WordCount.java 注意把job.setJarByClass(WordCount.class);改成job.setJar("wc.jar");,解决类找不到的问题
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.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<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());
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();
Job job = Job.getInstance(conf, "word count");
//job.setJarByClass(WordCount.class);
job.setJar("wc.jar");
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.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);
}
}
使用hadoop命令进行编译和执行
[hadoop@nn01 ~]$ mkdir demo
[hadoop@nn01 ~]$ cd demo
[hadoop@nn01 demo]$ mkdir input
[hadoop@nn01 demo]$ cd input/
[hadoop@nn01 input]$ echo "hello hadoop hello world" > 1.txt
[hadoop@nn01 input]$ echo "hello zheng from hadoop" > 2.txt
[hadoop@nn01 ~]$ hadoop fs -put ./demo /
[hadoop@nn01 hadoop-2.9.0]$ bin/hadoop com.sun.tools.javac.Main WordCount.java
[hadoop@nn01 hadoop-2.9.0]$ jar cf wc.jar WordCount*.class
[hadoop@nn01 hadoop-2.9.0]$ bin/hadoop jar wc.jar WordCount /demo/input /demo/output
执行结果