blob: 1101ce5041fce9d1965524b869bd4f3a3c2ba046 [file] [log] [blame]
/**
* 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.hadoop.mapred.lib;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
/** A {@link Mapper} that extracts text matching a regular expression.
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class RegexMapper<K> extends MapReduceBase
implements Mapper<K, Text, Text, LongWritable> {
private Pattern pattern;
private int group;
public void configure(JobConf job) {
pattern = Pattern.compile(job.get(org.apache.hadoop.mapreduce.lib.map.
RegexMapper.PATTERN));
group = job.getInt(org.apache.hadoop.mapreduce.lib.map.
RegexMapper.GROUP, 0);
}
public void map(K key, Text value,
OutputCollector<Text, LongWritable> output,
Reporter reporter)
throws IOException {
String text = value.toString();
Matcher matcher = pattern.matcher(text);
while (matcher.find()) {
output.collect(new Text(matcher.group(group)), new LongWritable(1));
}
}
}