001    /**
002     * Licensed to the Apache Software Foundation (ASF) under one
003     * or more contributor license agreements.  See the NOTICE file
004     * distributed with this work for additional information
005     * regarding copyright ownership.  The ASF licenses this file
006     * to you under the Apache License, Version 2.0 (the
007     * "License"); you may not use this file except in compliance
008     * with the License.  You may obtain a copy of the License at
009     *
010     *     http://www.apache.org/licenses/LICENSE-2.0
011     *
012     * Unless required by applicable law or agreed to in writing, software
013     * distributed under the License is distributed on an "AS IS" BASIS,
014     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015     * See the License for the specific language governing permissions and
016     * limitations under the License.
017     */
018    
019    package org.apache.hadoop.mapreduce.lib.map;
020    
021    import java.io.IOException;
022    import java.util.regex.Matcher;
023    import java.util.regex.Pattern;
024    
025    import org.apache.hadoop.classification.InterfaceAudience;
026    import org.apache.hadoop.classification.InterfaceStability;
027    import org.apache.hadoop.conf.Configuration;
028    import org.apache.hadoop.io.LongWritable;
029    import org.apache.hadoop.io.Text;
030    import org.apache.hadoop.mapreduce.Mapper;
031    
032    
033    /** A {@link Mapper} that extracts text matching a regular expression. */
034    @InterfaceAudience.Public
035    @InterfaceStability.Stable
036    public class RegexMapper<K> extends Mapper<K, Text, Text, LongWritable> {
037    
038      public static String PATTERN = "mapreduce.mapper.regex";
039      public static String GROUP = "mapreduce.mapper.regexmapper..group";
040      private Pattern pattern;
041      private int group;
042    
043      public void setup(Context context) {
044        Configuration conf = context.getConfiguration();
045        pattern = Pattern.compile(conf.get(PATTERN));
046        group = conf.getInt(GROUP, 0);
047      }
048    
049      public void map(K key, Text value,
050                      Context context)
051        throws IOException, InterruptedException {
052        String text = value.toString();
053        Matcher matcher = pattern.matcher(text);
054        while (matcher.find()) {
055          context.write(new Text(matcher.group(group)), new LongWritable(1));
056        }
057      }
058    }