# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: MIT-0

# Textract data post-processing with comprehend sentiment detection Application Stack.  **Attention** This template creates AWS resources that will incur charges on your account
AWSTemplateFormatVersion: 2010-09-09
Transform:
- AWS::Serverless-2016-10-31
Parameters:
  BucketName:
    Type: String
    Default: bucket-for-test
Resources:
  Bucket:
    Type: AWS::S3::Bucket
    Properties:
      BucketName: !Ref BucketName
      BucketEncryption:
        ServerSideEncryptionConfiguration:
          - ServerSideEncryptionByDefault:
              SSEAlgorithm: AES256
      PublicAccessBlockConfiguration:
        BlockPublicAcls: true
        BlockPublicPolicy: true
        IgnorePublicAcls: true
        RestrictPublicBuckets: true
      NotificationConfiguration:
        LambdaConfigurations:
          - Event: s3:ObjectCreated:*
            Filter:
              S3Key:
                Rules:
                  - Name: suffix
                    Value: .pdf
            Function: !GetAtt TextractInvocationLambda.Arn
  TextractInvocationLambda:
    Type: AWS::Serverless::Function
    Properties:
      Description: Triggered by S3 review upload to the repo bucket and start the textract call.
      Handler: textract-invocation.lambda_handler
      MemorySize: 128
      Role: !GetAtt
        - TextractProcessingRole
        - Arn
      Environment:
        Variables:
          SNSTOPIC:
            Ref: SNS
          IAMARN:
            Fn::GetAtt:
              - TextractProcessingRole
              - Arn
      Runtime: python3.6
      Timeout: 600
      CodeUri: s3://aws-ml-blog/artifacts/textract-paragraph-blog/textract-blog-source-code.zip
  TextractPostProcessLambda:
    Type: AWS::Serverless::Function
    Properties:
      Description: Triggered by notification from Textract after the job has been completed
      Handler: blog-code-format2.lambda_handler
      MemorySize: 128
      Role: !GetAtt
        - TextractProcessingRole
        - Arn
      Runtime: python3.6
      Timeout: 600
      CodeUri: s3://aws-ml-blog/artifacts/textract-paragraph-blog/textract-blog-source-code.zip
  SNS:
    Type: AWS::SNS::Topic
  S3InvokeLambdaPermission:
    Type: AWS::Lambda::Permission
    Properties:
      Action: lambda:InvokeFunction
      FunctionName: !Ref TextractInvocationLambda
      Principal: s3.amazonaws.com
      SourceAccount: !Ref 'AWS::AccountId'
      SourceArn: !Sub arn:aws:s3:::${BucketName}
  SNSInvokeLambdaPermission:
    Type: AWS::Lambda::Permission
    Properties:
      Action: lambda:InvokeFunction
      FunctionName: !Ref TextractPostProcessLambda
      Principal: sns.amazonaws.com
      SourceArn: !Ref SNS
  TextractProcessingRole:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Principal:
              Service:
                - lambda.amazonaws.com
                - textract.amazonaws.com
                - comprehend.amazonaws.com
            Action: sts:AssumeRole
      ManagedPolicyArns:
        - arn:aws:iam::aws:policy/service-role/AWSLambdaBasicExecutionRole
      Policies:
        - PolicyName: PolicyForRole
          PolicyDocument:
            Version: 2012-10-17
            Statement:
              - Effect: Allow
                Action:
                  - s3:PutBucketNotification
                  - s3:PutObject
                  - s3:GetObject
                  - s3:ListBucket
                Resource:
                  - !Sub arn:aws:s3:::${BucketName}
                  - !Sub arn:aws:s3:::${BucketName}/*
              - Effect: Allow
                Action:
                  - dynamodb:*
                Resource:
                  - !Join
                    - ''
                    - - 'arn:aws:dynamodb:'
                      - !Ref 'AWS::Region'
                      - ':'
                      - !Ref 'AWS::AccountId'
                      - ':table/textract-job-details'
                  - !Join
                    - ''
                    - - 'arn:aws:dynamodb:'
                      - !Ref 'AWS::Region'
                      - ':'
                      - !Ref 'AWS::AccountId'
                      - ':table/textract-post-process-data'
              - Effect: Allow
                Action:
                  - textract:DetectDocumentText
                  - textract:StartDocumentTextDetection
                  - textract:StartDocumentAnalysis
                  - textract:AnalyzeDocument
                  - textract:GetDocumentTextDetection
                  - textract:GetDocumentAnalysis
                Resource: '*'
              - Effect: Allow
                Action:
                  - comprehend:DetectSentiment
                  - comprehend:DetectKeyPhrases
                Resource: '*'
              - Effect: Allow
                Action:
                  - sns:Publish
                  - sns:Subscribe
                Resource:
                  - !Ref SNS
  Subscription:
    Type: 'AWS::SNS::Subscription'
    Properties:
      Endpoint: !GetAtt
        - TextractPostProcessLambda
        - Arn
      Protocol: lambda
      TopicArn: !Ref SNS
  DynamoParagraphDataTable:
    Type: AWS::DynamoDB::Table
    Properties:
      AttributeDefinitions:
        - AttributeName: "file_path"
          AttributeType: "S"
        - AttributeName: "paragraph_header"
          AttributeType: "S"
      BillingMode: "PAY_PER_REQUEST"
      KeySchema:
        - AttributeName: "file_path"
          KeyType: "HASH"
        - AttributeName: "paragraph_header"
          KeyType: "RANGE"
      TableName: "textract-post-process-data"
  DynamoTextractJobStatusTable:
    Type: AWS::DynamoDB::Table
    Properties:
      AttributeDefinitions:
        - AttributeName: "file_path"
          AttributeType: "S"
        - AttributeName: "job_id"
          AttributeType: "S"
      BillingMode: "PAY_PER_REQUEST"
      KeySchema:
        - AttributeName: "file_path"
          KeyType: "HASH"
        - AttributeName: "job_id"
          KeyType: "RANGE"
      TableName: "textract-job-details"