feat(codespaces): auto-setup Python venv with dependencies (#34409)

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Maxime Beauchemin
2025-07-30 13:57:54 -07:00
committed by GitHub
parent a611278e04
commit 54a5b58e40
9 changed files with 296 additions and 42 deletions

20
.devcontainer/Dockerfile Normal file
View File

@@ -0,0 +1,20 @@
# Keep this in sync with the base image in the main Dockerfile (ARG PY_VER)
FROM python:3.11.13-bookworm AS base
# Install system dependencies that Superset needs
# This layer will be cached across Codespace sessions
RUN apt-get update && apt-get install -y \
libsasl2-dev \
libldap2-dev \
libpq-dev \
tmux \
gh \
&& rm -rf /var/lib/apt/lists/*
# Install uv for fast Python package management
# This will also be cached in the image
RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
echo 'export PATH="/root/.cargo/bin:$PATH"' >> /etc/bash.bashrc
# Set the cargo/bin directory in PATH for all users
ENV PATH="/root/.cargo/bin:${PATH}"

View File

@@ -3,3 +3,14 @@
For complete documentation on using GitHub Codespaces with Apache Superset, please see:
**[Setting up a Development Environment - GitHub Codespaces](https://superset.apache.org/docs/contributing/development#github-codespaces-cloud-development)**
## Pre-installed Development Environment
When you create a new Codespace from this repository, it automatically:
1. **Creates a Python virtual environment** using `uv venv`
2. **Installs all development dependencies** via `uv pip install -r requirements/development.txt`
3. **Sets up pre-commit hooks** with `pre-commit install`
4. **Activates the virtual environment** automatically in all terminals
The virtual environment is located at `/workspaces/{repository-name}/.venv` and is automatically activated through environment variables set in the devcontainer configuration.

View File

@@ -0,0 +1,62 @@
# Superset Codespaces environment setup
# This file is appended to ~/.bashrc during Codespace setup
# Find the workspace directory (handles both 'superset' and 'superset-2' names)
WORKSPACE_DIR=$(find /workspaces -maxdepth 1 -name "superset*" -type d | head -1)
if [ -n "$WORKSPACE_DIR" ]; then
# Check if virtual environment exists
if [ -d "$WORKSPACE_DIR/.venv" ]; then
# Activate the virtual environment
source "$WORKSPACE_DIR/.venv/bin/activate"
echo "✅ Python virtual environment activated"
# Verify pre-commit is installed and set up
if command -v pre-commit &> /dev/null; then
echo "✅ pre-commit is available ($(pre-commit --version))"
# Install git hooks if not already installed
if [ -d "$WORKSPACE_DIR/.git" ] && [ ! -f "$WORKSPACE_DIR/.git/hooks/pre-commit" ]; then
echo "🪝 Installing pre-commit hooks..."
cd "$WORKSPACE_DIR" && pre-commit install
fi
else
echo "⚠️ pre-commit not found. Run: pip install pre-commit"
fi
else
echo "⚠️ Python virtual environment not found at $WORKSPACE_DIR/.venv"
echo " Run: cd $WORKSPACE_DIR && .devcontainer/setup-dev.sh"
fi
# Always cd to the workspace directory for convenience
cd "$WORKSPACE_DIR"
fi
# Add helpful aliases for Superset development
alias start-superset="$WORKSPACE_DIR/.devcontainer/start-superset.sh"
alias setup-dev="$WORKSPACE_DIR/.devcontainer/setup-dev.sh"
# Show helpful message on login
echo ""
echo "🚀 Superset Codespaces Environment"
echo "=================================="
# Check if Superset is running
if docker ps 2>/dev/null | grep -q "superset"; then
echo "✅ Superset is running!"
echo " - Check the 'Ports' tab for your live Superset URL"
echo " - Initial startup takes 10-20 minutes"
echo " - Login: admin/admin"
else
echo "⚠️ Superset is not running. Use: start-superset"
# Check if there's a startup log
if [ -f "/tmp/superset-startup.log" ]; then
echo " 📋 Startup log found: cat /tmp/superset-startup.log"
fi
fi
echo ""
echo "Quick commands:"
echo " start-superset - Start Superset with Docker Compose"
echo " setup-dev - Set up Python environment (if not already done)"
echo " pre-commit run - Run pre-commit checks on staged files"
echo ""

View File

@@ -0,0 +1,20 @@
#!/bin/bash
# Script to build and push the devcontainer image to GitHub Container Registry
# This allows caching the image between Codespace sessions
# You'll need to run this with appropriate GitHub permissions
# gh auth login --scopes write:packages
REGISTRY="ghcr.io"
OWNER="apache"
REPO="superset"
TAG="devcontainer-base"
echo "Building devcontainer image..."
docker build -t $REGISTRY/$OWNER/$REPO:$TAG .devcontainer/
echo "Pushing to GitHub Container Registry..."
docker push $REGISTRY/$OWNER/$REPO:$TAG
echo "Done! Update .devcontainer/devcontainer.json to use:"
echo " \"image\": \"$REGISTRY/$OWNER/$REPO:$TAG\""

View File

@@ -1,8 +1,15 @@
{
"name": "Apache Superset Development",
// Keep this in sync with the base image in Dockerfile (ARG PY_VER)
// Using the same base as Dockerfile, but non-slim for dev tools
"image": "python:3.11.13-bookworm",
// Option 1: Use pre-built image directly
// "image": "ghcr.io/apache/superset:devcontainer-base",
// Option 2: Build from Dockerfile with cache (current approach)
"build": {
"dockerfile": "Dockerfile",
"context": ".",
// Cache from the Apache registry image
"cacheFrom": ["ghcr.io/apache/superset:devcontainer-base"]
},
"features": {
"ghcr.io/devcontainers/features/docker-in-docker:2": {
@@ -32,10 +39,17 @@
},
// Run commands after container is created
"postCreateCommand": "chmod +x .devcontainer/setup-dev.sh && .devcontainer/setup-dev.sh",
"postCreateCommand": "bash .devcontainer/setup-dev.sh || echo '⚠️ Setup had issues - run .devcontainer/setup-dev.sh manually'",
// Auto-start Superset on Codespace resume
"postStartCommand": ".devcontainer/start-superset.sh",
// Auto-start Superset after ensuring Docker is ready
// Run in foreground to see any errors, but don't block on failures
"postStartCommand": "bash -c 'echo \"Waiting 30s for services to initialize...\"; sleep 30; .devcontainer/start-superset.sh || echo \"⚠️ Auto-start failed - run start-superset manually\"'",
// Set environment variables
"remoteEnv": {
// Removed automatic venv activation to prevent startup issues
// The setup script will handle this
},
// VS Code customizations
"customizations": {

View File

@@ -3,30 +3,76 @@
echo "🔧 Setting up Superset development environment..."
# The universal image has most tools, just need Superset-specific libs
echo "📦 Installing Superset-specific dependencies..."
sudo apt-get update
sudo apt-get install -y \
libsasl2-dev \
libldap2-dev \
libpq-dev \
tmux \
gh
# System dependencies and uv are now pre-installed in the Docker image
# This speeds up Codespace creation significantly!
# Install uv for fast Python package management
echo "📦 Installing uv..."
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create virtual environment using uv
echo "🐍 Creating Python virtual environment..."
if ! uv venv; then
echo "❌ Failed to create virtual environment"
exit 1
fi
# Add cargo/bin to PATH for uv
echo 'export PATH="$HOME/.cargo/bin:$PATH"' >> ~/.bashrc
echo 'export PATH="$HOME/.cargo/bin:$PATH"' >> ~/.zshrc
# Install Python dependencies
echo "📦 Installing Python dependencies..."
if ! uv pip install -r requirements/development.txt; then
echo "❌ Failed to install Python dependencies"
echo "💡 You may need to run this manually after the Codespace starts"
exit 1
fi
# Install pre-commit hooks
echo "🪝 Installing pre-commit hooks..."
if source .venv/bin/activate && pre-commit install; then
echo "✅ Pre-commit hooks installed"
else
echo "⚠️ Pre-commit hooks installation failed (non-critical)"
fi
# Install Claude Code CLI via npm
echo "🤖 Installing Claude Code..."
npm install -g @anthropic-ai/claude-code
if npm install -g @anthropic-ai/claude-code; then
echo "✅ Claude Code installed"
else
echo "⚠️ Claude Code installation failed (non-critical)"
fi
# Make the start script executable
chmod +x .devcontainer/start-superset.sh
# Add bashrc additions for automatic venv activation
echo "🔧 Setting up automatic environment activation..."
if [ -f ~/.bashrc ]; then
# Check if we've already added our additions
if ! grep -q "Superset Codespaces environment setup" ~/.bashrc; then
echo "" >> ~/.bashrc
cat .devcontainer/bashrc-additions >> ~/.bashrc
echo "✅ Added automatic venv activation to ~/.bashrc"
else
echo "✅ Bashrc additions already present"
fi
else
# Create bashrc if it doesn't exist
cat .devcontainer/bashrc-additions > ~/.bashrc
echo "✅ Created ~/.bashrc with automatic venv activation"
fi
# Also add to zshrc since that's the default shell
if [ -f ~/.zshrc ] || [ -n "$ZSH_VERSION" ]; then
if ! grep -q "Superset Codespaces environment setup" ~/.zshrc; then
echo "" >> ~/.zshrc
cat .devcontainer/bashrc-additions >> ~/.zshrc
echo "✅ Added automatic venv activation to ~/.zshrc"
fi
fi
echo "✅ Development environment setup complete!"
echo "🚀 Run '.devcontainer/start-superset.sh' to start Superset"
echo ""
echo "📝 The virtual environment will be automatically activated in new terminals"
echo ""
echo "🔄 To activate in this terminal, run:"
echo " source ~/.bashrc"
echo ""
echo "🚀 To start Superset:"
echo " start-superset"
echo ""

View File

@@ -1,6 +1,11 @@
#!/bin/bash
# Startup script for Superset in Codespaces
# Log to a file for debugging
LOG_FILE="/tmp/superset-startup.log"
echo "[$(date)] Starting Superset startup script" >> "$LOG_FILE"
echo "[$(date)] User: $(whoami), PWD: $(pwd)" >> "$LOG_FILE"
echo "🚀 Starting Superset in Codespaces..."
echo "🌐 Frontend will be available at port 9001"
@@ -13,10 +18,37 @@ else
echo "📁 Using current directory: $(pwd)"
fi
# Check if docker is running
if ! docker info > /dev/null 2>&1; then
echo " Waiting for Docker to start..."
sleep 5
# Wait for Docker to be available
echo "⏳ Waiting for Docker to start..."
echo "[$(date)] Waiting for Docker..." >> "$LOG_FILE"
max_attempts=30
attempt=0
while ! docker info > /dev/null 2>&1; do
if [ $attempt -eq $max_attempts ]; then
echo "❌ Docker failed to start after $max_attempts attempts"
echo "[$(date)] Docker failed to start after $max_attempts attempts" >> "$LOG_FILE"
echo "🔄 Please restart the Codespace or run this script manually later"
exit 1
fi
echo " Attempt $((attempt + 1))/$max_attempts..."
echo "[$(date)] Docker check attempt $((attempt + 1))/$max_attempts" >> "$LOG_FILE"
sleep 2
attempt=$((attempt + 1))
done
echo "✅ Docker is ready!"
echo "[$(date)] Docker is ready" >> "$LOG_FILE"
# Check if Superset containers are already running
if docker ps | grep -q "superset"; then
echo "✅ Superset containers are already running!"
echo ""
echo "🌐 To access Superset:"
echo " 1. Click the 'Ports' tab at the bottom of VS Code"
echo " 2. Find port 9001 and click the globe icon to open"
echo " 3. Wait 10-20 minutes for initial startup"
echo ""
echo "📝 Login credentials: admin/admin"
exit 0
fi
# Clean up any existing containers
@@ -24,16 +56,33 @@ echo "🧹 Cleaning up existing containers..."
docker-compose -f docker-compose-light.yml down
# Start services
echo "🏗️ Building and starting services..."
echo "🏗️ Starting Superset in background (daemon mode)..."
echo ""
echo "📝 Once started, login with:"
echo " Username: admin"
echo " Password: admin"
echo ""
echo "📋 Running in foreground with live logs (Ctrl+C to stop)..."
# Run docker-compose and capture exit code
docker-compose -f docker-compose-light.yml up
# Start in detached mode
docker-compose -f docker-compose-light.yml up -d
echo ""
echo "✅ Docker Compose started successfully!"
echo ""
echo "📋 Important information:"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo "⏱️ Initial startup takes 10-20 minutes"
echo "🌐 Check the 'Ports' tab for your Superset URL (port 9001)"
echo "👤 Login: admin / admin"
echo ""
echo "📊 Useful commands:"
echo " docker-compose -f docker-compose-light.yml logs -f # Follow logs"
echo " docker-compose -f docker-compose-light.yml ps # Check status"
echo " docker-compose -f docker-compose-light.yml down # Stop services"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
echo "💤 Keeping terminal open for 60 seconds to test persistence..."
sleep 60
echo "✅ Test complete - check if this terminal is still visible!"
# Show final status
docker-compose -f docker-compose-light.yml ps
EXIT_CODE=$?
# If it failed, provide helpful instructions