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

     * 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 = wvws.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

    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();


    if (docs.size() >= mincount) { 
    do {
      Term t = te.term();

View Full Code Here

  public void addTaxonomies(Directory[] taxonomies, OrdinalMap[] ordinalMaps) throws IOException {
    // To prevent us stepping on the rest of this class's decisions on when
    // to open a reader, and when not, we'll be opening a new reader instead
    // of using the existing "reader" object:
    IndexReader mainreader = openReader();
    TermEnum mainte = mainreader.terms(new Term(Consts.FULL));


    IndexReader[] otherreaders = new IndexReader[taxonomies.length];
    TermEnum[] othertes = new TermEnum[taxonomies.length];
    for (int i=0; i<taxonomies.length; i++) {
      otherreaders[i] = IndexReader.open(taxonomies[i]);

View Full Code Here


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


    TermEnum terms = reader.terms();
    TermDocs termDocs = reader.termDocs();
    int totalTokenCount2 = 0;
    while(terms.next()) {
      Term term = terms.term();
      /* not-tokenized, but indexed field */

View Full Code Here

    LinkedList<Term> termsWithPrefix = new LinkedList<Term>();
    IndexReader ir = reader;


    // this TermEnum gives "piccadilly", "pie" and "pizza".
    String prefix = "pi";
    TermEnum te = ir.terms(new Term("body", prefix));
    do {
        if (te.term().text().startsWith(prefix))
        {
            termsWithPrefix.add(te.term());
        }

View Full Code Here


    // 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

        System.out.println("FST stores ord");
      } else {
        System.out.println("FST stores docFreq");
      }
    }
    TermEnum termEnum = r.terms(new Term("body", ""));
    if (VERBOSE) {
      System.out.println("TEST: got termEnum=" + termEnum);
    }
    int ord = 0;
    while(true) {

View Full Code Here


        if (VERBOSE) {
          System.out.println("TEST: seek " + randomTerm + " ch[0]=" + (randomTerm.length() == 0 ? -1 : randomTerm.charAt(0)));
        }


        termEnum = r.terms(new Term("body", randomTerm));
        final IntsRefFSTEnum.InputOutput fstSeekResult = fstEnum.seekCeil(toIntsRef(randomTerm));


        if (termEnum.term() == null || !"body".equals(termEnum.term().field())) {
          assertNull("got " + (fstSeekResult == null ? "null" : toString(fstSeekResult.input) + " but expected null"), fstSeekResult);
        } else {

View Full Code Here

                TermEnum terms = null;
                try
                {
                    indexReader = IndexReader.open( indexLocation );
    
                    terms = indexReader.terms( new Term( fieldName, "" ) );
                    while ( fieldName.equals( terms.term().field() ) )
                    {
                        keys.add( terms.term().text() );
    
                        if ( !terms.next() )

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.