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 data\resources
  2. 准备好测试表和资源。
    • 创建测试表。
      create table mr_upload_src(key bigint, value string);
    • 添加测试资源。
      add jar data\resources\mapreduce-examples.jar -f;
      add file data\resources\import.txt -f;
    • import.txt的数据内容,如下所示:
      1000,odps

测试步骤

在odpscmd中执行Upload,如下所示:
jar -resources mapreduce-examples.jar,import.txt -classpath data\resources\mapreduce-examples.jar
com.aliyun.odps.mapred.open.example.Upload import.txt mr_upload_src;

预期结果

作业成功结束后,输出表mr_upload_src中的内容,如下所示:
+------------+------------+
| key        | value      |
+------------+------------+
| 1000       | odps       |
+------------+------------+

代码示例

    package com.aliyun.odps.mapred.open.example;
    import java.io.BufferedInputStream;
    import java.io.FileNotFoundException;
    import java.io.IOException;
    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.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;
    /**
     * Upload
     *
     * Import data from text file into table
     *
     **/
    public class Upload {
      public static class UploadMapper extends MapperBase {
        @Override
        public void setup(TaskContext context) throws IOException {
          Record record = context.createOutputRecord();
          StringBuilder importdata = new StringBuilder();
          BufferedInputStream bufferedInput = null;
          try {
            byte[] buffer = new byte[1024];
            int bytesRead = 0;
            String filename = context.getJobConf().get("import.filename");
            bufferedInput = context.readResourceFileAsStream(filename);
            while ((bytesRead = bufferedInput.read(buffer)) != -1) {
              String chunk = new String(buffer, 0, bytesRead);
              importdata.append(chunk);
            }
            String lines[] = importdata.toString().split("\n");
            for (int i = 0; i < lines.length; i++) {
              String[] ss = lines[i].split(",");
              record.set(0, Long.parseLong(ss[0].trim()));
              record.set(1, ss[1].trim());
              context.write(record);
            }
          } catch (FileNotFoundException ex) {
            throw new IOException(ex);
          } catch (IOException ex) {
            throw new IOException(ex);
          } finally {
          }
        }
        @Override
        public void map(long recordNum, Record record, TaskContext context)
            throws IOException {
        }
      }
      public static void main(String[] args) throws Exception {
        if (args.length != 2) {
          System.err.println("Usage: Upload <import_txt> <out_table>");
          System.exit(2);
        }
        JobConf job = new JobConf();
        job.setMapperClass(UploadMapper.class);
        job.set("import.filename", args[0]);
        job.setNumReduceTasks(0);
        job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint"));
        job.setMapOutputValueSchema(SchemaUtils.fromString("value:string"));
        InputUtils.addTable(TableInfo.builder().tableName("mr_empty").build(), job);
        OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
        JobClient.runJob(job);
      }
    }

实际上,您可通过以下两种方式设置JobConf。

  • 通过SDK中JobConf的接口设置,本示例即是通过此方法实现。
  • 在Jar命令行中,通过–conf参数指定新的JobConf文件。