1 package org.apache.lucene.analysis.standard;
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;
22 import org.apache.lucene.analysis.TokenFilter;
23 import org.apache.lucene.analysis.TokenStream;
24 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
25 import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
26 import org.apache.lucene.util.Version;
29 * Normalizes tokens extracted with {@link StandardTokenizer}.
31 public class StandardFilter extends TokenFilter {
32 private final Version matchVersion;
34 /** @deprecated Use {@link #StandardFilter(Version, TokenStream)} instead. */
36 public StandardFilter(TokenStream in) {
37 this(Version.LUCENE_30, in);
40 public StandardFilter(Version matchVersion, TokenStream in) {
42 this.matchVersion = matchVersion;
45 private static final String APOSTROPHE_TYPE = ClassicTokenizer.TOKEN_TYPES[ClassicTokenizer.APOSTROPHE];
46 private static final String ACRONYM_TYPE = ClassicTokenizer.TOKEN_TYPES[ClassicTokenizer.ACRONYM];
48 // this filters uses attribute type
49 private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
50 private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
53 public final boolean incrementToken() throws IOException {
54 if (matchVersion.onOrAfter(Version.LUCENE_31))
55 return input.incrementToken(); // TODO: add some niceties for the new grammar
57 return incrementTokenClassic();
60 public final boolean incrementTokenClassic() throws IOException {
61 if (!input.incrementToken()) {
65 final char[] buffer = termAtt.buffer();
66 final int bufferLength = termAtt.length();
67 final String type = typeAtt.type();
69 if (type == APOSTROPHE_TYPE && // remove 's
71 buffer[bufferLength-2] == '\'' &&
72 (buffer[bufferLength-1] == 's' || buffer[bufferLength-1] == 'S')) {
73 // Strip last 2 characters off
74 termAtt.setLength(bufferLength - 2);
75 } else if (type == ACRONYM_TYPE) { // remove dots
77 for(int i=0;i<bufferLength;i++) {
82 termAtt.setLength(upto);