package com.zkpk.us;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
class UserMapper extends Mapper {
protected void map(
LongWritable key,
Text value,
org.apache.hadoop.mapreduce.Mapper.Context context)
throws java.io.IOException, InterruptedException {
IntWritable one = new IntWritable(1);
String[] columns = value.toString().split("\t");
if (columns != null && columns.length == 6) {
Text uid = new Text(columns[1]);
context.write(uid, one);
}
};
}
class UserReducer extends Reducer {
protected void reduce(
Text key,
java.lang.Iterable values,
org.apache.hadoop.mapreduce.Reducer.Context context)
throws java.io.IOException, InterruptedException {
int sum = 0;
for(IntWritable value : values){
sum += value.get();
}
context.write(key, new IntWritable(sum));
};
}
public class UserCount {
/**
* @param args
*/
public static void main(String[] args)throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf, "UserUid");
job.setJarByClass(UserCount.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setMapperClass(UserMapper.class);
job.setReducerClass(UserReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.waitForCompletion(true);
}
} |
天盟APP下载
