MapReduce编程实战2——倒排索引（jar包）-创新互联
任务要求：
//输入文件格式
18661629496 110
13107702446 110
1234567 120
2345678 120
987654 110
2897839274 18661629496
//输出文件格式格式
11018661629496|13107702446|987654|18661629496|13107702446|987654|
1201234567|2345678|1234567|2345678|
186616294962897839274|2897839274|
mapreduce程序编写：
import java.io.IOException;
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.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.output.FileOutputFormat;
public class Test2 {
enum Counter
{
LINESKIP,//记录出错的行
}
public static class Map extends Mapper{
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();//读取源数据
try
{
//数据处理
String [] lineSplit = line.split(" ");//18661629496,110
String anum = lineSplit[0];
String bnum = lineSplit[1];
//输出格式：110,18661629496
context.write(new Text(bnum), new Text(anum));
}
catch(ArrayIndexOutOfBoundsException e)
{
context.getCounter(Counter.LINESKIP).increment(1);//出错时计数器+1
return;
}
}
}
public static class Reduce extends Reducer {
public void reduce(Text key, Iterable values, Context context)
throws IOException, InterruptedException {
String valueString;
String out="";
for(Text value:values)
{
valueString=value.toString();
out+=valueString+"|";
}
context.write(key, new Text(out));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
if (args.length != 2) {
System.err.println("请配置输入输出路径 ");
System.exit(2);
}
//各种配置
Job job = new Job(conf, "telephone ");//作业名称配置
//类配置
job.setJarByClass(Test2.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
//map输出格式配置
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
//作业输出格式配置
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
//增加输入输出路径
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//任务完成时退出
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
将mapreduce程序打包为jar文件：
1.右键项目名称->Export->java->jar file
2.配置jar文件存储位置
3.选择main calss
4.运行jar文件
[liuqingjie@master hadoop-0.20.2]$ bin/hadoop jar /home/liuqingjie/test2.jar /user/liuqingjie/in /user/liuqingjie/out
15/05/14 01:46:47 WARN mapred.JobClient: Use GenericOptionsParser for parsing the arguments. Applications should implement Tool for the same.
15/05/14 01:46:47 INFO input.FileInputFormat: Total input paths to process : 2
15/05/14 01:46:48 INFO mapred.JobClient: Running job: job_201505132004_0005
15/05/14 01:46:49 INFO mapred.JobClient: map 0% reduce 0%
15/05/14 01:46:57 INFO mapred.JobClient: map 100% reduce 0%
15/05/14 01:47:09 INFO mapred.JobClient: map 100% reduce 100%
……………………………………………………………………………………
查看结果
[liuqingjie@master hadoop-0.20.2]$ bin/hadoop dfs -cat ./out/*
cat: Source must be a file.
110 18661629496|13107702446|987654|18661629496|13107702446|987654|
120 1234567|2345678|1234567|2345678|
18661629496 2897839274|2897839274|
另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。
文章题目：MapReduce编程实战2——倒排索引（jar包）-创新互联
文章转载：http://6mz.cn/article/dihpps.html