mapreduce-implementing a single-table association

Map class

Package hadoop3;

Import java.io.IOException;

Import org.apache.hadoop.io.LongWritable;
Import Org.apache.hadoop.io.Text;
Import Org.apache.hadoop.mapreduce.Mapper;

public class Danbiaomap extends Mapper <longwritable,text,text,text>{


String Childname=new string ();
String Parientname=new string ();
String Flag=new string ();


protected void Map (longwritable key,text value,context Context) throws IOException, Interruptedexception

{
String [] str=value.tostring (). Split ("\ t");
if (Str[0].compareto ("Child")!=0)


{//left table
flag= "1";
CHILDNAME=STR[0];
PARIENTNAME=STR[1];
Context.write (new text (parientname), new text (flag+ "+" +childname+ "+" +parientname));

Right table
Flag= "2";
Context.write (new text (childname), new text (flag+ "+" +childname+ "+" +parientname));


}


}

}

Reduce class

Package hadoop3;

Import java.io.IOException;
Import Java.util.Iterator;

Import Org.apache.hadoop.io.Text;
Import Org.apache.hadoop.mapreduce.Reducer;

public class Danbiaoreduce extends reducer<text,text,text,text>{

private int num=0;
protected void reduce (Text key,iterable<text> value, Context context) throws IOException, Interruptedexception

{
if (num==0)

{

Context.write (new text ("grandchild"), new text ("Grandparient"));
num++;
}

Iterator <Text> itr=value.iterator ();
int grandchildnum=0;
String [] grandchild=new string[100];
int grandparientnum=0;
String [] grandparient=new string[100];

while (Itr.hasnext ())

{
String [] Record=itr.next (). toString (). Split ("\\+");
if (Record[0].compareto ("1") ==0)
{
GRANDCHILD[GRANDCHILDNUM]=RECORD[1];
grandchildnum++;

}
else if (Record[0].compareto ("2") ==0)
{
GRANDPARIENT[GRANDPARIENTNUM]=RECORD[2];
grandparientnum++;

}
Else
{}
}
if (grandchildnum!=0 && grandparientnum!=0)
{
for (int i=0;i<grandparientnum;i++)
{
for (int j=0;j<grandchildnum;j++)
{
Context.write (new text (Grandchild[i]), new text (Grandparient[j]));

}

}


}



}



}

Main class

Package hadoop3;

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.Text;
Import Org.apache.hadoop.mapreduce.Job;
Import Org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
Import Org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
Import Org.apache.hadoop.util.Tool;
Import Org.apache.hadoop.util.ToolRunner;

Import Com.sun.jersey.core.impl.provider.entity.XMLJAXBElementProvider.Text;

public class Danbiao extends configured implements tool{

public static void Main (string[] args) throws Exception {
TODO auto-generated Method Stub
Toolrunner.run (New Danbiao (), args);
}

@Override
public int run (string[] arg0) throws Exception {
TODO auto-generated Method Stub

Configuration conf=getconf ();
Job Job=new job ();
Job.setjarbyclass (GetClass ());
FileSystem fs=filesystem.get (conf);
Fs.delete (New Path ("/outfile1104"), true);
Fileinputformat.addinputpath (job,new Path ("/luo/danbiao.txt"));
Fileoutputformat.setoutputpath (Job, New Path ("/outfile1104"));
Job.setoutputkeyclass (Text.class);
Job.setoutputvalueclass (Text.class);

Job.setmapperclass (Danbiaomap.class);
Job.setreducerclass (Danbiaoreduce.class);

Job.waitforcompletion (TRUE);








return 0;
}

}

mapreduce-implementing a single-table association