MapReduce的KeyValueTextInputFormat

如果行中有分隔符，那么分隔符前面的作为key，后面的作为value；如果没有分隔符，那么整行作为key，value为空

当输入数据的每一行是两列，并用tab分离的形式的时候，KeyValueTextInputformat处理这种格式的文件非常适合。

代码示例：

package com.bigdata.hadoop.mapred;

import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MyKeyValueTextInputFormatApp {

private static final String INPUT_PATH = "hdfs://hadoop1:9000/dir1/hello";
private static final String OUTPUT_PATH = "hdfs://hadoop1:9000/dir1/out";

public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
//分隔符默认是\t
configuration.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, "\t");
Job job = new Job(configuration,MyKeyValueTextInputFormatApp.class.getSimpleName());

final FileSystem fileSystem = FileSystem.get(new URI(OUTPUT_PATH), configuration);
fileSystem.delete(new Path(OUTPUT_PATH),true);

job.setJarByClass(MyKeyValueTextInputFormatApp.class);

FileInputFormat.setInputPaths(job, INPUT_PATH);
//指定使用KeyValueTextInputFormat解析内容 分隔key和value的分隔符默认是\t
job.setInputFormatClass(KeyValueTextInputFormat.class);

job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

job.setNumReduceTasks(0);

FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH));

job.waitForCompletion(true);
}
//做简单输出
public static class MyMapper extends Mapper<Text, Text, Text, LongWritable>{
@Override
protected void map(Text key, Text value,
Mapper<Text, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
context.write(new Text(key), new LongWritable(1));
context.write(new Text(value), new LongWritable(1));
}
}

}