docker

Author: soodoku

.dockerignore

@@ -0,0 +1,118 @@
+# Version control
+.git
+.gitignore
+.gitattributes
+
+# Python
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env
+pip-log.txt
+pip-delete-this-directory.txt
+.tox
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.pytest_cache
+
+# Virtual environments
+venv/
+env/
+ENV/
+.venv/
+.env
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Testing and development
+test_*
+*_test.py
+tests/
+/tmp/
+*.tmp
+
+# Documentation
+*.md
+!README.md
+docs/
+*.rst
+*.txt
+LICENSE
+
+# Build artifacts
+build/
+dist/
+*.egg-info/
+.eggs/
+
+# Cache and temporary files
+cache/
+*.cache
+.cache/
+/model/
+/images/
+screenshots/
+*.png
+*.jpg
+*.jpeg
+
+# Jupyter notebooks
+*.ipynb
+.ipynb_checkpoints
+
+# Local configuration
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# Backup files
+*.bak
+*.backup
+*.old
+*.orig
+
+# Node modules (if any)
+node_modules/
+npm-debug.log*
+
+# Test environments and outputs
+/tmp/
+/test_*/
+test_*.py
+benchmark_*
+output/
+
+# Development tools
+.pre-commit-config.yaml
+setup.cfg
+.flake8
+.mypy.ini
+.pylintrc
+
+# Don't ignore essential files
+!pyproject.toml
+!piedomains/
+!examples/sandbox/
+!docker-entrypoint.sh

Dockerfile

@@ -7,38 +7,85 @@ ENV PYTHONUNBUFFERED=1 \
     PIP_NO_CACHE_DIR=1 \
     DEBIAN_FRONTEND=noninteractive
 
-# Install system dependencies
+# Install system dependencies for Playwright
 RUN apt-get update && apt-get install -y \
     wget \
     gnupg \
     curl \
     unzip \
+    # Playwright system dependencies
+    libnss3 \
+    libnspr4 \
+    libatk-bridge2.0-0 \
+    libdrm2 \
+    libxkbcommon0 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxrandr2 \
+    libgbm1 \
+    libxss1 \
+    libasound2 \
+    libatspi2.0-0 \
+    libgtk-3-0 \
+    # Additional dependencies for headless operation
+    xvfb \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
-# Install Google Chrome
-RUN wget -q -O - https://dl.google.com/linux/linux_signing_key.pub | gpg --dearmor -o /usr/share/keyrings/googlechrome-linux-keyring.gpg \
-    && echo "deb [arch=amd64 signed-by=/usr/share/keyrings/googlechrome-linux-keyring.gpg] http://dl.google.com/linux/chrome/deb/ stable main" > /etc/apt/sources.list.d/google.list \
-    && apt-get update \
-    && apt-get install -y google-chrome-stable \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install uv
+# Install uv for fast package management
 RUN pip install uv
 
 # Set working directory
 WORKDIR /app
 
-# Copy pyproject.toml and install dependencies
-COPY pyproject.toml ./
+# Copy essential files for package installation
+COPY pyproject.toml README.md ./
+
+# Install Python dependencies
 RUN uv pip install --system -e .
 
-# Copy source code
+# Install Playwright system dependencies
+RUN python -m playwright install-deps chromium
+
+# Create non-root user for security
+RUN groupadd -r playwright && useradd -r -g playwright -G audio,video playwright \
+    && mkdir -p /home/playwright/Downloads \
+    && chown -R playwright:playwright /home/playwright \
+    && chown -R playwright:playwright /app
+
+# Copy entrypoint script first (as root)
+COPY docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+
+# Copy source code (before switching user)
 COPY . .
 
+# Set ownership of the app directory (as root)
+RUN chown -R playwright:playwright /app
+
+# Switch to non-root user
+USER playwright
+
+# Set Playwright environment variables
+ENV PLAYWRIGHT_BROWSERS_PATH=/home/playwright/.cache/ms-playwright
+
+# Install browsers as playwright user
+RUN python -m playwright install chromium
+
+# Create cache directories
+RUN mkdir -p /home/playwright/.cache/ms-playwright \
+    && mkdir -p /app/cache/html \
+    && mkdir -p /app/cache/images
+
 # Expose port (if running web service)
 EXPOSE 8000
 
-# Default command
-CMD ["python", "-c", "from piedomains.api import DomainClassifier; print('piedomains v0.4.0 ready!')"]
+# Set entrypoint
+ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]
+
+# Health check to verify installation
+HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
+    CMD python -c "import piedomains; print('✓ piedomains ready')" || exit 1
+
+# Default command - interactive shell
+CMD []

docker-entrypoint.sh

@@ -0,0 +1,80 @@
+#!/bin/bash
+# Docker entrypoint script for piedomains container
+# Handles Playwright browser installation at runtime
+
+set -e
+
+BROWSER_CACHE_DIR="/home/playwright/.cache/ms-playwright"
+PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD="${PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD:-0}"
+
+echo "🐳 Starting piedomains container..."
+
+# Function to check if browsers are installed
+check_browsers() {
+    if ls "$BROWSER_CACHE_DIR"/chromium-* 1> /dev/null 2>&1; then
+        return 0  # Browsers found
+    elif ls "$BROWSER_CACHE_DIR"/chromium_headless_shell-* 1> /dev/null 2>&1; then
+        return 0  # Headless browser found
+    else
+        return 1  # Browsers not found
+    fi
+}
+
+# Function to install browsers
+install_browsers() {
+    echo "📦 Installing Playwright browsers (this may take a few minutes)..."
+
+    # Create cache directory with proper permissions
+    mkdir -p "$BROWSER_CACHE_DIR"
+
+    # Try installing browsers with retries
+    local retries=3
+    local count=0
+
+    while [ $count -lt $retries ]; do
+        if python -m playwright install chromium; then
+            echo "✅ Browsers installed successfully"
+            return 0
+        else
+            count=$((count + 1))
+            if [ $count -lt $retries ]; then
+                echo "⚠️  Browser installation failed, retrying ($count/$retries)..."
+                sleep 2
+            fi
+        fi
+    done
+
+    echo "❌ Failed to install browsers after $retries attempts"
+    echo "💡 You can skip browser installation by setting PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1"
+    echo "💡 Or mount a pre-downloaded browser cache volume"
+    return 1
+}
+
+# Main logic
+if [ "$PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD" = "1" ]; then
+    echo "⏭️  Skipping browser installation (PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1)"
+elif check_browsers; then
+    echo "✅ Browsers already installed"
+else
+    if ! install_browsers; then
+        echo "⚠️  Continuing without browsers - some functionality may be limited"
+    fi
+fi
+
+# Verify piedomains can be imported
+echo "🔍 Verifying piedomains installation..."
+if python -c "import piedomains; print('✅ piedomains imported successfully')"; then
+    echo "🚀 piedomains container ready!"
+else
+    echo "❌ piedomains import failed"
+    exit 1
+fi
+
+# Execute the provided command or default to interactive bash
+if [ "$#" -eq 0 ]; then
+    echo "🐚 Starting interactive shell..."
+    exec bash
+else
+    echo "🏃 Executing: $*"
+    exec "$@"
+fi