package com.hadoop.sample;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class MTJoin {
private static int time = 0;
public static class Map extends Mapper<Object,Text,Text,Text>{
//在map中先区分输入行属于左表还是右表,然后对两列值进行分割,
//保存连接列在key值,剩余列和左右表标志在value中,最后输出
public void map(Object key,Text value,Context context) throws IOException,InterruptedException{
String line = value.toString();
int i = 0;
//输入文件首行,不处理
if(line.contains("factoryname")==true||line.contains("addressID")==true){
return;
}
//找出数据中的分割点
while(line.charAt(i)>='9'||line.charAt(i)<='0'){
i++;
}
if(line.charAt(i)>='9'||line.charAt(i)<='0'){
//左表
int j = i-1;
while(line.charAt(j)!=' ') j--;
String[] values = {line.substring(0, j),line.substring(i)};
context.write(new Text(values[1]), new Text("1+"+values[0]));
}else{//右表
int j = i+1;
while(line.charAt(j)!=' ') j++;
String[] values = {line.substring(0, i+1),line.substring(j)};
context.write(new Text(values[0]), new Text("2+"+values[1]));
}
}
}
public static class Reduce extends Reducer<Text,Text,Text,Text>{
//reduce解析map输出,将value中数据按照左右表分别保存,然后求笛卡尔积,输出
public void reduce(Text key,Iterable<Text> values,Context context) throws IOException,InterruptedException{
if(time == 0){//输入文件第一行
context.write(new Text("factoryname"),new Text("addressname"));
time++;
}
int factorynum = 0;
String factory[] = new String[10];
int adressnum = 0;
String adress[] = new String[10];
Iterator iter = values.iterator();
while(iter.hasNext()){
String record = iter.next().toString();
int len = record.length();
int i = 2;
char type = record.charAt(0);
String factoryname = new String();
String adressname = new String();
if(type == '1'){//左表
factory[factorynum] = record.substring(2);
factorynum++;
}else{//右表
adress[adressnum] = record.substring(2);
}
}
if(factorynum!=0&&adressnum!=0){//笛卡尔积
for(int m=0;m<factorynum;m++){
for(int n=0;n<adressnum;n++){
context.write(new Text(factory[m]), new Text(adress[n]));
}
}
}
}
}
/**
* @param args
*/
public static void main(String[] args) throws Exception{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
if(otherArgs.length != 2){
System.err.println("Usage WordCount <int> <out>");
System.exit(2);
}
Job job = new Job(conf,"word count");
job.setJarByClass(MTJoin.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
分享到:
相关推荐
赠送源代码:hadoop-mapreduce-client-jobclient-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-jobclient-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-jobclient-2.6.5-...
Hadoop 3.x(MapReduce)----【MapReduce 概述】---- 代码 Hadoop 3.x(MapReduce)----【MapReduce 概述】---- 代码 Hadoop 3.x(MapReduce)----【MapReduce 概述】---- 代码 Hadoop 3.x(MapReduce)----...
hadoop-mapreduce-examples-2.7.1.jar
赠送源代码:hadoop-mapreduce-client-core-2.5.1-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-core-2.5.1.pom; 包含翻译后的API文档:hadoop-mapreduce-client-core-2.5.1-javadoc-API文档-...
赠送源代码:hadoop-mapreduce-client-jobclient-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-jobclient-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-jobclient-2.6.5-...
赠送源代码:hadoop-mapreduce-client-app-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-app-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-app-2.6.5-javadoc-API文档-中文...
Hadoop-0.20.0-HDFS+MapReduce+Hive+HBase十分钟快速入门
赠送源代码:hadoop-mapreduce-client-app-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-app-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-app-2.6.5-javadoc-API文档-中文...
赠送源代码:hadoop-mapreduce-client-app-2.7.3-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-app-2.7.3.pom; 包含翻译后的API文档:hadoop-mapreduce-client-app-2.7.3-javadoc-API文档-中文...
hadoop-annotations-3.1.1.jar hadoop-common-3.1.1.jar hadoop-mapreduce-client-core-3.1.1.jar hadoop-yarn-api-3.1.1.jar hadoop-auth-3.1.1.jar hadoop-hdfs-3.1.1.jar hadoop-mapreduce-client-hs-3.1.1.jar ...
赠送源代码:hadoop-mapreduce-client-core-2.7.3-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-core-2.7.3.pom; 包含翻译后的API文档:hadoop-mapreduce-client-core-2.7.3-javadoc-API文档-...
赠送源代码:hadoop-mapreduce-client-common-2.6.5-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-common-2.6.5.pom; 包含翻译后的API文档:hadoop-mapreduce-client-common-2.6.5-javadoc-API...
赠送源代码:hadoop-mapreduce-client-core-2.6.5-sources.jar 包含翻译后的API文档:hadoop-mapreduce-client-core-2.6.5-javadoc-API文档-中文(简体)-英语-对照版.zip 对应Maven信息:groupId:org.apache.hadoop...
博客中的大数据-hadoop的mapreduce相关代码,需要的朋友下吧
hadoop-mapreduce-examples-2.6.5.jar 官方案例源码
尚硅谷大数据技术之Hadoop-Mapreduce
Hadoop实现了一个分布式文件系统(Hadoop Distributed File System),简称HDFS。HDFS有高容错性的特点,并且设计用来部署在低廉的(low-cost)硬件上;而且它提供高吞吐量(high throughput)来访问应用程序的数据...
Hadoop 3.x(MapReduce)----【Hadoop 序列化】---- 代码 Hadoop 3.x(MapReduce)----【Hadoop 序列化】---- 代码 Hadoop 3.x(MapReduce)----【Hadoop 序列化】---- 代码 Hadoop 3.x(MapReduce)----【Hadoop ...
赠送源代码:hadoop-mapreduce-client-common-2.7.3-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-common-2.7.3.pom; 包含翻译后的API文档:hadoop-mapreduce-client-common-2.7.3-javadoc-API...
赠送源代码:hadoop-mapreduce-client-jobclient-2.5.1-sources.jar; 赠送Maven依赖信息文件:hadoop-mapreduce-client-jobclient-2.5.1.pom; 包含翻译后的API文档:hadoop-mapreduce-client-jobclient-2.5.1-...