Hadoop 处理不同的输入文件，文件关联

426次阅读

没有评论

共计 3356 个字符，预计需要花费 9 分钟才能阅读完成。

类型一：一一对应

file1：

a 1

b 2

c 3

file2：

1！

2 @

3 #

file1 和 file2 进行关联，想要的结果：

a !

b @

3 #

思路：

1、标记不同输入文件

2、将 file1 的 key、value 颠倒；file1 和 file2 的 key 相同，file1 的 value 做 key，file2 的 value 做 value，输出。

程序：

package smiple;

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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class FileJoin {

public static class MyMap extends Mapper<LongWritable , Text, Text, Text> {

public void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {
// String line = value.toString();
String line=new String(value.getBytes(),0,value.getLength(),”GBK”);
StringTokenizer tokenizer = new StringTokenizer(line);
String keystr = tokenizer.nextToken();
String valuestr = tokenizer.nextToken();

// 获取文件名
InputSplit inputSplit = context.getInputSplit();
String fileName = ((FileSplit) inputSplit).getPath().getName();

if(“file1”.equals(fileName)){// 加标记
context.write(new Text(valuestr),new Text(“file1_”+keystr));
}else if(“file2”.equals(fileName)){
context.write(new Text(keystr), new Text(“file2_”+valuestr));
}

}
}

public static class MyReduce extends Reducer<Text, Text, Text, Text> {

public void reduce(Text key, Iterable<Text> values,Context context) throws IOException, InterruptedException {
Text resultKey = new Text(“key0”);
Text resultValue = new Text(“value0”);
for (Text val : values) {
if(“file1_”.equals(val.toString().substring(0, 6))){
resultKey = new Text(val.toString().substring(6));
}else if(“file2_”.equals(val.toString().substring(0, 6))){
resultValue = new Text(val.toString().substring(6));
}
}
System.out.println(resultKey.toString()+” ” + resultValue.toString());
context.write(resultKey, resultValue);
}
}

public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] ioArgs = new String[] {“hdfs://ip:port/mr/join/in”,”hdfs://ip:port/mr/join/out”};
String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();

if (otherArgs.length != 2) {
System.err.println(“Usage: Data Sort <in> <out>”);
System.exit(2);
}
Job job = new Job(conf, “file join “);

job.setJarByClass(Sort.class);

// 设置 Map 和 Reduce 处理类
job.setMapperClass(MyMap.class);
job.setReducerClass(MyReduce.class);

// 设置输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);

// 设置输入和输出目录
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

System.exit(job.waitForCompletion(true) ? 0 : 1);

}

Hadoop 处理不同的输入文件，文件关联