MaxCompute：使用資源樣本

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data\resources。
2. 在MaxCompute用戶端中執行如下操作，準備好測試表和資源。
   1. 建立測試表。

      create table mr_upload_src(key bigint, value string);

   2. 添加測試資源。

      add jar data\resources\mapreduce-examples.jar -f;
      add file data\resources\import.txt -f;

   3. import.txt的資料內容如下。

      1000,odps

測試步驟

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;

預期結果

+------------+------------+
| key        | value      |
+------------+------------+
| 1000       | odps       |
+------------+------------+

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.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);
        /**設定資源名字, 可以在map中通過jobconf擷取到。*/
        job.set("import.filename", args[0]);
        /**maponly作業需要顯式設定reducer的數目為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);
    }
}

您可以通過以下兩種方式設定JobConf。

• 通過SDK中JobConf的介面設定，本樣本即是通過此方法實現。
• 在Jar命令列中，通過–conf參數指定新的JobConf檔案。