从CLI提交 Spark Job

export JOB_ROLE_ARN=<<EMRServerlessS3RuntimeRoleARN>>
export S3_BUCKET=s3://<<YOUR_BUCKET>>

export APPLICATION_ID=<<application_id>>

aws emr-serverless start-job-run --application-id ${APPLICATION_ID} --execution-role-arn ${JOB_ROLE_ARN} --name "Spark-WordCount-CLI" --job-driver '{
        "sparkSubmit": {
            "entryPoint": "s3://us-east-1.elasticmapreduce/emr-containers/samples/wordcount/scripts/wordcount.py",
            "entryPointArguments": [
          "'"$S3_BUCKET"'/wordcount_output/"
        ],
            "sparkSubmitParameters": "--conf spark.executor.cores=1 --conf spark.executor.memory=4g --conf spark.driver.cores=1 --conf spark.driver.memory=4g --conf spark.executor.instances=1 --conf spark.hadoop.hive.metastore.client.factory.class=com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory"
        }
    }'