MapReduce的多输入、多mapper
虽然一个MapReduce作业的输入可能包含多个输入文件（由文件glob、过滤器和路径组成），但所有文件都由同一个InputFormat和同一个Mapper来解释。然而，数据格式往往会随时间而演变，所以必须写自己的mapper来处理应用中的遗留数据格式问题。或者，有些数据源会提供相同的数据，但是格式不同。
这些问题可以用MultipleInputs类来妥善处理，它允许为每条输入路径指定InputFormat和Mapper。
代码如下
package com.zhen.mapreduce.multipleInput;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* @author FengZhen
* @date 2018年8月25日
* 多输入、多mapper
*/
public class MultipleInputsTest extends Configured implements Tool{
/**
* 根据 ` 分隔字符串
* @author FengZhen
*
*/
static class SplitMapper1 extends Mapper<LongWritable, Text, Text, IntWritable>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
String[] values = value.toString().split("`");
for (String string : values) {
context.write(new Text(string), new IntWritable(1));
}
}
}
/**
* 根据 , 分隔字符串
* @author FengZhen
*
*/
static class SplitMapper2 extends Mapper<LongWritable, Text, Text, IntWritable>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
String[] values = value.toString().split(",");
for (String string : values) {
context.write(new Text(string), new IntWritable(1));
}
}
}
/**
* 同一个reduce
* @author FengZhen
*
*/
static class SplitReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
@Override
protected void reduce(Text key, Iterable<IntWritable> value,
Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable intWritable : value) {
sum += intWritable.get();
}
context.write(key, new IntWritable(sum));
}
}
public int run(String[] args) throws Exception {
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
job.setJobName("MultipleInputs");
job.setJarByClass(MultipleInputsTest.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setReducerClass(SplitReducer.class);
//设置多输入、多mapper
MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, SplitMapper1.class);
MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, SplitMapper2.class);
job.setOutputFormatClass(TextOutputFormat.class);
TextOutputFormat.setOutputPath(job, new Path(args[2]));
return job.waitForCompletion(true) ? 0 : 1;
}
public static void main(String[] args) {
try {
String[] params = {"hdfs://fz/user/hdfs/MapReduce/data/multipleInputs/test1","hdfs://fz/user/hdfs/MapReduce/data/multipleInputs/test1", "hdfs://fz/user/hdfs/MapReduce/data/multipleInputs/output"};
int exitCode = ToolRunner.run(new MultipleInputsTest(), params);
System.exit(exitCode);
} catch (Exception e) {
e.printStackTrace();
}
}
}