package com.gong.mrmysql;
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.FileSystem;
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.FileOutputFormat;
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
* @author june*/
public classMysql2Mr {//DROP TABLE IF EXISTS `hadoop`.`studentinfo`;//CREATE TABLE studentinfo (//id INTEGER NOT NULL PRIMARY KEY,//name VARCHAR(32) NOT NULL);
public static classStudentinfoRecord implements Writable, DBWritable {intid;
String name;//构造方法
publicStudentinfoRecord() { }//Writable接口是对数据流进行操作的,所以输入是DataInput类对象
public void readFields(DataInput in) throws IOException {this.id = in.readInt(); //输入流中的读取下一个整数,并返回
this.name = Text.readString(in);
}publicString toString() {return new String(this.id + " " + this.name);
}//DBWritable负责对数据库进行操作,所以输出格式是PreparedStatement//PreparedStatement接口继承并扩展了Statement接口,用来执行动态的SQL语句,即包含参数的SQL语句
@Overridepublic voidwrite(PreparedStatement stmt) throws SQLException {
stmt.setInt(1, this.id);
stmt.setString(2, this.name);
}//DBWritable负责对数据库进行操作,输入格式是ResultSet//ResultSet接口类似于一张数据表,用来暂时存放从数据库查询操作所获得的结果集
@Overridepublic voidreadFields(ResultSet result) throws SQLException {this.id = result.getInt(1);this.name = result.getString(2);
}//Writable接口是对数据流进行操作的,所以输出是DataOutput类对象
@Overridepublic void write(DataOutput out) throws IOException {out.writeInt(this.id);
Text.writeString(out, this.name);
}
}//记住此处是静态内部类,要不然你自己实现无参构造器,或者等着抛异常://Caused by: java.lang.NoSuchMethodException: DBInputMapper.()// http://stackoverflow.com/questions/7154125/custom-mapreduce-input-format-cant-find-constructor
//网上脑残式的转帖,没见到一个写对的。。。
public static classDBInputMapper extends MapReduceBase implements
Mapper{public voidmap(LongWritable key, StudentinfoRecord value,
OutputCollectorcollector, Reporter reporter) throws IOException {
collector.collect(new LongWritable(value.id), newText(value.toString()));
}
}public static classMyReducer extends MapReduceBase implements
Reducer{
@Overridepublic void reduce(LongWritable key, Iteratorvalues,
OutputCollectoroutput, Reporter reporter) throws IOException {
String[] splits= values.next().toString().split(" ");
StudentinfoRecord r= newStudentinfoRecord();
r.id= Integer.parseInt(splits[0]);
r.name= splits[1];
output.collect(r,newText(r.name));
}
}public static voidmain(String[] args) throws IOException {
JobConf conf= new JobConf(Mysql2Mr.class);
DistributedCache.addFileToClassPath(new Path("hdfs://192.168.241.13:9000/mysqlconnector/mysql-connector-java-5.1.38-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.set("fs.defaultFS", "hdfs://192.168.241.13:9000");//在配置文件conf中指定所用的文件系统---HDFS
conf.setReducerClass(IdentityReducer.class);
Path outPath= new Path("hdfs://192.168.241.13:9000/student/out1");
FileSystem.get(conf).delete(outPath, true);
FileOutputFormat.setOutputPath(conf, outPath);
DBConfiguration.configureDB(conf,"com.mysql.jdbc.Driver", "jdbc:mysql://192.168.241.13:3306/mrtest","root", "543116");
String[] fields= { "id", "name"};//从 t 表读数据
DBInputFormat.setInput(conf, StudentinfoRecord.class, "t", null, "id", fields);//mapreduce 将数据输出到 t2 表//DBOutputFormat.setOutput(conf, "t2", "id", "name");//FileOutputFormat.setOutputPath(conf, new Path("hdfs://192.168.241.13:9000/student/out1"));
conf.setMapperClass(org.apache.hadoop.mapred.lib.IdentityMapper.class);
conf.setMapperClass(DBInputMapper.class);//conf.setReducerClass(MyReducer.class);
JobClient.runJob(conf);
}
}