利用hadoop访问数据库

1、编写Recoder

package hadoop.db;

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 org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.lib.db.DBWritable;

public class DBRecoder implements Writable, DBWritable {
	 int xxbh;
	private String zbh;
	private String zmc;
	private String bh;
	private String mc;
	
	
	@Override
	public void readFields(ResultSet rs) throws SQLException {
		this.xxbh = rs.getInt(1);
		this.zbh = rs.getString(2);
		this.zmc = rs.getString(3);
		this.bh = rs.getString(4);
		this.mc = rs.getString(5);
	}

	@Override
	public void write(PreparedStatement ps) throws SQLException {
		ps.setInt(1, this.xxbh);
		ps.setString(2, zbh);
		ps.setString(3, zmc);
		ps.setString(4, bh);
		ps.setString(5, mc);
	}

	@Override
	public void readFields(DataInput in) throws IOException {
		this.xxbh = in.readInt();
		this.zbh = Text.readString(in);
		this.zmc = Text.readString(in);
		this.bh = Text.readString(in);
		this.mc = Text.readString(in);
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeInt(xxbh);
		Text.writeString(out, zbh);
		Text.writeString(out, zmc);
		Text.writeString(out, bh);
		Text.writeString(out, mc);
//		out.write(zbh.getBytes("utf-8"));
//		out.write(zmc.getBytes("utf-8"));
//		out.write(bh.getBytes("utf-8"));
//		out.write(mc.getBytes("utf-8"));
	}

	@Override
	public String toString() {
		// TODO Auto-generated method stub
		return xxbh+":"+zbh+":"+zmc+":"+bh+":"+mc;
	}

}

二、Mapper

package hadoop.db;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapreduce.Mapper;

public class DBMapper extends Mapper <LongWritable,DBRecoder, LongWritable, Text>{

	public void map(LongWritable arg0, DBRecoder arg1, OutputCollector arg2,
			Reporter arg3) throws IOException {
		// TODO Auto-generated method stub
		arg2.collect(new LongWritable(arg1.xxbh), new Text(arg1.toString()));
	}

}

三、Reducer

package hadoop.db;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapreduce.Reducer;

public class IdentityReducer<K, Text> extends Reducer<K, Text, K, Text> {

	  /** Writes all keys and values directly to output. */
	  public void reduce(K key, Iterator<Text> values,
	                     OutputCollector<K, Text> output, Reporter reporter)
	    throws IOException {
	    while (values.hasNext()) {
	    	Text v = (Text) values.next();
	    	System.out.println(v.toString());
	      output.collect(key, v);
	    }
	  }

}

等同org.apache.hadoop.mapred.lib.IdentityReducer作用。

四、测试方法

package hadoop.db;

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.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.mapreduce.lib.db.DBInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class Test {
private static String driverClass = "oracle.jdbc.driver.OracleDriver";
private static String dbUrl = "jdbc:oracle:thin:@172.16.60.33:1521:igatest0";
	
	public static void main(String[] args) throws Exception {
//引入org.apache.hadoop.mapred包下的API
		/*JobClient client = new JobClient();
		JobConf conf = new JobConf(hadoop.db.Test.class);

		// TODO: specify output types
		conf.setOutputKeyClass(LongWritable.class);
		conf.setOutputValueClass(Text.class);

		// TODO: specify input and output DIRECTORIES (not files)
		conf.setInputFormat(DBInputFormat.class);

		FileOutputFormat.setOutputPath(conf, new Path("hdfs://172.16.60.33:9000/home/hadoop/db/output-"+System.currentTimeMillis()));
		
		
		DBConfiguration.configureDB(conf, driverClass, dbUrl,"igate320_sz","igate320_sz");
		String [] fields = {"xxbh","zbh", "zmc", "bh","mc"};
//		DBInputFormat.setInput(conf,DBRecoder.class, "T_SYS_XTZD",null, "xxbh", fields);
		DBInputFormat.setInput(conf, DBRecoder.class, "SELECT xxbh,zbh,zmc,bh,mc FROM t_sys_xtzd ORDER BY xxbh ", "SELECT count(1) FROM t_sys_xtzd ");
		
		
		// TODO: specify a mapper
		conf.setMapperClass(DBMapper.class);

		// TODO: specify a reducer
		conf.setReducerClass(IdentityReducer.class);

		client.setConf(conf);
		try {
			JobClient.runJob(conf);
		} catch (Exception e) {
			e.printStackTrace();
		}*/

//引入org.apache.hadoop.mapreduce 包下的API
		Configuration conf = new Configuration();
		
		Job job = new Job(conf, "word count sunsu");
		job.setJarByClass(Test.class);
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(DBRecoder.class);
		FileOutputFormat.setOutputPath(job, new Path("hdfs://172.16.60.33:9000/home/hadoop/db/output-"+System.currentTimeMillis()));
		
		DBConfiguration.configureDB(job.getConfiguration(), driverClass, dbUrl,"igate320_sz","igate320_sz");
		String [] fields = {"xxbh","zbh", "zmc", "bh","mc"};
//		DBInputFormat.setInput(job,DBRecoder.class, "T_SYS_XTZD","", "xxbh", fields);
		DBInputFormat.setInput(job, DBRecoder.class, "select xxbh,zbh,zmc,bh,mc from T_SYS_XTZD", "select count(1) from T_SYS_XTZD");
		
		job.setMapperClass(DBMapper.class);
		job.setReducerClass(IdentityReducer.class);
		
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}

}

hadoop-1.1.1版本不支持oracle数据库，可修改org.apache.hadoop.mapred.lib.db.DBInputFormat中getSelectQuery()方法生成对应数据库SQL