feat: Terraform and GitHub workflows initial commit

.devcontainer/devcontainer.json

@@ -0,0 +1,28 @@
+{
+  "name": "data-lake",
+  "image": "mcr.microsoft.com/devcontainers/base:bullseye@sha256:c8955c35eff4aaf6078713a66cb83121fea893bd8fd908703733e4a38d54448c",
+  "containerEnv": {
+    "SHELL": "/bin/zsh"
+  },
+  "features": {
+    "ghcr.io/devcontainers/features/aws-cli:1": {
+      "version": "latest"
+    },
+    "ghcr.io/devcontainers/features/terraform:1": {
+      "version": "1.9.8",
+      "terragrunt": "0.68.6"
+    }
+  },
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "hashicorp.terraform",
+        "github.copilot",
+        "github.vscode-github-actions",
+        "hashicorp.hcl",
+        "redhat.vscode-yaml"
+      ]
+    }
+  },
+  "remoteUser": "vscode"
+}

.github/workflows/terraform-security-scan.yml

@@ -0,0 +1,29 @@
+
+name: "Terraform security scan"
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "terragrunt/**"
+      - ".github/workflows/terraform-security-scan.yml"      
+  pull_request:
+    paths:
+      - "terragrunt/**"
+      - ".github/workflows/terraform-security-scan.yml"
+
+jobs:
+  terraform-security-scan:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
+
+      - name: Checkov security scan
+        uses: bridgecrewio/checkov-action@99bb2caf247dfd9f03cf984373bc6043d4e32ebf # v12.1347.0
+        with:
+          directory: terragrunt/aws
+          framework: terraform
+          output_format: cli
+          soft_fail: false

.github/workflows/terragrunt-apply-production.yml

@@ -0,0 +1,53 @@
+name: "Terragrunt apply PRODUCTION"
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "terragrunt/aws/**"
+      - "terragrunt/env/production/**"
+      - "terragrunt/env/common/**"
+      - "terragrunt/env/terragrunt.hcl"
+      - ".github/workflows/terragrunt-apply-production.yml"
+
+env:
+  AWS_REGION: ca-central-1
+  CONFTEST_VERSION: 0.27.0
+  TERRAFORM_VERSION: 1.9.8
+  TERRAGRUNT_VERSION: 0.68.6
+  TF_INPUT: false
+
+permissions:
+  id-token: write
+  contents: read
+
+jobs:
+  terragrunt-apply-production:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
+
+      - name: Setup terraform tools
+        uses: cds-snc/terraform-tools-setup@v1
+
+      - name: Configure AWS credentials using OIDC
+        uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
+        with:
+          role-to-assume: arn:aws:iam::739275439843:role/data-lake-apply
+          role-session-name: TFApply
+          aws-region: ${{ env.AWS_REGION }}
+
+      - name: Terragrunt apply buckets
+        working-directory: terragrunt/env/production/buckets
+        run: terragrunt apply --terragrunt-non-interactive -auto-approve
+
+      - name: Report deployment to Sentinel
+        if: always()
+        uses: cds-snc/sentinel-forward-data-action@main
+        with:
+          input_data: '{"product": "data-lake", "sha": "${{ github.sha }}", "version": "Infrastructure ${{ github.sha }}", "repository": "${{ github.repository }}", "environment": "production", "status": "${{ job.status }}"}'
+          log_type: CDS_Product_Deployment_Data
+          log_analytics_workspace_id: ${{ secrets.LOG_ANALYTICS_WORKSPACE_ID }}
+          log_analytics_workspace_key: ${{ secrets.LOG_ANALYTICS_WORKSPACE_KEY }}

.github/workflows/terragrunt-plan-production.yml

@@ -0,0 +1,50 @@
+name: "Terragrunt plan PRODUCTION"
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "terragrunt/aws/**"
+      - "terragrunt/env/production/**"
+      - "terragrunt/env/common/**"
+      - "terragrunt/env/terragrunt.hcl"
+      - ".github/workflows/terragrunt-plan-production.yml"
+
+env:
+  AWS_REGION: ca-central-1
+  CONFTEST_VERSION: 0.27.0
+  TERRAFORM_VERSION: 1.9.8
+  TERRAGRUNT_VERSION: 0.68.6
+  TF_INPUT: false
+
+permissions:
+  id-token: write
+  contents: read
+  pull-requests: write
+
+jobs:
+  terragrunt-plan-production:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
+
+      - name: Setup terraform tools
+        uses: cds-snc/terraform-tools-setup@v1
+
+      - name: Configure AWS credentials using OIDC
+        uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
+        with:
+          role-to-assume: arn:aws:iam::739275439843:role/data-lake-plan
+          role-session-name: TFPlan
+          aws-region: ${{ env.AWS_REGION }}
+
+      - name: Terragrunt plan buckets
+        uses: cds-snc/terraform-plan@25afd759b2ada46a94b011fab7a81963c4f3a61a # v3.3.0
+        with:
+          directory: "terragrunt/env/production/buckets"
+          comment-delete: "true"
+          comment-title: "Production: buckets"
+          github-token: "${{ secrets.GITHUB_TOKEN }}"
+          terragrunt: "true"

.github/workflows/workflow-failure.yml

@@ -0,0 +1,18 @@
+name: Workflow failure
+
+on:
+  workflow_run:
+    workflows:
+      - "Terragrunt apply PRODUCTION"
+    types:
+      - completed
+
+jobs:
+  on-failure:
+    runs-on: ubuntu-latest
+    if: github.event.workflow_run.conclusion == 'failure'
+    steps:
+      - name: Notify Slack
+        run: |
+          json='{"blocks":[{"type":"section","text":{"type":"mrkdwn","text":":red: Data Lake workflow failed: <${{ github.event.workflow_run.html_url }}|${{ github.event.workflow.name }}>"}}]}'
+          curl -X POST -H 'Content-type: application/json' --data "$json" ${{ secrets.PRODUCTION_SLACK_WEBHOOK_OPS }}

.gitignore

@@ -0,0 +1,5 @@
+# Terraform
+.terragrunt-cache
+.terraform
+*.tfstate
+*.tfvars

README.md

@@ -1,10 +1,2 @@
-# Generic Project Template
-
-This repository provides some base files for setting up a repository at
-CDS. Plan is to create more project template for specific technologies:
-
-- project-template-terraform
-- project-template-python
-- project-template-nodejs
-
-Note that default community health files are maintained at https://github.com/cds-snc/.github 
+# Data Lake
+This repository holds the Terraform and AWS Glue jobs that manage the Platform Data Lake.

terragrunt/aws/buckets/s3.tf

@@ -0,0 +1,71 @@
+#
+# Holds exported data before transformation
+#
+module "raw_bucket" {
+  source            = "github.com/cds-snc/terraform-modules//S3?ref=v9.6.7"
+  bucket_name       = "cds-data-lake-raw-${var.env}"
+  billing_tag_value = var.billing_tag_value
+
+  logging = {
+    target_bucket = module.log_bucket.s3_bucket_id
+    target_prefix = "raw/"
+  }
+
+  versioning = {
+    enabled = true
+  }
+}
+
+#
+# ETL jobs process the `Raw` bucket and store the transformed data here
+#
+module "transformed_bucket" {
+  source            = "github.com/cds-snc/terraform-modules//S3?ref=v9.6.7"
+  bucket_name       = "cds-data-lake-transformed-${var.env}"
+  billing_tag_value = var.billing_tag_value
+
+  logging = {
+    target_bucket = module.log_bucket.s3_bucket_id
+    target_prefix = "transformed/"
+  }
+
+  versioning = {
+    enabled = true
+  }
+}
+
+#
+# Holds enriched data that has been created by combining multiple transformed datasets
+#
+module "curated_bucket" {
+  source            = "github.com/cds-snc/terraform-modules//S3?ref=v9.6.7"
+  bucket_name       = "cds-data-lake-curated-${var.env}"
+  billing_tag_value = var.billing_tag_value
+
+  logging = {
+    target_bucket = module.log_bucket.s3_bucket_id
+    target_prefix = "curated/"
+  }
+
+  versioning = {
+    enabled = true
+  }
+}
+
+#
+# Bucket access logs, stored for 30 days
+#
+module "log_bucket" {
+  source            = "github.com/cds-snc/terraform-modules//S3_log_bucket?ref=v9.6.7"
+  bucket_name       = "cds-data-lake-bucket-logs-${var.env}"
+  versioning_status = "Enabled"
+
+  lifecycle_rule = {
+    "lifecycle_rule" : {
+      "enabled" : "true",
+      "expiration" : { "days" : "30" }
+    }
+  }
+
+  billing_tag_value = var.billing_tag_value
+}

terragrunt/env/common/common_variables.tf

@@ -0,0 +1,19 @@
+variable "account_id" {
+  description = "(Required) The account ID to perform actions on."
+  type        = string
+}
+
+variable "billing_tag_value" {
+  description = "(Required) the value we use to track billing"
+  type        = string
+}
+
+variable "env" {
+  description = "(Required) The current running environment"
+  type        = string
+}
+
+variable "region" {
+  description = "(Required) The region to build infra in"
+  type        = string
+}

terragrunt/env/common/provider.tf

@@ -0,0 +1,15 @@
+
+terraform {
+  required_version = "1.9.8"
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+  }
+}
+
+provider "aws" {
+  region              = var.region
+  allowed_account_ids = [var.account_id]
+}

terragrunt/env/production/buckets/terragrunt.hcl

@@ -0,0 +1,7 @@
+include {
+  path = find_in_parent_folders()
+}
+
+terraform {
+  source = "../../../aws//buckets"
+}

terragrunt/env/production/env_vars.hcl

@@ -0,0 +1,5 @@
+inputs = {
+  account_id        = "739275439843"
+  env               = "production"
+  billing_tag_value = "PlatformDataLake"
+}

terragrunt/env/terragrunt.hcl

@@ -0,0 +1,37 @@
+locals {
+  vars = read_terragrunt_config("../env_vars.hcl")
+}
+
+inputs = {
+  account_id        = "${local.vars.inputs.account_id}"
+  billing_tag_value = "${local.vars.inputs.billing_tag_value}"
+  env               = "${local.vars.inputs.env}"
+  region            = "ca-central-1"
+}
+
+remote_state {
+  backend = "s3"
+  generate = {
+    path      = "backend.tf"
+    if_exists = "overwrite_terragrunt"
+  }
+  config = {
+    encrypt        = true
+    bucket         = "cds-data-lake-tfstate-${local.vars.inputs.env}"
+    dynamodb_table = "terraform-state-lock-dynamo"
+    region         = "ca-central-1"
+    key            = "${path_relative_to_include()}/terraform.tfstate"
+  }
+}
+
+generate "provider" {
+  path      = "provider.tf"
+  if_exists = "overwrite"
+  contents  = file("./common/provider.tf")
+}
+
+generate "common_variables" {
+  path      = "common_variables.tf"
+  if_exists = "overwrite"
+  contents  = file("./common/common_variables.tf")
+}