Fork me on GitHub

MapReduce例子

发表于 | 分类于 

这是崔斯特的第一百一十篇原创文章

努力、奋斗

最近在学习《Hive编程指南》，尝试动手了第一个MapReduce案例，记录下。

JAVA

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
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.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.StringTokenizer;
/**
 * @author zhujian on 2019/12/29.
 */
public class WorldCount {
    public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable ONE = new IntWritable(1);
        private Text word = new Text();
        @Override
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                context.write(value, ONE);
            }
        }
    }
    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = new Job(conf, "world count");
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}

分别继承Mapper和Reducer这两个方法，重写自己的处理逻辑，最后设置map和reduce。

HQL

同样的功能用HQL来写会简单很多：

1
2
3
4
5
6
7
8
9
10
11
12
CREATE TABLE docs (line STRING);
LOAD DATA INPATH 'docs' OVERWRITE INTO TABLE docs;
CREATE TABLE world_counts AS
SELECT world, count(1) AS count
FROM (
    SELECT explode(split(line, '\s')) AS word
    FROM docs
) w
GROUP BY word
ORDER BY word;

so simple