RegexMapper.java
上传用户:quxuerui
上传日期:2018-01-08
资源大小:41811k
文件大小:2k
- /**
- * 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.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. */
- 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("mapred.mapper.regex"));
- group = job.getInt("mapred.mapper.regex.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));
- }
- }
- }