Package org.apache.lucene.index

Examples of org.apache.lucene.index.TermFreqVector

827
828
829
830
831
832
833
834
835
836
837
     */
    public PriorityQueue<Object[]> retrieveTerms(int docNum) throws IOException {
        Map<String,Int> termFreqMap = new HashMap<String,Int>();
        for (int i = 0; i < fieldNames.length; i++) {
            String fieldName = fieldNames[i];
            TermFreqVector vector = ir.getTermFreqVector(docNum, fieldName);

            // field does not store term vector info
            if (vector == null) {
              Document d=ir.document(docNum);
              String text[]=d.getValues(fieldName);
View Full Code Here
136
137
138
139
140
141
142
143
144
145
146
                        }
                    }
                }
                separator = " ";
            }
            TermFreqVector tfv = reader.getTermFreqVector(
                    docNumber, FieldNames.FULLTEXT);
            if (tfv instanceof TermPositionVector) {
                return createExcerpt((TermPositionVector) tfv, text.toString(),
                        maxFragments, maxFragmentSize);
            } else {
View Full Code Here
417
418
419
420
421
422
423
424
425
    @Override
    public TermFreqVector getTermFreqVector(int docNum, String field) throws IOException
    {

        TermFreqVector termVector = new lucandra.TermFreqVector(getIndexName(), field, docNum);

        return termVector;
    }
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
      f.add( "docFreq", t.text()==null ? 0 : reader.docFreq( t ) ); // this can be 0 for non-indexed fields
           
      // If we have a term vector, return that
      if( fieldable.isTermVectorStored() ) {
        try {
          TermFreqVector v = reader.getTermFreqVector( docId, fieldable.name() );
          if( v != null ) {
            SimpleOrderedMap<Integer> tfv = new SimpleOrderedMap<Integer>();
            for( int i=0; i<v.size(); i++ ) {
              tfv.add( v.getTerms()[i], v.getTermFrequencies()[i] );
            }
            f.add( "termVector", tfv );
          }
        }
        catch( Exception ex ) {
View Full Code Here
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
      f.add( "docFreq", reader.docFreq( t ) ); // this can be 0 for non-indexed fields
           
      // If we have a term vector, return that
      if( fieldable.isTermVectorStored() ) {
        try {
          TermFreqVector v = reader.getTermFreqVector( docId, fieldable.name() );
          if( v != null ) {
            SimpleOrderedMap<Integer> tfv = new SimpleOrderedMap<Integer>();
            for( int i=0; i<v.size(); i++ ) {
              tfv.add( v.getTerms()[i], v.getTermFrequencies()[i] );
            }
            f.add( "termVector", tfv );
          }
        }
        catch( Exception ex ) {
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
67
68
      is.search(tq, vc);
      float vcs = vc.getResultsVector().size();
      Map<Integer,Float> stf = new HashMap<Integer,Float>();
     
      for(Integer j : vc.getResultsVector().keySet()) {
        TermFreqVector tv = ir.getTermFreqVector(j, "txt");
        String [] terms = tv.getTerms();
        for(int k=0;k<tv.size();k++) {
          String term = terms[k];
          if(termMap.containsKey(term)) {
            int termId = termMap.get(term);
            if(!stf.containsKey(termId)) stf.put(termId, 0.0f);
            stf.put(termId, stf.get(termId) + 1.0f/vcs);           
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
    //return coWeightSum / (Math.sqrt(weightSumSquare1) * Math.sqrt(weightSumSquare2));
  }

  private static Map<String,Double> getTfIdfVector(IndexReader ir, int doc, String field) throws Exception {
    Map<String,Double> tfIdf = new HashMap<String,Double>();
    TermFreqVector tv = ir.getTermFreqVector(doc, field);
    double termTotal = 0.0;
    if(tv == null) return tfIdf;
    String [] terms = tv.getTerms();
    int [] counts = tv.getTermFrequencies();
    double docTotal = ir.numDocs();
    for(int i=0;i<tv.size();i++) {
      String term = terms[i];
      //if(!term.matches(".*[A-Za-z].*")) continue;
      termTotal += counts[i];
    }
    for(int i=0;i<tv.size();i++) {
      String term = terms[i].intern();
      //if(!term.matches(".*[A-Za-z].*")) continue;
      double tf = counts[i] / termTotal;
      double idf = Math.log(docTotal / ir.docFreq(new Term(field, term)));
      tfIdf.put(term, tf * idf);
 
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
      Hits h = is.search(getQuery());
      if(h.length() < 20) return null;
      IndexReader ir = is.getIndexReader();
      Bag<String> termBag = new Bag<String>();
      for(int i=0;i<h.length();i++) {
        TermFreqVector tv = ir.getTermFreqVector(h.id(i), "txt");
        String [] terms = tv.getTerms();
        for(int k=0;k<tv.size();k++) {
          String term = terms[k];
          if("In".equals(term)) continue;
          if(TermSets.getClosedClass().contains(term)) continue;
          if(!term.matches(".*[A-Za-z].*")) continue;
          if(!includeTerms.contains(term) && !excludeTerms.contains(term)) termBag.add(terms[k]);
View Full Code Here
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexSearcher is = lis.getIndexSearcher();
    IndexReader ir = lis.getIndexReader();
    Bag<String> tfBag = new Bag<String>();
    for(int i=0;i<ir.maxDoc();i++) {
      TermFreqVector tv = ir.getTermFreqVector(i, "txt");
      String [] terms = tv.getTerms();
      int [] freqs = tv.getTermFrequencies();
      for(int k=0;k<tv.size();k++) {
        String term = terms[k];
        if("In".equals(term)) continue;
        if(TermSets.getClosedClass().contains(term)) continue;
        if(!term.matches(".*[A-Za-z].*")) continue;
        tfBag.add(term, freqs[k]);
      }
    }
    double overallEntropy = tfBag.entropy();
    double totalEntropy = overallEntropy * tfBag.totalCount();
    System.out.println(totalEntropy);
   
    List<String> termList = tfBag.getList().subList(0, 2000);
    for(String splitTerm : termList) {
      Query q = new TermQuery(new Term("txt", splitTerm));
      VectorCollector vc = new VectorCollector();
      is.search(q, vc);
      Bag<String> inBag = new Bag<String>();
      Bag<String> outBag = new Bag<String>();
      for(int i=0;i<ir.maxDoc();i++) {
        Bag<String> bag = inBag;
        if(!vc.getResultsVector().containsKey(i)) continue;
       
        //Bag<String> bag = outBag;
        //if(vc.getResultsVector().containsKey(i)) bag = inBag;
        TermFreqVector tv = ir.getTermFreqVector(i, "txt");
        String [] terms = tv.getTerms();
        int [] freqs = tv.getTermFrequencies();
        for(int k=0;k<tv.size();k++) {
          String term = terms[k];
          if("In".equals(term)) continue;
          if(TermSets.getClosedClass().contains(term)) continue;
          if(!term.matches(".*[A-Za-z].*")) continue;
          bag.add(term, freqs[k]);
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
   
    List<File> clusterFiles = new ArrayList<File>();
    for(Integer i : cluster.keySet()) {
      clusterFiles.add(new File(ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source")));
      if(enriched) {
        TermFreqVector tvf = ir.getTermFreqVector(i, "InChI");
        if(tvf != null) {
          String [] termArray = tvf.getTerms();
          for(int j=0;j<termArray.length;j++) {
            inchis.add(termArray[j]);
          }       
        }
        tvf = ir.getTermFreqVector(i, "Ontology");
        if(tvf != null) {
          String [] termArray = tvf.getTerms();
          for(int j=0;j<termArray.length;j++) {
            onts.add(termArray[j]);
          }       
        }       
      }
View Full Code Here
TOP

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

  • com.browseengine.bobo.sort.SortCollectorImpl
  • edu.wiki.modify.IndexModifier
  • edu.wiki.modify.MemIndexModifier
  • it.unibz.instasearch.indexing.SearchResultDoc
  • lucandra.IndexReader
  • org.apache.jackrabbit.core.query.lucene.AbstractExcerpt
  • org.apache.jackrabbit.core.query.lucene.DefaultXMLExcerpt
  • org.apache.jackrabbit.core.query.lucene.MoreLikeThis
  • org.apache.lucene.analysis.ontology.Test
  • org.apache.lucene.search.highlight.TokenSources
    • 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.