Hadoop2.x 数据去重

数据是这样的文本文件，一行为一个单词

如: words.txt

aa
aaa
b
xxx
s
v

words2.txt:

aa
bb
aaa
bbb
ddddd
d

代码和单词计数没有太大差别，例如map阶段传入的key为行标,value为这一行所对应的单词, 只要将单词作为key传入下一步骤（shuffle阶段，此阶段默认做了数据排序，分类，combiler的工作), value可以随便指定，因为不会使用到，那shuffle阶段默认排序分类后 以key为输出的key就自动做了去重工作，那么shuffler阶段传入给reduce阶段后，只需要将key打印出来即可

代码为:

package deduplication;

import java.io.IOException;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


public class Dedup extends Configured implements Tool {

	public static class Map extends Mapper<LongWritable, Text, Text, Text> {
		private Text line = new Text();

		@Override
		protected void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			line = value;
			context.write(line, new Text(""));
		}

	}

	public static class Reduce extends Reducer<Text, Text, Text, Text> {
		protected void reduce(Text key, Iterable<Text> value, Context context)
				throws IOException, InterruptedException {
			context.write(key, new Text(""));
		}

	}

	public static void main(String[] args) throws Exception {
		int ret = ToolRunner.run(new Dedup(), args);
		System.exit(ret);
	}

	@Override
	public int run(String[] args) throws Exception {
		// TODO Auto-generated method stub

		Job job = new Job(getConf());
		job.setJarByClass(Dedup.class);
		job.setJobName("dep");

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

		job.setMapperClass(Map.class);
		job.setReducerClass(Reduce.class);

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

		FileInputFormat.setInputPaths(job, new Path(
				"src/deduplication/words.txt"), new Path(
				"src/deduplication/words2.txt"));
		FileOutputFormat.setOutputPath(job, new Path("rst2"));

		boolean success = job.waitForCompletion(true);

		return success ? 0 : 1;
	}

}

结果为：

aa	
aaa	
b	
bb	
bbb	
d	
ddddd	
s	
v	
xxx