AWS FargateでS3上のCSVを集計するシンプルなバッチ処理を構築してみた

import os
import boto3
import csv
from io import StringIO
s3 = boto3.client("s3")
bucket_name = os.environ["BUCKET_NAME"]
response = s3.get_object(
    Bucket=bucket_name,
    Key="sales.csv"
)
csv_data = response["Body"].read().decode("utf-8")
reader = csv.DictReader(
    StringIO(csv_data)
)
total = sum(
    int(row["amount"])
    for row in reader
)
print(f"Total Amount : {total}")

TaskDefinition:
  Type: AWS::ECS::TaskDefinition
  Properties:
    Family: csv-batch
    RequiresCompatibilities:
      - FARGATE
    Cpu: 256
    Memory: 512
    NetworkMode: awsvpc
    ContainerDefinitions:
      - Name: csv-batch
        Environment:
          - Name: BUCKET_NAME
            Value: 

ACCOUNT_ID=$(aws sts get-caller-identity --query Account --output text)
REGION=${AWS_REGION}
aws ecr get-login-password \
| docker login \
  --username AWS \
  --password-stdin \
  ${ACCOUNT_ID}.dkr.ecr.${REGION}.amazonaws.com && \
docker tag csv-batch-app:latest \
  ${ACCOUNT_ID}.dkr.ecr.${REGION}.amazonaws.com/csv-batch-app:latest && \
docker push \
  ${ACCOUNT_ID}.dkr.ecr.${REGION}.amazonaws.com/csv-batch-app:latest

AWSTemplateFormatVersion: '2010-09-09'
Description: CSV Aggregation Batch using AWS Fargate
Resources:
  VPC:
    Type: AWS::EC2::VPC
    Properties:
      CidrBlock: 10.100.0.0/16
      EnableDnsSupport: true
      EnableDnsHostnames: true
  InternetGateway:
    Type: AWS::EC2::InternetGateway
  VPCGatewayAttachment:
    Type: AWS::EC2::VPCGatewayAttachment
    Properties:
      VpcId: !Ref VPC
      InternetGatewayId: !Ref InternetGateway
  PublicSubnet:
    Type: AWS::EC2::Subnet
    Properties:
      VpcId: !Ref VPC
      AvailabilityZone: !Select [0, !GetAZs '']
      CidrBlock: 10.100.1.0/24
      MapPublicIpOnLaunch: true
  PublicRouteTable:
    Type: AWS::EC2::RouteTable
    Properties:
      VpcId: !Ref VPC
  DefaultRoute:
    Type: AWS::EC2::Route
    DependsOn: VPCGatewayAttachment
    Properties:
      RouteTableId: !Ref PublicRouteTable
      DestinationCidrBlock: 0.0.0.0/0
      GatewayId: !Ref InternetGateway
  PublicSubnetAssociation:
    Type: AWS::EC2::SubnetRouteTableAssociation
    Properties:
      RouteTableId: !Ref PublicRouteTable
      SubnetId: !Ref PublicSubnet
  FargateSecurityGroup:
    Type: AWS::EC2::SecurityGroup
    Properties:
      GroupDescription: Fargate Batch Security Group
      VpcId: !Ref VPC
      SecurityGroupEgress:
        - IpProtocol: "-1"
          CidrIp: 0.0.0.0/0
  SalesBucket:
    Type: AWS::S3::Bucket
    Properties:
      BucketName: !Sub sales-batch-${AWS::AccountId}-${AWS::Region}
  ECRRepository:
    Type: AWS::ECR::Repository
    Properties:
      RepositoryName: csv-batch-app
  LogGroup:
    Type: AWS::Logs::LogGroup
    Properties:
      LogGroupName: /ecs/csv-batch
      RetentionInDays: 30
  ECSCluster:
    Type: AWS::ECS::Cluster
    Properties:
      ClusterName: csv-batch-cluster
  TaskExecutionRole:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Principal:
              Service:
                - ecs-tasks.amazonaws.com
            Action:
              - sts:AssumeRole
      ManagedPolicyArns:
        - arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy
  TaskRole:
    Type: AWS::IAM::Role
    Properties:
      AssumeRolePolicyDocument:
        Version: '2012-10-17'
        Statement:
          - Effect: Allow
            Principal:
              Service:
                - ecs-tasks.amazonaws.com
            Action:
              - sts:AssumeRole
      Policies:
        - PolicyName: ReadCsvFromS3
          PolicyDocument:
            Version: '2012-10-17'
            Statement:
              - Effect: Allow
                Action:
                  - s3:GetObject
                Resource:
                  - !Sub '${SalesBucket.Arn}/*'
  TaskDefinition:
    Type: AWS::ECS::TaskDefinition
    Properties:
      Family: csv-batch
      RequiresCompatibilities:
        - FARGATE
      Cpu: 256
      Memory: 512
      NetworkMode: awsvpc
      ExecutionRoleArn: !GetAtt TaskExecutionRole.Arn
      TaskRoleArn: !GetAtt TaskRole.Arn
      ContainerDefinitions:
        - Name: csv-batch
          Image: !Sub "${ECRRepository.RepositoryUri}:latest"
          Essential: true
          Environment:
            - Name: BUCKET_NAME
              Value: !Ref SalesBucket
          LogConfiguration:
            LogDriver: awslogs
            Options:
              awslogs-group: !Ref LogGroup
              awslogs-region: !Ref AWS::Region
              awslogs-stream-prefix: ecs
Outputs:
  BucketName:
    Description: S3 Bucket Name
    Value: !Ref SalesBucket
  RepositoryUri:
    Description: ECR Repository URI
    Value: !GetAtt ECRRepository.RepositoryUri
  ClusterName:
    Description: ECS Cluster Name
    Value: !Ref ECSCluster
  TaskDefinitionArn:
    Description: ECS Task Definition ARN
    Value: !Ref TaskDefinition
  PublicSubnetId:
    Description: Public Subnet ID
    Value: !Ref PublicSubnet
  SecurityGroupId:
    Description: Fargate Security Group ID
    Value: !Ref FargateSecurityGroup