以 JSON 格式定义管道 - AWS Data Pipeline

AWS Data Pipeline 不再向新客户提供。的现有客户 AWS Data Pipeline 可以继续照常使用该服务。了解更多

本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

以 JSON 格式定义管道

此示例情景说明如何将数据从 Amazon S3 存储桶复制到 Amazon Redshift。

这是完整管道定义 JSON 文件，其每个部分后跟说明。我们建议您使用文本编辑器，这可帮助您验证 JSON 格式文件的语法，并使用 .json 文件扩展名来命名文件。

{
  "objects": [
    {
      "id": "CSVId1",
      "name": "DefaultCSV1",
      "type": "CSV"
    },
    {
      "id": "RedshiftDatabaseId1",
      "databaseName": "dbname",
      "username": "user",
      "name": "DefaultRedshiftDatabase1",
      "*password": "password",
      "type": "RedshiftDatabase",
      "clusterId": "redshiftclusterId"
    },
    {
      "id": "Default",
      "scheduleType": "timeseries",
      "failureAndRerunMode": "CASCADE",
      "name": "Default",
      "role": "DataPipelineDefaultRole",
      "resourceRole": "DataPipelineDefaultResourceRole"
    },
    {
      "id": "RedshiftDataNodeId1",
      "schedule": {
        "ref": "ScheduleId1"
      },
      "tableName": "orders",
      "name": "DefaultRedshiftDataNode1",
      "createTableSql": "create table StructuredLogs (requestBeginTime CHAR(30) PRIMARY KEY DISTKEY SORTKEY, requestEndTime CHAR(30), hostname CHAR(100), requestDate varchar(20));",
      "type": "RedshiftDataNode",
      "database": {
        "ref": "RedshiftDatabaseId1"
      }
    },
    {
      "id": "Ec2ResourceId1",
      "schedule": {
        "ref": "ScheduleId1"
      },
      "securityGroups": "MySecurityGroup",
      "name": "DefaultEc2Resource1",
      "role": "DataPipelineDefaultRole",
      "logUri": "s3://myLogs",
      "resourceRole": "DataPipelineDefaultResourceRole",
      "type": "Ec2Resource"
    },
    {
      "id": "ScheduleId1",
      "startDateTime": "yyyy-mm-ddT00:00:00",
      "name": "DefaultSchedule1",
      "type": "Schedule",
      "period": "period",
      "endDateTime": "yyyy-mm-ddT00:00:00"
    },
    {
      "id": "S3DataNodeId1",
      "schedule": {
        "ref": "ScheduleId1"
      },
      "filePath": "s3://datapipeline-us-east-1/samples/hive-ads-samples.csv",
      "name": "DefaultS3DataNode1",
      "dataFormat": {
        "ref": "CSVId1"
      },
      "type": "S3DataNode"
    },
    {
      "id": "RedshiftCopyActivityId1",
      "input": {
        "ref": "S3DataNodeId1"
      },
      "schedule": {
        "ref": "ScheduleId1"
      },
      "insertMode": "KEEP_EXISTING",
      "name": "DefaultRedshiftCopyActivity1",
      "runsOn": {
        "ref": "Ec2ResourceId1"
      },
      "type": "RedshiftCopyActivity",
      "output": {
        "ref": "RedshiftDataNodeId1"
      }
    }
  ]
}

有关这些对象的更多信息，请参阅以下文档。

对象