Sort示例

前提条件

已通过快速入门完成测试所需环境配置。

测试准备

1. 准备好测试程序的JAR包，假设名字为mapreduce-examples.jar，本地存放路径为MaxCompute客户端bin目录下data\resources。

2. 准备好Sort的测试表和资源。

   1. 创建测试表。

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

   2. 添加测试资源。

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

3. 使用Tunnel将MaxCompute客户端bin目录下data.txt导入ss_in表中。

   tunnel upload data.txt ss_in;

   导入ss_in表的数据文件data的内容。

    2,1
    1,1
    3,1

测试步骤

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

预期结果

+------------+------------+
| key        | value      |
+------------+------------+
| 1          | 1          |
| 2          | 1          |
| 3          | 1          |
+------------+------------+

代码示例

Pom依赖信息，请参见注意事项。

package com.aliyun.odps.mapred.open.example;
import java.io.IOException;
import java.util.Date;
import com.aliyun.odps.data.Record;
import com.aliyun.odps.data.TableInfo;
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.InputUtils;
import com.aliyun.odps.mapred.utils.OutputUtils;
import com.aliyun.odps.mapred.utils.SchemaUtils;
/**
     * This is the trivial map/reduce program that does absolutely nothing other
     * than use the framework to fragment and sort the input values.
     *
     **/
public class Sort {
    static int printUsage() {
        System.out.println("sort <input> <output>");
        return -1;
    }
    /**
       * Implements the identity function, mapping record's first two columns to
       * outputs.
       **/
    public static class IdentityMapper 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 {
            key.set(new Object[] { (Long) record.get(0) });
            value.set(new Object[] { (Long) record.get(1) });
            context.write(key, value);
        }
    }
    
    public static class IdentityReducer extends ReducerBase {
        private Record result = null;

        @Override
        public void setup(TaskContext context) throws IOException {
            result = context.createOutputRecord();
        }

        /**
         * Writes all keys and values directly to output.
         */
        @Override
        public void reduce(Record key, Iterator<Record> values, TaskContext context)
                throws IOException {
            result.set(0, key.get(0));

            while (values.hasNext()) {
                Record val = values.next();
                result.set(1, val.get(0));
                context.write(result);
            }
        }
    }
    
    /**
       * The main driver for sort program. Invoke this method to submit the
       * map/reduce job.
       *
       * @throws IOException
       *           When there is communication problems with the job tracker.
       **/
    public static void main(String[] args) throws Exception {
        JobConf jobConf = new JobConf();
        jobConf.setMapperClass(IdentityMapper.class);
        jobConf.setReducerClass(IdentityReducer.class);
        /**为了全局有序，这里设置了reducer的个数为1，所有的数据都会集中到一个reducer上面。*/
        /**只能用于小数据量，大数据量需要考虑其他的方式，比如TeraSort。*/
        jobConf.setNumReduceTasks(1);
        jobConf.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint"));
        jobConf.setMapOutputValueSchema(SchemaUtils.fromString("value:bigint"));
        InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), jobConf);
        OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), jobConf);
        Date startTime = new Date();
        System.out.println("Job started: " + startTime);
        JobClient.runJob(jobConf);
        Date end_time = new Date();
        System.out.println("Job ended: " + end_time);
        System.out.println("The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds.");
    }
}