Java tutorial
/** * 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. */ 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.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class LinkedGraph { public static class TokenizerMapper extends Mapper<Object, Text, Text, Text> { private final static IntWritable one = new IntWritable(1); // private Text word1 = new Text(); private Text word2 = new Text(); // text can accept string public void map(Object key, Text value, Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); // int count = 0; String[] words = new String[2]; while (itr.hasMoreTokens()) { String tmp = itr.nextToken(); words[count] = tmp; if (count == 1) { word1.set(words[1]); word2.set(words[0]); context.write(word1, word2); // // word2.set(word[0]); // context.write(word2, words[0]); } count = (count + 1) % 2; // word.set(itr.nextToken()); // context.write(word, one); } } } public static class IntSumReducer extends Reducer<Text, Text, Text, Text> { private IntWritable result = new IntWritable(); //accept a string sth = new Text() private Text res = new Text(); public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException { // int sum = 0; StringBuilder sb = new StringBuilder(); String str = null; for (Text val : values) { sb.append(val + " "); } if (sb.length() > 0) { str = "(" + sb.toString().trim() + ")"; } res.set(str); context.write(key, res); // for (IntWritable val : values) { // sum += val.get(); // } // result.set(sum); // //sth.set(res) // 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> <out>"); System.exit(2); } Job job = new Job(conf, "Graph"); job.setJarByClass(LinkedGraph.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }