eoy-pdf-sortandmerge/ubuntu-install.sh

#!/bin/bash

# PDF Sort and Merge Application - Ubuntu Installation Script
# This script installs and configures the Flask web application for PDF processing

set -e  # Exit on any error

# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color

# Logging functions
log_info() {
    echo -e "${BLUE}[INFO]${NC} $1"
}

log_success() {
    echo -e "${GREEN}[SUCCESS]${NC} $1"
}

log_warning() {
    echo -e "${YELLOW}[WARNING]${NC} $1"
}

log_error() {
    echo -e "${RED}[ERROR]${NC} $1"
}

# Check if running as root
if [[ $EUID -eq 0 ]]; then
   log_error "This script should not be run as root. Please run as a regular user with sudo privileges."
   exit 1
fi

# Check Ubuntu version
UBUNTU_VERSION=$(lsb_release -rs)
log_info "Detected Ubuntu version: $UBUNTU_VERSION"

# Update system
log_info "Updating system packages..."
sudo apt update && sudo apt upgrade -y

# Install Python 3.9+ and pip
log_info "Installing Python and pip..."
sudo apt install -y python3 python3-pip python3-venv python3-dev

# Install system dependencies for PDF processing
log_info "Installing system dependencies..."
sudo apt install -y build-essential libpoppler-cpp-dev pkg-config

# Install Node.js and npm (for potential frontend assets)
log_info "Installing Node.js and npm..."
curl -fsSL https://deb.nodesource.com/setup_18.x | sudo -E bash -
sudo apt install -y nodejs

# Create application directory
APP_DIR="$HOME/pdf-sort-merge"
log_info "Creating application directory: $APP_DIR"
mkdir -p "$APP_DIR"
cd "$APP_DIR"

# Clone or download the application
REPO_URL="https://gitlab.com/trbc-dev/eoy-pdf-sortandmerge.git"
log_info "Cloning application repository..."
if command -v git &> /dev/null; then
    sudo apt install -y git
    if [[ -d ".git" ]]; then
        log_info "Repository already exists, pulling latest changes..."
        git pull origin web-app
        git checkout web-app
    else
        log_info "Cloning fresh repository..."
        git clone "$REPO_URL" .
        git checkout web-app
    fi
else
    log_warning "Git not available. Please manually download and extract the application files to $APP_DIR"
    exit 1
fi

# Create Python virtual environment
log_info "Creating Python virtual environment..."
python3 -m venv venv
source venv/bin/activate

# Install Python dependencies
log_info "Installing Python dependencies..."
pip install --upgrade pip
pip install -r requirements.txt

# Create .env file with Azure AD configuration
log_info "Configuring Azure AD authentication..."
echo ""
echo "=================================================================="
echo "AZURE AD CONFIGURATION REQUIRED"
echo "=================================================================="
echo "You need to provide your Azure AD app registration details."
echo "If you don't have them, follow these steps:"
echo "1. Go to https://portal.azure.com"
echo "2. Navigate to Azure Active Directory > App registrations"
echo "3. Create a new registration or use existing one"
echo "4. Note the Application (client) ID and Directory (tenant) ID"
echo "5. Create a client secret under Certificates & secrets"
echo "6. Add redirect URI: http://your-domain-name/auth/callback (will be configured automatically)"
echo "=================================================================="
echo ""

# Prompt for Azure AD credentials
read -p "Enter Azure AD Tenant ID (Directory ID): " AZURE_TENANT_ID
read -p "Enter Azure AD Client ID (Application ID): " AZURE_CLIENT_ID
read -s -p "Enter Azure AD Client Secret: " AZURE_CLIENT_SECRET
echo ""
read -p "Enter DNS domain name (e.g., eoypdf.trbc.org) [localhost]: " DNS_DOMAIN
DNS_DOMAIN=${DNS_DOMAIN:-localhost}
read -p "Enter server IP/domain (for redirect URI) [$DNS_DOMAIN]: " SERVER_HOST
SERVER_HOST=${SERVER_HOST:-$DNS_DOMAIN}

# Determine if we should use HTTPS
USE_HTTPS=false
GENERATE_SELF_SIGNED=false
if [[ "$DNS_DOMAIN" != "localhost" && "$DNS_DOMAIN" != "127.0.0.1" ]]; then
    read -p "Do you have SSL certificates for $DNS_DOMAIN? (y/n) [n]: " HAS_SSL
    if [[ "${HAS_SSL,,}" == "y" || "${HAS_SSL,,}" == "yes" ]]; then
        USE_HTTPS=true
    else
        read -p "Would you like to generate self-signed SSL certificates? (y/n) [y]: " GEN_SELF
        GEN_SELF=${GEN_SELF:-y}
        if [[ "${GEN_SELF,,}" == "y" || "${GEN_SELF,,}" == "yes" ]]; then
            USE_HTTPS=true
            GENERATE_SELF_SIGNED=true
        fi
    fi
fi

# Create .env file with real values
cat > .env << EOF
# Microsoft Entra (Azure AD) Configuration
# Get these values from your Azure AD app registration in the Azure portal

# Azure AD Tenant ID (Directory ID)
AZURE_TENANT_ID=$AZURE_TENANT_ID

# Azure AD Client ID (Application ID)
AZURE_CLIENT_ID=$AZURE_CLIENT_ID

# Azure AD Client Secret
AZURE_CLIENT_SECRET=$AZURE_CLIENT_SECRET

# Azure AD Authority URL (usually https://login.microsoftonline.com/{tenant_id})
AZURE_AUTHORITY=https://login.microsoftonline.com/$AZURE_TENANT_ID

# Redirect URI (must match what's configured in Azure AD app registration)
AZURE_REDIRECT_URI=http${USE_HTTPS:+s}://$SERVER_HOST/auth/callback

# Scopes to request (openid, profile, email are common)
AZURE_SCOPES=openid profile email

# Flask Configuration
SECRET_KEY=$(openssl rand -hex 32)
EOF

log_success "Azure AD configuration saved to .env file"

# Generate self-signed SSL certificates if requested
if [[ "$GENERATE_SELF_SIGNED" == "true" ]]; then
    log_info "Generating self-signed SSL certificates..."
    sudo mkdir -p /etc/ssl/certs /etc/ssl/private

    # Generate self-signed certificate
    sudo openssl req -x509 -nodes -days 365 -newkey rsa:2048 \
        -keyout /etc/ssl/private/pdf-sort-merge.key \
        -out /etc/ssl/certs/pdf-sort-merge.crt \
        -subj "/C=US/ST=State/L=City/O=Organization/CN=$DNS_DOMAIN" \
        -addext "subjectAltName=DNS:$DNS_DOMAIN"

    log_success "Self-signed SSL certificates generated"
fi

# Install and configure nginx
log_info "Installing and configuring nginx..."
sudo apt install -y nginx

# Create nginx configuration
NGINX_CONF="/etc/nginx/sites-available/pdf-sort-merge"
if [[ "$USE_HTTPS" == "true" ]]; then
    # HTTPS configuration with SSL
    sudo tee "$NGINX_CONF" > /dev/null << EOF
server {
    listen 80;
    server_name $DNS_DOMAIN;
    return 301 https://\$server_name\$request_uri;
}

server {
    listen 443 ssl http2;
    server_name $DNS_DOMAIN;

    ssl_certificate /etc/ssl/certs/pdf-sort-merge.crt;
    ssl_certificate_key /etc/ssl/private/pdf-sort-merge.key;

    # SSL security settings
    ssl_protocols TLSv1.2 TLSv1.3;
    ssl_ciphers ECDHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-RSA-AES128-SHA256:ECDHE-RSA-AES256-SHA384;
    ssl_prefer_server_ciphers off;

    # Security headers
    add_header X-Frame-Options "SAMEORIGIN" always;
    add_header X-XSS-Protection "1; mode=block" always;
    add_header X-Content-Type-Options "nosniff" always;
    add_header Referrer-Policy "no-referrer-when-downgrade" always;
    add_header Content-Security-Policy "default-src 'self' http: https: data: blob: 'unsafe-inline'" always;
    add_header Strict-Transport-Security "max-age=31536000; includeSubDomains" always;

    # Proxy to Flask app
    location / {
        proxy_pass http://127.0.0.1:5000;
        proxy_set_header Host \$host;
        proxy_set_header X-Real-IP \$remote_addr;
        proxy_set_header X-Forwarded-For \$proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto \$scheme;

        # WebSocket support (if needed)
        proxy_http_version 1.1;
        proxy_set_header Upgrade \$http_upgrade;
        proxy_set_header Connection "upgrade";

        # Timeout settings
        proxy_connect_timeout 60s;
        proxy_send_timeout 60s;
        proxy_read_timeout 60s;
    }

    # Static files
    location /static/ {
        alias $APP_DIR/static/;
        expires 1y;
        add_header Cache-Control "public, immutable";
    }
}
EOF
else
    # HTTP-only configuration
    sudo tee "$NGINX_CONF" > /dev/null << EOF
server {
    listen 80;
    server_name $DNS_DOMAIN;

    # Security headers
    add_header X-Frame-Options "SAMEORIGIN" always;
    add_header X-XSS-Protection "1; mode=block" always;
    add_header X-Content-Type-Options "nosniff" always;
    add_header Referrer-Policy "no-referrer-when-downgrade" always;
    add_header Content-Security-Policy "default-src 'self' http: https: data: blob: 'unsafe-inline'" always;

    # Proxy to Flask app
    location / {
        proxy_pass http://127.0.0.1:5000;
        proxy_set_header Host \$host;
        proxy_set_header X-Real-IP \$remote_addr;
        proxy_set_header X-Forwarded-For \$proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto \$scheme;

        # WebSocket support (if needed)
        proxy_http_version 1.1;
        proxy_set_header Upgrade \$http_upgrade;
        proxy_set_header Connection "upgrade";

        # Timeout settings
        proxy_connect_timeout 60s;
        proxy_send_timeout 60s;
        proxy_read_timeout 60s;
    }

    # Static files
    location /static/ {
        alias $APP_DIR/static/;
        expires 1y;
        add_header Cache-Control "public, immutable";
    }
}
EOF
fi

# Enable the site
sudo ln -sf "$NGINX_CONF" /etc/nginx/sites-enabled/
sudo rm -f /etc/nginx/sites-enabled/default

# Test nginx configuration
log_info "Testing nginx configuration..."
if sudo nginx -t; then
    log_success "Nginx configuration is valid"
else
    log_error "Nginx configuration has errors"
    exit 1
fi

# Restart nginx
sudo systemctl restart nginx
sudo systemctl enable nginx

log_success "Nginx configured to serve $DNS_DOMAIN on port 80"

# Create systemd service file
log_info "Creating systemd service..."
SERVICE_FILE="/etc/systemd/system/pdf-sort-merge.service"
sudo tee "$SERVICE_FILE" > /dev/null << EOF
[Unit]
Description=PDF Sort and Merge Flask Application
After=network.target

[Service]
Type=simple
User=$USER
WorkingDirectory=$APP_DIR
Environment=PATH=$APP_DIR/venv/bin
ExecStart=$APP_DIR/venv/bin/python $APP_DIR/app.py
Restart=always
RestartSec=5

[Install]
WantedBy=multi-user.target
EOF

# Set proper permissions
sudo chmod 644 "$SERVICE_FILE"

# Create log directory
log_info "Creating log directory..."
sudo mkdir -p /var/log/pdf-sort-merge
sudo chown $USER:$USER /var/log/pdf-sort-merge

# Create application data directories
log_info "Creating application data directories..."
mkdir -p results static templates

# Create Flask session directory for server-side sessions
log_info "Creating Flask session directory..."
sudo mkdir -p /tmp/flask_sessions
sudo chown $USER:$USER /tmp/flask_sessions

# Set up firewall (optional)
log_info "Configuring firewall..."
sudo ufw allow 80/tcp || log_warning "Failed to configure firewall for port 80 - you may need to do this manually"
if [[ "$USE_HTTPS" == "true" ]]; then
    sudo ufw allow 443/tcp || log_warning "Failed to configure firewall for port 443 - you may need to do this manually"
fi
sudo ufw allow ssh/tcp || log_warning "Failed to configure firewall for SSH - you may need to do this manually"

# Enable and start service
log_info "Enabling and starting service..."
sudo systemctl daemon-reload
sudo systemctl enable pdf-sort-merge
sudo systemctl start pdf-sort-merge

# Check service status
sleep 3
if sudo systemctl is-active --quiet pdf-sort-merge; then
    log_success "Service started successfully!"
else
    log_error "Service failed to start. Check logs with: sudo journalctl -u pdf-sort-merge -f"
fi

# Create management script
log_info "Creating management script..."
cat > manage.sh << 'EOF'
#!/bin/bash

case "$1" in
    start)
        sudo systemctl start pdf-sort-merge
        echo "Service started"
        ;;
    stop)
        sudo systemctl stop pdf-sort-merge
        echo "Service stopped"
        ;;
    restart)
        sudo systemctl restart pdf-sort-merge
        echo "Service restarted"
        ;;
    status)
        sudo systemctl status pdf-sort-merge
        ;;
    logs)
        sudo journalctl -u pdf-sort-merge -f
        ;;
    update)
        cd /home/$USER/pdf-sort-merge
        source venv/bin/activate
        git pull
        pip install -r requirements.txt
        sudo systemctl restart pdf-sort-merge
        echo "Application updated"
        ;;
    *)
        echo "Usage: $0 {start|stop|restart|status|logs|update}"
        exit 1
        ;;
esac
EOF

chmod +x manage.sh

# Final instructions
log_success "Installation completed!"
echo ""
echo "=================================================================="
echo "NEXT STEPS:"
echo "1. Point your DNS for $DNS_DOMAIN to this server's IP address"
echo ""
if [[ "$GENERATE_SELF_SIGNED" == "true" ]]; then
    echo "2. IMPORTANT: Self-signed certificates are now active!"
    echo "   - Browsers will show a security warning - click 'Advanced' and 'Proceed'"
    echo "   - For production, consider getting a proper SSL certificate from Let's Encrypt"
    echo ""
fi
echo "3. Update your Azure AD app registration redirect URI to:"
if [[ "$USE_HTTPS" == "true" ]]; then
    echo "   https://$SERVER_HOST/auth/callback"
else
    echo "   http://$SERVER_HOST/auth/callback"
fi
echo ""
echo "4. Access the application at:"
if [[ "$USE_HTTPS" == "true" ]]; then
    echo "   https://$DNS_DOMAIN"
else
    echo "   http://$DNS_DOMAIN"
fi
echo ""
echo "MANAGEMENT COMMANDS:"
echo "  Start service:   sudo systemctl start pdf-sort-merge"
echo "  Stop service:    sudo systemctl stop pdf-sort-merge"
echo "  Restart nginx:   sudo systemctl restart nginx"
echo "  Check status:    sudo systemctl status pdf-sort-merge"
echo "  View logs:       sudo journalctl -u pdf-sort-merge -f"
echo "  Update app:      ./manage.sh update"
echo "=================================================================="

# Check if .env needs configuration
if grep -q "your-tenant-id-here" .env; then
    log_warning "IMPORTANT: Configure your .env file before using the application!"
fi