Examples of org.apache.lucene.index.TermPositions

org.apache.lucene.index.TermPositions
TermPositions provides an interface for enumerating the <document, frequency, <position>* > tuples for a term.
The document and frequency are the same as for a TermDocs. The positions portion lists the ordinal positions of each occurrence of a term in a document. @see IndexReader#termPositions

    }
    
    @Override
    public void load() throws Exception
    {
      TermPositions tp = null;
      byte[] payloadBuffer = new byte[4];        // four bytes for an int
      try
      {
        tp = _reader.termPositions(_sizeTerm);


        if(tp == null) return;
        
        while(tp.next())
        {
          if(tp.freq() > 0)
          {
            tp.nextPosition();
            tp.getPayload(payloadBuffer, 0);
            int len = bytesToInt(payloadBuffer);
            allocate(tp.doc(), Math.min(len, _maxItems), true);
          }
        }
      }
      finally
      {
        if(tp != null) tp.close();
      }
    }

View Full Code Here

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


      // compare term positions


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


      if (aprioriTermPositions != null) {


        for (int docIndex = 0; docIndex < aprioriReader.maxDoc(); docIndex++) {
          boolean hasNext = aprioriTermPositions.next();
          if (hasNext) {
            assertTrue(testTermPositions.next());


            assertEquals(aprioriTermPositions.freq(), testTermPositions.freq());




            for (int termPositionIndex = 0; termPositionIndex < aprioriTermPositions.freq(); termPositionIndex++) {
              int aprioriPos = aprioriTermPositions.nextPosition();
              int testPos = testTermPositions.nextPosition();


              if (aprioriPos != testPos) {
                assertEquals(aprioriPos, testPos);
              }




              assertEquals(aprioriTermPositions.isPayloadAvailable(), testTermPositions.isPayloadAvailable());
              if (aprioriTermPositions.isPayloadAvailable()) {
                assertEquals(aprioriTermPositions.getPayloadLength(), testTermPositions.getPayloadLength());
                byte[] aprioriPayloads = aprioriTermPositions.getPayload(new byte[aprioriTermPositions.getPayloadLength()], 0);
                byte[] testPayloads = testTermPositions.getPayload(new byte[testTermPositions.getPayloadLength()], 0);
                for (int i = 0; i < aprioriPayloads.length; i++) {
                  assertEquals(aprioriPayloads[i], testPayloads[i]);
                }
              }


            }
          }
        }


        aprioriTermPositions.close();
        testTermPositions.close();


      }
    }

View Full Code Here

  
    @Override
    public TermPositions termPositions() {
      if (DEBUG) System.err.println("MemoryIndexReader.termPositions");
      
      return new TermPositions() {
  
        private boolean hasNext;
        private int cursor = 0;
        private ArrayIntList current;
        private Term term;

View Full Code Here

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


      // compare term positions


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


      if (aprioriTermPositions != null) {


        for (int docIndex = 0; docIndex < aprioriReader.maxDoc(); docIndex++) {
          boolean hasNext = aprioriTermPositions.next();
          if (hasNext) {
            assertTrue(testTermPositions.next());


            assertEquals(aprioriTermPositions.freq(), testTermPositions.freq());




            for (int termPositionIndex = 0; termPositionIndex < aprioriTermPositions.freq(); termPositionIndex++) {
              int aprioriPos = aprioriTermPositions.nextPosition();
              int testPos = testTermPositions.nextPosition();


              if (aprioriPos != testPos) {
                assertEquals(aprioriPos, testPos);
              }




              assertEquals(aprioriTermPositions.isPayloadAvailable(), testTermPositions.isPayloadAvailable());
              if (aprioriTermPositions.isPayloadAvailable()) {
                assertEquals(aprioriTermPositions.getPayloadLength(), testTermPositions.getPayloadLength());
                byte[] aprioriPayloads = aprioriTermPositions.getPayload(new byte[aprioriTermPositions.getPayloadLength()], 0);
                byte[] testPayloads = testTermPositions.getPayload(new byte[testTermPositions.getPayloadLength()], 0);
                for (int i = 0; i < aprioriPayloads.length; i++) {
                  assertEquals(aprioriPayloads[i], testPayloads[i]);
                }
              }


            }
          }
        }


        aprioriTermPositions.close();
        testTermPositions.close();


      }
    }

View Full Code Here

    //    don't reset the stream here, the DocumentWriter should do that implicitly
    writer.addDocument(doc);
    writer.close();
    
    IndexReader reader = IndexReader.open(dir, true);
    TermPositions termPositions = reader.termPositions(new Term("preanalyzed", "term1"));
    assertTrue(termPositions.next());
    assertEquals(1, termPositions.freq());
    assertEquals(0, termPositions.nextPosition());


    termPositions.seek(new Term("preanalyzed", "term2"));
    assertTrue(termPositions.next());
    assertEquals(2, termPositions.freq());
    assertEquals(1, termPositions.nextPosition());
    assertEquals(3, termPositions.nextPosition());
    
    termPositions.seek(new Term("preanalyzed", "term3"));
    assertTrue(termPositions.next());
    assertEquals(1, termPositions.freq());
    assertEquals(2, termPositions.nextPosition());
    reader.close();
    
    // 3) reset stream and consume tokens again
    stream.reset();
    checkTokens(stream);

View Full Code Here

    termEnum.close();
    orderedTerms = terms.toArray(new InstantiatedTerm[terms.size()]);


    // create term-document informations
    for (InstantiatedTerm term : orderedTerms) {
      TermPositions termPositions = sourceIndexReader.termPositions(term.getTerm());
      int position = 0;
      while (termPositions.next()) {
        InstantiatedDocument document = documentsByNumber[termPositions.doc()];


        byte[][] payloads = new byte[termPositions.freq()][];
        int[] positions = new int[termPositions.freq()];
        for (int i = 0; i < termPositions.freq(); i++) {
          positions[i] = termPositions.nextPosition();


          if (termPositions.isPayloadAvailable()) {
            payloads[i] = new byte[termPositions.getPayloadLength()];
            termPositions.getPayload(payloads[i], 0);
          }
        }


        InstantiatedTermDocumentInformation termDocumentInformation = new InstantiatedTermDocumentInformation(term, document, positions, payloads);
        term.getAssociatedDocuments()[position++] = termDocumentInformation;

View Full Code Here

      if (terms.size() == 0)        // optimize zero-term case
        return null;


      TermPositions[] tps = new TermPositions[terms.size()];
      for (int i = 0; i < terms.size(); i++) {
        TermPositions p = reader.termPositions(terms.get(i));
        if (p == null)
          return null;
        tps[i] = p;
      }

View Full Code Here

  
    @Override
    public TermPositions termPositions() {
      if (DEBUG) System.err.println("MemoryIndexReader.termPositions");
      
      return new TermPositions() {
  
        private boolean hasNext;
        private int cursor = 0;
        private ArrayIntList current;
        private Term term;

View Full Code Here

    termEnum.close();
    orderedTerms = terms.toArray(new InstantiatedTerm[terms.size()]);


    // create term-document informations
    for (InstantiatedTerm term : orderedTerms) {
      TermPositions termPositions = sourceIndexReader.termPositions(term.getTerm());
      int position = 0;
      while (termPositions.next()) {
        InstantiatedDocument document = documentsByNumber[termPositions.doc()];


        byte[][] payloads = new byte[termPositions.freq()][];
        int[] positions = new int[termPositions.freq()];
        for (int i = 0; i < termPositions.freq(); i++) {
          positions[i] = termPositions.nextPosition();


          if (termPositions.isPayloadAvailable()) {
            payloads[i] = new byte[termPositions.getPayloadLength()];
            termPositions.getPayload(payloads[i], 0);
          }
        }


        InstantiatedTermDocumentInformation termDocumentInformation = new InstantiatedTermDocumentInformation(term, document, positions, payloads);
        term.getAssociatedDocuments()[position++] = termDocumentInformation;

View Full Code Here

      PhraseQuery.PostingsAndFreq[] postingsFreqs = new PhraseQuery.PostingsAndFreq[termArrays.size()];


      for (int pos=0; pos<postingsFreqs.length; pos++) {
        Term[] terms = termArrays.get(pos);


        final TermPositions p;
        int docFreq;


        if (terms.length > 1) {
          p = new MultipleTermPositions(reader, terms);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.index.TermPositions

com.browseengine.bobo.facets.data.MultiValueFacetDataCache$AllocOnlyLoader

com.browseengine.bobo.search.section.IntMetaDataCache

com.flaptor.indextank.index.lsi.term.IndexReaderTermMatcher

com.greplin.lucene.filter.FilteredMultiReader

com.greplin.lucene.filter.PhraseFilter

org.apache.jackrabbit.core.query.lucene.SharedFieldCache

org.apache.lucene.analysis.TestCachingTokenFilter

org.apache.lucene.analysis.TestClassicAnalyzer

org.apache.lucene.facet.taxonomy.directory.ParentArray

org.apache.lucene.facet.taxonomy.lucene.ParentArray

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.