Examples of TermFreqVector

org.apache.lucene.index.TermFreqVector
Provides access to stored term vector of a document field.
uk.ac.ucl.panda.utility.structure.TermFreqVector
Provides access to stored term vector of a document field. The vector consists of the name of the field, an array of the terms tha occur in the field of the {@link org.apache.lucene.document.Document} and a parallel array of frequencies. Thus, getTermFrequencies()[5] corresponds with thefrequency of getTerms()[5], assuming there are at least 5 terms in the Document.

Examples of org.apache.lucene.index.TermFreqVector

   */
  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

Examples of org.apache.lucene.index.TermFreqVector

                        }
                    }
                }
                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

Examples of org.apache.lucene.index.TermFreqVector

     */
    private PriorityQueue retrieveTerms(int docNum) throws IOException {
        Map termFreqMap = new HashMap();
        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

Examples of org.apache.lucene.index.TermFreqVector

     */
    public PriorityQueue retrieveTerms(int docNum) throws IOException {
        Map termFreqMap = new HashMap();
        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

Examples of org.apache.lucene.index.TermFreqVector

     */
    public PriorityQueue 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

Examples of org.apache.lucene.index.TermFreqVector

                }
                text.append(separator);
                text.append(fields[i].stringValue());
                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

Examples of org.apache.lucene.index.TermFreqVector

                        }
                    }
                }
                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

Examples of org.apache.lucene.index.TermFreqVector

     */
    private PriorityQueue retrieveTerms(int docNum) throws IOException {
        Map termFreqMap = new HashMap();
        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

Examples of uk.ac.ucl.panda.utility.structure.TermFreqVector

    Iterator i = fieldToReader.entrySet().iterator();
    while (i.hasNext()) {
      Map.Entry e = (Map.Entry)i.next();
      String field = (String)e.getKey();
      IndexReader reader = (IndexReader)e.getValue();
      TermFreqVector vector = reader.getTermFreqVector(n, field);
      if (vector != null)
        results.add(vector);
    }
    return (TermFreqVector[])
      results.toArray(new TermFreqVector[results.size()]);

View Full Code Here

Examples of uk.ac.ucl.panda.utility.structure.TermFreqVector

      df = reader.docFreq(term) * 1.0d;
      DocNum = reader.numDocs();
      idf = Math.log(DocNum / df) * log2toe;
      // calculating P(t|M) M - document collection - LM
      // tfc += f;
      TermFreqVector freqVector = reader.getTermFreqVector(doc, "body");
      populateLengthNormalization(freqVector);
      populateDocumentSpecificityScore(freqVector, DL, DocNum);


      double score = 0;
      // score = model.getscore(tf, df, idf, DL, aveDL, DocNum, CL,

View Full Code Here

0 1 2 3 4 5

TOP

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.