对于两个输入文件,即文件A和文件B,编写MapReduce程序,对两个文件进行合并,并剔除其中重复的内容,得到一个新的输出文件C。
数据放TXT文件时,不能多出数据外的空行光标,不然运行程序时会显示错误:For input string: “”
直接运行Java代码得出结果
package Merge;
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 Merge {
/**
* @param args
* 对 A,B 两个文件进行合并,并剔除其中重复的内容,得到一个新的输出文件 C
*/
//重载 map 函数,直接将输入中的 value 复制到输出数据的 key 上
public static class Map extends Mapper<Object, Text, Text, Text>{
private static Text text = new Text();
public void map(Object key, Text value, Context context) throws
IOException,InterruptedException{
text = value;
context.write(text, new Text(""));
} }
//重载 reduce 函数,直接将输入中的 key 复制到输出数据的 key 上
public static class Reduce extends Reducer<Text, Text, Text, Text>{
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{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("fs.default.name","hdfs://localhost:9000");
String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数
*/
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in><out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and duplicate removal");
job.setJarByClass(Merge.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.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);
}
}