package com.reducer.wc;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.fs.*;
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 void main(String args[]) throws Exception {
int res = ToolRunner.run(new WordCount(), args);
System.exit(res);
}
public int run(String[] args) throws Exception {
Path inputPath = new Path(args[0]);
Path outputPath = new Path(args[1]);
Configuration conf = getConf();
Job job = new Job(conf, this.getClass().toString());
FileInputFormat.setInputPaths(job, inputPath);
FileOutputFormat.setOutputPath(job, outputPath);
job.setJobName("WordCount");
job.setJarByClass(WordCount.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
return job.waitForCompletion(true) ? 0 : 1;
}
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
@Override
public void map(LongWritable key, Text value,
Mapper.Context context) throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable value : values) {
sum += value.get();
}
context.write(key, new IntWritable(sum));
}
}
}
我在eclipse中运行它会出现以下错误!
Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/commons/cli/ParseException
at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:59)
at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:79)
at com.reducer.wc.WordCount.main(WordCount.java:17)
Caused by: java.lang.ClassNotFoundException: org.apache.commons.cli.ParseException
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)
... 3 more
此错误的实际原因是什么。做,我必须制作罐子 并在hadoop中运行它以查看输出?或者我可以看到它 日食。我在eclipse中使用了一个hadoop插件。
提前致谢。