mapreduce代码整理之实现压缩输出减少网络传输

在mian函数里这样写

public static void main(String[] args) throws Exception {  
Configuration conf = new Configuration();
conf.setStrings("mapred.tasktracker.reduce.tasks.maximum", "4");
conf.setClass("mapred.map.output.compression.codec", GzipCodec.class, CompressionCodec.class);//代码实现map输出压缩减少网络传输压力
Job job = new Job(conf);  
job.setJarByClass(fenxi.class);  
job.setJobName("wordcount");  

job.setOutputKeyClass(Text.class);  
job.setOutputValueClass(IntWritable.class);  
job.setNumReduceTasks(2);
job.setMapperClass(WordCountMap.class);  
job.setReducerClass(WordCountReduce.class);  

job.setInputFormatClass(TextInputFormat.class);  
job.setOutputFormatClass(TextOutputFormat.class);  

FileInputFormat.addInputPath(job, new Path(args[0]));  
FileOutputFormat.setOutputPath(job, new Path(args[1]));  

FileOutputFormat.setCompressOutput(job,true);//代码实现输出压缩
FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

job.waitForCompletion(true);  
}  
}

输出结果：