MR案例：CombineFileInputFormat

CombineFileInputFormat是一个抽象类。Hadoop提供了两个实现类CombineTextInputFormat和CombineSequenceFileInputFormat。

此案例让我明白了三点：详见 解读：MR多路径输入 和 解读：CombineFileInputFormat类

• 对于单一输入路径情况：

//指定输入格式CombineFileInputFormat
job.setInputFormatClass(CombineTextInputFormat.class); 

//指定SplitSize
CombineTextInputFormat.setMaxInputSplitSize(job, 60*1024*1024L);

//指定输入路径
CombineTextInputFormat.addInputPath(job, new Path(args[0]));

• 对于多路径输入情况①：

//指定输入格式CombineFileInputFormat
job.setInputFormatClass(CombineTextInputFormat.class); 

//指定SplitSize
CombineTextInputFormat.setMaxInputSplitSize(job, 60*1024*1024L);

//指定输入路径(两个)
CombineTextInputFormat.addInputPath(job, new Path(args[0]));
CombineTextInputFormat.addInputPath(job, new Path(args[1]));

• 多路径输入情况②：

//指定SplitSize
CombineTextInputFormat.setMaxInputSplitSize(job, 60*1024*1024L);

//指定输入路径,以及指定输入格式
MultipleInputs.addInputPath(job, new Path(args[0]), CombineTextInputFormat.class);
MultipleInputs.addInputPath(job, new Path(args[1]), CombineTextInputFormat.class);

细心观察，还会发现两种多路径输入① ②的区别：(已验证)

1. 第一种方案：先把所有的输入集中起来求出总的输入大小，再除以SplitSize算出总的map个数
2. 第二种方案：先分别算出每个MultipleInputs路径对应的map个数，再对两个MultipleInputs的map个数求和

完整的代码：

package test0820;

import java.io.IOException;

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.io.VLongWritable;
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.CombineTextInputFormat;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount0826 {

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(WordCount0826.class);      

        job.setMapperClass(IIMapper.class);
        job.setReducerClass(IIReducer.class);
        job.setNumReduceTasks(5);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(VLongWritable.class);

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

        //CombineFileInputFormat类
        //job.setInputFormatClass(CombineTextInputFormat.class); 
        CombineTextInputFormat.setMaxInputSplitSize(job, 60*1024*1024L);

        
        //CombineTextInputFormat.addInputPath(job, new Path(args[0]));
        //CombineTextInputFormat.addInputPath(job, new Path(args[1]));

        MultipleInputs.addInputPath(job, new Path(args[0]), CombineTextInputFormat.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), CombineTextInputFormat.class);

        
        FileOutputFormat.setOutputPath(job, new Path(args[2]));

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

    //map
    public static class IIMapper extends Mapper<LongWritable, Text, Text, VLongWritable>{
        @Override
        protected void map(LongWritable key, Text value,Context context)
                throws IOException, InterruptedException {

            String[] splited = value.toString().split(" "); 

            for(String word : splited){
                context.write(new Text(word),new VLongWritable(1L));
            }
        }
    }

    //reduce
    public static class IIReducer extends Reducer<Text, VLongWritable, Text, VLongWritable>{
        @Override
        protected void reduce(Text key, Iterable<VLongWritable> v2s, Context context)
                throws IOException, InterruptedException {

            long sum=0;

            for(VLongWritable vl : v2s){
                sum += vl.get();                 
            }
            context.write(key, new VLongWritable(sum));
        }
    }
}