前提條件

已通過(guò)快速入門完成測(cè)試所需環(huán)境配置。

測(cè)試準(zhǔn)備

1. 準(zhǔn)備好測(cè)試程序的JAR包，假設(shè)名字為mapreduce-examples.jar，本地存放路徑為MaxCompute客戶端bin目錄下data\resources。

2. 準(zhǔn)備好UserDefinedCounters測(cè)試表和資源。

   1. 創(chuàng)建測(cè)試表。

      CREATE TABLE wc_in (key STRING, value STRING);
      CREATE TABLE wc_out(key STRING, cnt BIGINT);

   2. 添加測(cè)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客戶端bin目錄下data.txt導(dǎo)入wc_in表中。

   tunnel upload data.txt wc_in;

   導(dǎo)入wc_in表的數(shù)據(jù)如下。

   hello,odps

測(cè)試步驟

jar -resources mapreduce-examples.jar -classpath data\resources\mapreduce-examples.jar
com.aliyun.odps.mapred.open.example.UserDefinedCounters wc_in wc_out

預(yù)期結(jié)果

Counters: 3
com.aliyun.odps.mapred.open.example.UserDefinedCounters$MyCounter
MAP_TASKS=1
REDUCE_TASKS=1
TOTAL_TASKS=2

+------------+------------+
| key        | cnt        |
+------------+------------+
| hello      | 1          |
| odps       | 1          |
+------------+------------+

代碼示例

Pom依賴信息，請(qǐng)參見(jiàn)注意事項(xiàng)。

package com.aliyun.odps.mapred.open.example;
import java.io.IOException;
import java.util.Iterator;
import com.aliyun.odps.counter.Counter;
import com.aliyun.odps.counter.Counters;
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.RunningJob;
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;
/**
     *
     * User Defined Counters
     *
     **/
public class UserDefinedCounters {
    enum MyCounter {
        TOTAL_TASKS, MAP_TASKS, REDUCE_TASKS
    }
    public static class TokenizerMapper extends MapperBase {
        private Record word;
        private Record one;
        @Override
            public void setup(TaskContext context) throws IOException {
            super.setup(context);
            Counter map_tasks = context.getCounter(MyCounter.MAP_TASKS);
            Counter total_tasks = context.getCounter(MyCounter.TOTAL_TASKS);
            map_tasks.increment(1);
            total_tasks.increment(1);
            word = context.createMapOutputKeyRecord();
            one = context.createMapOutputValueRecord();
            one.set(new Object[] { 1L });
        }
        @Override
            public void map(long recordNum, Record record, TaskContext context)
            throws IOException {
            for (int i = 0; i < record.getColumnCount(); i++) {
                word.set(new Object[] { record.get(i).toString() });
                context.write(word, one);
            }
        }
    }
    public static class SumReducer extends ReducerBase {
        private Record result = null;
        @Override
            public void setup(TaskContext context) throws IOException {
            result = context.createOutputRecord();
            Counter reduce_tasks = context.getCounter(MyCounter.REDUCE_TASKS);
            Counter total_tasks = context.getCounter(MyCounter.TOTAL_TASKS);
            reduce_tasks.increment(1);
            total_tasks.increment(1);
        }
        @Override
            public void reduce(Record key, Iterator<Record> values, TaskContext context)
            throws IOException {
            long count = 0;
            while (values.hasNext()) {
                Record val = values.next();
                count += (Long) val.get(0);
            }
            result.set(0, key.get(0));
            result.set(1, count);
            context.write(result);
        }
    }
    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            System.err
                .println("Usage: TestUserDefinedCounters <in_table> <out_table>");
            System.exit(2);
        }
        JobConf job = new JobConf();
        job.setMapperClass(TokenizerMapper.class);
        job.setReducerClass(SumReducer.class);
        job.setMapOutputKeySchema(SchemaUtils.fromString("word:string"));
        job.setMapOutputValueSchema(SchemaUtils.fromString("count:bigint"));
        InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
        OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
        RunningJob rJob = JobClient.runJob(job);
        /**在作業(yè)成功結(jié)束后，可以獲取到Job里面的自定義Counter的值。*/
        Counters counters = rJob.getCounters();
        long m = counters.findCounter(MyCounter.MAP_TASKS).getValue();
        long r = counters.findCounter(MyCounter.REDUCE_TASKS).getValue();
        long total = counters.findCounter(MyCounter.TOTAL_TASKS).getValue();
        System.exit(0);
    }
}