2
* Licensed to the Apache Software Foundation (ASF) under one or more
3
* contributor license agreements. See the NOTICE file distributed with
4
* this work for additional information regarding copyright ownership.
5
* The ASF licenses this file to You under the Apache License, Version 2.0
6
* (the "License"); you may not use this file except in compliance with
7
* the License. You may obtain a copy of the License at
9
* http://www.apache.org/licenses/LICENSE-2.0
11
* Unless required by applicable law or agreed to in writing, software
12
* distributed under the License is distributed on an "AS IS" BASIS,
13
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
* See the License for the specific language governing permissions and
15
* limitations under the License.
18
package org.apache.solr.analysis;
20
import org.apache.lucene.analysis.*;
22
import java.io.Reader;
23
import java.io.IOException;
26
* @version $Id: SolrAnalyzer.java 1065312 2011-01-30 16:08:25Z rmuir $
28
public abstract class SolrAnalyzer extends Analyzer {
31
public void setPositionIncrementGap(int gap) {
36
public int getPositionIncrementGap(String fieldName) {
40
/** wrap the reader in a CharStream, if appropriate */
41
public Reader charStream(Reader reader){
46
public TokenStream tokenStream(String fieldName, Reader reader) {
47
return getStream(fieldName, reader).getTokenStream();
50
public static class TokenStreamInfo {
51
private final Tokenizer tokenizer;
52
private final TokenStream tokenStream;
53
public TokenStreamInfo(Tokenizer tokenizer, TokenStream tokenStream) {
54
this.tokenizer = tokenizer;
55
this.tokenStream = tokenStream;
57
public Tokenizer getTokenizer() { return tokenizer; }
58
public TokenStream getTokenStream() { return tokenStream; }
62
public abstract TokenStreamInfo getStream(String fieldName, Reader reader);
65
public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
66
// if (true) return tokenStream(fieldName, reader);
67
TokenStreamInfo tsi = (TokenStreamInfo)getPreviousTokenStream();
69
tsi.getTokenizer().reset(charStream(reader));
70
// the consumer will currently call reset() on the TokenStream to hit all the filters.
71
// this isn't necessarily guaranteed by the APIs... but is currently done
72
// by lucene indexing in DocInverterPerField, and in the QueryParser
73
return tsi.getTokenStream();
75
tsi = getStream(fieldName, reader);
76
setPreviousTokenStream(tsi);
77
return tsi.getTokenStream();