Examples of org.apache.lucene.index.TermPositionVector

org.apache.lucene.index.TermPositionVector
Extends TermFreqVector to provide additional information about positions in which each of the terms is found. A TermPositionVector not necessarily contains both positions and offsets, but at least one of these arrays exists.

      if (document == null) {
        continue; // deleted
      }
      for (Fieldable field : document.getDocument().getFields()) {
        if (field.isTermVectorStored() && field.isStoreOffsetWithTermVector()) {
          TermPositionVector termPositionVector = (TermPositionVector) sourceIndexReader.getTermFreqVector(document.getDocumentNumber(), field.name());
          if (termPositionVector != null) {
            for (int i = 0; i < termPositionVector.getTerms().length; i++) {
              String token = termPositionVector.getTerms()[i];
              InstantiatedTerm term = findTerm(field.name(), token);
              InstantiatedTermDocumentInformation termDocumentInformation = term.getAssociatedDocument(document.getDocumentNumber());
              termDocumentInformation.setTermOffsets(termPositionVector.getOffsets(i));
            }
          }
        }
      }
    }

View Full Code Here

      if (DEBUG) System.err.println("MemoryIndexReader.getTermFreqVector");
      final Info info = getInfo(fieldName);
      if (info == null) return null; // TODO: or return empty vector impl???
      info.sortTerms();
      
      return new TermPositionVector() { 
  
        private final Map.Entry[] sortedTerms = info.sortedTerms;
        
        public String getField() {
          return fieldName;

View Full Code Here

        for (int freqVectorIndex = 0; freqVectorIndex < aprioriFreqVectors.length; freqVectorIndex++) {
          assertTrue(Arrays.equals(aprioriFreqVectors[freqVectorIndex].getTermFrequencies(), testFreqVectors[freqVectorIndex].getTermFrequencies()));
          assertTrue(Arrays.equals(aprioriFreqVectors[freqVectorIndex].getTerms(), testFreqVectors[freqVectorIndex].getTerms()));


          if (aprioriFreqVectors[freqVectorIndex] instanceof TermPositionVector) {
            TermPositionVector aprioriTermPositionVector = (TermPositionVector) aprioriFreqVectors[freqVectorIndex];
            TermPositionVector testTermPositionVector = (TermPositionVector) testFreqVectors[freqVectorIndex];


            for (int positionVectorIndex = 0; positionVectorIndex < aprioriFreqVectors[freqVectorIndex].getTerms().length; positionVectorIndex++)
            {
              if (aprioriTermPositionVector.getOffsets(positionVectorIndex) != null) {
                assertTrue(Arrays.equals(aprioriTermPositionVector.getOffsets(positionVectorIndex), testTermPositionVector.getOffsets(positionVectorIndex)));
              }


              if (aprioriTermPositionVector.getTermPositions(positionVectorIndex) != null) {
                assertTrue(Arrays.equals(aprioriTermPositionVector.getTermPositions(positionVectorIndex), testTermPositionVector.getTermPositions(positionVectorIndex)));
              }
            }
          }


        }

View Full Code Here

    for (InstantiatedDocument document : getDocumentsByNumber()) {
      if (document == null) {
        continue; // deleted
      }
      for (Fieldable field : document.getDocument().getFields()) {
        TermPositionVector termPositionVector = (TermPositionVector) sourceIndexReader.getTermFreqVector(document.getDocumentNumber(), field.name());
        if (termPositionVector != null) {
          for (int i = 0; i < termPositionVector.getTerms().length; i++) {
            String token = termPositionVector.getTerms()[i];
            InstantiatedTerm term = findTerm(field.name(), token);
            InstantiatedTermDocumentInformation termDocumentInformation = term.getAssociatedDocument(document.getDocumentNumber());
            termDocumentInformation.setTermOffsets(termPositionVector.getOffsets(i));
          }
        }
      }
    }
  }

View Full Code Here

      catch (IOException e)
      {
         // should never happen, we are reading from a string
      }


      return new TermPositionVector()
      {


         private String[] terms = (String[])termMap.keySet().toArray(new String[termMap.size()]);


         public int[] getTermPositions(int index)

View Full Code Here

    if (tfv == null) {
      throw new IllegalArgumentException(field + " in doc #" + docId
          + "does not have any term position data stored");
    }
    if (tfv instanceof TermPositionVector) {
      TermPositionVector tpv = (TermPositionVector) reader.getTermFreqVector(
          docId, field);
      return getTokenStream(tpv);
    }
    throw new IllegalArgumentException(field + " in doc #" + docId
        + "does not have any term position data stored");

View Full Code Here

      if (DEBUG) System.err.println("MemoryIndexReader.getTermFreqVector");
      final Info info = getInfo(fieldName);
      if (info == null) return null; // TODO: or return empty vector impl???
      info.sortTerms();
      
      return new TermPositionVector() { 
  
        private final Map.Entry<String,ArrayIntList>[] sortedTerms = info.sortedTerms;
        
        public String getField() {
          return fieldName;

View Full Code Here

      catch (IOException e)
      {
         // should never happen, we are reading from a string
      }


      return new TermPositionVector()
      {


         private String[] terms = (String[])termMap.keySet().toArray(new String[termMap.size()]);


         public int[] getTermPositions(int index)

View Full Code Here

         {
            LOG.trace("An exception occurred: " + e.getMessage());
         }
      }


      return new TermPositionVector()
      {


         private String[] terms = termMap.keySet().toArray(new String[termMap.size()]);


         public int[] getTermPositions(int index)

View Full Code Here

         {
            LOG.trace("An exception occurred: " + e.getMessage());
         }
      }


      return new TermPositionVector()
      {


         private String[] terms = termMap.keySet().toArray(new String[termMap.size()]);


         public int[] getTermPositions(int index)

View Full Code Here

0 1 2 3 4 5 6 7

TOP

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

com.sohospace.lucene.analysis.xanalyzer.TestHighLight

net.paoding.analysis.examples.gettingstarted.ch1.English

net.paoding.analysis.examples.gettingstarted.ch2.Chinese

net.paoding.analysis.examples.gettingstarted.ch3.Chinese

net.paoding.analysis.examples.gettingstarted.ch4.Chinese

net.paoding.analysis.examples.gettingstarted.ch5.Chinese

org.apache.jackrabbit.core.query.lucene.AbstractExcerpt

org.apache.lucene.index.memory.MemoryIndex$MemoryIndexReader

org.apache.lucene.search.highlight.TokenSources

org.apache.lucene.search.vectorhighlight.FieldTermStack

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.