package org.apache.lucene.analysis.miscellaneous;
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.IOException;
import java.util.List;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.miscellaneous.StemmerOverrideFilter;
import org.apache.lucene.analysis.util.*;
/**
* Factory for {@link StemmerOverrideFilter}.
* <pre class="prettyprint" >
* <fieldType name="text_dicstem" class="solr.TextField" positionIncrementGap="100">
* <analyzer>
* <tokenizer class="solr.WhitespaceTokenizerFactory"/>
* <filter class="solr.StemmerOverrideFilterFactory" dictionary="dictionary.txt" ignoreCase="false"/>
* </analyzer>
* </fieldType></pre>
*
*/
public class StemmerOverrideFilterFactory extends TokenFilterFactory implements ResourceLoaderAware {
private CharArrayMap<String> dictionary = null;
private boolean ignoreCase;
@Override
public void inform(ResourceLoader loader) throws IOException {
String dictionaryFiles = args.get("dictionary");
ignoreCase = getBoolean("ignoreCase", false);
if (dictionaryFiles != null) {
assureMatchVersion();
List<String> files = splitFileNames(dictionaryFiles);
if (files.size() > 0) {
dictionary = new CharArrayMap<String>(luceneMatchVersion,
files.size() * 10, ignoreCase);
for (String file : files) {
List<String> list = getLines(loader, file.trim());
for (String line : list) {
String[] mapping = line.split("\t", 2);
dictionary.put(mapping[0], mapping[1]);
}
}
}
}
}
public boolean isIgnoreCase() {
return ignoreCase;
}
@Override
public TokenStream create(TokenStream input) {
return dictionary == null ? input : new StemmerOverrideFilter(input, dictionary);
}
}