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

Class org.apache.lucene.index.IndexReader

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

org.apache.lucene.index.IndexReader.docFreq()
Returns the number of documents containing the term t. @throws IOException if there is a low-level IO error

  }
  
  public static void getTermInfo(Directory dir, Term term) throws Exception {
    IndexReader reader = DirectoryReader.open(dir);
    System.out.printf(Locale.ROOT, "%s:%s \t totalTF = %,d \t doc freq = %,d \n",
         term.field(), term.text(), reader.totalTermFreq(term), reader.docFreq(term)); 
  }
   
  private static void usage() {
    System.out
        .println("\n\nusage:\n\t"

View Full Code Here

      aprioriTermDocsSeeker.close();
      testTermDocsSeeker.close();


      // 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) {

View Full Code Here

          //final int docOffset = 0;


          final boolean doCache = random.nextBoolean();
          final boolean doAllGroups = random.nextBoolean();
          if (VERBOSE) {
            System.out.println("TEST: groupSort=" + groupSort + " docSort=" + docSort + " searchTerm=" + searchTerm + " dF=" + r.docFreq(new Term("content", searchTerm))  +" dFBlock=" + rBlocks.docFreq(new Term("content", searchTerm)) + " topNGroups=" + topNGroups + " groupOffset=" + groupOffset + " docOffset=" + docOffset + " doCache=" + doCache + " docsPerGroup=" + docsPerGroup + " doAllGroups=" + doAllGroups + " getScores=" + getScores + " getMaxScores=" + getMaxScores);
          }


          final TermAllGroupsCollector allGroupsCollector;
          if (doAllGroups) {
            allGroupsCollector = new TermAllGroupsCollector("group");

View Full Code Here


    int clusterSize = wpvws.size();


    for (TermEntry termEntry : termEntryMap.values()) {
        
      int corpusDF = reader.docFreq(new Term(this.contentField,termEntry.getTerm()));
      int outDF = corpusDF - termEntry.getDocFreq();
      int inDF = termEntry.getDocFreq();
      double logLikelihoodRatio = scoreDocumentFrequencies(inDF, outDF, clusterSize, numDocs);
      TermInfoClusterInOut termInfoCluster =
          new TermInfoClusterInOut(termEntry.getTerm(), inDF, outDF, logLikelihoodRatio);

View Full Code Here

      aprioriTermDocsSeeker.close();
      testTermDocsSeeker.close();


      // 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) {

View Full Code Here

    writer.close();


    IndexReader reader = IndexReader.open(dir, true);


    // Make sure all terms < max size were indexed
    assertEquals(2, reader.docFreq(new Term("content", "abc")));
    assertEquals(1, reader.docFreq(new Term("content", "bbb")));
    assertEquals(1, reader.docFreq(new Term("content", "term")));
    assertEquals(1, reader.docFreq(new Term("content", "another")));


    // Make sure position is still incremented when

View Full Code Here


    IndexReader reader = IndexReader.open(dir, true);


    // Make sure all terms < max size were indexed
    assertEquals(2, reader.docFreq(new Term("content", "abc")));
    assertEquals(1, reader.docFreq(new Term("content", "bbb")));
    assertEquals(1, reader.docFreq(new Term("content", "term")));
    assertEquals(1, reader.docFreq(new Term("content", "another")));


    // Make sure position is still incremented when
    // massive term is skipped:

View Full Code Here

    IndexReader reader = IndexReader.open(dir, true);


    // Make sure all terms < max size were indexed
    assertEquals(2, reader.docFreq(new Term("content", "abc")));
    assertEquals(1, reader.docFreq(new Term("content", "bbb")));
    assertEquals(1, reader.docFreq(new Term("content", "term")));
    assertEquals(1, reader.docFreq(new Term("content", "another")));


    // Make sure position is still incremented when
    // massive term is skipped:
    TermPositions tps = reader.termPositions(new Term("content", "another"));

View Full Code Here


    // Make sure all terms < max size were indexed
    assertEquals(2, reader.docFreq(new Term("content", "abc")));
    assertEquals(1, reader.docFreq(new Term("content", "bbb")));
    assertEquals(1, reader.docFreq(new Term("content", "term")));
    assertEquals(1, reader.docFreq(new Term("content", "another")));


    // Make sure position is still incremented when
    // massive term is skipped:
    TermPositions tps = reader.termPositions(new Term("content", "another"));
    assertTrue(tps.next());

View Full Code Here

    sa.setMaxTokenLength(100000);
    writer  = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, sa));
    writer.addDocument(doc);
    writer.close();
    reader = IndexReader.open(dir, true);
    assertEquals(1, reader.docFreq(new Term("content", bigTerm)));
    reader.close();


    dir.close();
  }

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.