您好,登錄后才能下訂單哦!
這篇文章主要介紹了hadoop中如何實現DBInputFormat,具有一定借鑒價值,感興趣的朋友可以參考下,希望大家閱讀完這篇文章之后大有收獲,下面讓小編帶著大家一起了解一下。
代碼未做測試,先做記錄
package com.test; import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; import java.net.URI; import java.sql.PreparedStatement; import java.sql.ResultSet; import java.sql.SQLException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; 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.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.lib.db.DBConfiguration; import org.apache.hadoop.mapreduce.lib.db.DBInputFormat; import org.apache.hadoop.mapreduce.lib.db.DBWritable; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; /** * 要運行本示例 * 1、把mysql的jdbc驅動放到taskTracker的lib目錄下,重啟集群 * */ public class WordCountDB extends Configured implements Tool { private String OUT_PATH = "hdfs://grid131:9000/output"; public static class Map extends Mapper<LongWritable, MyUser, LongWritable, Text> { public void map(LongWritable key, MyUser value, Context context) throws IOException, InterruptedException { context.write(key, new Text(value.toString())); } } public int run(String[] args) throws Exception { Configuration conf = this.getConf(); DBConfiguration.configureDB(conf, "com.mysql.jdbc.Driver", "jdbc:mysql://grid131:3306/test", "root", "admin"); //輸出路徑如果存在,則刪除 FileSystem fs = FileSystem.get(new URI(OUT_PATH), conf); fs.delete(new Path(OUT_PATH), true); Job job = new Job(conf, WordCountDB.class.getSimpleName()); job.setJarByClass(WordCountDB.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); //指定不需要reduce,直接把map輸出寫入到hdfs中 job.setNumReduceTasks(0); job.setInputFormatClass(DBInputFormat.class); //指定表、字段 //DBInputFormat.setInput(job, inputClass, tableName, conditions, orderBy, fieldNames) DBInputFormat.setInput(job, MyUser.class, "myuser", null, null, "id", "name"); job.setMapperClass(Map.class); //當reduce輸出類型與map輸出類型一致時,map的輸出類型可以不設置 job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.waitForCompletion(true); return job.isSuccessful()?0:1; } public static void main(String[] args) throws Exception { int exit = ToolRunner.run(new WordCount(), args); System.exit(exit); } } class MyUser implements Writable, DBWritable { private Long id; private String name; public Long getId() { return id; } public void setId(Long id) { this.id = id; } public String getName() { return name; } public void setName(String name) { this.name = name; } @Override public void write(DataOutput out) throws IOException { out.writeLong(this.id); Text.writeString(out, this.name); } @Override public void readFields(DataInput in) throws IOException { this.id = in.readLong(); this.name = Text.readString(in); } @Override public void write(PreparedStatement statement) throws SQLException { statement.setLong(1, this.id); statement.setString(2, this.name); } @Override public void readFields(ResultSet resultSet) throws SQLException { this.id = resultSet.getLong(1); this.name = resultSet.getString(2); } @Override public String toString() { return this.id + "\t" + this.name; } }
感謝你能夠認真閱讀完這篇文章,希望小編分享的“hadoop中如何實現DBInputFormat”這篇文章對大家有幫助,同時也希望大家多多支持億速云,關注億速云行業資訊頻道,更多相關知識等著你來學習!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。