标签:c style class blog code java
<property> <name>hadoop.tmp.dir</name> <value>/usr/local/hadoop/tmp</value> </property>
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.Writable; import org.apache.hadoop.mapreduce.lib.db.DBWritable; public class DBRecoder implements Writable, DBWritable{ String test; int id; @Override public void write(DataOutput out) throws IOException { out.writeUTF(test); out.writeInt(id); } @Override public void readFields(DataInput in) throws IOException { test = in.readUTF(); id = in.readInt(); } @Override public void readFields(ResultSet arg0) throws SQLException { test = arg0.getString("test"); id = arg0.getInt("id"); } @Override public void write(PreparedStatement arg0) throws SQLException { arg0.setString(1, test); arg0.setInt(2, id); } }
import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; 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.DBInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class DataCountTest { public static class TokenizerMapper extends Mapper<LongWritable, DBRecoder, Text, IntWritable> { public void map(LongWritable key, DBRecoder value, Context context) throws IOException, InterruptedException { context.write(new Text(value.test), new IntWritable(1)); } } public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception { args = new String[1]; args[0] = "hdfs://192.168.203.137:9000/user/chenph/output1111221"; Configuration conf = new Configuration(); DBConfiguration.configureDB(conf, "oracle.jdbc.driver.OracleDriver", "jdbc:oracle:thin:@192.168.101.179:1521:orcl", "chenph", "chenph"); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); Job job = new Job(conf, "DB count"); job.setJarByClass(DataCountTest.class); job.setMapperClass(TokenizerMapper.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); String[] fields1 = { "id", "test"}; DBInputFormat.setInput(job, DBRecoder.class, "t1", null, "id", fields1); FileOutputFormat.setOutputPath(job, new Path(otherArgs[0])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }--------------------------------------------------------------------------------------------------
Win7中使用Eclipse连接虚拟机中的Ubuntu中的Hadoop2.4<3>,布布扣,bubuko.com
Win7中使用Eclipse连接虚拟机中的Ubuntu中的Hadoop2.4<3>
标签:c style class blog code java
原文地址:http://www.cnblogs.com/mengfanrong/p/3763413.html