Examples of org.apache.lucene.index.IndexReader.termDocs()

Class org.apache.lucene.index.IndexReader

Examples of org.apache.lucene.index.IndexReader.termDocs()

org.apache.lucene.index.IndexReader.termDocs()
Returns an enumeration of all the documents which contain term. For each document, the document number, the frequency of the term in that document is also provided, for use in search scoring. If term is null, then all non-deleted docs are returned with freq=1. Thus, this method implements the mapping:
The enumeration is ordered by document number. Each document number is greater than all that precede it in the enumeration. @throws IOException if there is a low-level IO error

      if (te.docFreq() > 30) {
        File f = new File(output, term.text() + ".txt");
        PrintWriter pw = new PrintWriter(new FileWriter(f));
        System.err.printf("%s %d\n", term.text(), te.docFreq());
        
        TermDocs td = reader.termDocs(term);
        while (td.next()) {
          int doc = td.doc();
          buf.setLength(0);
          appendVectorTerms(buf, reader.getTermFreqVector(doc, "description-clustering"));
          appendVectorTerms(buf, reader.getTermFreqVector(doc, "extended-clustering"));

View Full Code Here

    // Separately count how many tokens are actually in the index:
    IndexReader reader = IndexReader.open(benchmark.getRunData().getDirectory());
    assertEquals(NUM_DOCS, reader.numDocs());


    TermEnum terms = reader.terms();
    TermDocs termDocs = reader.termDocs();
    int totalTokenCount2 = 0;
    while(terms.next()) {
      termDocs.seek(terms.term());
      while(termDocs.next())
        totalTokenCount2 += termDocs.freq();

View Full Code Here

    IndexReader testReader = testIndex.indexReaderFactory();


    TermEnum aprioriTermEnum = aprioriReader.terms(new Term("c", "danny"));


    TermDocs aprioriTermDocs = aprioriReader.termDocs(aprioriTermEnum.term());
    TermDocs testTermDocs = testReader.termDocs(aprioriTermEnum.term());


    assertEquals(aprioriTermDocs.next(), testTermDocs.next());
    assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());


    assertEquals(aprioriTermDocs.skipTo(100), testTermDocs.skipTo(100));

View Full Code Here

      assertTrue(aprioriTermEnum.docFreq() == testTermEnum.docFreq());


      // compare termDocs seeking


      TermDocs aprioriTermDocsSeeker = aprioriReader.termDocs(aprioriTermEnum.term());
      TermDocs testTermDocsSeeker = testReader.termDocs(testTermEnum.term());


      while (aprioriTermDocsSeeker.next()) {
        assertTrue(testTermDocsSeeker.skipTo(aprioriTermDocsSeeker.doc()));
        assertEquals(aprioriTermDocsSeeker.doc(), testTermDocsSeeker.doc());
      }

View Full Code Here

      // compare documents per term


      assertEquals(aprioriReader.docFreq(aprioriTermEnum.term()), testReader.docFreq(testTermEnum.term()));


      TermDocs aprioriTermDocs = aprioriReader.termDocs(aprioriTermEnum.term());
      TermDocs testTermDocs = testReader.termDocs(testTermEnum.term());


      while (true) {
        if (!aprioriTermDocs.next()) {
          assertFalse(testTermDocs.next());
          break;

View Full Code Here

    doc.add(new Field("partnum", "Q37", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);
    writer.close();


    IndexReader reader = IndexReader.open(dir, true);
    TermDocs td = reader.termDocs(new Term("partnum", "Q36"));
    assertTrue(td.next());
    td = reader.termDocs(new Term("partnum", "Q37"));
    assertTrue(td.next());
  }

View Full Code Here

    writer.close();


    IndexReader reader = IndexReader.open(dir, true);
    TermDocs td = reader.termDocs(new Term("partnum", "Q36"));
    assertTrue(td.next());
    td = reader.termDocs(new Term("partnum", "Q37"));
    assertTrue(td.next());
  }


  // LUCENE-1441
  public void testOffsets() throws Exception {

View Full Code Here


    aprioriTermEnum.close();
    testTermEnum.close();


    TermDocs aprioriTermDocs = aprioriReader.termDocs(t);
    TermDocs testTermDocs = testReader.termDocs(t);


    assertEquals(aprioriTermDocs.next(), testTermDocs.next());
    assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
    assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());

View Full Code Here






    // test seek null (AllTermDocs)
    aprioriTermDocs = aprioriReader.termDocs(null);
    testTermDocs = testReader.termDocs(null);


    while (aprioriTermDocs.next()) {
      assertTrue(testTermDocs.next());
      assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());

View Full Code Here

    testTermDocs.close();




    // test seek default
    aprioriTermDocs = aprioriReader.termDocs();
    testTermDocs = testReader.termDocs();


    // this is invalid use of the API,
    // but if the response differs then it's an indication that something might have changed.
    // in 2.9 and 3.0 the two TermDocs-implementations returned different values at this point.
//    assertEquals("Descripency during invalid use of the TermDocs API, see comments in test code for details.",

View Full Code Here

0 1 2 3 4 5 6 7 8 9

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.