ASCIIDuplicatingFilterFactory.java

package org.apache.solr.analysis;

/*
 * 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.util.Map;

import org.apache.lucene.analysis.util.AbstractAnalysisFactory;
import org.apache.lucene.analysis.util.MultiTermAwareComponent;
import org.apache.lucene.analysis.util.TokenFilterFactory;
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
import org.apache.lucene.analysis.TokenStream;

/** 
 * A wrapper for the {@link ASCIIFoldingFilter}. It retains the original token and returns the 
 * ASCII folded variant.
 * 
 * It is little bit crazy, because we have to wrap the ASCII filter with two other filters
 * in order to get to the original value.
 *
 */
public class ASCIIDuplicatingFilterFactory extends TokenFilterFactory implements MultiTermAwareComponent {
  public ASCIIDuplicatingFilterFactory(Map<String,String> args) {
    super(args);
    if (!args.isEmpty()) {
      throw new IllegalArgumentException("Unknown parameter(s): " + args);
    }
  }

  public OnChangeDuplicatingFilter create(TokenStream input) {
    return new OnChangeDuplicatingFilter(new ASCIIFoldingFilter(new DuplicatingFilter(input)));
  }

  public AbstractAnalysisFactory getMultiTermComponent() {
	return this;
  }
}