二次排序
package sort;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
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;
/**
* 需求:第一列升序排列,第一列相同的第二列再升序排列
sortinput
3 3
3 2
3 1
2 2
2 1
1 1
sortout
1 1
2 1
2 2
3 1
3 2
3 3
* @author Administrator
*
*/
public class SortApp {
static final String INPUT_PATH = "hdfs://chaoren:9000/sortinput";
static final String OUT_PATH = "hdfs://chaoren:9000/sortout";
public static void main(String[] args) throws Exception{
final Configuration configuration = new Configuration();
final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), configuration);
if(fileSystem.exists(new Path(OUT_PATH))){
fileSystem.delete(new Path(OUT_PATH), true);
}
final Job job = new Job(configuration, SortApp.class.getSimpleName());
FileInputFormat.setInputPaths(job, INPUT_PATH);
job.setInputFormatClass(TextInputFormat.class);
job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(NewK2.class);
job.setMapOutputValueClass(LongWritable.class);
job.setPartitionerClass(HashPartitioner.class);
job.setNumReduceTasks(1);
job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(LongWritable.class);
job.setOutputValueClass(LongWritable.class);
FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
job.setOutputFormatClass(TextOutputFormat.class);
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, NewK2, LongWritable>{
protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,NewK2,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
final String[] splited = value.toString().split("\t");
final NewK2 k2 = new NewK2(Long.parseLong(splited[0]), Long.parseLong(splited[1]));
final LongWritable v2 = new LongWritable(Long.parseLong(splited[1]));
context.write(k2, v2);
};
}
static class MyReducer extends Reducer<NewK2, LongWritable, LongWritable, LongWritable>{
protected void reduce(NewK2 k2, java.lang.Iterable<LongWritable> v2s, org.apache.hadoop.mapreduce.Reducer<NewK2,LongWritable,LongWritable,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
context.write(new LongWritable(k2.first), new LongWritable(k2.second));
};
}
/**
* 问:为什么实现该类?
* 答:因为原来的v2不能参与排序,把原来的k2和v2封装到一个类中,作为新的k2
*
*/
static class NewK2 implements WritableComparable<NewK2>{
Long first;
Long second;
public NewK2(){}
public NewK2(long first, long second){
this.first = first;
this.second = second;
}
@Override
public void readFields(DataInput in) throws IOException {
this.first = in.readLong();
this.second = in.readLong();
}
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(first);
out.writeLong(second);
}
/**
* 当k2进行排序时,会调用该方法.
* 当第一列不同时,升序;当第一列相同时,第二列升序
*/
@Override
public int compareTo(NewK2 o) {
final long minus = this.first - o.first;
if(minus !=0){
return (int)minus;
}
return (int)(this.second - o.second);
}
@Override
public int hashCode() {
return this.first.hashCode()+this.second.hashCode();
}
@Override
public boolean equals(Object obj) {
if(!(obj instanceof NewK2)){
return false;
}
NewK2 oK2 = (NewK2)obj;
return (this.first==oK2.first)&&(this.second==oK2.second);
}
}
}