Hadoop之——自定義分組比較器實現分組功能
阿新 • • 發佈：2019-01-25
不多說，直接上程式碼,大家都懂得
1、Mapper類的實現
/** * Mapper類的實現 * @author liuyazhuang * */ 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); }; }
2、Reducer類的實現
/** * Reducer類的實現 * @author liuyazhuang * */ 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 { long min = Long.MAX_VALUE; for (LongWritable v2 : v2s) { if(v2.get()<min){ min = v2.get(); } } context.write(new LongWritable(k2.first), new LongWritable(min)); }; }
3、WritableComparable類的實現
/** * 問：為什麼實現該類？ * 答：因為原來的v2不能參與排序，把原來的k2和v2封裝到一個類中，作為新的k2 * @author liuyazhuang */ 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); } /** * 當k2進行排序時，會呼叫該方法. * 當第一列不同時，升序；當第一列相同時，第二列升序 * @author liuyazhuang */ @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); } }
4、分組比較器RawComparator的實現
/**
* 自定義分組比較器
* 問：為什麼自定義該類？
* 答：業務要求分組是按照第一列分組，但是NewK2的比較規則決定了不能按照第一列分。只能自定義分組比較器。
* @author liuyazhuang
*
*/
static class MyGroupingComparator implements RawComparator<NewK2>{
@Override
public int compare(NewK2 o1, NewK2 o2) {
return (int)(o1.first - o2.first);
}
/**
* @param arg0 表示第一個參與比較的位元組陣列
* @param arg1 表示第一個參與比較的位元組陣列的起始位置
* @param arg2 表示第一個參與比較的位元組陣列的偏移量
*
* @param arg3 表示第二個參與比較的位元組陣列
* @param arg4 表示第二個參與比較的位元組陣列的起始位置
* @param arg5 表示第二個參與比較的位元組陣列的偏移量
*/
@Override
public int compare(byte[] arg0, int arg1, int arg2, byte[] arg3,
int arg4, int arg5) {
return WritableComparator.compareBytes(arg0, arg1, 8, arg3, arg4, 8);
}
}5、程式入口Main
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, GroupApp.class.getSimpleName());
//1.1 指定輸入檔案路徑
FileInputFormat.setInputPaths(job, INPUT_PATH);
//指定哪個類用來格式化輸入檔案
job.setInputFormatClass(TextInputFormat.class);
//1.2指定自定義的Mapper類
job.setMapperClass(MyMapper.class);
//指定輸出<k2,v2>的型別
job.setMapOutputKeyClass(NewK2.class);
job.setMapOutputValueClass(LongWritable.class);
//1.3 指定分割槽類
job.setPartitionerClass(HashPartitioner.class);
job.setNumReduceTasks(1);
//1.4 TODO 排序、分割槽
job.setGroupingComparatorClass(MyGroupingComparator.class);
//1.5 TODO （可選）合併
//2.2 指定自定義的reduce類
job.setReducerClass(MyReducer.class);
//指定輸出<k3,v3>的型別
job.setOutputKeyClass(LongWritable.class);
job.setOutputValueClass(LongWritable.class);
//2.3 指定輸出到哪裡
FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
//設定輸出檔案的格式化類
job.setOutputFormatClass(TextOutputFormat.class);
//把程式碼提交給JobTracker執行
job.waitForCompletion(true);
}6、完整程式碼
package com.lyz.hadoop.group;
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.RawComparator;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
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;
/**
* Hadoop實現分組操作
* 當第一列不同時，升序；當第一列相同時，第二列升序
* @author liuyazhuang
*
*/
public class GroupApp {
//要統計的檔案位置
static final String INPUT_PATH = "hdfs://liuyazhuang:9000/input";
//統計結果輸出的位置
static final String OUT_PATH = "hdfs://liuyazhuang:9000/out";
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, GroupApp.class.getSimpleName());
//1.1 指定輸入檔案路徑
FileInputFormat.setInputPaths(job, INPUT_PATH);
//指定哪個類用來格式化輸入檔案
job.setInputFormatClass(TextInputFormat.class);
//1.2指定自定義的Mapper類
job.setMapperClass(MyMapper.class);
//指定輸出<k2,v2>的型別
job.setMapOutputKeyClass(NewK2.class);
job.setMapOutputValueClass(LongWritable.class);
//1.3 指定分割槽類
job.setPartitionerClass(HashPartitioner.class);
job.setNumReduceTasks(1);
//1.4 TODO 排序、分割槽
job.setGroupingComparatorClass(MyGroupingComparator.class);
//1.5 TODO （可選）合併
//2.2 指定自定義的reduce類
job.setReducerClass(MyReducer.class);
//指定輸出<k3,v3>的型別
job.setOutputKeyClass(LongWritable.class);
job.setOutputValueClass(LongWritable.class);
//2.3 指定輸出到哪裡
FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
//設定輸出檔案的格式化類
job.setOutputFormatClass(TextOutputFormat.class);
//把程式碼提交給JobTracker執行
job.waitForCompletion(true);
}
/**
* Mapper類的實現
* @author liuyazhuang
*
*/
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);
};
}
/**
* Reducer類的實現
* @author liuyazhuang
*
*/
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 {
long min = Long.MAX_VALUE;
for (LongWritable v2 : v2s) {
if(v2.get()<min){
min = v2.get();
}
}
context.write(new LongWritable(k2.first), new LongWritable(min));
};
}
/**
* 問：為什麼實現該類？
* 答：因為原來的v2不能參與排序，把原來的k2和v2封裝到一個類中，作為新的k2
* @author liuyazhuang
*/
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);
}
/**
* 當k2進行排序時，會呼叫該方法.
* 當第一列不同時，升序；當第一列相同時，第二列升序
* @author liuyazhuang
*/
@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);
}
}
/**
* 自定義分組比較器
* 問：為什麼自定義該類？
* 答：業務要求分組是按照第一列分組，但是NewK2的比較規則決定了不能按照第一列分。只能自定義分組比較器。
* @author liuyazhuang
*
*/
static class MyGroupingComparator implements RawComparator<NewK2>{
@Override
public int compare(NewK2 o1, NewK2 o2) {
return (int)(o1.first - o2.first);
}
/**
* @param arg0 表示第一個參與比較的位元組陣列
* @param arg1 表示第一個參與比較的位元組陣列的起始位置
* @param arg2 表示第一個參與比較的位元組陣列的偏移量
*
* @param arg3 表示第二個參與比較的位元組陣列
* @param arg4 表示第二個參與比較的位元組陣列的起始位置
* @param arg5 表示第二個參與比較的位元組陣列的偏移量
*/
@Override
public int compare(byte[] arg0, int arg1, int arg2, byte[] arg3,
int arg4, int arg5) {
return WritableComparator.compareBytes(arg0, arg1, 8, arg3, arg4, 8);
}
}
}