MapReduce 查询mysql表中的数据，打印记录数，并转储回mysql表

package com.laoxiao.mr02;


import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.util.Iterator;

import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.lib.IdentityReducer;
import org.apache.hadoop.mapred.lib.db.DBConfiguration;
import org.apache.hadoop.mapred.lib.db.DBInputFormat;
import org.apache.hadoop.mapred.lib.db.DBOutputFormat;
import org.apache.hadoop.mapred.lib.db.DBWritable;

/**
* Function: 测试 mr 与 mysql 的数据交互，此测试用例将一个表中的数据复制到另一张表中
* 实际当中，可能只需要从 mysql 读，或者写到 mysql 中。
* date: 2013-7-29 上午2:34:04 <br/>
* @author june
*/
public class Mysql2Mr {

private static int i = 0 ;

//定义了一个实体类，与数据库表对应起来
public static class StudentinfoRecord implements Writable, DBWritable {
int id;
String name;

public StudentinfoRecord() {

}

public void readFields(DataInput in) throws IOException {
this.id = in.readInt();
this.name = Text.readString(in);
}

public String toString() {
return new String(this.id + " " + this.name);
}

@Override
public void write(PreparedStatement stmt) throws SQLException {
stmt.setInt(1, this.id);
stmt.setString(2, this.name);
}

@Override
public void readFields(ResultSet result) throws SQLException {
this.id = result.getInt(1);
this.name = result.getString(2);
}

@Override
public void write(DataOutput out) throws IOException {
out.writeInt(this.id);
Text.writeString(out, this.name);
}
}

public static class DBInputMapper extends MapReduceBase implements
Mapper<LongWritable, StudentinfoRecord, LongWritable, Text> {
public void map(LongWritable key, StudentinfoRecord value,
OutputCollector<LongWritable, Text> collector, Reporter reporter) throws IOException {
collector.collect(new LongWritable(value.id), new Text(value.toString()));
}
}

public static class MyReducer extends MapReduceBase implements
Reducer<LongWritable, Text, StudentinfoRecord, Text> {
@Override
public void reduce(LongWritable key, Iterator<Text> values,
OutputCollector<StudentinfoRecord, Text> output, Reporter reporter) throws IOException {
String[] splits = values.next().toString().split(" ");
i++;
//每读取到一行记录打印一下
System.out.println("总共"+i+"行记录");
StudentinfoRecord r = new StudentinfoRecord();
r.id = Integer.parseInt(splits[0]);
r.name = splits[1];
output.collect(r, new Text(r.name));
}
}

public static void main(String[] args) throws IOException {
JobConf conf = new JobConf(Mysql2Mr.class);
DistributedCache.addFileToClassPath(new Path("D:/tools/lib/mysql-connector-java-5.1.6-bin.jar"), conf);
conf.setMapOutputKeyClass(LongWritable.class);
conf.setMapOutputValueClass(Text.class);
conf.setOutputKeyClass(LongWritable.class);
conf.setOutputValueClass(Text.class);

conf.setOutputFormat(DBOutputFormat.class);
conf.setInputFormat(DBInputFormat.class);
// // mysql to hdfs
// conf.setReducerClass(IdentityReducer.class);
// Path outPath = new Path("/tmp/1");
// FileSystem.get(conf).delete(outPath, true);
// FileOutputFormat.setOutputPath(conf, outPath);

DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver", "jdbc:mysql://127.0.0.1:3306/test",
"root", "123456");
String[] fields = { "id", "name" };
// 从 t 表读数据
DBInputFormat.setInput(conf, StudentinfoRecord.class, "test", null, "id", fields);
// mapreduce 将数据输出到 t2 表
DBOutputFormat.setOutput(conf, "t2", "id", "name");
// conf.setMapperClass(org.apache.hadoop.mapred.lib.IdentityMapper.class);
conf.setMapperClass(DBInputMapper.class);
conf.setReducerClass(MyReducer.class);

JobClient.runJob(conf);
}
}