1 package org.apache.lucene.analysis.miscellaneous;
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.io.IOException;
23 import org.apache.lucene.analysis.CharArrayMap;
24 import org.apache.lucene.analysis.TokenFilter;
25 import org.apache.lucene.analysis.TokenStream;
26 import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
27 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
28 import org.apache.lucene.util.Version;
31 * Provides the ability to override any {@link KeywordAttribute} aware stemmer
32 * with custom dictionary-based stemming.
34 public final class StemmerOverrideFilter extends TokenFilter {
35 private final CharArrayMap<String> dictionary;
37 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
38 private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
41 * Create a new StemmerOverrideFilter, performing dictionary-based stemming
42 * with the provided <code>dictionary</code>.
44 * Any dictionary-stemmed terms will be marked with {@link KeywordAttribute}
45 * so that they will not be stemmed with stemmers down the chain.
48 public StemmerOverrideFilter(Version matchVersion, TokenStream input,
49 Map<?,String> dictionary) {
51 this.dictionary = dictionary instanceof CharArrayMap ?
52 (CharArrayMap<String>) dictionary : CharArrayMap.copy(matchVersion, dictionary);
56 public boolean incrementToken() throws IOException {
57 if (input.incrementToken()) {
58 if (!keywordAtt.isKeyword()) { // don't muck with already-keyworded terms
59 String stem = dictionary.get(termAtt.buffer(), 0, termAtt.length());
61 termAtt.setEmpty().append(stem);
62 keywordAtt.setKeyword(true);