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

AWSTemplateFormatVersion: '2010-09-09'
Transform: AWS::Serverless-2016-10-31
Parameters: 
  CrawlSchedule:
    Type: String
    Default: rate(1 day)
  URLs: 
    Type: String
    Default: https://aws.amazon.com/kendra/faqs/,https://aws.amazon.com/lex/faqs/,https://aws.amazon.com/comprehend/faqs/
    Description: A comma separate list of URLS to crawl.  The pages can either be HTML or PDFs
Resources:
  PuppeteerHeadlessChromium:
    Type: AWS::Serverless::LayerVersion
    Properties: 
      CompatibleRuntimes:
        - nodejs12.x
        - nodejs14.x
      ContentUri: ./src/layer
      Description: Lambda layer to execute Puppeteer on headless chromium
      LayerName: puppeteer-headless-chromium-node
      LicenseInfo: MIT-0
      RetentionPolicy: Delete
    Metadata:
      BuildMethod: nodejs12.x
  CrawlPage:
    Type: AWS::Serverless::Function
    Properties:
      Handler: index.handler
      Runtime: nodejs12.x

      FunctionName: CrawlPage
      Timeout: 900
      MemorySize: 1024
      CodeUri: ./src/lambda
      Layers:
        - !Ref PuppeteerHeadlessChromium
      Environment:
        Variables:
          URLS: !Ref URLs
          NODE_PATH: /opt/nodejs/node12/node_modules:/opt/nodejs/node14/node_modules:/opt/nodejs/node_modules:/var/runtime/node_modules:/var/runtime:/var/task:/opt/nodejs/lib/
      Events:
        CrawlPageEvent:
          Type: Schedule
          Properties:
              Schedule: !Ref CrawlSchedule