【hadoop学习笔记】4.eclipse运行wordcount实例

新建一个hadoop工程，如图

建一个运行wordcount的类，先不管他什么意思，代码如下

/**
 * Project: hadoop
 * 
 * File Created at 2012-5-21
 * $Id$
 */
package seee.you.app;
import java.io.IOException;
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.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.output.FileOutputFormat;
public class WordCount {
    public static class TokenizerMapper extends 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, Context context)
                throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }
    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
        public void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        if (args.length != 2) {
            System.err.println("Usage: wordcount  ");
            System.exit(2);
        }
        Job job = new Job(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setReducerClass(IntSumReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

这时候右键run on hadoop

 

这时候不幸的是，报错了，错误信息如下：

12/05/23 19:38:51 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
12/05/23 19:38:51 ERROR security.UserGroupInformation: PriviledgedActionException as:yongkang.qiyk cause:java.io.IOException: Failed to set permissions of path: \tmp\hadoop-yongkang\mapred\staging\yongkang.qiyk-1840800210\.staging to 0700
Exception in thread "main" java.io.IOException: Failed to set permissions of path: \tmp\hadoop-yongkang\mapred\staging\yongkang.qiyk-1840800210\.staging to 0700
 at org.apache.hadoop.fs.FileUtil.checkReturnValue(FileUtil.java:682)
 at org.apache.hadoop.fs.FileUtil.setPermission(FileUtil.java:655)
 at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:509)
 at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:344)
 at org.apache.hadoop.fs.FilterFileSystem.mkdirs(FilterFileSystem.java:189)
 at org.apache.hadoop.mapreduce.JobSubmissionFiles.getStagingDir(JobSubmissionFiles.java:116)
 at org.apache.hadoop.mapred.JobClient$2.run(JobClient.java:856)
 at org.apache.hadoop.mapred.JobClient$2.run(JobClient.java:850)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:396)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1093)
 at org.apache.hadoop.mapred.JobClient.submitJobInternal(JobClient.java:850)
 at org.apache.hadoop.mapreduce.Job.submit(Job.java:500)
 at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:530)
 at seee.you.app.WordCount.main(WordCount.java:80)

 

错误信息很明显了，at org.apache.hadoop.fs.FileUtil.checkReturnValue(FileUtil.java:682) 这一行的方法报错了

 

网上查到这是由于0.20.203.0以后的版本的权限认证引起的，只有去掉才行

修改hadoop源代码，去除权限认证，修改FileUtil.java的checkReturnValue方法，如下：

private static void checkReturnValue(boolean rv, File p,
FsPermission permission
) throws IOException {
// if (!rv) {
// throw new IOException("Failed to set permissions of path: " + p +
// " to " +
// String.format("%04o", permission.toShort()));
// }
}

 

去掉这一行后，需要重新编译打包下，打包成功之后，可以将hadoop-core-1.0.2.jar拷贝到hadoop根目录下，eclipse中重新导入下即可（我用的这个1.0.2是从网上下载的修改好的，比较省事）

 

这时重新运行下实例，运行实例需要配置下arguments参数，我的配置如下：

 

run一下，结果如下，说明已经成功了

12/05/28 21:16:29 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
12/05/28 21:16:29 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
****hdfs://10.16.110.7:9000/user/yongkang/test-in
12/05/28 21:16:29 INFO input.FileInputFormat: Total input paths to process : 0
12/05/28 21:16:30 INFO mapred.JobClient: Running job: job_local_0001
12/05/28 21:16:30 INFO mapred.Task:  Using ResourceCalculatorPlugin : null
12/05/28 21:16:30 INFO mapred.LocalJobRunner: 
12/05/28 21:16:30 INFO mapred.Merger: Merging 0 sorted segments
12/05/28 21:16:30 INFO mapred.Merger: Down to the last merge-pass, with 0 segments left of total size: 0 bytes
12/05/28 21:16:30 INFO mapred.LocalJobRunner: 
12/05/28 21:16:30 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
12/05/28 21:16:30 INFO mapred.LocalJobRunner: 
12/05/28 21:16:30 INFO mapred.Task: Task attempt_local_0001_r_000000_0 is allowed to commit now
12/05/28 21:16:30 INFO output.FileOutputCommitter: Saved output of task 'attempt_local_0001_r_000000_0' to /user/yongkang/test-out6
12/05/28 21:16:31 INFO mapred.JobClient:  map 0% reduce 0%
12/05/28 21:16:33 INFO mapred.LocalJobRunner: reduce > reduce
12/05/28 21:16:33 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
12/05/28 21:16:34 INFO mapred.JobClient:  map 0% reduce 100%
12/05/28 21:16:34 INFO mapred.JobClient: Job complete: job_local_0001
12/05/28 21:16:34 INFO mapred.JobClient: Counters: 10
12/05/28 21:16:34 INFO mapred.JobClient:   File Output Format Counters 
12/05/28 21:16:34 INFO mapred.JobClient:     Bytes Written=0
12/05/28 21:16:34 INFO mapred.JobClient:   FileSystemCounters
12/05/28 21:16:34 INFO mapred.JobClient:     FILE_BYTES_READ=8604
12/05/28 21:16:34 INFO mapred.JobClient:     FILE_BYTES_WRITTEN=51882
12/05/28 21:16:34 INFO mapred.JobClient:   Map-Reduce Framework
12/05/28 21:16:34 INFO mapred.JobClient:     Reduce input groups=0
12/05/28 21:16:34 INFO mapred.JobClient:     Combine output records=0
12/05/28 21:16:34 INFO mapred.JobClient:     Reduce shuffle bytes=0
12/05/28 21:16:34 INFO mapred.JobClient:     Reduce output records=0
12/05/28 21:16:34 INFO mapred.JobClient:     Spilled Records=0
12/05/28 21:16:34 INFO mapred.JobClient:     Total committed heap usage (bytes)=5177344
12/05/28 21:16:34 INFO mapred.JobClient:     Reduce input records=0