个人比笔记,记录一下自己学到的内容:
大数据使用mappereducer分析时,将要排序的内容放在键中,mappereducer会自动帮你排序。
(一定需要注意输入和输出要一致)
初学者,如有错误,望大佬指点一二!!!
package gongtonghaoyou;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
class Onesortmap extends Mapper<LongWritable, Text,LongWritable, NullWritable> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
int line=Integer.parseInt(value.toString());
context.write(new LongWritable(line),NullWritable.get());//将得到的值放入输出的key中,会自动排序
}
}
class Onesortreducer extends Reducer<LongWritable,NullWritable,Text,NullWritable>{
@Override
protected void reduce(LongWritable key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
//将内容转换为Text然后输出将会自动排序好
context.write(new Text(key.toString()),NullWritable.get());
}
}
class Driver{
public static void main(String[] args) throws Exception {
Configuration conf=new Configuration();
Job job=Job.getInstance(conf);
job.setMapperClass(Onesortmap.class);
job.setReducerClass(Onesortreducer.class);
job.setJarByClass(Driver.class);
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
FileInputFormat.setInputPaths(job,new Path("E://sz.txt"));
FileOutputFormat.setOutputPath(job,new Path("E://tmp"));
System.exit(job.waitForCompletion(true)?0:1);
}
}