HDFS中MapReduce读取多中文件内容进行处理

话不多说，直接上代码：

package Compression;

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.mapred.MultiFileInputFormat;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;



public class Multipule_worldCount {
    //读取逗号分隔符map 
    public static class dhMaper extends Mapper<LongWritable, Text,Text,LongWritable>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] values = value.toString().split(",");
            for (String val:values){
                Text k2 = new Text(val);
                LongWritable v2 = new LongWritable(1);
                context.write(k2,v2);
            }
        }
    }
    //读取空格分隔符map
    public static class kgMapper extends Mapper<LongWritable, Text,Text,LongWritable>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] values = value.toString().split("\\s+");
            for (String val:values){
                Text k2 = new Text(val);
                LongWritable v2 = new LongWritable(1);
                context.write(k2,v2);
            }
        }
    }
//reduce函数
    public static class myReducer extends Reducer<Text,LongWritable,Text,LongWritable>{
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
            Long sum =new Long(0) ;
            for (LongWritable val:values) sum += val.get();
            LongWritable v2 = new LongWritable(sum);
            context.write(key,v2);
        }
    }
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        System.setProperty("HADOOP_USER_NAME","root");
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://bg00:9000");
        conf.set("dfs.client.use.datanode.hostname","true");
        Job job = Job.getInstance(conf);
        job.setJarByClass(Multipule_worldCount.class);
        //利用MultipleInputs实现多种map的输入，需要指定Job，路径，InputFormat，需要执行的Maper类
        MultipleInputs.addInputPath(job,new Path("/s1/"), TextInputFormat.class,kgMapper.class);
        MultipleInputs.addInputPath(job,new Path("/s2/"),TextInputFormat.class,dhMaper.class);
        FileOutputFormat.setOutputPath(job,new Path("/tmp/mul2"));
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        job.setReducerClass(myReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        job.waitForCompletion(true);
    }
}