MapReduce一次读取多个文件（详细步骤）

在Map代码中添加以下代码，可以获取每条数据所属的文件名

Map代码

package com.czxy.Test03;

import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

public class MoreFileMap extends Mapper {

代码语言：javascript复制

@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {


    //获取所属的文件名称
     FileSplit inputSplit = (FileSplit) context.getInputSplit();
    String name = inputSplit.getPath().getName();
    context.write(new Text(name),value);
}

}

Reduce代码

package com.czxy.Test03;

import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class MoreFileReduce extends Reducer {

代码语言：javascript复制

@Override
protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
    for (Text value : values) {

        context.write(key,value);
    }
}

}

Driver代码

package com.czxy.Test03;

import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; 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;

public class MoreFileDriver extends Configured implements Tool { @Override public int run(String[] args) throws Exception { Job job = Job.getInstance(new Configuration(),“lineCount”);

代码语言：javascript复制

    job.setInputFormatClass(TextInputFormat.class);
    TextInputFormat.addInputPath(job,new Path("E:\aaaa.txt"));    文件所在路径

    job.setMapperClass(MoreFileMap.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

    job.setReducerClass(MoreFileReduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);


    job.setOutputFormatClass(TextOutputFormat.class);
    TextOutputFormat.setOutputPath(job,new Path("E:\cccc.txt"));  



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

public static void main(String[] args) throws Exception {
    int run = ToolRunner.run(new MoreFileDriver(), args);
}

}

效果：

aaaa.txt

cccc.txt

hadoop mapreduce java

0 人点赞