MaxCompute：二次排序樣本

前提條件

已通過快速入門完成測試所需環境配置。

測試準備

1. 準備好測試程式的JAR包，假設名字為mapreduce-examples.jar，本地存放路徑為MaxCompute用戶端bin目錄下data\resources。

2. 準備好SecondarySort的測試表和資源。

   1. 建立測試表。

      CREATE TABLE ss_in(key BIGINT, value BIGINT);
      CREATE TABLE ss_out(key BIGINT, value BIGINT);

   2. 添加測試資源。

      -- 首次添加忽略-f覆蓋指令。
      add jar data\resources\mapreduce-examples.jar -f;

3. 使用Tunnel將MaxCompute用戶端bin目錄下data.txt匯入ss_in表中。

   tunnel upload data.txt ss_in;

   匯入ss_in表的資料如下。

   1,2
   2,1
   1,1
   2,2

測試步驟

jar -resources mapreduce-examples.jar -classpath data\resources\mapreduce-examples.jar 
com.aliyun.odps.mapred.open.example.SecondarySort ss_in ss_out;

預期結果

+------------+------------+
| key        | value      |
+------------+------------+
| 1          | 1          |
| 1          | 2          |
| 2          | 1          |
| 2          | 2          |
+------------+------------+

程式碼範例

Pom依賴資訊，請參見注意事項。

package com.aliyun.odps.mapred.open.example;
import java.io.IOException;
import java.util.Iterator;
import com.aliyun.odps.data.Record;
import com.aliyun.odps.mapred.JobClient;
import com.aliyun.odps.mapred.MapperBase;
import com.aliyun.odps.mapred.ReducerBase;
import com.aliyun.odps.mapred.TaskContext;
import com.aliyun.odps.mapred.conf.JobConf;
import com.aliyun.odps.mapred.utils.SchemaUtils;
import com.aliyun.odps.mapred.utils.InputUtils;
import com.aliyun.odps.mapred.utils.OutputUtils;
import com.aliyun.odps.data.TableInfo;
/**
     *
     * This is an example ODPS Map/Reduce application. It reads the input table that
     * must contain two integers per record. The output is sorted by the first and
     * second number and grouped on the first number.
     *
     **/
public class SecondarySort {
    /**
       * Read two integers from each line and generate a key, value pair as ((left,
       * right), right).
       **/
    public static class MapClass extends MapperBase {
        private Record key;
        private Record value;
        @Override
            public void setup(TaskContext context) throws IOException {
            key = context.createMapOutputKeyRecord();
            value = context.createMapOutputValueRecord();
        }
        @Override
            public void map(long recordNum, Record record, TaskContext context)
            throws IOException {
            long left = 0;
            long right = 0;
            if (record.getColumnCount() > 0) {
                left = (Long) record.get(0);
                if (record.getColumnCount() > 1) {
                    right = (Long) record.get(1);
                }
                key.set(new Object[] { (Long) left, (Long) right });
                value.set(new Object[] { (Long) right });
                context.write(key, value);
            }
        }
    }
    /**
       * A reducer class that just emits the sum of the input values.
       **/
    public static class ReduceClass extends ReducerBase {
        private Record result = null;
        @Override
            public void setup(TaskContext context) throws IOException {
            result = context.createOutputRecord();
        }
        @Override
            public void reduce(Record key, Iterator<Record> values, TaskContext context)
            throws IOException {
            result.set(0, key.get(0));
            while (values.hasNext()) {
                Record value = values.next();
                result.set(1, value.get(0));
                context.write(result);
            }
        }
    }
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err.println("Usage: secondarysrot <in> <out>");
            System.exit(2);
        }
        JobConf job = new JobConf();
        job.setMapperClass(MapClass.class);
        job.setReducerClass(ReduceClass.class);
        /**將多列設定為Key。*/
        //compare first and second parts of the pair
        job.setOutputKeySortColumns(new String[] { "i1", "i2" });
        //partition based on the first part of the pair
        job.setPartitionColumns(new String[] { "i1" });
        //grouping comparator based on the first part of the pair
        job.setOutputGroupingColumns(new String[] { "i1" });
        //the map output is LongPair, Long
        job.setMapOutputKeySchema(SchemaUtils.fromString("i1:bigint,i2:bigint"));
        job.setMapOutputValueSchema(SchemaUtils.fromString("i2x:bigint"));
        InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
        OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
        JobClient.runJob(job);
        System.exit(0);
    }
}