chore(glue-alpha): refactor spark jobs code-related props handling (#33567)

### Issue # (if applicable)

Related to #33356 

### Reason for this change

address the feedback section of **extraJars, extraFiles, extraPythonFiles, extraJarsFirst** + refactor to reduce duplicative code across the different spark job classes

### Description of changes

- update the different spark jobs props to
  - make `extraPythonFiles`, `extraFiles`, `extraJars`, and `extraJarsFirst` available in pyspark jobs
  - make `extraFiles`, `extraJars`, and `extraJarsFirst` available in scala spark jobs
- introduce a base `SparkJob` class and `SparkJobProps` to reduce duplicate logic across different spark job classes
  - introduce `setupSparkCodeArguments` `protected` method along with an interface `SparkExtraCodeProps` to handle setting up `Code`-related arguments
  - fix spark ui setup to be consistent with docs for `sparkUI` prop
  - merge content of `spark-ui-utils.ts` into `spark-job.ts` and retire it
  - cleanup comma expression for role setup
- fix typos and do renames to follow conventions

### Describe any new or updated permissions being added



N/A

### Description of how you validated changes



updated unit tests

### 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*

Author: humanzz

packages/@aws-cdk/aws-glue-alpha/lib/index.ts

@@ -12,6 +12,7 @@ export * from './security-configuration';
 export * from './storage-parameter';
 export * from './constants';
 export * from './jobs/job';
+export * from './jobs/spark-job';
 export * from './jobs/pyspark-etl-job';
 export * from './jobs/pyspark-flex-etl-job';
 export * from './jobs/pyspark-streaming-job';
@@ -20,7 +21,6 @@ export * from './jobs/ray-job';
 export * from './jobs/scala-spark-etl-job';
 export * from './jobs/scala-spark-flex-etl-job';
 export * from './jobs/scala-spark-streaming-job';
-export * from './jobs/spark-ui-utils';
 export * from './table-base';
 export * from './table-deprecated';
 export * from './triggers/workflow';

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

@@ -4,7 +4,7 @@ import * as iam from 'aws-cdk-lib/aws-iam';
 import * as logs from 'aws-cdk-lib/aws-logs';
 import * as cdk from 'aws-cdk-lib/core';
 import * as constructs from 'constructs';
-import { Code } from '..';
+import { Code } from '../code';
 import { MetricType, JobState, WorkerType, GlueVersion } from '../constants';
 import { IConnection } from '../connection';
 import { ISecurityConfiguration } from '../security-configuration';
@@ -88,7 +88,7 @@ export interface IJob extends cdk.IResource, iam.IGrantable {
  */
 export interface ContinuousLoggingProps {
   /**
-   * Enable continouous logging.
+   * Enable continuous logging.
    */
   readonly enabled: boolean;
 
@@ -126,8 +126,8 @@ export interface ContinuousLoggingProps {
 /**
  * A base class is needed to be able to import existing Jobs into a CDK app to
  * reference as part of a larger stack or construct. JobBase has the subset
- * of attribtues required to idenitfy and reference an existing Glue Job,
- * as well as some CloudWatch metric conveneince functions to configure an
+ * of attributes required to identify and reference an existing Glue Job,
+ * as well as some CloudWatch metric convenience functions to configure an
  * event-driven flow using the job.
  */
 export abstract class JobBase extends cdk.Resource implements IJob {
@@ -282,10 +282,10 @@ export abstract class JobBase extends cdk.Resource implements IJob {
 
 /**
  * A subset of Job attributes are required for importing an existing job
- * into a CDK project. This is ionly used when using fromJobAttributes
+ * into a CDK project. This is only used when using fromJobAttributes
  * to identify and reference the existing job.
  */
-export interface JobImportAttributes {
+export interface JobAttributes {
   /**
    * The name of the job.
    */
@@ -301,9 +301,9 @@ export interface JobImportAttributes {
 }
 
 /**
- * JobProperties will be used to create new Glue Jobs using this L2 Construct.
+ * JobProps will be used to create new Glue Jobs using this L2 Construct.
  */
-export interface JobProperties {
+export interface JobProps {
   /**
    * Script Code Location (required)
    * Script to run when the Glue job executes. Can be uploaded
@@ -463,7 +463,7 @@ export abstract class Job extends JobBase {
    * @param id The construct's id.
    * @param attrs Attributes for the Glue Job we want to import
    */
-  public static fromJobAttributes(scope: constructs.Construct, id: string, attrs: JobImportAttributes): IJob {
+  public static fromJobAttributes(scope: constructs.Construct, id: string, attrs: JobAttributes): IJob {
     class Import extends JobBase {
       public readonly jobName = attrs.jobName;
       public readonly jobArn = this.buildJobArn(scope, attrs.jobName);
@@ -496,12 +496,12 @@ export abstract class Job extends JobBase {
   }
 
   /**
-   * Setup Continuous Loggiung Properties
+   * Setup Continuous Logging Properties
    * @param role The IAM role to use for continuous logging
    * @param props The properties for continuous logging configuration
    * @returns String containing the args for the continuous logging command
    */
-  public setupContinuousLogging(role: iam.IRole, props: ContinuousLoggingProps | undefined) : any {
+  protected setupContinuousLogging(role: iam.IRole, props: ContinuousLoggingProps | undefined) : any {
     // If the developer has explicitly disabled continuous logging return no args
     if (props && !props.enabled) {
       return {};
@@ -552,7 +552,7 @@ function metricRule(rule: events.IRule, props?: cloudwatch.MetricOptions): cloud
     namespace: 'AWS/Events',
     metricName: 'TriggeredRules',
     dimensionsMap: { RuleName: rule.ruleName },
-    statistic: cloudwatch.Statistic.SUM,
+    statistic: cloudwatch.Stats.SUM,
     ...props,
   }).attachTo(rule);
 }

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

@@ -1,27 +1,13 @@
-import * as iam from 'aws-cdk-lib/aws-iam';
-import { Bucket, BucketEncryption } from 'aws-cdk-lib/aws-s3';
 import { CfnJob } from 'aws-cdk-lib/aws-glue';
-import { Job, JobProperties } from './job';
 import { Construct } from 'constructs';
 import { JobType, GlueVersion, JobLanguage, PythonVersion, WorkerType } from '../constants';
-import { SparkUIProps, SparkUILoggingLocation, validateSparkUiPrefix, cleanSparkUiPrefixForGrant } from './spark-ui-utils';
 import { Code } from '../code';
-import { addConstructMetadata } from 'aws-cdk-lib/core/lib/metadata-resource';
+import { SparkJob, SparkJobProps } from './spark-job';
 
 /**
  * Properties for creating a Python Spark ETL job
  */
-export interface PySparkEtlJobProps extends JobProperties {
-  /**
-   * Enables the Spark UI debugging and monitoring with the specified props.
-   *
-   * @default - Spark UI debugging and monitoring is disabled.
-   *
-   * @see https://docs.aws.amazon.com/glue/latest/dg/monitor-spark-ui-jobs.html
-   * @see https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
-   */
-  readonly sparkUI?: SparkUIProps;
-
+export interface PySparkEtlJobProps extends SparkJobProps {
   /**
    * Extra Python Files S3 URL (optional)
    * S3 URL where additional python dependencies are located
@@ -46,6 +32,15 @@ export interface PySparkEtlJobProps extends JobProperties {
    */
   readonly extraJars?: Code[];
 
+  /**
+   * Setting this value to true prioritizes the customer's extra JAR files in the classpath.
+   *
+   * @default false - priority is not given to user-provided jars
+   *
+   * @see `--user-jars-first` in https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
+   */
+  readonly extraJarsFirst?: boolean;
+
   /**
    * 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.
@@ -71,57 +66,20 @@ export interface PySparkEtlJobProps extends JobProperties {
  * You can find more details about version, worker type and other features
  * in Glue's public documentation.
  */
-export class PySparkEtlJob extends Job {
+export class PySparkEtlJob extends SparkJob {
   public readonly jobArn: string;
   public readonly jobName: string;
-  public readonly role: iam.IRole;
-  public readonly grantPrincipal: iam.IPrincipal;
-
-  /**
-   * The Spark UI logs location if Spark UI monitoring and debugging is enabled.
-   *
-   * @see https://docs.aws.amazon.com/glue/latest/dg/monitor-spark-ui-jobs.html
-   * @see https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html
-   */
-  public readonly sparkUILoggingLocation?: SparkUILoggingLocation;
 
   /**
    * PySparkEtlJob constructor
    */
   constructor(scope: Construct, id: string, props: PySparkEtlJobProps) {
-    super(scope, id, {
-      physicalName: props.jobName,
-    });
-    // Enhanced CDK Analytics Telemetry
-    addConstructMetadata(this, props);
-
-    // Set up role and permissions for principal
-    this.role = props.role, {
-      assumedBy: new iam.ServicePrincipal('glue.amazonaws.com'),
-      managedPolicies: [iam.ManagedPolicy.fromAwsManagedPolicyName('service-role/AWSGlueServiceRole')],
-    };
-    this.grantPrincipal = this.role;
+    super(scope, id, props);
 
-    // Enable SparkUI by default as a best practice
-    const sparkUIArgs = props.sparkUI?.bucket ? this.setupSparkUI(this.role, props.sparkUI) : undefined;
-    this.sparkUILoggingLocation = sparkUIArgs?.location;
-
-    // Enable CloudWatch metrics and continuous logging by default as a best practice
-    const continuousLoggingArgs = this.setupContinuousLogging(this.role, props.continuousLogging);
-    const profilingMetricsArgs = { '--enable-metrics': '' };
-    const observabilityMetricsArgs = { '--enable-observability-metrics': 'true' };
-
-    // Gather executable arguments
-    const execuatbleArgs = this.executableArguments(props);
-
-    // Conbine command line arguments into a single line item
+    // Combine command line arguments into a single line item
     const defaultArguments = {
-      ...execuatbleArgs,
-      ...continuousLoggingArgs,
-      ...profilingMetricsArgs,
-      ...observabilityMetricsArgs,
-      ...sparkUIArgs?.args,
-      ...this.checkNoReservedArgs(props.defaultArguments),
+      ...this.executableArguments(props),
+      ...this.nonExecutableCommonArguments(props),
     };
 
     const jobResource = new CfnJob(this, 'Resource', {
@@ -159,35 +117,7 @@ export class PySparkEtlJob extends Job {
   private executableArguments(props: PySparkEtlJobProps) {
     const args: { [key: string]: string } = {};
     args['--job-language'] = JobLanguage.PYTHON;
-
-    if (props.extraPythonFiles && props.extraPythonFiles.length > 0) {
-      args['--extra-py-files'] = props.extraPythonFiles.map(code => this.codeS3ObjectUrl(code)).join(',');
-    }
-    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(',');
-    }
-
+    this.setupExtraCodeArguments(args, props);
     return args;
   }
-
-  private setupSparkUI(role: iam.IRole, sparkUiProps: SparkUIProps) {
-    validateSparkUiPrefix(sparkUiProps.prefix);
-    const bucket = sparkUiProps.bucket ?? new Bucket(this, 'SparkUIBucket', { enforceSSL: true, encryption: BucketEncryption.S3_MANAGED });
-    bucket.grantReadWrite(role, cleanSparkUiPrefixForGrant(sparkUiProps.prefix));
-    const args = {
-      '--enable-spark-ui': 'true',
-      '--spark-event-logs-path': bucket.s3UrlForObject(sparkUiProps.prefix).replace(/\/?$/, '/'), // path will always end with a slash
-    };
-
-    return {
-      location: {
-        prefix: sparkUiProps.prefix,
-        bucket,
-      },
-      args,
-    };
-  }
 }