lucene/analysis/common/src/java/org/apache/lucene/analysis/pattern/PatternTokenizerFactory.java

/*
 * 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.pattern;


import java.util.Map;
import java.util.regex.Pattern;

import org.apache.lucene.analysis.util.TokenizerFactory;
import org.apache.lucene.util.AttributeFactory;

/**
 * Factory for {@link PatternTokenizer}.
 * This tokenizer uses regex pattern matching to construct distinct tokens
 * for the input stream.  It takes two arguments:  "pattern" and "group".
 * <br>
 * <ul>
 * <li>"pattern" is the regular expression.</li>
 * <li>"group" says which group to extract into tokens.</li>
 *  </ul>
 * <p>
 * group=-1 (the default) is equivalent to "split".  In this case, the tokens will
 * be equivalent to the output from (without empty tokens):
 * {@link String#split(java.lang.String)}
 * </p>
 * <p>
 * Using group &gt;= 0 selects the matching group as the token.  For example, if you have:<br>
 * <pre>
 *  pattern = \'([^\']+)\'
 *  group = 0
 *  input = aaa 'bbb' 'ccc'
 * </pre>
 * the output will be two tokens: 'bbb' and 'ccc' (including the ' marks).  With the same input
 * but using group=1, the output would be: bbb and ccc (no ' marks)
 * <p>NOTE: This Tokenizer does not output tokens that are of zero length.</p>
 *
 * <pre class="prettyprint">
 * &lt;fieldType name="text_ptn" class="solr.TextField" positionIncrementGap="100"&gt;
 *   &lt;analyzer&gt;
 *     &lt;tokenizer class="solr.PatternTokenizerFactory" pattern="\'([^\']+)\'" group="1"/&gt;
 *   &lt;/analyzer&gt;
 * &lt;/fieldType&gt;</pre> 
 * 
 * @see PatternTokenizer
 * @since solr1.2
 * @lucene.spi {@value #NAME}
 */
public class PatternTokenizerFactory extends TokenizerFactory {

  /** SPI name */
  public static final String NAME = "pattern";

  public static final String PATTERN = "pattern";
  public static final String GROUP = "group";
 
  protected final Pattern pattern;
  protected final int group;
  
  /** Creates a new PatternTokenizerFactory */
  public PatternTokenizerFactory(Map<String,String> args) {
    super(args);
    pattern = getPattern(args, PATTERN);
    group = getInt(args, GROUP, -1);
    if (!args.isEmpty()) {
      throw new IllegalArgumentException("Unknown parameters: " + args);
    }
  }
  
  /**
   * Split the input using configured pattern
   */
  @Override
  public PatternTokenizer create(final AttributeFactory factory) {
    return new PatternTokenizer(factory, pattern, group);
  }
}