feat(glue-alpha): include extra jars parameter in pyspark jobs (aws#3…

…3238)

### Issue # (if applicable)

Closes aws#33225.

### Reason for this change

PySpark jobs with extra JAR dependencies cannot be defined with the new L2 constructs introduced in [v2.177.0](https://github.com/aws/aws-cdk/releases/tag/v2.177.0).

### Description of changes

Add the `extraJars` parameter in the PySpark job L2 constructs.

### Checklist
- [x] My code adheres to the [CONTRIBUTING GUIDE](https://github.com/aws/aws-cdk/blob/main/CONTRIBUTING.md) and [DESIGN GUIDELINES](https://github.com/aws/aws-cdk/blob/main/docs/DESIGN_GUIDELINES.md)

----

*By submitting this pull request, I confirm that my contribution is made under the terms of the Apache-2.0 license*

packages/@aws-cdk/aws-glue-alpha/lib/jobs/pyspark-etl-job.ts

@@ -39,6 +39,13 @@ export interface PySparkEtlJobProps extends JobProperties {
    */
   readonly extraFiles?: Code[];
 
+  /**
+   * Extra Jars S3 URL (optional)
+   * S3 URL where additional jar dependencies are located
+   * @default - no extra jar files
+   */
+  readonly extraJars?: Code[];
+
   /**
    * Specifies whether job run queuing is enabled for the job runs for this job.
    * A value of true means job run queuing is enabled for the job runs.
@@ -159,6 +166,9 @@ export class PySparkEtlJob extends Job {
     if (props.extraFiles && props.extraFiles.length > 0) {
       args['--extra-files'] = props.extraFiles.map(code => this.codeS3ObjectUrl(code)).join(',');
     }
+    if (props.extraJars && props.extraJars?.length > 0) {
+      args['--extra-jars'] = props.extraJars.map(code => this.codeS3ObjectUrl(code)).join(',');
+    }
 
     return args;
   }

packages/@aws-cdk/aws-glue-alpha/lib/jobs/pyspark-flex-etl-job.ts

@@ -48,6 +48,13 @@ export interface PySparkFlexEtlJobProps extends JobProperties {
    */
   readonly extraFiles?: Code[];
 
+  /**
+   * Extra Jars S3 URL (optional)
+   * S3 URL where additional jar dependencies are located
+   * @default - no extra jar files
+   */
+  readonly extraJars?: Code[];
+
 }
 
 /**
@@ -160,6 +167,9 @@ export class PySparkFlexEtlJob extends Job {
     if (props.extraFiles && props.extraFiles.length > 0) {
       args['--extra-files'] = props.extraFiles.map(code => this.codeS3ObjectUrl(code)).join(',');
     }
+    if (props.extraJars && props.extraJars?.length > 0) {
+      args['--extra-jars'] = props.extraJars.map(code => this.codeS3ObjectUrl(code)).join(',');
+    }
 
     return args;
   }

packages/@aws-cdk/aws-glue-alpha/lib/jobs/pyspark-streaming-job.ts

@@ -39,6 +39,13 @@ export interface PySparkStreamingJobProps extends JobProperties {
    */
   readonly extraFiles?: Code[];
 
+  /**
+   * Extra Jars S3 URL (optional)
+   * S3 URL where additional jar dependencies are located
+   * @default - no extra jar files
+   */
+  readonly extraJars?: Code[];
+
   /**
    * Specifies whether job run queuing is enabled for the job runs for this job.
    * A value of true means job run queuing is enabled for the job runs.
@@ -159,6 +166,9 @@ export class PySparkStreamingJob extends Job {
     if (props.extraFiles && props.extraFiles.length > 0) {
       args['--extra-files'] = props.extraFiles.map(code => this.codeS3ObjectUrl(code)).join(',');
     }
+    if (props.extraJars && props.extraJars?.length > 0) {
+      args['--extra-jars'] = props.extraJars.map(code => this.codeS3ObjectUrl(code)).join(',');
+    }
 
     return args;
   }

packages/@aws-cdk/aws-glue-alpha/test/pyspark-etl-jobs.test.ts

@@ -365,7 +365,7 @@ describe('Job', () => {
     });
   });
 
-  describe('Create PySpark ETL Job with extraPythonFiles and extraFiles', () => {
+  describe('Create PySpark ETL Job with extraPythonFiles, extraFiles and extraJars', () => {
     beforeEach(() => {
       job = new glue.PySparkEtlJob(stack, 'PySparkETLJob', {
         role,
@@ -381,6 +381,11 @@ describe('Job', () => {
             s3.Bucket.fromBucketName(stack, 'extraFilesBucket', 'extra-files-bucket'),
             'prefix/file.txt'),
         ],
+        extraJars: [
+          glue.Code.fromBucket(
+            s3.Bucket.fromBucketName(stack, 'extraJarsBucket', 'extra-jars-bucket'),
+            'prefix/file.jar'),
+        ],
       });
     });
 
@@ -408,6 +413,7 @@ describe('Job', () => {
           '--enable-continuous-cloudwatch-log': 'true',
           '--extra-py-files': 's3://extra-python-files-bucket/prefix/file.py',
           '--extra-files': 's3://extra-files-bucket/prefix/file.txt',
+          '--extra-jars': 's3://extra-jars-bucket/prefix/file.jar',
         }),
       });
     });

packages/@aws-cdk/aws-glue-alpha/test/pyspark-streaming-jobs.test.ts

@@ -377,7 +377,7 @@ describe('Job', () => {
     });
   });
 
-  describe('Create PySpark Streaming Job with extraPythonFiles and extraFiles', () => {
+  describe('Create PySpark Streaming Job with extraPythonFiles, extraFiles and extraJars', () => {
     beforeEach(() => {
       job = new glue.PySparkStreamingJob(stack, 'PySparkStreamingJob', {
         role,
@@ -393,6 +393,11 @@ describe('Job', () => {
             s3.Bucket.fromBucketName(stack, 'extraFilesBucket', 'extra-files-bucket'),
             'prefix/file.txt'),
         ],
+        extraJars: [
+          glue.Code.fromBucket(
+            s3.Bucket.fromBucketName(stack, 'extraJarsBucket', 'extra-jars-bucket'),
+            'prefix/file.jar'),
+        ],
       });
     });
 
@@ -420,6 +425,7 @@ describe('Job', () => {
           '--enable-continuous-cloudwatch-log': 'true',
           '--extra-py-files': 's3://extra-python-files-bucket/prefix/file.py',
           '--extra-files': 's3://extra-files-bucket/prefix/file.txt',
+          '--extra-jars': 's3://extra-jars-bucket/prefix/file.jar',
         }),
       });
     });