package org.apache.hadoop.examples; 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 WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); 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, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
1)Map过程
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } }
Map过程需要继承org.apache.hadoop.mapreduce包中Mapper类,并重写其map方法。通过在map方法中添加两句把key值和value值输出到控制台的代码, 可以发现map方法中value值存储的是文本文件中的一行(以回车符为行结束标记),而key值为该行的首字母相对于文本文件的首地址的偏移量。然后StringTokenizer类将每一行拆分成为一个个的单词,并将<word,1>作为map方法的结果输出,其余的工作都交有MapReduce框架处理。
2)Reduce过程
public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } }
Reduce过程需要继承org.apache.hadoop.mapreduce包中Reducer类,并重写其reduce方法。Map过程输出<key,values>中key为单个单词,而values是对应单词的计数值所组成的列表,Map的输出就是Reduce的输入,所以reduce方法只要遍历values并求和,即可得到某个单词的总次数。
3)执行MapReduce任务
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, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
在MapReduce中, 由Job对象负责管理和运行一个计算任务,并通过Job的一些方法对任务的参数进行相关的设置。此处设置了使用TokenizerMapper完成Map过程中的处理和使用IntSumReducer完成Combine和Reduce过程中的处理。还设置了Map过程和Reduce过程的输出类型:key的类型为Text,value的类型为IntWritable。任务的输出和输入路径则由命令行参数指定,并由FileInputFormat和FileOutputFormat分别设定。完成相应任务的参数设定后,即可调用job.waitForCompletion()方法执行任务。
转自: http://www.cnblogs.com/xia520pi/archive/2012/05/16/2504205.html