MaxCompute：WordCount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。

   1. 建立測試表。

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

2. 使用Tunnel將MaxCompute用戶端bin目錄下data.txt匯入wc_in表中。

   tunnel upload data.txt wc_in;

   匯入wc_in表的資料如下。

   hello,odps

測試步驟

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

預期結果

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

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.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.conf.JobConf;
import com.aliyun.odps.mapred.utils.InputUtils;
import com.aliyun.odps.mapred.utils.OutputUtils;
import com.aliyun.odps.mapred.utils.SchemaUtils;
public class WordCount {
    public static class TokenizerMapper extends MapperBase {
        private Record word;
        private Record one;
        @Override
            public void setup(TaskContext context) throws IOException {
            word = context.createMapOutputKeyRecord();
            one = context.createMapOutputValueRecord();
            one.set(new Object[] { 1L });
            System.out.println("TaskID:" + context.getTaskID().toString());
        }
        @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);
            }
        }
    }
    /**
       * A combiner class that combines map output by sum them.
       **/
    public static class SumCombiner extends ReducerBase {
        private Record count;
        @Override
            public void setup(TaskContext context) throws IOException {
            count = context.createMapOutputValueRecord();
        }
        /**Combiner實現的介面和Reducer一樣，是可以立即在Mapper本地執行的一個Reduce，作用是減少Mapper的輸出量。*/
        @Override
            public void reduce(Record key, Iterator<Record> values, TaskContext context)
            throws IOException {
            long c = 0;
            while (values.hasNext()) {
                Record val = values.next();
                c += (Long) val.get(0);
            }
            count.set(0, c);
            context.write(key, count);
        }
    }
    /**
       * A reducer class that just emits the sum of the input values.
       **/
    public static class SumReducer 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 {
            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: WordCount <in_table> <out_table>");
            System.exit(2);
        }
        JobConf job = new JobConf();
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(SumCombiner.class);
        job.setReducerClass(SumReducer.class);
        /**設定Mapper中間結果的key和value的Schema, Mapper的中間結果輸出也是Record的形式。*/
        job.setMapOutputKeySchema(SchemaUtils.fromString("word:string"));
        job.setMapOutputValueSchema(SchemaUtils.fromString("count:bigint"));
        /**設定輸入和輸出的表資訊。*/
        InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
        OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
        JobClient.runJob(job);
    }
}