Hadoop--引用计数
package com.smartmap.example;
import java.io.IOException;
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.Reducer.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class CiteCount {
public static class MapClass extends Mapper<Text, Text, Text, Text> {
public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
context.write(value, key);
}
}
public static class ReduceClass extends Reducer<Text, Text, Text, IntWritable> {
public void reduce(Text key, Iterable<Text> values,Context context) throws IOException, InterruptedException {
int count = 0;
for (Text val : values) {
count++;
}
context.write(key, new IntWritable(count));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: CiteCount <int> <out>");
System.exit(2);
}
conf.set("key.value.separator.in.input.line", ",");
Path in = new Path(args[0]);
Path out = new Path(args[1]);
Job job = new Job(conf);
job.setJarByClass(CiteCount.class);
job.setMapperClass(MapClass.class);
job.setReducerClass(ReduceClass.class);
job.setInputFormatClass(KeyValueTextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, in);
FileOutputFormat.setOutputPath(job, out);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
----------------------------------------------------------------------------------------------------------
hdfs://192.168.1.30:9000/data/cite /opt/eclipse/workspace/data/out
浙公网安备 33010602011771号