全部产品
MaxCompute

WordCount示例

更新时间:2017-06-07 13:26:11   分享:   

(1)准备好测试程序jar包,假设名字为mapreduce-examples.jar;

(2)准备好wordCount测试表和资源;

  • 创建表

    create table wc_in (key string, value string);
    create table wc_out(key string, cnt bigint);
    
  • 添加资源

    add jar mapreduce-examples.jar -f;
    

(3)使用tunnel导入数据;

   tunnel upload data wc_in;
  • 导入wc_in表的数据文件data内容为:
    hello,odps

测试步骤

在odpscmd中执行WordCount

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

预期结果

作业成功结束。 输出表wc_out中内容为:

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

代码示例

    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.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;

    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();
        }

        @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);

        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);

        JobClient.runJob(job);
      }

    }
本文导读目录
本文导读目录
以上内容是否对您有帮助?