# macOS
brew install terraform

# Linux
wget https://releases.hashicorp.com/terraform/1.5.0/terraform_1.5.0_linux_amd64.zip
unzip terraform_1.5.0_linux_amd64.zip
sudo mv terraform /usr/local/bin/

# Verify installation
terraform version

# macOS
brew install awscli

# Linux
curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"
unzip awscliv2.zip
sudo ./aws/install

# Configure AWS credentials
aws configure

terraform/
├── main.tf           # Main infrastructure definitions
├── variables.tf      # Input variables
├── outputs.tf        # Output values
└── terraform.tfstate # State file (generated)

# Initialize backend and download providers
terraform -chdir=terraform init

# Check syntax and validate configuration
terraform -chdir=terraform validate

# Auto-format HCL files
terraform -chdir=terraform fmt

# Preview what will be created/changed
terraform -chdir=terraform plan

# Create or update infrastructure
terraform -chdir=terraform apply

# Auto-approve without confirmation (use carefully)
terraform -chdir=terraform apply -auto-approve

# Remove all managed infrastructure
terraform -chdir=terraform destroy

# Auto-approve destruction (use carefully)
terraform -chdir=terraform destroy -auto-approve

# List all resources in state
terraform -chdir=terraform state list

# Show detailed resource information
terraform -chdir=terraform state show aws_s3_bucket.data_bucket

# View state as JSON
cat terraform/terraform.tfstate | jq -r '.resources[] | [.type, .name] | join(",")'

# terraform/main.tf
terraform {
  required_providers {
    aws = {
      source  = "hashicorp/aws"
      version = "~> 5.0"
    }
  }
}

provider "aws" {
  region = var.aws_region
}

resource "aws_s3_bucket" "data_lake" {
  bucket = "my-unique-data-lake-bucket-${var.environment}"
  
  tags = {
    Name        = "Data Lake Bucket"
    Environment = var.environment
    Project     = "data-engineering"
  }
}

resource "aws_s3_bucket_versioning" "data_lake_versioning" {
  bucket = aws_s3_bucket.data_lake.id
  
  versioning_configuration {
    status = "Enabled"
  }
}

resource "aws_s3_bucket_lifecycle_configuration" "data_lake_lifecycle" {
  bucket = aws_s3_bucket.data_lake.id

  rule {
    id     = "archive_old_data"
    status = "Enabled"

    transition {
      days          = 90
      storage_class = "GLACIER"
    }

    expiration {
      days = 365
    }
  }
}

# terraform/main.tf (continued)
data "aws_ami" "ubuntu" {
  most_recent = true
  owners      = ["099720109477"] # Canonical

  filter {
    name   = "name"
    values = ["ubuntu/images/hvm-ssd/ubuntu-jammy-22.04-amd64-server-*"]
  }
}

resource "aws_instance" "data_processor" {
  ami           = data.aws_ami.ubuntu.id
  instance_type = var.instance_type

  tags = {
    Name        = "Data Processing Server"
    Environment = var.environment
  }

  user_data = <<-EOF
              #!/bin/bash
              sudo apt-get update
              sudo apt-get install -y python3-pip
              pip3 install pandas boto3 apache-airflow
              EOF
}

resource "aws_eip" "data_processor_eip" {
  instance = aws_instance.data_processor.id
  domain   = "vpc"
}

# terraform/variables.tf
variable "aws_region" {
  description = "AWS region for resources"
  type        = string
  default     = "us-east-1"
}

variable "environment" {
  description = "Environment name"
  type        = string
  default     = "dev"
}

variable "instance_type" {
  description = "EC2 instance type"
  type        = string
  default     = "t3.medium"
}

# terraform/outputs.tf
output "s3_bucket_name" {
  description = "Name of the S3 data lake bucket"
  value       = aws_s3_bucket.data_lake.id
}

output "ec2_public_ip" {
  description = "Public IP of data processing EC2 instance"
  value       = aws_eip.data_processor_eip.public_ip
}

output "ec2_instance_id" {
  description = "Instance ID of data processor"
  value       = aws_instance.data_processor.id
}

# Use workspace or separate state files
terraform workspace new staging
terraform workspace new production

# Or use variable files
terraform apply -var-file="environments/dev.tfvars"
terraform apply -var-file="environments/prod.tfvars"

# terraform/backend.tf
terraform {
  backend "s3" {
    bucket         = "my-terraform-state-bucket"
    key            = "data-engineering/terraform.tfstate"
    region         = "us-east-1"
    encrypt        = true
    dynamodb_table = "terraform-state-lock"
  }
}

resource "aws_iam_role" "data_processor_role" {
  name = "data-processor-role"

  assume_role_policy = jsonencode({
    Version = "2012-10-17"
    Statement = [{
      Action = "sts:AssumeRole"
      Effect = "Allow"
      Principal = {
        Service = "ec2.amazonaws.com"
      }
    }]
  })
}

resource "aws_iam_role_policy_attachment" "s3_access" {
  role       = aws_iam_role.data_processor_role.name
  policy_arn = "arn:aws:iam::aws:policy/AmazonS3FullAccess"
}

resource "aws_iam_instance_profile" "data_processor_profile" {
  name = "data-processor-profile"
  role = aws_iam_role.data_processor_role.name
}

resource "aws_instance" "data_processor" {
  ami                  = data.aws_ami.ubuntu.id
  instance_type        = var.instance_type
  iam_instance_profile = aws_iam_instance_profile.data_processor_profile.name
}

# List all S3 buckets
aws s3 ls

# Get bucket details
aws s3api get-bucket-location --bucket my-data-lake-bucket

# List bucket contents
aws s3 ls s3://my-data-lake-bucket/

# List running instances
aws ec2 describe-instances \
  --filters "Name=instance-state-name,Values=running" \
  --query 'Reservations[].Instances[].{ID:InstanceId, Name:Tags[?Key==`Name`].Value, Type:InstanceType, State:State.Name, PublicIP:PublicIpAddress, PrivateIP:PrivateIpAddress}' \
  --output table

# Get specific instance details
aws ec2 describe-instances --instance-ids i-1234567890abcdef0

# SSH into instance (requires key pair)
ssh -i ~/.ssh/my-key.pem ubuntu@$(terraform -chdir=terraform output -raw ec2_public_ip)

# Clear cache and reinitialize
rm -rf terraform/.terraform
rm terraform/.terraform.lock.hcl
terraform -chdir=terraform init

# Force unlock (use with caution)
terraform -chdir=terraform force-unlock LOCK_ID

# Verify AWS configuration
aws configure list
aws sts get-caller-identity

# Set credentials explicitly
export AWS_ACCESS_KEY_ID="${AWS_ACCESS_KEY_ID}"
export AWS_SECRET_ACCESS_KEY="${AWS_SECRET_ACCESS_KEY}"
export AWS_DEFAULT_REGION="us-east-1"

# Import existing resource into state
terraform -chdir=terraform import aws_s3_bucket.data_lake my-existing-bucket

# Or recreate with unique name
terraform -chdir=terraform apply -var="bucket_suffix=$(date +%s)"

# Test S3 permissions
aws s3 ls

# Test EC2 permissions
aws ec2 describe-instances

# Test IAM permissions
aws iam list-users

# Enable debug logging
export TF_LOG=DEBUG
terraform -chdir=terraform apply

# Show detailed plan
terraform -chdir=terraform plan -out=tfplan
terraform -chdir=terraform show tfplan

# Refresh state from actual infrastructure
terraform -chdir=terraform refresh