本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。 # `CreateJob` 搭配 AWS SDK 或 CLI 使用 `CreateJob` 下列程式碼範例示範如何使用 `CreateJob`。動作範例是大型程式的程式碼摘錄，必須在內容中執行。您可以在下列程式碼範例的內容中看到此動作： + [了解基本概念](example_glue_Scenario_GetStartedCrawlersJobs_section.md) ------ #### [ .NET ] **適用於 .NET 的 SDK** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/Glue#code-examples)中設定和執行。 ``` ///

/// Create an AWS Glue job. ///

/// The name of the job. /// The name of the IAM role to be assumed by /// the job. /// A description of the job. /// The URL to the script. /// A Boolean value indicating the success of the action. public async Task CreateJobAsync(string dbName, string tableName, string bucketUrl, string jobName, string roleName, string description, string scriptUrl) { var command = new JobCommand { PythonVersion = "3", Name = "glueetl", ScriptLocation = scriptUrl, }; var arguments = new Dictionary { { "--input_database", dbName }, { "--input_table", tableName }, { "--output_bucket_url", bucketUrl } }; var request = new CreateJobRequest { Command = command, DefaultArguments = arguments, Description = description, GlueVersion = "3.0", Name = jobName, NumberOfWorkers = 10, Role = roleName, WorkerType = "G.1X" }; var response = await _amazonGlue.CreateJobAsync(request); return response.HttpStatusCode == HttpStatusCode.OK; } ``` + 如需 API 詳細資訊，請參閱《*適用於 .NET 的 AWS SDK API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/goto/DotNetSDKV3/glue-2017-03-31/CreateJob)。 ------ #### [ C\$1\$1 ] **適用於 C\$1\$1 的 SDK** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/cpp/example_code/glue#code-examples)中設定和執行。 ``` Aws::Client::ClientConfiguration clientConfig; // Optional: Set to the AWS Region in which the bucket was created (overrides config file). // clientConfig.region = "us-east-1"; Aws::Glue::GlueClient client(clientConfig); Aws::Glue::Model::CreateJobRequest request; request.SetName(JOB_NAME); request.SetRole(roleArn); request.SetGlueVersion(GLUE_VERSION); Aws::Glue::Model::JobCommand command; command.SetName(JOB_COMMAND_NAME); command.SetPythonVersion(JOB_PYTHON_VERSION); command.SetScriptLocation( Aws::String("s3://") + bucketName + "/" + PYTHON_SCRIPT); request.SetCommand(command); Aws::Glue::Model::CreateJobOutcome outcome = client.CreateJob(request); if (outcome.IsSuccess()) { std::cout << "Successfully created the job." << std::endl; } else { std::cerr << "Error creating the job. " << outcome.GetError().GetMessage() << std::endl; deleteAssets(CRAWLER_NAME, CRAWLER_DATABASE_NAME, "", bucketName, clientConfig); return false; } ``` + 如需 API 詳細資訊，請參閱《*適用於 C\$1\$1 的 AWS SDK API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/goto/SdkForCpp/glue-2017-03-31/CreateJob)。 ------ #### [ CLI ] **AWS CLI** **建立工作以轉換資料** 下列 `create-job` 範例會建立串流工作，它可執行存放在 S3 中的指令碼。 ``` aws glue create-job \ --name my-testing-job \ --role AWSGlueServiceRoleDefault \ --command '{ \ "Name": "gluestreaming", \ "ScriptLocation": "s3://amzn-s3-demo-bucket/folder/" \ }' \ --region us-east-1 \ --output json \ --default-arguments '{ \ "--job-language":"scala", \ "--class":"GlueApp" \ }' \ --profile my-profile \ --endpoint https://glue.us-east-1.amazonaws.com ``` `test_script.scala` 的內容： ``` import com.amazonaws.services.glue.ChoiceOption import com.amazonaws.services.glue.GlueContext import com.amazonaws.services.glue.MappingSpec import com.amazonaws.services.glue.ResolveSpec import com.amazonaws.services.glue.errors.CallSite import com.amazonaws.services.glue.util.GlueArgParser import com.amazonaws.services.glue.util.Job import com.amazonaws.services.glue.util.JsonOptions import org.apache.spark.SparkContext import scala.collection.JavaConverters._ object GlueApp { def main(sysArgs: Array[String]) { val spark: SparkContext = new SparkContext() val glueContext: GlueContext = new GlueContext(spark) // @params: [JOB_NAME] val args = GlueArgParser.getResolvedOptions(sysArgs, Seq("JOB_NAME").toArray) Job.init(args("JOB_NAME"), glueContext, args.asJava) // @type: DataSource // @args: [database = "tempdb", table_name = "s3-source", transformation_ctx = "datasource0"] // @return: datasource0 // @inputs: [] val datasource0 = glueContext.getCatalogSource(database = "tempdb", tableName = "s3-source", redshiftTmpDir = "", transformationContext = "datasource0").getDynamicFrame() // @type: ApplyMapping // @args: [mapping = [("sensorid", "int", "sensorid", "int"), ("currenttemperature", "int", "currenttemperature", "int"), ("status", "string", "status", "string")], transformation_ctx = "applymapping1"] // @return: applymapping1 // @inputs: [frame = datasource0] val applymapping1 = datasource0.applyMapping(mappings = Seq(("sensorid", "int", "sensorid", "int"), ("currenttemperature", "int", "currenttemperature", "int"), ("status", "string", "status", "string")), caseSensitive = false, transformationContext = "applymapping1") // @type: SelectFields // @args: [paths = ["sensorid", "currenttemperature", "status"], transformation_ctx = "selectfields2"] // @return: selectfields2 // @inputs: [frame = applymapping1] val selectfields2 = applymapping1.selectFields(paths = Seq("sensorid", "currenttemperature", "status"), transformationContext = "selectfields2") // @type: ResolveChoice // @args: [choice = "MATCH_CATALOG", database = "tempdb", table_name = "my-s3-sink", transformation_ctx = "resolvechoice3"] // @return: resolvechoice3 // @inputs: [frame = selectfields2] val resolvechoice3 = selectfields2.resolveChoice(choiceOption = Some(ChoiceOption("MATCH_CATALOG")), database = Some("tempdb"), tableName = Some("my-s3-sink"), transformationContext = "resolvechoice3") // @type: DataSink // @args: [database = "tempdb", table_name = "my-s3-sink", transformation_ctx = "datasink4"] // @return: datasink4 // @inputs: [frame = resolvechoice3] val datasink4 = glueContext.getCatalogSink(database = "tempdb", tableName = "my-s3-sink", redshiftTmpDir = "", transformationContext = "datasink4").writeDynamicFrame(resolvechoice3) Job.commit() } } ``` 輸出： ``` { "Name": "my-testing-job" } ``` 如需詳細資訊，請參閱《[Glue AWS 開發人員指南》中的在 Glue 中編寫任務](https://docs.aws.amazon.com/glue/latest/dg/author-job.html)。 *AWS * + 如需 API 詳細資訊，請參閱《AWS CLI 命令參考》**中的 [CreateJob](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/glue/create-job.html)。 ------ #### [ Java ] **SDK for Java 2.x** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/example_code/glue#code-examples)中設定和執行。 ``` /** * Creates a new AWS Glue job. * * @param glueClient the AWS Glue client to use for the operation * @param jobName the name of the job to create * @param iam the IAM role to associate with the job * @param scriptLocation the location of the script to be used by the job * @throws GlueException if there is an error creating the job */ public static void createJob(GlueClient glueClient, String jobName, String iam, String scriptLocation) { try { JobCommand command = JobCommand.builder() .pythonVersion("3") .name("glueetl") .scriptLocation(scriptLocation) .build(); CreateJobRequest jobRequest = CreateJobRequest.builder() .description("A Job created by using the AWS SDK for Java V2") .glueVersion("2.0") .workerType(WorkerType.G_1_X) .numberOfWorkers(10) .name(jobName) .role(iam) .command(command) .build(); glueClient.createJob(jobRequest); System.out.println(jobName + " was successfully created."); } catch (GlueException e) { throw e; } } ``` + 如需 API 詳細資訊，請參閱《*AWS SDK for Java 2.x API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/goto/SdkForJavaV2/glue-2017-03-31/CreateJob)。 ------ #### [ JavaScript ] **適用於 JavaScript (v3) 的 SDK** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/glue#code-examples)中設定和執行。 ``` const createJob = (name, role, scriptBucketName, scriptKey) => { const client = new GlueClient({}); const command = new CreateJobCommand({ Name: name, Role: role, Command: { Name: "glueetl", PythonVersion: "3", ScriptLocation: `s3://${scriptBucketName}/${scriptKey}`, }, GlueVersion: "3.0", }); return client.send(command); }; ``` + 如需 API 詳細資訊，請參閱《*適用於 JavaScript 的 AWS SDK API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/client/glue/command/CreateJobCommand)。 ------ #### [ PHP ] **適用於 PHP 的 SDK** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/php/example_code/glue#code-examples)中設定和執行。 ``` $role = $iamService->getRole("AWSGlueServiceRole-DocExample"); $jobName = 'test-job-' . $uniqid; $scriptLocation = "s3://$bucketName/run_job.py"; $job = $glueService->createJob($jobName, $role['Role']['Arn'], $scriptLocation); public function createJob($jobName, $role, $scriptLocation, $pythonVersion = '3', $glueVersion = '3.0'): Result { return $this->glueClient->createJob([ 'Name' => $jobName, 'Role' => $role, 'Command' => [ 'Name' => 'glueetl', 'ScriptLocation' => $scriptLocation, 'PythonVersion' => $pythonVersion, ], 'GlueVersion' => $glueVersion, ]); } ``` + 如需 API 詳細資訊，請參閱《*適用於 PHP 的 AWS SDK API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/goto/SdkForPHPV3/glue-2017-03-31/CreateJob)。 ------ #### [ PowerShell ] **Tools for PowerShell V4** **範例 1：此範例會在 Glue AWS 中建立新的任務。命令名稱值一律為 `glueetl`. AWS Glue，支援執行以 Python 或 Scala 撰寫的任務指令碼。在此範例中，任務指令碼 (MyTestGlueJob.py) 以 Python 撰寫。Python 參數在 `$DefArgs` 變數中指定，然後在 `DefaultArguments` 參數中傳遞至 PowerShell 命令，該命令接受雜湊表。`$JobParams`變數中的參數來自 CreateJob API，記錄在 Glue API 參考的任務 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-jobs-job.html：//) AWS 主題中。** ``` $Command = New-Object Amazon.Glue.Model.JobCommand $Command.Name = 'glueetl' $Command.ScriptLocation = 's3://amzn-s3-demo-source-bucket/admin/MyTestGlueJob.py' $Command $Source = "source_test_table" $Target = "target_test_table" $Connections = $Source, $Target $DefArgs = @{ '--TempDir' = 's3://amzn-s3-demo-bucket/admin' '--job-bookmark-option' = 'job-bookmark-disable' '--job-language' = 'python' } $DefArgs $ExecutionProp = New-Object Amazon.Glue.Model.ExecutionProperty $ExecutionProp.MaxConcurrentRuns = 1 $ExecutionProp $JobParams = @{ "AllocatedCapacity" = "5" "Command" = $Command "Connections_Connection" = $Connections "DefaultArguments" = $DefArgs "Description" = "This is a test" "ExecutionProperty" = $ExecutionProp "MaxRetries" = "1" "Name" = "MyOregonTestGlueJob" "Role" = "Amazon-GlueServiceRoleForSSM" "Timeout" = "20" } New-GlueJob @JobParams ``` + 如需 API 詳細資訊，請參閱《AWS Tools for PowerShell Cmdlet 參考 (V4)》**中的 [CreateJob](https://docs.aws.amazon.com/powershell/v4/reference)。 **Tools for PowerShell V5** **範例 1：此範例會在 Glue AWS 中建立新的任務。命令名稱值一律為 `glueetl`. AWS Glue，支援執行以 Python 或 Scala 撰寫的任務指令碼。在此範例中，任務指令碼 (MyTestGlueJob.py) 以 Python 撰寫。Python 參數在 `$DefArgs` 變數中指定，然後在 `DefaultArguments` 參數中傳遞至 PowerShell 命令，該命令接受雜湊表。`$JobParams`變數中的參數來自 CreateJob API，記錄在 Glue API 參考的任務 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-jobs-job.html：//) AWS 主題中。** ``` $Command = New-Object Amazon.Glue.Model.JobCommand $Command.Name = 'glueetl' $Command.ScriptLocation = 's3://amzn-s3-demo-source-bucket/admin/MyTestGlueJob.py' $Command $Source = "source_test_table" $Target = "target_test_table" $Connections = $Source, $Target $DefArgs = @{ '--TempDir' = 's3://amzn-s3-demo-bucket/admin' '--job-bookmark-option' = 'job-bookmark-disable' '--job-language' = 'python' } $DefArgs $ExecutionProp = New-Object Amazon.Glue.Model.ExecutionProperty $ExecutionProp.MaxConcurrentRuns = 1 $ExecutionProp $JobParams = @{ "AllocatedCapacity" = "5" "Command" = $Command "Connections_Connection" = $Connections "DefaultArguments" = $DefArgs "Description" = "This is a test" "ExecutionProperty" = $ExecutionProp "MaxRetries" = "1" "Name" = "MyOregonTestGlueJob" "Role" = "Amazon-GlueServiceRoleForSSM" "Timeout" = "20" } New-GlueJob @JobParams ``` + 如需 API 詳細資訊，請參閱《AWS Tools for PowerShell Cmdlet 參考 (V5)》**中的 [CreateJob](https://docs.aws.amazon.com/powershell/v5/reference)。 ------ #### [ Python ] **適用於 Python 的 SDK (Boto3)** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/glue#code-examples)中設定和執行。 ``` class GlueWrapper: """Encapsulates AWS Glue actions.""" def __init__(self, glue_client): """ :param glue_client: A Boto3 Glue client. """ self.glue_client = glue_client def create_job(self, name, description, role_arn, script_location): """ Creates a job definition for an extract, transform, and load (ETL) job that can be run by AWS Glue. :param name: The name of the job definition. :param description: The description of the job definition. :param role_arn: The ARN of an IAM role that grants AWS Glue the permissions it requires to run the job. :param script_location: The Amazon S3 URL of a Python ETL script that is run as part of the job. The script defines how the data is transformed. """ try: self.glue_client.create_job( Name=name, Description=description, Role=role_arn, Command={ "Name": "glueetl", "ScriptLocation": script_location, "PythonVersion": "3", }, GlueVersion="3.0", ) except ClientError as err: logger.error( "Couldn't create job %s. Here's why: %s: %s", name, err.response["Error"]["Code"], err.response["Error"]["Message"], ) raise ``` + 如需 API 詳細資訊，請參閱《*AWS SDK for Python (Boto3) API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/goto/boto3/glue-2017-03-31/CreateJob)。 ------ #### [ Ruby ] **SDK for Ruby** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/ruby/example_code/glue#code-examples)中設定和執行。 ``` # The `GlueWrapper` class serves as a wrapper around the AWS Glue API, providing a simplified interface for common operations. # It encapsulates the functionality of the AWS SDK for Glue and provides methods for interacting with Glue crawlers, databases, tables, jobs, and S3 resources. # The class initializes with a Glue client and a logger, allowing it to make API calls and log any errors or informational messages. class GlueWrapper def initialize(glue_client, logger) @glue_client = glue_client @logger = logger end # Creates a new job with the specified configuration. # # @param name [String] The name of the job. # @param description [String] The description of the job. # @param role_arn [String] The ARN of the IAM role to be used by the job. # @param script_location [String] The location of the ETL script for the job. # @return [void] def create_job(name, description, role_arn, script_location) @glue_client.create_job( name: name, description: description, role: role_arn, command: { name: 'glueetl', script_location: script_location, python_version: '3' }, glue_version: '3.0' ) rescue Aws::Glue::Errors::GlueException => e @logger.error("Glue could not create job #{name}: \n#{e.message}") raise end ``` + 如需 API 詳細資訊，請參閱《*適用於 Ruby 的 AWS SDK API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/goto/SdkForRubyV3/glue-2017-03-31/CreateJob)。 ------ #### [ Rust ] **適用於 Rust 的 SDK** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/rustv1/examples/glue#code-examples)中設定和執行。 ``` let create_job = glue .create_job() .name(self.job()) .role(self.iam_role.expose_secret()) .command( JobCommand::builder() .name("glueetl") .python_version("3") .script_location(format!("s3://{}/job.py", self.bucket())) .build(), ) .glue_version("3.0") .send() .await .map_err(GlueMvpError::from_glue_sdk)?; let job_name = create_job.name().ok_or_else(|| { GlueMvpError::Unknown("Did not get job name after creating job".into()) })?; ``` + 如需 API 詳細資訊，請參閱《*AWS SDK for Rust API 參考*》中的 [CreateJob](https://docs.rs/aws-sdk-glue/latest/aws_sdk_glue/client/struct.Client.html#method.create_job)。 ------ #### [ SAP ABAP ] **適用於 SAP ABAP 的開發套件** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/sap-abap/services/glu#code-examples)中設定和執行。 ``` TRY. " iv_job_name = 'my-etl-job' " iv_description = 'ETL job for data transformation' " iv_role_arn = 'arn:aws:iam::123456789012:role/AWSGlueServiceRole-Test' " iv_script_location = 's3://example-bucket/scripts/my-script.py' DATA(lo_command) = NEW /aws1/cl_glujobcommand( iv_name = 'glueetl' iv_scriptlocation = iv_script_location iv_pythonversion = '3' ). lo_glu->createjob( iv_name = iv_job_name iv_description = iv_description iv_role = iv_role_arn io_command = lo_command iv_glueversion = '3.0' ). MESSAGE 'Job created successfully.' TYPE 'I'. CATCH /aws1/cx_glualreadyexistsex. MESSAGE 'Job already exists.' TYPE 'E'. CATCH /aws1/cx_gluinvalidinputex INTO DATA(lo_invalid_ex). DATA(lv_invalid_error) = lo_invalid_ex->if_message~get_longtext( ). MESSAGE lv_invalid_error TYPE 'E'. CATCH /aws1/cx_gluinternalserviceex INTO DATA(lo_internal_ex). DATA(lv_internal_error) = lo_internal_ex->if_message~get_longtext( ). MESSAGE lv_internal_error TYPE 'E'. CATCH /aws1/cx_gluoperationtimeoutex INTO DATA(lo_timeout_ex). DATA(lv_timeout_error) = lo_timeout_ex->if_message~get_longtext( ). MESSAGE lv_timeout_error TYPE 'E'. CATCH /aws1/cx_gluresrcnumlmtexcdex INTO DATA(lo_limit_ex). DATA(lv_limit_error) = lo_limit_ex->if_message~get_longtext( ). MESSAGE lv_limit_error TYPE 'E'. ENDTRY. ``` + 如需 API 詳細資訊，請參閱《適用於 *AWS SAP ABAP 的 SDK API 參考*》中的 [CreateJob](https://docs.aws.amazon.com/sdk-for-sap-abap/v1/api/latest/index.html)。 ------ #### [ Swift ] **適用於 Swift 的 SDK** GitHub 上提供更多範例。尋找完整範例，並了解如何在 [AWS 程式碼範例儲存庫](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/swift/example_code/glue#code-examples)中設定和執行。 ``` import AWSClientRuntime import AWSGlue /// Create a new AWS Glue job. /// /// - Parameters: /// - glueClient: The AWS Glue client to use. /// - jobName: The name to give the new job. /// - role: The IAM role for the job to use when accessing AWS services. /// - scriptLocation: The AWS S3 URI of the script to be run by the job. /// /// - Returns: `true` if the job is created successfully, otherwise `false`. func createJob(glueClient: GlueClient, name jobName: String, role: String, scriptLocation: String) async -> Bool { let command = GlueClientTypes.JobCommand( name: "glueetl", pythonVersion: "3", scriptLocation: scriptLocation ) do { _ = try await glueClient.createJob( input: CreateJobInput( command: command, description: "Created by the AWS SDK for Swift Glue basic scenario example.", glueVersion: "3.0", name: jobName, numberOfWorkers: 10, role: role, workerType: .g1x ) ) } catch { return false } return true } ``` + 如需 API 詳細資訊，請參閱《適用於 Swift 的AWS SDK API 參考》**中的 [CreateJob](https://sdk.amazonaws.com/swift/api/awsglue/latest/documentation/awsglue/glueclient/createjob(input:))。 ------ 如需 AWS SDK 開發人員指南和程式碼範例的完整清單，請參閱 [搭配 AWS SDK 使用此服務](sdk-general-information-section.md)。此主題也包含有關入門的資訊和舊版 SDK 的詳細資訊。