Examples of org.apache.lucene.index.TermEnum

org.apache.lucene.index.TermEnum
Abstract class for enumerating terms.
Term enumerations are always ordered by Term.compareTo(). Each term in the enumeration is greater than all that precede it.

      private void collectTermDocs(IndexReader reader, Term start, TermDocsCollector collector) throws IOException
      {
         TermDocs tDocs = reader.termDocs();
         try
         {
            TermEnum terms = reader.terms(start);
            try
            {
               int count = 0;
               do
               {
                  Term t = terms.term();
                  if (t != null && t.field() == start.field())
                  {
                     tDocs.seek(terms);
                     collector.collect(t, tDocs);
                  }
                  else
                  {
                     break;
                  }
                  // once in a while check if we should quit
                  if (++count % 10000 == 0)
                  {
                     if (stopRequested)
                     {
                        break;
                     }
                  }
               }
               while (terms.next());
            }
            finally
            {
               terms.close();
            }
         }
         finally
         {
            tDocs.close();

View Full Code Here

  }


  private void initFacetCounts(IndexReader reader) throws IOException {
    String fieldName = facetRequest.getFieldName();
    // term are enumerated by field name and within field names by term value
    TermEnum terms = reader.terms( new Term( fieldName, "" ) );
    try {
      while ( fieldName.equals( terms.term().field() ) ) {
        String fieldValue = terms.term().text();
        facetCounts.initCount( fieldValue );
        if ( !terms.next() ) {
          break;
        }
      }
    }
    finally {
      terms.close();
    }
  }

View Full Code Here

  }


  private void initFacetCounts(IndexReader reader) throws IOException {
    String fieldName = facetRequest.getFieldName();
    // term are enumerated by field name and within field names by term value
    TermEnum terms = reader.terms( new Term( fieldName, "" ) );
    try {
      while ( fieldName.equals( terms.term().field() ) ) {
        String fieldValue = terms.term().text();
        facetCounts.initCount( fieldValue );
        if ( !terms.next() ) {
          break;
        }
      }
    }
    finally {
      terms.close();
    }
  }

View Full Code Here

                log.debug("IndexFormatVersion >= V3, no migration needed");
                return;
            }
            // assert: there is at least one node in the index, otherwise the
            //         index format version would be at least V3
            TermEnum terms = reader.terms(new Term(FieldNames.PROPERTIES, ""));
            try {
                Term t = terms.term();
                if (t.text().indexOf(oldSeparatorChar) == -1) {
                    log.debug("Index already migrated");
                    return;
                }
            } finally {
                terms.close();
            }
        } finally {
            reader.release();
            index.releaseWriterAndReaders();
        }

View Full Code Here

                            s2 = s2.replace(oldSepChar, '[');
                            return s1.compareTo(s2);
                        }
            });
            // scan through terms and find embedded field names
            TermEnum terms = new RangeScan(in,
                    new Term(FieldNames.PROPERTIES, ""),
                    new Term(FieldNames.PROPERTIES, "\uFFFF"));
            String previous = null;
            while (terms.next()) {
                Term t = terms.term();
                String name = t.text().substring(0, t.text().indexOf(oldSepChar) + 1);
                if (!name.equals(previous)) {
                    termEnums.put(name, new RangeScan(in,
                            new Term(FieldNames.PROPERTIES, name),
                            new Term(FieldNames.PROPERTIES, name + "\uFFFF")));

View Full Code Here

            queue.addAll(enums);
        }


        public boolean next() throws IOException {
            for (;;) {
                TermEnum terms = queue.peek();
                if (terms == null) {
                    // no more enums
                    break;
                }
                if (terms.next()) {
                    return true;
                } else {
                    queue.remove();
                    terms.close();
                }
            }
            return false;
        }

View Full Code Here

            }
            return false;
        }


        public Term term() {
            TermEnum terms = queue.peek();
            if (terms != null) {
                return terms.term();
            }
            return null;
        }

View Full Code Here

            }
            return null;
        }


        public int docFreq() {
            TermEnum terms = queue.peek();
            if (terms != null) {
                return terms.docFreq();
            }
            return 0;
        }

View Full Code Here

   * @throws IOException
   */
  public int addStopWords(IndexReader reader, String fieldName, int maxDocFreq) throws IOException {
    HashSet stopWords = new HashSet();
    String internedFieldName = StringHelper.intern(fieldName);
    TermEnum te = reader.terms(new Term(fieldName));
    Term term = te.term();
    while (term != null) {
      if (term.field() != internedFieldName) {
        break;
      }
      if (te.docFreq() > maxDocFreq) {
        stopWords.add(term.text());
      }
      if (!te.next()) {
        break;
      }
      term = te.term();
    }
    stopWordsPerField.put(fieldName, stopWords);
    
    /* if the stopwords for a field are changed,
     * then saved streams for that field are erased.

View Full Code Here

  private void testTermDocs(Directory aprioriIndex, InstantiatedIndex testIndex) throws Exception {


    IndexReader aprioriReader = IndexReader.open(aprioriIndex);
    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

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.index.TermEnum

com.browseengine.bobo.api.BoboIndexReader

com.browseengine.bobo.facets.data.FacetDataCache

com.browseengine.bobo.facets.data.MultiValueFacetDataCache

com.browseengine.bobo.facets.impl.CompactMultiValueFacetHandler

com.greplin.lucene.filter.PrefixFilter

com.greplin.lucene.query.PhrasePrefixQuery

com.tamingtext.tagging.LuceneTagExtractor

er.indexing.ERIndex

it.unibz.instasearch.indexing.Searcher

lucli.LuceneMethods

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.