import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class ModuleMapReduce extends Configured implements Tool {
static class ModuleMapper extends
Mapper<LongWritable, Text, Text, IntWritable> {
@Override
protected void setup(
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.setup(context);
}
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.map(key, value, context);
}
@Override
protected void cleanup(
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.cleanup(context);
}
@Override
public void run(
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.run(context);
}
}
static class ModuleReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
@Override
protected void setup(
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.setup(context);
}
@Override
protected void reduce(Text key, Iterable<IntWritable> values,
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.reduce(key, values, context);
}
@Override
protected void cleanup(
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.cleanup(context);
}
@Override
public void run(
Reducer<Text, IntWritable, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.run(context);
}
}
@Override
public int run(String[] args) throws Exception {
if (checkArgs(args) != 0)
return checkArgs(args);
Job job = getJob();
//set input/output path
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// set run jar class when package need
job.setJarByClass(ModuleMapper.class);
//set map info
job.setMapperClass(ModuleMapper.class);
job.setInputFormatClass(TextInputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
//set partition
job.setPartitionerClass(HashPartitioner.class);
job.setNumReduceTasks(1);
//set reduce info
job.setReducerClass(ModuleReducer.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
return job.waitForCompletion(true) ? 0 : 1;
}
private Configuration getConfiguration() {
Configuration conf = new Configuration();
return conf;
}
private Job getJob() throws IOException {
Configuration conf = getConfiguration();
Job job = new Job(conf, ModuleMapReduce.class.getSimpleName());
return job;
}
private int checkArgs(String[] args) {
if (args.length != 2) {
System.err.println("args error");
return 1;
}
return 0;
}
public static void main(String[] args) throws Exception {
int exitCode = ToolRunner.run(new ModuleMapReduce(), args);
System.exit(exitCode);
}
}