hadoop笔记九：MapReduce做业配置

1.MapReduce做业中有一些默认的配置

当未配置时就会使用自动的配置。

2.mapper介绍

Mapper：封装了应用程序Mapper阶段的数据处理逻辑，下面是hadoop中以及现实了的mapper子类

ChainMapper：方便用户编写链式Map任务， 即Map阶段包含多个Mapper，便可以别写多个自定义map去参与运算。
InverseMapper：一个能交换key和value的Mapper
RegexMapper：检查输入是否匹配某正则表达式， 输出匹配字符串和计数器（用的不多）
TockenCounterMapper：将输入分解为独立的单词， 输出个单词和计数器（以空格分割单词，value值为1）

代码实例：

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.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.chain.ChainMapper;
import org.apache.hadoop.mapreduce.lib.chain.ChainReducer;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.map.InverseMapper;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class PatentReference_0010 extends Configured implements Tool{

    static class PatentReferenceMapper extends Mapper<Text,Text,Text,IntWritable>{
        private IntWritable one=new IntWritable(1);
        @Override
        protected void map(Text key,Text value,Context context) throws IOException, InterruptedException{
            context.write(key,one);
        }
    }

    @Override
    public int run(String[] args) throws Exception{
        Configuration conf=getConf();
        Path input=new Path(conf.get("input"));
        Path output=new Path(conf.get("output"));

        //输入格式为KeyValueTextInputFormat时能够指定key和value的分隔符是什么，它的默认分隔符是"\t"也就是tab键
        conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator",",");

        Job job=Job.getInstance(conf,this.getClass().getSimpleName());
        job.setJarByClass(this.getClass());

        ChainMapper.addMapper(job,InverseMapper.class,
            // 输入的键值类型由InputFormat决定
            Text.class,Text.class,
            // 输出的键值类型与输入的键值类型相反
            Text.class,Text.class,conf);

        ChainMapper.addMapper(job,PatentReferenceMapper.class,
            // 输入的键值类型由前一个Mapper输出的键值类型决定
            Text.class,Text.class,
            Text.class,IntWritable.class,conf);

        ChainReducer.setReducer(job,IntSumReducer.class,
            Text.class,IntWritable.class,
            Text.class,IntWritable.class,conf);

        ChainReducer.addMapper(job,InverseMapper.class,
            Text.class,IntWritable.class,
            IntWritable.class,Text.class,conf);

        job.setInputFormatClass(KeyValueTextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        KeyValueTextInputFormat.addInputPath(job,input);
        TextOutputFormat.setOutputPath(job,output);

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

    public static void main(String[] args) throws Exception{
        System.exit(ToolRunner.run(new P00010_PatentReference_0010(),args));
    }
}