Save This Page
Home » lucene-3.0.1-src » org.apache » lucene » search » highlight » [javadoc | source]
    1   package org.apache.lucene.search.highlight;
    2   
    3   /**
    4    * Licensed to the Apache Software Foundation (ASF) under one or more
    5    * contributor license agreements.  See the NOTICE file distributed with
    6    * this work for additional information regarding copyright ownership.
    7    * The ASF licenses this file to You under the Apache License, Version 2.0
    8    * (the "License"); you may not use this file except in compliance with
    9    * the License.  You may obtain a copy of the License at
   10    *
   11    *     http://www.apache.org/licenses/LICENSE-2.0
   12    *
   13    * Unless required by applicable law or agreed to in writing, software
   14    * distributed under the License is distributed on an "AS IS" BASIS,
   15    * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   16    * See the License for the specific language governing permissions and
   17    * limitations under the License.
   18    */
   19   
   20   import org.apache.lucene.analysis.Token;
   21   import org.apache.lucene.analysis.TokenStream;
   22   import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
   23   import org.apache.lucene.analysis.tokenattributes.TermAttribute;
   24   
   25   /**
   26    * One, or several overlapping tokens, along with the score(s) and the scope of
   27    * the original text
   28    */
   29   public class TokenGroup {
   30   
   31     private static final int MAX_NUM_TOKENS_PER_GROUP = 50;
   32     Token [] tokens=new Token[MAX_NUM_TOKENS_PER_GROUP];
   33     float[] scores = new float[MAX_NUM_TOKENS_PER_GROUP];
   34     int numTokens = 0;
   35     int startOffset = 0;
   36     int endOffset = 0;
   37     float tot;
   38     int matchStartOffset, matchEndOffset;
   39   
   40     private OffsetAttribute offsetAtt;
   41     private TermAttribute termAtt;
   42   
   43     public TokenGroup(TokenStream tokenStream) {
   44       offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
   45       termAtt = tokenStream.addAttribute(TermAttribute.class);
   46     }
   47   
   48     void addToken(float score) {
   49       if (numTokens < MAX_NUM_TOKENS_PER_GROUP) {
   50         int termStartOffset = offsetAtt.startOffset();
   51         int termEndOffset = offsetAtt.endOffset();
   52         if (numTokens == 0) {
   53           startOffset = matchStartOffset = termStartOffset;
   54           endOffset = matchEndOffset = termEndOffset;
   55           tot += score;
   56         } else {
   57           startOffset = Math.min(startOffset, termStartOffset);
   58           endOffset = Math.max(endOffset, termEndOffset);
   59           if (score > 0) {
   60             if (tot == 0) {
   61               matchStartOffset = offsetAtt.startOffset();
   62               matchEndOffset = offsetAtt.endOffset();
   63             } else {
   64               matchStartOffset = Math.min(matchStartOffset, termStartOffset);
   65               matchEndOffset = Math.max(matchEndOffset, termEndOffset);
   66             }
   67             tot += score;
   68           }
   69         }
   70         Token token = new Token(termStartOffset, termEndOffset);
   71         token.setTermBuffer(termAtt.term());
   72         tokens[numTokens] = token;
   73         scores[numTokens] = score;
   74         numTokens++;
   75       }
   76     }
   77   
   78     boolean isDistinct() {
   79       return offsetAtt.startOffset() >= endOffset;
   80     }
   81   
   82     void clear() {
   83       numTokens = 0;
   84       tot = 0;
   85     }
   86     
   87     /* 
   88     * @param index a value between 0 and numTokens -1
   89     * @return the "n"th token
   90     */
   91    public Token getToken(int index)
   92    {
   93        return tokens[index];
   94    }
   95   
   96     /**
   97      * 
   98      * @param index a value between 0 and numTokens -1
   99      * @return the "n"th score
  100      */
  101     public float getScore(int index) {
  102       return scores[index];
  103     }
  104   
  105     /**
  106      * @return the end position in the original text
  107      */
  108     public int getEndOffset() {
  109       return endOffset;
  110     }
  111   
  112     /**
  113      * @return the number of tokens in this group
  114      */
  115     public int getNumTokens() {
  116       return numTokens;
  117     }
  118   
  119     /**
  120      * @return the start position in the original text
  121      */
  122     public int getStartOffset() {
  123       return startOffset;
  124     }
  125   
  126     /**
  127      * @return all tokens' scores summed up
  128      */
  129     public float getTotalScore() {
  130       return tot;
  131     }
  132   }

Save This Page
Home » lucene-3.0.1-src » org.apache » lucene » search » highlight » [javadoc | source]