實現原理分析:
map函數數將輸入的文本按照行讀取, 並將Key--每一行的內容 輸出 value--空。
reduce 會自動統計所有的key,我們讓reduce輸出key->輸入的key value->空,這樣就利用reduce自動合並相同的key的原理實現了數據去重。
源代碼:
package com.duking.hadoop;
import java.io.IOException;
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 Dedup {
// map將輸入中的value復制到輸出數據的key上,並直接輸出
public static class Map extends Mapper<Object, Text, Text, Text> {
private static Text line = new Text();// 每行數據
// 實現map函數
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
line = value;
context.write(line, new Text(""));
}
}
// reduce將輸入中的key復制到輸出數據的key上,並直接輸出 這是數據區重的思想
public static class Reduce extends Reducer<Text, Text, Text, Text> {
// 實現reduce函數
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
context.write(key, new Text(""));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
// 這句話很關鍵
conf.set("mapred.job.tracker", "192.168.60.129:9000");
//指定帶運行參數的目錄為輸入輸出目錄
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
/* 指定工程下的input2為文件輸入目錄 output2為文件輸出目錄
String[] ioArgs = new String[] { "input2", "output2" };
String[] otherArgs = new GenericOptionsParser(conf, ioArgs)
.getRemainingArgs();*/
if (otherArgs.length != 2) { //判斷路徑參數是否為2個
System.err.println("Usage: Data Deduplication <in> <out>");
System.exit(2);
}
//set maprduce job name
Job job = new Job(conf, "Data Deduplication");
job.setJarByClass(Dedup.class);
// 設置Map、Combine和Reduce處理類
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
// 設置輸出類型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 設置輸入和輸出目錄
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
