org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilterFactory Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of infinispan-embedded-query
Infinispan Embedded Query All-in-One module
There is a newer version: 9.1.7.Final
package org.apache.lucene.analysis.compound;

/*
 * 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 org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.ResourceLoader;
import org.apache.lucene.analysis.util.ResourceLoaderAware;
import org.apache.lucene.analysis.util.TokenFilterFactory;
import org.apache.lucene.util.IOUtils;

import java.util.Map;
import java.io.IOException;
import java.io.InputStream;
import org.xml.sax.InputSource;

/**
 * Factory for {@link HyphenationCompoundWordTokenFilter}.
 * 
 * This factory accepts the following parameters:
 * 

 *  hyphenator (mandatory): path to the FOP xml hyphenation pattern. 
 *  See http://offo.sourceforge.net/hyphenation/.
 *  
encoding (optional): encoding of the xml hyphenation file. defaults to UTF-8.
 *  
dictionary (optional): dictionary of words. defaults to no dictionary.
 *  
minWordSize (optional): minimal word length that gets decomposed. defaults to 5.
 *  
minSubwordSize (optional): minimum length of subwords. defaults to 2.
 *  
maxSubwordSize (optional): maximum length of subwords. defaults to 15.
 *  
onlyLongestMatch (optional): if true, adds only the longest matching subword 
 *    to the stream. defaults to false.
 * 
 * 
 * 
 * <fieldType name="text_hyphncomp" class="solr.TextField" positionIncrementGap="100">
 *   <analyzer>
 *     <tokenizer class="solr.WhitespaceTokenizerFactory"/>
 *     <filter class="solr.HyphenationCompoundWordTokenFilterFactory" hyphenator="hyphenator.xml" encoding="UTF-8"
 *         dictionary="dictionary.txt" minWordSize="5" minSubwordSize="2" maxSubwordSize="15" onlyLongestMatch="false"/>
 *   </analyzer>
 * </fieldType>
 *
 * @see HyphenationCompoundWordTokenFilter
 */
public class HyphenationCompoundWordTokenFilterFactory extends TokenFilterFactory implements ResourceLoaderAware {
  private CharArraySet dictionary;
  private HyphenationTree hyphenator;
  private final String dictFile;
  private final String hypFile;
  private final String encoding;
  private final int minWordSize;
  private final int minSubwordSize;
  private final int maxSubwordSize;
  private final boolean onlyLongestMatch;
  
  /** Creates a new HyphenationCompoundWordTokenFilterFactory */
  public HyphenationCompoundWordTokenFilterFactory(Map args) {
    super(args);
    assureMatchVersion();
    dictFile = get(args, "dictionary");
    encoding = get(args, "encoding");
    hypFile = require(args, "hyphenator");
    minWordSize = getInt(args, "minWordSize", CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE);
    minSubwordSize = getInt(args, "minSubwordSize", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
    maxSubwordSize = getInt(args, "maxSubwordSize", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
    onlyLongestMatch = getBoolean(args, "onlyLongestMatch", false);
    if (!args.isEmpty()) {
      throw new IllegalArgumentException("Unknown parameters: " + args);
    }
  }
  
  @Override
  public void inform(ResourceLoader loader) throws IOException {
    InputStream stream = null;
    try {
      if (dictFile != null) // the dictionary can be empty.
        dictionary = getWordSet(loader, dictFile, false);
      // TODO: Broken, because we cannot resolve real system id
      // ResourceLoader should also supply method like ClassLoader to get resource URL
      stream = loader.openResource(hypFile);
      final InputSource is = new InputSource(stream);
      is.setEncoding(encoding); // if it's null let xml parser decide
      is.setSystemId(hypFile);
      hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
    } finally {
      IOUtils.closeWhileHandlingException(stream);
    }
  }
  
  @Override
  public HyphenationCompoundWordTokenFilter create(TokenStream input) {
    return new HyphenationCompoundWordTokenFilter(luceneMatchVersion, input, hyphenator, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
  }
}