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

Class org.apache.lucene.index.IndexReader

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

org.apache.lucene.index.IndexReader.terms()
Returns an enumeration of all the terms in the index. The enumeration is ordered by Term.compareTo(). Each term is greater than all that precede it in the enumeration. Note that after calling terms(), {@link TermEnum#next()} must be calledon the resulting enumeration before calling other methods such as {@link TermEnum#term()}. @throws IOException if there is a low-level IO error


    // search for "blue* pizza":
    MultiPhraseQuery query3 = new MultiPhraseQuery();
    termsWithPrefix.clear();
    prefix = "blue";
    te = ir.terms(new Term("body", prefix));
    do {
        if (te.term().text().startsWith(prefix))
        {
            termsWithPrefix.add(te.term());
        }

View Full Code Here


    // test seek


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


    assertEquals(aprioriTermEnum.term(), testTermEnum.term());


    t = aprioriTermEnum.term();

View Full Code Here

    }


    // compare term enumeration stepping


    TermEnum aprioriTermEnum = aprioriReader.terms();
    TermEnum testTermEnum = testReader.terms();




    while (true) {


      if (!aprioriTermEnum.next()) {

View Full Code Here

     * in the entire index. To get the in-cluster frequency, we need to query the index to get the term
     * frequencies in each document. The number of results of this call will be the in-cluster document
     * frequency.
     */
    
    TermEnum te = reader.terms(new Term(contentField, ""));
    int count = 0;
    
    Map<String,TermEntry> termEntryMap = new LinkedHashMap<String,TermEntry>();
    do {
      Term term = te.term();

View Full Code Here

    List<TermInfoClusterInOut> clusteredTermInfo = new LinkedList<TermInfoClusterInOut>();
    
    int clusterSize = ids.size();


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

View Full Code Here

    
    List<String> uniqueMimeTypes = null;
    if (retrieveUniqueMimeTypes) {
      // retrieve all possible file types
      uniqueMimeTypesIndexReader = indexAccessor.getReader(false);
      final TermEnum termEnum = uniqueMimeTypesIndexReader.terms(new Term(LUCENE_INDEX_MIMETYPE, ""));
      uniqueMimeTypes = new ArrayList<String>();
      while (termEnum.next() && termEnum.term().field().equals(LUCENE_INDEX_MIMETYPE)) {
        uniqueMimeTypes.add(termEnum.term().text());
      }
    }

View Full Code Here

        reader = IndexReader.open(FSDirectory.open(new File(args[i])));
      }
    }


    TermFreqQueue tiq = new TermFreqQueue(count);
    TermEnum terms = reader.terms();
      
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        TermFreq top = tiq.add(new TermFreq(terms.term(), terms.docFreq()));

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())

View Full Code Here

      usage();
      System.exit(1);
    }


    TermInfoQueue tiq = new TermInfoQueue(numTerms);
    TermEnum terms = reader.terms();


    if (field != null) { 
      while (terms.next()) {
        if (terms.term().field().equals(field)) {
          tiq.insertWithOverflow(new TermInfo(terms.term(), terms.docFreq()));

View Full Code Here

    int min=mincount-1;  // the smallest value in the top 'N' values    
    int off=offset;
    int lim=limit>=0 ? limit : Integer.MAX_VALUE;


    String startTerm = prefix==null ? "" : ft.toInternal(prefix);
    TermEnum te = r.terms(new Term(field,startTerm));
    TermDocs td = r.termDocs();
    SolrIndexSearcher.TermDocsState tdState = new SolrIndexSearcher.TermDocsState();
    tdState.tenum = te;
    tdState.tdocs = td;

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.