package com.sun.mysql;
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.conf.Configuration;
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.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.mapreduce.lib.db.DBOutputFormat;
import org.apache.hadoop.mapreduce.lib.db.DBWritable;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
/**
* 將mapreduce的結果數據寫入mysql中
* @author asheng
*/
public class WriteDataToMysql {
/**
* 重寫DBWritable
* @author asheng
* TblsWritable需要向mysql中寫入數據
*/
public static class TblsWritable implements Writable, DBWritable
{
String tbl_name;
String tbl_type;
public TblsWritable()
{
}
public TblsWritable(String tbl_name,String tab_type)
{
this.tbl_name = tbl_name;
this.tbl_type = tab_type;
}
@Override
public void write(PreparedStatement statement) throws SQLException
{
statement.setString(1, this.tbl_name);
statement.setString(2, this.tbl_type);
}
@Override
public void readFields(ResultSet resultSet) throws SQLException
{
this.tbl_name = resultSet.getString(1);
this.tbl_type = resultSet.getString(2);
}
@Override
public void write(DataOutput out) throws IOException
{
out.writeUTF(this.tbl_name);
out.writeUTF(this.tbl_type);
}
@Override
public void readFields(DataInput in) throws IOException
{
this.tbl_name = in.readUTF();
this.tbl_type = in.readUTF();
}
public String toString()
{
return new String(this.tbl_name + " " + this.tbl_type);
}
}
public static class ConnMysqlMapper extends Mapper<LongWritable,Text,Text,Text>
//TblsRecord是自定義的類型,也就是上面重寫的DBWritable類
{
public void map(LongWritable key,Text value,Context context)throws IOException,InterruptedException
{
//<首字母偏移量,該行內容>接收進來,然后處理value,將abc和x作為map的輸出
//key對於本程序沒有太大的意義,沒有使用
String name = value.toString().split(" ")[0];
String type = value.toString().split(" ")[1];
context.write(new Text(name),new Text(type));
}
}
public static class ConnMysqlReducer extends Reducer<Text,Text,TblsWritable,TblsWritable>
{
public void reduce(Text key,Iterable<Text> values,Context context)throws IOException,
InterruptedException
{
//接收到的key value對即為要輸入數據庫的字段,所以在reduce中:
//wirte的第一個參數,類型是自定義類型TblsWritable,利用key和value將其組合成TblsWritable,
然后等待寫入數據庫
//wirte的第二個參數,wirte的第一個參數已經涵蓋了要輸出的類型,所以第二個類型沒有用,設為null
for(Iterator<Text> itr = values.iterator();itr.hasNext();)
{
context.write(new TblsWritable(key.toString(),itr.next().toString()),null);
}
}
}
public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException
{
Configuration conf = new Configuration();
DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver","jdbc:mysql://127.0.0.1:3306/mapreduce_test","root", "root");
Job job = new Job(conf,"test mysql connection");
job.setJarByClass(ReadDataFromMysql.class);
job.setMapperClass(ConnMysqlMapper.class);
job.setReducerClass(ConnMysqlReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(DBOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
DBOutputFormat.setOutput(job, "lxw_tabls", "TBL_NAME","TBL_TYPE");
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
//執行輸入參數為/home/asheng/hadoop/in/test3.txt
//test3.txt中的內容為
/*
abc x
def y
chd z
*/
//即將abc x分別做為TBL_NAME,和TBL_TYPE插入數據庫中
//輸出結果在mysql數據庫中查看
//select * from lxw_tabls;
//發現新增三行
/*
abc x
def y
chd z
*/