我对hadoop的map reduce概念完全陌生
我有一些文件是用“：：”分隔的，而不是用空格（“”）分隔的。
hadoop map reduce是否默认使用空格作为分隔符。如果是这样，如何将其更改为接受用户定义的分隔符。
谢谢
谢谢praveen，100gods和eric给我的指导。再次出现了一个问题。我将编写我的代码和错误
我想我可能做错了。所以请澄清我的问题
再次感谢 enter code here ```
package com;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;

public class WordCount {

public static class Map extends MapReduceBase implements
        Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(LongWritable key, Text value,
            OutputCollector<Text, IntWritable> output, Reporter reporter)
            throws IOException {
        String line = value.toString();

        StringTokenizer tokenizer = new StringTokenizer(line);
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            output.collect(word, one);
        }
    }
}

public static class Reduce extends MapReduceBase implements
        Reducer<Text, IntWritable, Text, IntWritable> {
    public void reduce(Text key, Iterator<IntWritable> values,
            OutputCollector<Text, IntWritable> output, Reporter reporter)
            throws IOException {
        int sum = 0;
        while (values.hasNext()) {
            sum += values.next().get();
        }
        output.collect(key, new IntWritable(sum));
    }
}

public static void main(String[] args) throws Exception {
    /*
     * JobConf conf = new JobConf(WordCount.class);
     * conf.setJobName("wordcount");
     */
    Configuration configuration = new Configuration();
    JobConf conf = new JobConf(configuration);

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

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(KeyValueTextInputFormat.class);
    conf.set("key.value.separator.in.input.line", ":::");

    // conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
    // conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator",
    // ":::");

    FileInputFormat.setInputPaths(conf, "/home/vishal/note.txt");
    FileOutputFormat.setOutputPath(conf, new Path("/home/vishal/output"));

    JobClient.runJob(conf);
}

}

下面是错误

12/10/30 12:23:04 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
12/10/30 12:23:04 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
12/10/30 12:23:04 WARN mapred.JobClient: No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
12/10/30 12:23:04 WARN snappy.LoadSnappy: Snappy native library not loaded
12/10/30 12:23:04 INFO mapred.FileInputFormat: Total input paths to process : 1
12/10/30 12:23:04 INFO mapred.JobClient: Running job: job_local_0001
12/10/30 12:23:04 INFO util.ProcessTree: setsid exited with exit code 0
12/10/30 12:23:04 INFO mapred.Task: Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@193722c
12/10/30 12:23:04 INFO mapred.MapTask: numReduceTasks: 1
12/10/30 12:23:04 INFO mapred.MapTask: io.sort.mb = 100
12/10/30 12:23:05 INFO mapred.MapTask: data buffer = 79691776/99614720
12/10/30 12:23:05 INFO mapred.MapTask: record buffer = 262144/327680
12/10/30 12:23:05 WARN mapred.LocalJobRunner: job_local_0001

`java.lang.ClassCastException: org.apache.hadoop.io.Text cannot be cast to org.apache.hadoop.io.LongWritable
at com.WordCount$Map.map(WordCount.java:1)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:50)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:436)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:372)
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:212)
12/10/30 12:23:05 INFO mapred.JobClient: map 0% reduce 0%
12/10/30 12:23:05 INFO mapred.JobClient: Job complete: job_local_0001
12/10/30 12:23:05 INFO mapred.JobClient: Counters: 0
12/10/30 12:23:05 INFO mapred.JobClient: Job Failed: NA
Exception in thread "main" java.io.IOException: Job failed!
at org.apache.hadoop.mapred.JobClient.runJob(JobClient.java:1327)
at com.WordCount.main(WordCount.java:84)