capturer.valueMerge.java Source code

Introduction

Here is the source code for capturer.valueMerge.java

Source

/**
 * 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 capturer;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class valueMerge {
    public static class TokenizerMapper extends Mapper<Object, Text, Text, Text> {
        private Text word = new Text();
        private Text trafficInfo = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] OneRecord = value.toString().split("\t");
            if (OneRecord.length > 6 && !OneRecord[0].equals("time")) {
                String userID = OneRecord[1];
                String hostName = OneRecord[3];
                String spName = OneRecord[4];
                String upTraffic = OneRecord[5];
                String dnTraffic = OneRecord[6];
                word.set(userID + '\t' + spName);
                trafficInfo.set(upTraffic + '\t' + dnTraffic);
                context.write(word, trafficInfo);
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, Text, Text, Text> {
        private Text result = new Text();

        public void reduce(Text key, Iterable<Text> values, Context context)
                throws IOException, InterruptedException {
            int upTrafficSum = 0;
            int dnTrafficSum = 0;
            int count = 0;
            for (Text val : values) {
                String[] trafficInfo = val.toString().split("\t");
                upTrafficSum += Integer.parseInt(trafficInfo[0]);
                dnTrafficSum += Integer.parseInt(trafficInfo[1]);
                count += 1;
            }
            result.set(String.valueOf(count) + '\t' + String.valueOf(upTrafficSum) + '\t'
                    + String.valueOf(dnTrafficSum));
            context.write(key, result);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "so fast");
        job.setJarByClass(valueMerge.class);

        job.setMapperClass(TokenizerMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        for (int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}