|
package testMap;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;
import org.apache.hadoop.util.*;
public class WordCount extends Configured implements Tool {
public static class Map extends Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
int count = 0;
Text aa = new Text();
aa.set("AA");
while (itr.hasMoreTokens()) {
count++;
word.set(itr.nextToken());
System.out.println("word=" + word.toString() + ",count="
+ count);
context.write(word, one);
}
}
}
public static class Reduce 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) {
System.out.println("val=" + val.get());
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public int run(String[] args) throws Exception {
boolean useJobTracker = true;
Configuration conf = new Configuration();
conf.set("fs.default.name", "hdfs://localhost:9000");
if (useJobTracker)
conf.set("mapred.job.tracker", "localhost:9001");
else
conf.set("mapred.job.tracker", "local");
FileSystem hdfs = FileSystem.get(conf);
Job job = new Job(conf, "WordCount");
job.setJarByClass(WordCount.class);
job.setJobName("WordCount");
job.setInputFormatClass(TextInputFormat.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setOutputFormatClass(TextOutputFormat.class);
Path dst_path = new Path(args[1]);
if (hdfs.exists(dst_path)) {
hdfs.delete(dst_path, true);
System.out.println("檔案已經存在");
} else {
System.out.println("檔案不存在");
}
FileOutputFormat.setOutputPath(job, dst_path);
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;// 如果是true 回傳0 如果fales
}
public static void main(String[] args) throws Exception {
int ret = ToolRunner.run(new WordCount(), args);
System.out.println("new WordCount");
System.exit(ret);
}
}
以下是錯誤訊息:
13/12/23 03:58:24 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
13/12/23 03:58:25 WARN mapred.JobClient: No job jar file set. User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
13/12/23 03:58:25 INFO input.FileInputFormat: Total input paths to process : 3
13/12/23 03:58:25 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
13/12/23 03:58:25 WARN snappy.LoadSnappy: Snappy native library not loaded
13/12/23 03:58:25 INFO mapred.JobClient: Running job: job_201312222115_0016
13/12/23 03:58:26 INFO mapred.JobClient: map 0% reduce 0%
13/12/23 03:58:55 INFO mapred.JobClient: Task Id : attempt_201312222115_0016_m_000000_0, Status : FAILED
java.lang.RuntimeException: java.lang.ClassNotFoundException: testMap.WordCount$Map
at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:867)
at org.apache.hadoop.mapreduce.JobContext.getMapperClass(JobContext.java:199)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:719)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:370)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Unknown Source)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1121)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
Caused by: java.lang.ClassNotFoundException: testMap.WordCount$Map
at java.net.URLClassLoader$1.run(Unknown Source)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(Unknown Source)
at java.lang.ClassLoader.loadClass(Unknown Source)
at sun.misc.Launcher$AppClassLoader.loadClass(Unknown Source)
at java.lang.ClassLoader.loadClass(Unknown Source)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Unknown Source)
at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:820)
at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:865)
... 8 more
煩請大大門指教 謝謝!!我是用(windoop寫的)
|
登入
註冊
問答集
搜尋
