1 package org.apache.lucene.search.vectorhighlight;
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
11 * http://www.apache.org/licenses/LICENSE-2.0
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.
20 import java.util.ArrayList;
21 import java.util.Iterator;
22 import java.util.List;
24 import org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo;
27 * A simple implementation of {@link FragListBuilder}.
29 public class SimpleFragListBuilder implements FragListBuilder {
31 public static final int MARGIN = 6;
32 public static final int MIN_FRAG_CHAR_SIZE = MARGIN * 3;
34 public FieldFragList createFieldFragList(FieldPhraseList fieldPhraseList, int fragCharSize) {
35 if( fragCharSize < MIN_FRAG_CHAR_SIZE )
36 throw new IllegalArgumentException( "fragCharSize(" + fragCharSize + ") is too small. It must be " +
37 MIN_FRAG_CHAR_SIZE + " or higher." );
39 FieldFragList ffl = new FieldFragList( fragCharSize );
41 List<WeightedPhraseInfo> wpil = new ArrayList<WeightedPhraseInfo>();
42 Iterator<WeightedPhraseInfo> ite = fieldPhraseList.phraseList.iterator();
43 WeightedPhraseInfo phraseInfo = null;
45 boolean taken = false;
48 if( !ite.hasNext() ) break;
49 phraseInfo = ite.next();
52 if( phraseInfo == null ) break;
54 // if the phrase violates the border of previous fragment, discard it and try next phrase
55 if( phraseInfo.getStartOffset() < startOffset ) continue;
58 wpil.add( phraseInfo );
59 int st = phraseInfo.getStartOffset() - MARGIN < startOffset ?
60 startOffset : phraseInfo.getStartOffset() - MARGIN;
61 int en = st + fragCharSize;
62 if( phraseInfo.getEndOffset() > en )
63 en = phraseInfo.getEndOffset();
68 phraseInfo = ite.next();
70 if( phraseInfo == null ) break;
74 if( phraseInfo.getEndOffset() <= en )
75 wpil.add( phraseInfo );
79 ffl.add( st, en, wpil );