不多说，直接上代码。
假如这里有一份邮箱数据文件，我们期望统计邮箱出现次数并按照邮箱的类别，将这些邮箱分别输出到不同文件路径下。
代码
package zhouls.bigdata.myMapReduce.Email;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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;
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
//假如这里有一份邮箱数据文件，我们期望统计邮箱出现次数并按照邮箱的类别，将这些邮箱分别输出到不同文件路径下。
/*[email protected]m
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
/out/163-r-00000
/out/126-r-00000
/out/21cn-r-00000
/out/gmail-r-00000
/out/qq-r-00000
/out/sina-r-00000
/out/sohu-r-00000
/out/yahoo-r-00000
/out/part-r-00000
*/
public class Email extends Configured implements Tool
{
public static class MailMapper extends Mapper<LongWritable, Text, Text, IntWritable>
{
private final static IntWritable one = new IntWritable(1);
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
{
context.write(value, one);//将value和one写入到context里。
}
}
public static class MailReducer extends Reducer<Text, IntWritable, Text, IntWritable>
{
private IntWritable result = new IntWritable();
private MultipleOutputs<Text, IntWritable> multipleOutputs;
@Override
protected void setup(Context context) throws IOException ,InterruptedException
{
multipleOutputs = new MultipleOutputs<Text, IntWritable>(context);
}
protected void reduce(Text Key, Iterable<IntWritable> Values,Context context) throws IOException, InterruptedException
{//[email protected]
int begin = Key.toString().indexOf("@");//indexOf() 方法可返回某个指定的字符串值在字符串中首次出现的位置。 即begin是9
int end = Key.toString().indexOf(".");//indexOf() 方法可返回某个指定的字符串值在字符串中首次出现的位置。 即end是12
if(begin>=end)
{
return;
}
//获取邮箱类别，比如 qq
String name = Key.toString().substring(begin+1, end);//substring()是去除指定字符串的方法，及substring(10，12)
int sum = 0;
for (IntWritable value : Values)
{
sum += value.get();
}
result.set(sum);
multipleOutputs.write(Key, result, name);//将Key和result和name一起写入multipleOutputs
}
@Override
protected void cleanup(Context context) throws IOException ,InterruptedException
{
multipleOutputs.close();
}
}
public int run(String[] arg0) throws Exception {
Configuration conf = new Configuration();// 读取配置文件
Path mypath = new Path(arg0[1]);//下标为1，即是输出路径
FileSystem hdfs = mypath.getFileSystem(conf);//FileSystem对象hdfs
if (hdfs.isDirectory(mypath))
{
hdfs.delete(mypath, true);
}
Job job = Job.getInstance();// 新建一个任务
job.setJarByClass(Email.class);// 主类
job.setMapperClass(MailMapper.class);// Mapper
job.setReducerClass(MailReducer.class);// Reducer
job.setOutputKeyClass(Text.class);// key输出类型
job.setOutputValueClass(IntWritable.class);// value输出类型
FileInputFormat.addInputPath(job, new Path(arg0[0]));// 文件输入路径
FileOutputFormat.setOutputPath(job, new Path(arg0[1]));// 文件输出路径
job.waitForCompletion(true);
return 0;
}
public static void main(String[] args) throws Exception
{
//集群路径
// String[] args0 = { "hdfs://HadoopMaster:9000/email/email.txt",
// "hdfs://HadoopMaster:9000/out/email"};
//本地路径
String[] args0 = { "./data/email/email.txt",
"out/email/"};
int ec = ToolRunner.run( new Configuration(), new Email(), args0);
System. exit(ec);
}
}