直接上代码：Mapper package com.winksi.dotstat;import java.io.IOException;import org.apache.hadoop.io.Text;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.mapreduce.Mapper;public class DotProducedMapper extends MapperLongW
直接上代码：Mapper
package com.winksi.dotstat;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Mapper;
public class DotProducedMapper extends Mapper{
@Override
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException{
String line = value.toString();
String fileds[] = line.split(",");
String imsi = fileds[0];
String adccompany = fileds[1];
String phone = fileds[2];
String cur_time = fileds[3];
String call_length = fileds[4];
String call_type = fileds[5];
String show_length = fileds[6];
String pkgname = fileds[7];
String ip = fileds[8];
String model = fileds[9];
String ossdk = fileds[10];
String av = fileds[11];
String cityId = fileds[12];
StringBuffer strKey = new StringBuffer();
strKey.append(model).append(",").append(adccompany).append(",")
.append(ossdk.toUpperCase()).append(",").append(av).append(",")
.append(phone);
context.write(new Text(strKey.toString()), new Text(imsi));
}
}
Reducer:
package com.winksi.dotstat;
import java.io.IOException;
import java.util.Date;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Set;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class DotProducedReducer extends Reducer{
public void reduce(Text key, Iterator values,
Context context)
throws IOException, InterruptedException {
int count = 0;
Set set = new HashSet();
while (values.hasNext()) {
set.add(values.next().toString());
count++;
}
StringBuffer sb = new StringBuffer();
sb.append(count).append(",").append(set.size());
Date yesterdayDate = new Date(new Date().getTime() - 1*24*60*60*1000);
String yesterday = DotStatPvUv.getCurrentDay(yesterdayDate);
StringBuffer sbKey = new StringBuffer();
sbKey.append(key.toString()).append(",").append(yesterday);
context.write(new Text(sbKey.toString()), new Text(sb.toString()));
}
}
Spring配置文件：
fs.default.name=${hd.fs}
maven的jar包pom.xml
org.springframework.data
spring-data-hadoop
1.0.2.RELEASE-cdh4
org.apache.hadoop
hadoop-core
${hadoop.core.version}
java代码：
public class Test {
public static void main(String[] args) {
ApplicationContext ctx = new ClassPathXmlApplicationContext("hadoop-mr.xml");
}
}
运行报错：
Exception in thread "main" java.io.IOException: Cannot run program "cygpath": CreateProcess error=2, ?????μ???
at java.lang.ProcessBuilder.start(ProcessBuilder.java:459)
at org.apache.hadoop.util.Shell.runCommand(Shell.java:201)
at org.apache.hadoop.util.Shell.run(Shell.java:183)
at org.apache.hadoop.fs.FileUtil$CygPathCommand.(FileUtil.java:413)
at org.apache.hadoop.fs.FileUtil.makeShellPath(FileUtil.java:439)
at org.apache.hadoop.fs.FileUtil.makeShellPath(FileUtil.java:466)
at org.apache.hadoop.fs.RawLocalFileSystem.execCommand(RawLocalFileSystem.java:559)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:551)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:355)
at org.apache.hadoop.fs.FilterFileSystem.mkdirs(FilterFileSystem.java:212)
原因是尽管连接的hadoop平台是在linux上面，但是我们的eclipse调试环境是在windows，我们需要安装一个linux模拟器“cygwin”来支持程序的运行。
在windows开发服务器上安装好cygwin，然后在环境变量中添加cygwin的bin目录，比如“D:\Program\cygwin\bin”，问题得以解决。
注意是在系统环境变量的Path上加入“D:\Program\cygwin\bin”这样我们就行像在linux上运行命令一样在windows的dos窗口下执行ls,cd等命令。
刚开始我一直是在系统环境变量下的classpath上加的D:\Program\cygwin\bin”，尝试了半天都是失败，后来才发现，是加错了地方。加完之后再cmd窗口中试一下ls,cd等命令。成功后重启myeclipse运行代码，就没有问题了。
------------------------------------------------------------------------------
之前纠结集成的Mapper和Reducer的问题，有两个文件可以继承，具体问题见：
http://wuyanzan60688.blog.163.com/blog/static/1277761632013101244955/
