在Hadoop中获取WordCount程序中的异常(Getting the exception in WordCount Program in Hadoop)

 尝试在hadoop上运行第一个程序时，我遇到了这个异常。 （我在版本0.20.2上使用hadoop新API）。 我在网上搜索，当他们没有在配置逻辑中设置MapperClass和ReducerClass时，看起来大多数人都遇到了这个问题。 但我查了一下，看起来代码还可以。 如果有人可以帮助我，我将非常感激。 
 
 java.io.IOException：键入map中的键不匹配：期望org.apache.hadoop.io.Text，收到org.apache.hadoop.mapred.MapTask上的org.apache.hadoop.io.LongWritable $ MapOutputBuffer.collect（MapTask的.java：871） 
 
package com.test.wc;
import java.io.IOException;
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 WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {

public void Map(LongWritable key,Text value,Context ctx) throws IOException , InterruptedException {
    String line = value.toString();
    for(String word:line.split("\\W+")) {
        if(word.length()> 0){
            ctx.write(new Text(word), new IntWritable(1));
        }
    }
}
}


package com.test.wc;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WordCountReducer extends Reducer<Text,IntWritable,Text,IntWritable> {

public void reduce(Text key, Iterable<IntWritable> values, Context ctx) throws IOException,InterruptedException {
 int wordCount = 0;
    for(IntWritable value:values)
    {
        wordCount+=value.get();
    }
    ctx.write(key,new IntWritable(wordCount));
}

}


package com.test.wc;
import java.io.IOException;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCountJob {
public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException{
    if(args.length!=2){
        System.out.println("invalid usage");
        System.exit(-1);
    }

    Job job = new Job();
    job.setJarByClass(WordCountJob.class);
    job.setJobName("WordCountJob");



    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(WordCountMapper.class);
    job.setReducerClass(WordCountReducer.class);

    //job.setCombinerClass(WordCountReducer.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);


    System.exit(job.waitForCompletion(true) ? 0:1);

}
}

I am facing this exception when trying to run the first program on hadoop. (I am using hadoop new API on version 0.20.2). I searched on web, it looks like most of the people faced this problem when they did not set MapperClass and ReducerClass in the configuration logic. But I checked and it looks the code is ok . I will really appreciate if someone can help me out.
 
java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.Text, recieved org.apache.hadoop.io.LongWritable at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.collect(MapTask.java:871)
 
package com.test.wc;
import java.io.IOException;
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 WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {

public void Map(LongWritable key,Text value,Context ctx) throws IOException , InterruptedException {
    String line = value.toString();
    for(String word:line.split("\\W+")) {
        if(word.length()> 0){
            ctx.write(new Text(word), new IntWritable(1));
        }
    }
}
}


package com.test.wc;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WordCountReducer extends Reducer<Text,IntWritable,Text,IntWritable> {

public void reduce(Text key, Iterable<IntWritable> values, Context ctx) throws IOException,InterruptedException {
 int wordCount = 0;
    for(IntWritable value:values)
    {
        wordCount+=value.get();
    }
    ctx.write(key,new IntWritable(wordCount));
}

}


package com.test.wc;
import java.io.IOException;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCountJob {
public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException{
    if(args.length!=2){
        System.out.println("invalid usage");
        System.exit(-1);
    }

    Job job = new Job();
    job.setJarByClass(WordCountJob.class);
    job.setJobName("WordCountJob");



    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(WordCountMapper.class);
    job.setReducerClass(WordCountReducer.class);

    //job.setCombinerClass(WordCountReducer.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);


    System.exit(job.waitForCompletion(true) ? 0:1);

}
}

原文：https://stackoverflow.com/questions/16003237