大数据Hadoop之KeyValueTextInputFormat使用案例

1．需求

统计输入文件中每一行的第一个单词相同的行数。

（1）输入数据

banzhang ni hao
xihuan hadoop banzhang
banzhang ni hao
xihuan hadoop banzhang

（2）期望结果数据

banzhang	2
xihuan	2

2．需求分析

3. 代码实现

Mapper：

package com.mapreduce.kvsplit;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class KVSplitMapper extends Mapper<Text, Text, Text, LongWritable>{
	
	LongWritable v = new LongWritable(1);
	protected void map(Text key, Text value, Context context) 
			throws java.io.IOException ,InterruptedException {
		// 1. 直接写出
		context.write(key, v);
	}; 
}

Reducer：

package com.mapreduce.kvsplit;

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

public class KVSplitReducer extends Reducer<Text, LongWritable, Text, IntWritable>{
	
	protected void reduce(Text k, java.lang.Iterable<LongWritable> values, Context context) 
			throws java.io.IOException ,InterruptedException {
		int sum = 0; // 用于记录行数的总和
		// 1. 遍历values
		for(LongWritable l : values) {
			sum += l.get();
		}
		// 2. 写出
		context.write(k, new IntWritable(sum));
	}; 
}

Driver：

package com.mapreduce.kvsplit;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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.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 KVSplitDriver {
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		
		args = new String[] {"D:\\hadoop-2.7.1\\winMR\\KVSplit\\input", 
				"D:\\hadoop-2.7.1\\winMR\\KVSplit\\output1"};
		// 1. 获取job实例
		Configuration conf = new Configuration();
		// 8. 设置kv的分隔符为空格符
		conf.set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR, " ");
		Job job = Job.getInstance(conf);
		
		// 2. 设置jar
		job.setJarByClass(KVSplitDriver.class);
		
		// 3. 关联map和reduce
		job.setMapperClass(KVSplitMapper.class);
		job.setReducerClass(KVSplitReducer.class);
		
		// 4. 设置map的kv输出类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(LongWritable.class);
		
		// 5. 设置最终的kv类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		// 9. 设置job的分片机制
		job.setInputFormatClass(KeyValueTextInputFormat.class);
		// 6. 设置输入输出路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		// 7. 提交job
		job.waitForCompletion(true);
	}
}

4. 运行结果