Examples of org.apache.lucene.codecs.TermVectorsWriter

org.apache.lucene.codecs.TermVectorsWriter
Codec API for writing term vectors:
1. For every document, {@link #startDocument(int)} is called,informing the Codec how many fields will be written.
2. {@link #startField(FieldInfo,int,boolean,boolean,boolean)} is called for each field in the document, informing the codec how many terms will be written for that field, and whether or not positions, offsets, or payloads are enabled.
3. Within each field, {@link #startTerm(BytesRef,int)} is calledfor each term.
4. If offsets and/or positions are enabled, then {@link #addPosition(int,int,int,BytesRef)} will be called for each termoccurrence.
5. After all documents have been written, {@link #finish(FieldInfos,int)} is called for verification/sanity-checks.
6. Finally the writer is closed ( {@link #close()})
@lucene.experimental

  /**
   * Merge the TermVectors from each of the segments into the new one.
   * @throws IOException if there is a low-level IO error
   */
  private int mergeVectors() throws IOException {
    final TermVectorsWriter termVectorsWriter = codec.termVectorsFormat().vectorsWriter(directory, mergeState.segmentInfo, context);
    
    try {
      return termVectorsWriter.merge(mergeState);
    } finally {
      termVectorsWriter.close();
    }
  }

View Full Code Here

  /**
   * Merge the TermVectors from each of the segments into the new one.
   * @throws IOException if there is a low-level IO error
   */
  private int mergeVectors() throws IOException {
    final TermVectorsWriter termVectorsWriter = codec.termVectorsFormat().vectorsWriter(directory, mergeState.segmentInfo, context);
    
    try {
      return termVectorsWriter.merge(mergeState);
    } finally {
      termVectorsWriter.close();
    }
  }

View Full Code Here

    // This is called once, after inverting all occurrences
    // of a given field in the doc.  At this point we flush
    // our hash into the DocWriter.


    TermVectorsPostingsArray postings = termVectorsPostingsArray;
    final TermVectorsWriter tv = termsWriter.writer;


    final int[] termIDs = sortPostings(tv.getComparator());


    tv.startField(fieldInfo, numPostings, doVectorPositions, doVectorOffsets, hasPayloads);
    
    final ByteSliceReader posReader = doVectorPositions ? termsWriter.vectorSliceReaderPos : null;
    final ByteSliceReader offReader = doVectorOffsets ? termsWriter.vectorSliceReaderOff : null;
    
    for(int j=0;j<numPostings;j++) {
      final int termID = termIDs[j];
      final int freq = postings.freqs[termID];


      // Get BytesRef
      termBytePool.setBytesRef(flushTerm, postings.textStarts[termID]);
      tv.startTerm(flushTerm, freq);
      
      if (doVectorPositions || doVectorOffsets) {
        if (posReader != null) {
          initReader(posReader, termID, 0);
        }
        if (offReader != null) {
          initReader(offReader, termID, 1);
        }
        tv.addProx(freq, posReader, offReader);
      }
      tv.finishTerm();
    }
    tv.finishField();


    reset();


    fieldInfo.setStoreTermVectors();
  }

View Full Code Here

  /**
   * Merge the TermVectors from each of the segments into the new one.
   * @throws IOException if there is a low-level IO error
   */
  private int mergeVectors() throws IOException {
    final TermVectorsWriter termVectorsWriter = codec.termVectorsFormat().vectorsWriter(directory, mergeState.segmentInfo, context);
    
    try {
      return termVectorsWriter.merge(mergeState);
    } finally {
      termVectorsWriter.close();
    }
  }

View Full Code Here

  /**
   * Merge the TermVectors from each of the segments into the new one.
   * @throws IOException if there is a low-level IO error
   */
  private int mergeVectors() throws IOException {
    final TermVectorsWriter termVectorsWriter = codec.termVectorsFormat().vectorsWriter(directory, mergeState.segmentInfo, context);
    
    try {
      return termVectorsWriter.merge(mergeState);
    } finally {
      termVectorsWriter.close();
    }
  }

View Full Code Here

    // our hash into the DocWriter.


    assert termsWriter.vectorFieldsInOrder(fieldInfo);


    TermVectorsPostingsArray postings = (TermVectorsPostingsArray) termsHashPerField.postingsArray;
    final TermVectorsWriter tv = termsWriter.writer;


    final int[] termIDs = termsHashPerField.sortPostings(tv.getComparator());


    tv.startField(fieldInfo, numPostings, doVectorPositions, doVectorOffsets, hasPayloads);
    
    final ByteSliceReader posReader = doVectorPositions ? termsWriter.vectorSliceReaderPos : null;
    final ByteSliceReader offReader = doVectorOffsets ? termsWriter.vectorSliceReaderOff : null;
    
    final ByteBlockPool termBytePool = termsHashPerField.termBytePool;


    for(int j=0;j<numPostings;j++) {
      final int termID = termIDs[j];
      final int freq = postings.freqs[termID];


      // Get BytesRef
      termBytePool.setBytesRef(flushTerm, postings.textStarts[termID]);
      tv.startTerm(flushTerm, freq);
      
      if (doVectorPositions || doVectorOffsets) {
        if (posReader != null) {
          termsHashPerField.initReader(posReader, termID, 0);
        }
        if (offReader != null) {
          termsHashPerField.initReader(offReader, termID, 1);
        }
        tv.addProx(freq, posReader, offReader);
      }
      tv.finishTerm();
    }
    tv.finishField();


    termsHashPerField.reset();


    fieldInfo.setStoreTermVectors();
  }

View Full Code Here

  /**
   * Merge the TermVectors from each of the segments into the new one.
   * @throws IOException if there is a low-level IO error
   */
  private int mergeVectors() throws IOException {
    final TermVectorsWriter termVectorsWriter = codec.termVectorsFormat().vectorsWriter(directory, mergeState.segmentInfo, context);
    
    try {
      return termVectorsWriter.merge(mergeState);
    } finally {
      termVectorsWriter.close();
    }
  }

View Full Code Here

  /**
   * Merge the TermVectors from each of the segments into the new one.
   * @throws IOException if there is a low-level IO error
   */
  private int mergeVectors() throws IOException {
    final TermVectorsWriter termVectorsWriter = codec.termVectorsFormat().vectorsWriter(directory, mergeState.segmentInfo, context);
    
    try {
      return termVectorsWriter.merge(mergeState);
    } finally {
      termVectorsWriter.close();
    }
  }

View Full Code Here

    // our hash into the DocWriter.


    assert termsWriter.vectorFieldsInOrder(fieldInfo);


    TermVectorsPostingsArray postings = (TermVectorsPostingsArray) termsHashPerField.postingsArray;
    final TermVectorsWriter tv = termsWriter.writer;


    final int[] termIDs = termsHashPerField.sortPostings(tv.getComparator());


    tv.startField(fieldInfo, numPostings, doVectorPositions, doVectorOffsets, hasPayloads);
    
    final ByteSliceReader posReader = doVectorPositions ? termsWriter.vectorSliceReaderPos : null;
    final ByteSliceReader offReader = doVectorOffsets ? termsWriter.vectorSliceReaderOff : null;
    
    final ByteBlockPool termBytePool = termsHashPerField.termBytePool;


    for(int j=0;j<numPostings;j++) {
      final int termID = termIDs[j];
      final int freq = postings.freqs[termID];


      // Get BytesRef
      termBytePool.setBytesRef(flushTerm, postings.textStarts[termID]);
      tv.startTerm(flushTerm, freq);
      
      if (doVectorPositions || doVectorOffsets) {
        if (posReader != null) {
          termsHashPerField.initReader(posReader, termID, 0);
        }
        if (offReader != null) {
          termsHashPerField.initReader(offReader, termID, 1);
        }
        tv.addProx(freq, posReader, offReader);
      }
      tv.finishTerm();
    }
    tv.finishField();


    termsHashPerField.reset();


    fieldInfo.setStoreTermVectors();
  }

View Full Code Here

TOP

Related Classes of org.apache.lucene.codecs.TermVectorsWriter

org.apache.lucene.index.AtomicReader

org.apache.lucene.index.DocsAndPositionsEnum

org.apache.lucene.index.FieldInfo

org.apache.lucene.index.Fields

org.apache.lucene.index.SegmentMerger

org.apache.lucene.index.Terms

org.apache.lucene.index.TermsEnum

org.apache.lucene.index.TermVectorsConsumerPerField

org.apache.lucene.util.Bits

org.apache.lucene.util.BytesRef

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.