/*
* 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.
*/
package org.apache.lucene.analysis.ngram;
import java.util.Map;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.TokenFilterFactory;
/**
* Factory for {@link NGramTokenFilter}.
* <pre class="prettyprint">
* <fieldType name="text_ngrm" class="solr.TextField" positionIncrementGap="100">
* <analyzer>
* <tokenizer class="solr.WhitespaceTokenizerFactory"/>
* <filter class="solr.NGramFilterFactory" minGramSize="1" maxGramSize="2"/>
* </analyzer>
* </fieldType></pre>
*/
public class NGramFilterFactory extends TokenFilterFactory {
private final int maxGramSize;
private final int minGramSize;
/** Creates a new NGramFilterFactory */
public NGramFilterFactory(Map<String, String> args) {
super(args);
minGramSize = getInt(args, "minGramSize", NGramTokenFilter.DEFAULT_MIN_NGRAM_SIZE);
maxGramSize = getInt(args, "maxGramSize", NGramTokenFilter.DEFAULT_MAX_NGRAM_SIZE);
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
}
}
@Override
public TokenFilter create(TokenStream input) {
return new NGramTokenFilter(input, minGramSize, maxGramSize);
}
}