AWSTemplateFormatVersion: "2010-09-09"
Transform: AWS::Serverless-2016-10-31

Description: >
    SAM Template for Glue Step Functions.
    See the AWS::Glue::Job documentation for details (https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-glue-job.html).


Parameters:
    SourceBucket:
        Type: String
        Default: "DATA_BUCKET"
    ArtifactsBucket:
        Type: String
        Default: "ARTIFACTS_BUCKET"
    ETLParametersPath:
        Type: String
        Default: "/etl/hello/parameters"

Resources:

    FeatureEngineering:
        Type: AWS::Glue::Job
        Properties:
            Command:
                Name: pythonshell
                PythonVersion: "3"
                ScriptLocation: !Sub "s3://${ArtifactsBucket}/glue/scripts/feature_engineering.py"
            ExecutionProperty:
                MaxConcurrentRuns: 1
            DefaultArguments:
                "--extra-py-files": !Sub "s3://${ArtifactsBucket}/glue/libs/awswrangler-2.12.0-py3-none-any.whl"
                "--config_path": !Sub "${ETLParametersPath}"
            GlueVersion: "1.0"
            MaxCapacity: 1
            MaxRetries: 0
            Name: "Feature Engineering"
            Role: !GetAtt GlueExecutionRole.Arn

    ETLStepFunctions:
        Type: AWS::Serverless::StateMachine
        Properties:
            DefinitionUri: ../step_functions/statemachine.asl.json
            DefinitionSubstitutions:
                FeatureEngineering: !Sub "${FeatureEngineering}"
            Events:
                TriggerPersonalizeTrain:
                    Type: Schedule
                    Properties:
                        Schedule: rate(2 days)
                        Enabled: False   
            Role: !GetAtt ETLStatesExecutionRole.Arn

    ETLParameters:
        Type: AWS::SSM::Parameter
        Properties:
          Name: !Sub "${ETLParametersPath}"
          Tier: "Standard"
          Description: 'Configuration values for ETL'
          Type: String
          Value: !Sub '{"bucket": "${SourceBucket}", "last_update": "2021-10-20-18-34-26", "prefix": "data/input"}'

    ETLStatesExecutionRole:
        Type: "AWS::IAM::Role"
        Properties:
          AssumeRolePolicyDocument:
            Version: "2012-10-17"
            Statement:
              - Effect: "Allow"
                Principal:
                  Service:
                    - !Sub states.${AWS::Region}.amazonaws.com
                Action: "sts:AssumeRole"
          Path: "/"
          Policies:
            - PolicyName: StatesExecutionPolicy
              PolicyDocument:
                Version: "2012-10-17"
                Statement:
                  - Effect: Allow
                    Action:
                      - "glue:StartJobRun"
                      - "glue:GetJobRun"
                      - "glue:BatchStopJobRun"
                      - "glue:GetJobRuns"
                    Resource: 
                        - !Sub "arn:${AWS::Partition}:glue:${AWS::Region}:${AWS::AccountId}:job/${FeatureEngineering}"
                        
                        
  
    GlueExecutionRole:
        Type: "AWS::IAM::Role"
        Properties:
            AssumeRolePolicyDocument:
                Version: "2012-10-17"
                Statement:
                      - Effect: "Allow"
                        Principal:
                            Service:
                                - "glue.amazonaws.com"
                        Action:
                            - "sts:AssumeRole"
            Path: "/"
            Policies:
                - PolicyName: ReadWriteS3Policy
                  PolicyDocument:
                      Version: "2012-10-17"
                      Statement:
                          - Effect: "Allow"
                            Action: 
                                - "s3:GetObject"
                                - "s3:PutObject"
                                - "s3:PutObjectAcl"
                                - "s3:GetObjectVersion"
                                - "s3:DeleteObject"
                                - "s3:DeleteObjects"
                            Resource:
                                - !Sub "arn:${AWS::Partition}:s3:::${SourceBucket}/*"
                                - !Sub "arn:${AWS::Partition}:s3:::${ArtifactsBucket}/*"
                          - Effect: "Allow"
                            Action:
                                - "s3:GetBucketLocation"
                                - "s3:ListBucket"
                                - "s3:GetLifecycleConfiguration"
                                - "s3:PutLifecycleConfiguration"
                            Resource:
                                - !Sub "arn:${AWS::Partition}:s3:::${SourceBucket}"
                                - !Sub "arn:${AWS::Partition}:s3:::${ArtifactsBucket}"
                - PolicyName: "AccessLogging"
                  PolicyDocument:
                      Version: "2012-10-17"
                      Statement:
                          - Effect: "Allow"
                            Action:
                                - "logs:CreateLogStream"
                                - "logs:CreateLogGroup"
                                - "logs:PutLogEvents"
                            Resource:
                                - !Sub "arn:${AWS::Partition}:logs:${AWS::Region}:${AWS::AccountId}:log-group:/aws-glue/*"
                - PolicyName: "AccessSSM"
                  PolicyDocument:
                      Version: "2012-10-17"
                      Statement:
                          - Effect: "Allow"
                            Action: 
                                - "ssm:GetParameter"
                                - "ssm:PutParameter"
                            Resource: !Sub "arn:${AWS::Partition}:ssm:${AWS::Region}:${AWS::AccountId}:parameter${ETLParametersPath}"

Outputs:
    ETLStepFunctionsARN:
        Value: !GetAtt ETLStepFunctions.Arn
    GlueJobName:
        Value: !Ref FeatureEngineering