MapReduce之Map Join

如果在Reduce 端处理过多的表，容易出现数据倾斜，通常我们会在Map端缓存起来，提前把处理业务逻辑，减少Reduce端数据的压力，减少数据倾斜。

Map Join 适用于一张表十分小、一张表很大的场景。

Mapper的setup（初始化）的时候缓存到集合中，

job.addCacheFile(new URI("file:///D:/input/tablecache/pd.txt"));

代码如下：

 

创建MapJoinMapper，不需要Reducer

 

public class MapJoinMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
    private HashMap<String, String> pdMap = new HashMap<>();
    private Text outK = new Text();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        // 获取缓存的文件，并把文件内容封装到集合 pd.txt
        URI[] cacheFiles = context.getCacheFiles();

        FileSystem fs = FileSystem.get(context.getConfiguration());
        FSDataInputStream fis = fs.open(new Path(cacheFiles[0]));

        // 从流中读取数据
        BufferedReader reader = new BufferedReader(new InputStreamReader(fis, "UTF-8"));

        String line;
        while (StringUtils.isNotEmpty(line = reader.readLine())) {
            // 切割
            String[] fields = line.split("\t");

            // 赋值
            pdMap.put(fields[0], fields[1]);
        }

        // 关流
        IOUtils.closeStream(reader);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 处理 order.txt
        String line = value.toString();

        String[] fields = line.split("\t");

        // 获取pid
        String pname = pdMap.get(fields[1]);

        // 获取订单id 和订单数量
        // 封装
        outK.set(fields[0] + "\t" + pname + "\t" + fields[2]);

        context.write(outK, NullWritable.get());
    }
}
 

 创建MapJoinDriver

// 加载缓存数据
job.addCacheFile(new URI("file:///D:/input/tablecache/pd.txt"));
// Map端Join的逻辑不需要Reduce阶段，设置reduceTask数量为0
job.setNumReduceTasks(0);

public class MapJoinDriver {

    public static void main(String[] args) throws IOException, URISyntaxException, ClassNotFoundException, InterruptedException {

        // 1 获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2 设置加载jar包路径
        job.setJarByClass(MapJoinDriver.class);
        // 3 关联mapper
        job.setMapperClass(MapJoinMapper.class);
        // 4 设置Map输出KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        // 5 设置最终输出KV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        // 加载缓存数据
        job.addCacheFile(new URI("file:///D:/input/tablecache/pd.txt"));
        // Map端Join的逻辑不需要Reduce阶段，设置reduceTask数量为0
        job.setNumReduceTasks(0);

        // 6 设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\input\\inputtable2"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\hadoop\\output8888"));
        // 7 提交
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }

}