hadoop工作在伪分布模式。
统计一篇文章中每个单词出现的次数。
代码如下:
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 CiHui {
public static class CiHuiMapper 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 {
String line = value.toString();
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(new Text(word), one);
}
}
}
public static class CiHuiReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable res = 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();
}
res.set(sum);
context.write(key, res);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
if (args.length != 2) {
System.err.println("Usage: cihui <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "ci hui");
job.setJarByClass(CiHui.class);
job.setMapperClass(CiHuiMapper.class);
job.setCombinerClass(CiHuiReducer.class);
job.setReducerClass(CiHuiReducer.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);
}
}
用eclipse运行,参数输入如下:
hdfs://localhost:9000/user/tom/input hdfs://localhost:9000/user/tom/output
运行结果如下:
a 4
and 5
hadoop 7
hello 5
java 6
txt 6