处理流程:
Mapper分词 Reducer求和
数据==>Mapper==>Reducer==>HDFS
SalaryTotalMapper :
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class SalaryTotalMapper extends Mapper<LongWritable,IntWritable,IntWritable,IntWritable>{
@Override
protected void map(LongWritable key1, IntWritable value1, Context context) throws IOException, InterruptedException {
String data = value1.toString();
String[] words = data.split(",");
context.write(new IntWritable(Integer.parseInt(words[7])),
new IntWritable(Integer.parseInt(words[5])));
}
}
SalaryTotalReducer:(相同的key2,他的Value2会被同一个reduce处理)
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class SalaryTotalReducer extends Reducer<IntWritable,IntWritable,IntWritable,IntWritable>{
@Override
protected void reduce(IntWritable key3, Iterable values3, Context context) throws IOException, InterruptedException {
int total = 0;
for(IntWritable v:values3){
total +=v.get();
}
context.write(key3,new IntWritable(total));
}
}
SalaryTotalMain:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class SalaryTotalMain {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job =Job.getInstance(new Configuration());
job.setJarByClass(SalaryTotalMain.class);
job.setMapperClass(SalaryTotalMapper.class);
job.setMapOutputKeyClass(IntWritable.class);
job.setMapOutputValueClass(IntWritable.class);
job.setReducerClass(SalaryTotalReducer.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job,new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
job.waitForCompletion(true);
}
}