Package org.apache.lucene.index

Examples of org.apache.lucene.index.TermPositionVector

274
275
276
277
278
279
280
281
282
283
284
            }
        } 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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
    // just return to make null snippet if un-matched fieldName specified when fieldMatch == true
    if( termSet == null ) return;

    TermFreqVector tfv = reader.getTermFreqVector( docId, fieldName );
    if( tfv == null ) return; // just return to make null snippets
    TermPositionVector tpv = null;
    try{
      tpv = (TermPositionVector)tfv;
    }
    catch( ClassCastException e ){
      return; // just return to make null snippets
    }
   
   
    for( String term : tpv.getTerms() ){
      if( !termSet.contains( term ) ) continue;
      int index = tpv.indexOf( term );
      TermVectorOffsetInfo[] tvois = tpv.getOffsets( index );
      if( tvois == null ) return; // just return to make null snippets
      int[] poss = tpv.getTermPositions( index );
      if( poss == null ) return; // just return to make null snippets
      for( int i = 0; i < tvois.length; i++ )
        termList.add( new TermInfo( term, tvois[i].getStartOffset(), tvois[i].getEndOffset(), poss[i] ) );
    }
   
View Full Code Here
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
      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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
    // load offsets to term-document informations
    for (InstantiatedDocument document : getDocumentsByNumber()) {
      for (Field field : (List<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
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
      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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
      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
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
        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
248
249
250
251
252
253
254
255
256
257
258
    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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
  public FieldTermStack( IndexReader reader, int docId, String fieldName, final FieldQuery fieldQuery ) throws IOException {
    this.fieldName = fieldName;

    TermFreqVector tfv = reader.getTermFreqVector( docId, fieldName );
    if( tfv == null ) return; // just return to make null snippets
    TermPositionVector tpv = null;
    try{
      tpv = (TermPositionVector)tfv;
    }
    catch( ClassCastException e ){
      return; // just return to make null snippets
    }
   
    Set<String> termSet = fieldQuery.getTermSet( fieldName );
    // just return to make null snippet if un-matched fieldName specified when fieldMatch == true
    if( termSet == null ) return;
   
    for( String term : tpv.getTerms() ){
      if( !termSet.contains( term ) ) continue;
      int index = tpv.indexOf( term );
      TermVectorOffsetInfo[] tvois = tpv.getOffsets( index );
      if( tvois == null ) return; // just return to make null snippets
      int[] poss = tpv.getTermPositions( index );
      if( poss == null ) return; // just return to make null snippets
      for( int i = 0; i < tvois.length; i++ )
        termList.add( new TermInfo( term, tvois[i].getStartOffset(), tvois[i].getEndOffset(), poss[i] ) );
    }
   
View Full Code Here
987
988
989
990
991
992
993
994
995
996
997
      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
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
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.