每日总结

Mapreduce实例——排序

依赖：

<dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-common</artifactId>

      <version>3.2.0</version>

    </dependency>

    <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-mapreduce-client-app</artifactId>

      <version>3.2.0</version>

    </dependency>

 

    <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-hdfs</artifactId>

      <version>3.2.0</version>

    </dependency>

    <dependency>

      <groupId>org.slf4j</groupId>

      <artifactId>slf4j-log4j12</artifactId>

      <version>1.7.30</version>

    </dependency>

    <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-client</artifactId>

      <version>3.2.0</version>

</dependency>

 

实验代码：

package  mapreduce;    
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.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.input.TextInputFormat;    
import  org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;    
import  org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;    
public  class  OneSort {
    public static class Map extends Mapper<Object, Text, IntWritable, Text> {
        private static Text goods = new Text();
        private static IntWritable num = new IntWritable();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String arr[] = line.split("\t");
            num.set(Integer.parseInt(arr[1]));
            goods.set(arr[0]);
            context.write(num, goods);
        }
    }

    public static class Reduce extends Reducer<IntWritable, Text, IntWritable, Text> {
        private static IntWritable result = new IntWritable();

        public void reduce(IntWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            for (Text val : values) {
                context.write(key, val);
            }
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = new Job(conf, "OneSort");
        job.setJarByClass(OneSort.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(Text.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        Path in = new Path("hdfs://hadoop102:8020/mymapreduce2/in/goods_visit1");
        Path out = new Path("hdfs://hadoop102:8020/mymapreduce2/out2");
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        System.exit(job.waitForCompletion(true) ? 0 : 1);

    }
}