通過mapreduce把mysql的數據讀取到hdfs


前面講過了怎么通過mapreduce把mysql的一張表的數據放到另外一張表中,這次講的是把mysql的數據讀取到hdfs里面去

具體怎么搭建環境我這里就不多說了。參考

通過mapreduce把mysql的一張表的數據導到另外一張表中

 

也在eclipse里面創建一個mapreduce工程

 

具體的實現代碼

 

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: 測試 mr 與 mysql 的數據交互,此測試用例將一個表中的數據復制到另一張表中
*                          實際當中,可能只需要從 mysql 讀,或者寫到 mysql 中。
* date: 2013-7-29 上午2:34:04 <br/>
* @author june
*/
public class Mysql2Mr {
        // DROP TABLE IF EXISTS `hadoop`.`studentinfo`;
        // CREATE TABLE studentinfo (
        // id INTEGER NOT NULL PRIMARY KEY,
        // name VARCHAR(32) NOT NULL);

        public static class StudentinfoRecord implements Writable, DBWritable {
                int id;
                String name;

                //構造方法
                public StudentinfoRecord() { }
               
                //Writable接口是對數據流進行操作的,所以輸入是DataInput類對象
                public void readFields(DataInput in) throws IOException {
                        this.id = in.readInt(); //輸入流中的讀取下一個整數,並返回
                        this.name = Text.readString(in);
                }
                 
      
                public String toString() {
                        return new String(this.id + " " + this.name);
                }
                
                //DBWritable負責對數據庫進行操作,所以輸出格式是PreparedStatement 
                //PreparedStatement接口繼承並擴展了Statement接口,用來執行動態的SQL語句,即包含參數的SQL語句
                @Override
                public void write(PreparedStatement stmt) throws SQLException {
                        stmt.setInt(1, this.id);
                        stmt.setString(2, this.name);
                }
           
              //DBWritable負責對數據庫進行操作,輸入格式是ResultSet
                // ResultSet接口類似於一張數據表,用來暫時存放從數據庫查詢操作所獲得的結果集
                @Override
                public void readFields(ResultSet result) throws SQLException {
                        this.id = result.getInt(1);
                        this.name = result.getString(2);
                }

              //Writable接口是對數據流進行操作的,所以輸出是DataOutput類對象 
                @Override
                public void write(DataOutput out) throws IOException {
                        out.writeInt(this.id);
                        Text.writeString(out, this.name);
                }
        }

        // 記住此處是靜態內部類,要不然你自己實現無參構造器,或者等着拋異常:
        // Caused by: java.lang.NoSuchMethodException: DBInputMapper.<init>()
        // http://stackoverflow.com/questions/7154125/custom-mapreduce-input-format-cant-find-constructor
        // 網上腦殘式的轉帖,沒見到一個寫對的。。。
        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(" ");
                        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("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統---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" };
                // 從 t 表讀數據
                DBInputFormat.setInput(conf, StudentinfoRecord.class, "t", null, "id", fields);
                
                // mapreduce 將數據輸出到 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);
        }
}

 

 特別要主要的是在主函數里面添加這么一句話

如果不添加這句話的話就不能識別你的hdfs路徑了,除了這個方法之外還,不想添加這句話的話還可以把集群的core-site.xml文件直接拷貝一份放到工程的src目錄下

這樣也是可以的

 

運行程序

 

 

 可以看到hdfs的文件上面已經有mysql數據庫表的內容了

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM