc()];
          termDocs.seek (termEnum);
          while (termDocs.next()) {
            retArray[termDocs.doc()] = termval;
          }
        } while (termEnum.next());
      } catch (StopFillCacheException stop) {
      } finally {
        termDocs.close();
        termEnum.close();
      }
      if (retArray == null) // no values
        retArray = new long[reader.maxDoc()];
      return retArray;

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

        } catch (NumberFormatException ne) {
          return wrapper.getDoubles(reader, field, NUMERIC_UTILS_DOUBLE_PARSER);      
        }
      }
      double[] retArray = null;
      TermDocs termDocs = reader.termDocs();
      TermEnum termEnum = reader.terms (new Term (field));
      try {
        do {
          Term term = termEnum.term();
          if (term==null || term.field() != field) break;
          double termval = parser.parseDouble(term.text());
          if (retArray == null) // late init
            retArray = new double[reader.maxDoc()];
          termDocs.seek (termEnum);
          while (termDocs.next()) {
            retArray[termDocs.doc()] = termval;
          }
        } while (termEnum.next());
      } catch (StopFillCacheException stop) {
      } finally {
        termDocs.close();
        termEnum.close();
      }
      if (retArray == null) // no values
        retArray = new double[reader.maxDoc()];
      return retArray;

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

    assertTrue("Filtered searching should have found some matches",hits.length>0);
    for(int i=0;i<hits.length;i++)
    {
      Document d=searcher.doc(hits[i].doc);
      String url=d.get(KEY_FIELD);
      TermDocs td = reader.termDocs(new Term(KEY_FIELD,url));
      int lastDoc=0;
      while(td.next())
      {
        lastDoc=td.doc();
      }
      assertEquals("Duplicate urls should return last doc",lastDoc, hits[i].doc);
    }
  }

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

    assertTrue("Filtered searching should have found some matches",hits.length>0);
    for(int i=0;i<hits.length;i++)
    {
      Document d=searcher.doc(hits[i].doc);
      String url=d.get(KEY_FIELD);
      TermDocs td = reader.termDocs(new Term(KEY_FIELD,url));
      int lastDoc=0;
      td.next();
      lastDoc=td.doc();
      assertEquals("Duplicate urls should return first doc",lastDoc, hits[i].doc);
    }
  }

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

        break;
      }
      OpenBitSet termBitset = new OpenBitSet(reader.maxDoc());
      
      // Generate bitset for the term
      TermDocs termDocs = reader.termDocs(term);
      
      while (termDocs.next()) {
        termBitset.set(termDocs.doc());
      }
      
      // AND the term's bitset with cluster doc bitset to get the term's in-cluster frequency.
      // This modifies the termBitset, but that's fine as we are not using it anywhere else.
      termBitset.and(clusterDocBitset);

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

        try {
            CachingMultiIndexReader reader = index.getIndexReader();
            try {
                Term aggregateIds =
                    new Term(FieldNames.AGGREGATED_NODE_UUID, "");
                TermDocs tDocs = reader.termDocs();
                try {
                    ItemStateManager ism = getContext().getItemStateManager();
                    for (NodeId id : removedIds) {
                        aggregateIds =
                            aggregateIds.createTerm(id.toString());
                        tDocs.seek(aggregateIds);
                        while (tDocs.next()) {
                            Document doc = reader.document(
                                    tDocs.doc(), FieldSelectors.UUID);
                            NodeId nId = new NodeId(doc.get(FieldNames.UUID));
                            NodeState nodeState = (NodeState) ism.getItemState(nId);
                            aggregates.put(nId, nodeState);
                            found++;


                            // JCR-2989 Support for embedded index aggregates
                            int sizeBefore = aggregates.size();
                            retrieveAggregateRoot(nodeState, aggregates);
                            found += aggregates.size() - sizeBefore;
                        }
                    }
                } finally {
                    tDocs.close();
                }
            } finally {
                reader.release();
            }
        } catch (Exception e) {

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

               {
                  CachingMultiIndexReader reader = index.getIndexReader();
                  try
                  {
                     Term aggregateUUIDs = new Term(FieldNames.AGGREGATED_NODE_UUID, "");
                     TermDocs tDocs = reader.termDocs();
                     try
                     {
                        ItemDataConsumer ism = getContext().getItemStateManager();
                        for (Iterator<String> it = removedNodeIds.iterator(); it.hasNext();)
                        {
                           String id = it.next();
                           aggregateUUIDs = aggregateUUIDs.createTerm(id);
                           tDocs.seek(aggregateUUIDs);
                           while (tDocs.next())
                           {
                              Document doc = reader.document(tDocs.doc(), FieldSelectors.UUID);
                              String uuid = doc.get(FieldNames.UUID);
                              ItemData itd = ism.getItemData(uuid);
                              if (itd == null)
                              {
                                 continue;
                              }
                              if (!itd.isNode())
                              {
                                 throw new RepositoryException("Item with id:" + uuid + " is not a node");
                              }
                              map.put(uuid, (NodeData)itd);
                              found++;
                           }
                        }
                     }
                     finally
                     {
                        tDocs.close();
                     }
                  }
                  finally
                  {
                     reader.release();

View Full Code Here

Examples of org.apache.lucene.index.TermDocs

         {
            // process node uuids one-by-one
            try
            {
               String uuid = node.getIdentifier();
               TermDocs docs = indexReader.termDocs(new Term(FieldNames.UUID, uuid));


               if (docs.next())
               {
                  indexedNodes.add(uuid);
                  docs.doc();
                  if (docs.next())
                  {
                     //multiple entries
                     report.logComment("Multiple entires.");
                     report.logBrokenObjectAndSetInconsistency("ID=" + uuid);
                  }

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.