mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-04-29 17:20:21 -05:00
7fc8781064
Includes nltk in the list of install dependencies to resolve any missing dependency issues when running the quarto build.
493 lines
18 KiB
YAML
493 lines
18 KiB
YAML
name: '📚 Quarto Build'
|
|
|
|
# This workflow builds a Quarto project and deploys it to either a development site or GitHub Pages
|
|
# It handles both Windows and Linux environments with extensive caching for better performance
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
environment:
|
|
required: true
|
|
type: string
|
|
description: 'Build environment (development/production/test)'
|
|
os:
|
|
required: true
|
|
type: string
|
|
description: 'Operating system to run on (ubuntu-latest/windows-latest)'
|
|
quarto-version:
|
|
required: false
|
|
type: string
|
|
default: '1.7.31'
|
|
description: 'Version of Quarto to use'
|
|
r-version:
|
|
required: false
|
|
type: string
|
|
default: '4.3.2'
|
|
description: 'Version of R to use'
|
|
target:
|
|
required: false
|
|
type: string
|
|
default: ''
|
|
description: 'Target branch (dev/main) - determines build behavior'
|
|
format:
|
|
required: false
|
|
type: string
|
|
default: 'all'
|
|
description: 'Format to build (html/pdf/epub/all)'
|
|
deploy:
|
|
required: false
|
|
type: boolean
|
|
default: true
|
|
description: 'Whether to deploy the build or just validate'
|
|
secrets:
|
|
SSH_DEPLOY_KEY:
|
|
required: false
|
|
|
|
permissions:
|
|
contents: write
|
|
pages: write
|
|
|
|
jobs:
|
|
build:
|
|
runs-on: ${{ inputs.os }}
|
|
timeout-minutes: 60 # ⏰ Set job timeout to 60 minutes
|
|
environment:
|
|
name: ${{ inputs.environment }}
|
|
env:
|
|
R_LIBS_USER: ${{ github.workspace }}/.r-lib
|
|
QUARTO_LOG_LEVEL: DEBUG
|
|
|
|
steps:
|
|
- name: 🔍 Validate inputs
|
|
shell: pwsh
|
|
run: |
|
|
Write-Output "🔄 Validating workflow inputs..."
|
|
Write-Output "👉 Target: ${{ inputs.target }}"
|
|
Write-Output "👉 OS: ${{ inputs.os }}"
|
|
Write-Output "👉 Environment: ${{ inputs.environment }}"
|
|
Write-Output "👉 Format: ${{ inputs.format }}"
|
|
Write-Output "👉 Deploy: ${{ inputs.deploy }}"
|
|
|
|
$valid_formats = @("html", "pdf", "epub", "all")
|
|
if ("${{ inputs.format }}" -notin $valid_formats) {
|
|
Write-Error "❌ Format must be one of: $($valid_formats -join ', ')"
|
|
exit 1
|
|
}
|
|
|
|
Write-Output "✅ Input validation passed"
|
|
|
|
- name: 📥 Checkout repository
|
|
uses: actions/checkout@v4
|
|
with:
|
|
fetch-depth: 0
|
|
|
|
- name: 📦 Setup Quarto
|
|
uses: quarto-dev/quarto-actions/setup@v2
|
|
with:
|
|
version: ${{ inputs.quarto-version }}
|
|
# Outputs quarto version information after installation
|
|
id: quarto-setup
|
|
|
|
- name: 📋 Quarto Setup Info
|
|
shell: bash
|
|
run: |
|
|
echo "🔄 Checking Quarto installation..."
|
|
quarto check
|
|
echo "📊 Quarto version info:"
|
|
quarto --version
|
|
echo "📍 Quarto installation location:"
|
|
which quarto || where.exe quarto
|
|
|
|
- name: 🐍 Set up Python
|
|
uses: actions/setup-python@v5
|
|
with:
|
|
python-version: '3.13'
|
|
|
|
- name: 📦 Install jupyterlab-quarto (Mac/Linux)
|
|
if: runner.os != 'Windows'
|
|
run: |
|
|
python -m pip install --upgrade pip
|
|
python -m pip install jupyterlab-quarto jupyter nltk
|
|
|
|
- name: 📦 Install jupyterlab-quarto (Windows)
|
|
if: runner.os == 'Windows'
|
|
shell: pwsh
|
|
run: |
|
|
py -m pip install --upgrade pip
|
|
py -m pip install jupyterlab-quarto jupyter nltk
|
|
|
|
# Cache Linux system packages without hardcoded paths
|
|
- name: 💾 Cache APT packages
|
|
if: runner.os == 'Linux'
|
|
uses: actions/cache@v4
|
|
id: cache-apt
|
|
with:
|
|
path: ~/.apt-cache
|
|
key: apt-${{ runner.os }}-${{ hashFiles('.github/workflows/*.yml') }}
|
|
restore-keys: |
|
|
apt-${{ runner.os }}-
|
|
|
|
- name: 🛠️ Install Linux Dependencies
|
|
if: runner.os == 'Linux' && steps.cache-apt.outputs.cache-hit != 'true'
|
|
shell: bash
|
|
run: |
|
|
echo "🔄 Installing Linux dependencies..."
|
|
echo "📦 Creating APT cache directory"
|
|
mkdir -p ~/.apt-cache
|
|
|
|
echo "📦 Updating package lists"
|
|
sudo apt-get update
|
|
|
|
echo "📦 Installing required system libraries"
|
|
sudo apt-get -o dir::cache::archives="$HOME/.apt-cache" install -y \
|
|
fonts-dejavu \
|
|
fonts-freefont-ttf \
|
|
gdk-pixbuf2.0-bin \
|
|
libcairo2 \
|
|
libfontconfig1 \
|
|
libfreetype6 \
|
|
libpango-1.0-0 \
|
|
libpangocairo-1.0-0 \
|
|
libpangoft2-1.0-0 \
|
|
libxml2-dev \
|
|
libcurl4-openssl-dev \
|
|
libjpeg-dev \
|
|
libtiff5-dev \
|
|
libpng-dev
|
|
|
|
echo "✅ Linux dependencies installed"
|
|
|
|
- name: 🎨 Install Inkscape and font dependencies (Linux)
|
|
if: runner.os == 'Linux'
|
|
run: |
|
|
# First remove any existing Inkscape
|
|
sudo apt-get remove -y inkscape || true
|
|
# Install Inkscape from PPA for more reliable version
|
|
echo "📦 Installing Inkscape from PPA..."
|
|
sudo add-apt-repository ppa:inkscape.dev/stable -y
|
|
sudo apt-get update
|
|
sudo apt-get install -y inkscape
|
|
|
|
# Install font dependencies
|
|
echo "📦 Installing font dependencies..."
|
|
sudo apt-get install -y \
|
|
fonts-freefont-ttf \
|
|
fonts-liberation \
|
|
fontconfig
|
|
|
|
# Update font cache after installing Inkscape and fonts
|
|
echo "🧹 Updating font cache..."
|
|
sudo fc-cache -fv
|
|
|
|
# Verify Inkscape installation
|
|
echo "📊 Inkscape version:"
|
|
inkscape --version
|
|
|
|
# Test SVG to PDF conversion with the new Inkscape
|
|
echo "🧪 Testing Inkscape SVG to PDF conversion..."
|
|
echo '<svg xmlns="http://www.w3.org/2000/svg" width="100" height="100"><circle cx="50" cy="50" r="40" fill="red"/></svg>' > test.svg
|
|
inkscape --export-type=pdf --export-filename=test.pdf test.svg
|
|
|
|
# Verify if the PDF was created
|
|
if [ -f test.pdf ]; then
|
|
echo "✅ Inkscape SVG to PDF conversion successful!"
|
|
ls -lh test.pdf
|
|
else
|
|
echo "❌ Inkscape SVG to PDF conversion failed."
|
|
echo "🔍 Checking Inkscape installation..."
|
|
dpkg -l | grep inkscape
|
|
which inkscape
|
|
ldd $(which inkscape) | grep "not found" || echo "All dependencies resolved"
|
|
fi
|
|
|
|
- name: 🎨 Install Inkscape (Windows)
|
|
if: runner.os == 'Windows'
|
|
shell: pwsh
|
|
run: |
|
|
choco install inkscape -y
|
|
echo "C:\Program Files\Inkscape\bin" | Out-File -Append -Encoding ascii $env:GITHUB_PATH
|
|
|
|
# Verify Inkscape installation
|
|
inkscape --version
|
|
|
|
- name: 📦 Install & Update TeX Live
|
|
if: inputs.format == 'pdf' || inputs.format == 'epub' || inputs.format == 'all'
|
|
uses: teatimeguest/setup-texlive-action@v3
|
|
with:
|
|
version: 2025
|
|
packages: |
|
|
scheme-basic
|
|
collection-latex
|
|
collection-latexrecommended
|
|
collection-fontsrecommended
|
|
collection-latexextra
|
|
collection-pictures
|
|
collection-luatex
|
|
koma-script
|
|
standalone
|
|
tikz-cd
|
|
marginfix
|
|
newpx
|
|
luatex85
|
|
listings
|
|
update-all-packages: false # this slows builds down significantly
|
|
cache: true
|
|
|
|
- name: 📊 Setup R
|
|
uses: r-lib/actions/setup-r@v2
|
|
with:
|
|
r-version: ${{ inputs.r-version }}
|
|
use-public-rspm: true
|
|
|
|
- name: 📋 R Setup Info
|
|
shell: Rscript {0}
|
|
run: |
|
|
cat("🔄 R Version Information:\n")
|
|
cat(paste("R version:", R.version$version.string, "\n"))
|
|
cat(paste("R home:", R.home(), "\n"))
|
|
cat(paste("R library paths:", paste(.libPaths(), collapse=", "), "\n"))
|
|
|
|
# Cache R packages using standard paths
|
|
- name: 💾 Cache R packages
|
|
uses: actions/cache@v4
|
|
id: cache-r-packages
|
|
with:
|
|
path: |
|
|
${{ env.R_LIBS_USER }}
|
|
key: r-pkgs-${{ runner.os }}-${{ inputs.r-version }}-${{ hashFiles('**/install_packages.R', '**/*.qmd') }}
|
|
restore-keys: |
|
|
r-pkgs-${{ runner.os }}-${{ inputs.r-version }}-
|
|
|
|
- name: 📦 Install R packages
|
|
if: steps.cache-r-packages.outputs.cache-hit != 'true'
|
|
shell: Rscript {0}
|
|
run: |
|
|
# Set options for better package installation
|
|
options(repos = c(CRAN = "https://cran.rstudio.com"))
|
|
|
|
cat("🔄 Installing R packages...\n")
|
|
cat(paste("R library path:", Sys.getenv("R_LIBS_USER"), "\n"))
|
|
|
|
# Create and set library path
|
|
lib_path <- Sys.getenv("R_LIBS_USER")
|
|
dir.create(lib_path, showWarnings = FALSE, recursive = TRUE)
|
|
.libPaths(lib_path)
|
|
|
|
# Install packages
|
|
cat("📦 Installing remotes package...\n")
|
|
install.packages("remotes")
|
|
|
|
if (file.exists("install_packages.R")) {
|
|
cat("📦 Installing packages from install_packages.R...\n")
|
|
source("install_packages.R")
|
|
} else {
|
|
cat("⚠️ No install_packages.R found, installing common packages\n")
|
|
pkgs <- c("rmarkdown", "knitr", "tidyverse", "ggplot2", "bookdown")
|
|
cat(paste("📦 Installing packages:", paste(pkgs, collapse=", "), "\n"))
|
|
install.packages(pkgs)
|
|
}
|
|
|
|
cat("✅ R package installation complete\n")
|
|
cat("📊 Installed packages:\n")
|
|
ip <- installed.packages()[, c("Package", "Version")]
|
|
print(head(ip, 10))
|
|
cat(paste("Total packages installed:", nrow(ip), "\n"))
|
|
|
|
# Install before render cause we need it for rendering
|
|
- name: 📦 Install Ghostscript (Linux)
|
|
if: runner.os == 'Linux' && (inputs.format == 'pdf' || inputs.format == 'all')
|
|
run: sudo apt-get install -y ghostscript
|
|
|
|
- name: 📦 Install Ghostscript (Windows)
|
|
if: runner.os == 'Windows' && (inputs.format == 'pdf' || inputs.format == 'all')
|
|
shell: pwsh
|
|
run: |
|
|
choco install ghostscript
|
|
$gsPath = Get-ChildItem "C:\Program Files\gs" | Sort-Object Name -Descending | Select-Object -First 1
|
|
$binPath = Join-Path $gsPath.FullName "bin"
|
|
echo "Adding Ghostscript path: $binPath"
|
|
echo "$binPath" | Out-File -Append -FilePath $env:GITHUB_PATH
|
|
|
|
- name: 🔨 Render Quarto Project (HTML)
|
|
if: inputs.format == 'html' || inputs.format == 'all'
|
|
uses: quarto-dev/quarto-actions/render@v2
|
|
with:
|
|
to: html
|
|
|
|
# Build PDF after HTML to ensure all assets are available (esp. PDF)
|
|
- name: 🔨 Render Quarto Project (PDF)
|
|
if: inputs.format == 'pdf' || inputs.format == 'all'
|
|
uses: quarto-dev/quarto-actions/render@v2
|
|
with:
|
|
to: titlepage-pdf
|
|
|
|
- name: 🔨 Render Quarto Project (EPUB)
|
|
if: inputs.format == 'epub' || inputs.format == 'all'
|
|
uses: quarto-dev/quarto-actions/render@v2
|
|
with:
|
|
to: epub
|
|
|
|
- name: 📋 Check Quarto Build Output
|
|
shell: bash
|
|
run: |
|
|
echo "🔄 Checking Quarto build output..."
|
|
|
|
if [ -d "_book" ]; then
|
|
echo "✅ _book directory exists"
|
|
echo "📊 Files in _book directory:"
|
|
ls -la _book | head -n 20
|
|
echo "📊 Total files in _book:"
|
|
find _book -type f | wc -l
|
|
|
|
if [ -f "_book/Machine-Learning-Systems.pdf" ] && [ "${{ inputs.format }}" != "html" ]; then
|
|
echo "✅ PDF file exists"
|
|
echo "📊 PDF file size:"
|
|
du -h "_book/Machine-Learning-Systems.pdf"
|
|
elif [ "${{ inputs.format }}" != "html" ]; then
|
|
echo "⚠️ PDF file not found!"
|
|
fi
|
|
else
|
|
echo "❌ _book directory not found!"
|
|
fi
|
|
|
|
- name: 📉 Compress PDF with Ghostscript (Linux)
|
|
if: runner.os == 'Linux' && (inputs.format == 'pdf' || inputs.format == 'all')
|
|
run: |
|
|
if [ -f "_book/Machine-Learning-Systems.pdf" ]; then
|
|
gs \
|
|
-sDEVICE=pdfwrite \
|
|
-dCompatibilityLevel=1.4 \
|
|
-dPDFSETTINGS=/ebook \
|
|
-dNOPAUSE \
|
|
-dQUIET \
|
|
-dBATCH \
|
|
-sOutputFile="./_book/ebook.pdf" \
|
|
"./_book/Machine-Learning-Systems.pdf"
|
|
|
|
# Replace original with compressed
|
|
mv ./_book/ebook.pdf ./_book/Machine-Learning-Systems.pdf
|
|
else
|
|
echo "⚠️ PDF file not found for compression"
|
|
fi
|
|
|
|
- name: 📉 Compress PDF with Ghostscript (Windows)
|
|
if: runner.os == 'Windows' && (inputs.format == 'pdf' || inputs.format == 'all')
|
|
shell: pwsh
|
|
run: |
|
|
$input = "./_book/Machine-Learning-Systems.pdf"
|
|
$output = "./_book/ebook.pdf"
|
|
|
|
if (!(Test-Path $input)) {
|
|
Write-Warning "⚠️ Input PDF not found! Skipping compression..."
|
|
exit 0 # Non-zero exit would fail the workflow
|
|
}
|
|
|
|
Write-Output "📉 Compressing PDF using Ghostscript..."
|
|
|
|
# Unless you are a sucker for pain, don't try to line-break this command (it was a nightmare)
|
|
# Note that compatability should be written as -dCompatibilityLevel:1.4, not -dCompatibilityLevel=1.4!!!
|
|
& gswin64c -sDEVICE=pdfwrite -dCompatibilityLevel:1.4 -dPDFSETTINGS=/ebook -dNOPAUSE -dBATCH -sOutputFile="$output" "$input"
|
|
|
|
if (Test-Path $output) {
|
|
$afterSize = (Get-Item $output).Length / 1MB
|
|
Write-Output ("📏 Compressed PDF size: {0:N2} MB" -f $afterSize)
|
|
Write-Output "✅ Compression successful"
|
|
Move-Item -Force $output $input
|
|
} else {
|
|
Write-Warning "⚠️ Compression failed but continuing"
|
|
}
|
|
|
|
- name: 📤 Upload _book directory as artifact
|
|
if: github.event_name == 'pull_request' || inputs.deploy == false || inputs.format != 'html'
|
|
uses: actions/upload-artifact@v4
|
|
with:
|
|
name: _book-${{ inputs.os }}-${{ inputs.format }}
|
|
path: _book
|
|
|
|
- name: 🚀 Stage to Dev Site
|
|
if: inputs.target == 'dev' && inputs.deploy == true && inputs.format == 'html' && runner.os == 'Linux'
|
|
shell: bash
|
|
env:
|
|
SSH_DEPLOY_KEY: ${{ secrets.SSH_DEPLOY_KEY }}
|
|
run: |
|
|
echo "🔐 Starting ssh-agent..."
|
|
eval "$(ssh-agent -s)"
|
|
echo "$SSH_DEPLOY_KEY" | tr -d '\r' | ssh-add - > /dev/null
|
|
|
|
git config --global user.email "khoshnevis.naeem@gmail.com"
|
|
git config --global user.name "github-actions"
|
|
|
|
echo "🔄 Cloning target repo..."
|
|
git clone --depth=1 git@github.com:harvard-edge/cs249r_book_dev.git target-repo
|
|
cd target-repo
|
|
git checkout main
|
|
git pull origin main
|
|
|
|
echo "🧹 Cleaning existing docs/"
|
|
rm -rf docs
|
|
cp -r "${GITHUB_WORKSPACE}/_book" docs
|
|
rm -f docs/CNAME # remove if present
|
|
|
|
echo "🔍 Validating deployment content..."
|
|
test -f docs/index.html || (echo "❌ index.html missing" && exit 1)
|
|
[ "$(ls -1 docs | wc -l)" -gt 3 ] || (echo "❌ docs/ too empty — something went wrong" && exit 1)
|
|
|
|
echo "📦 Committing and pushing changes..."
|
|
git add docs
|
|
git commit -m "📚 Push dev branch build (manual version)" || echo "🟡 Nothing to commit"
|
|
git push origin main
|
|
|
|
- name: 📋 Dev Deployment Info
|
|
if: inputs.target == 'dev' && runner.os == 'Linux' && inputs.deploy == true
|
|
shell: bash
|
|
run: |
|
|
echo "🔄 Development deployment information:"
|
|
echo "📊 Deployed to repository: harvard-edge/cs249r_book_dev"
|
|
echo "📊 Target branch: main"
|
|
echo "📊 Target directory: docs"
|
|
echo "📊 Source directory: _book"
|
|
echo "✅ Deployment should be complete"
|
|
|
|
# Deploy to GitHub Pages
|
|
- name: 🚀 Deploy to GitHub Pages
|
|
if: inputs.target == 'main' && runner.os == 'Linux' && inputs.deploy == true
|
|
uses: quarto-dev/quarto-actions/publish@v2
|
|
with:
|
|
target: gh-pages
|
|
render: false
|
|
env:
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
|
|
- name: 📋 GitHub Pages Deployment Info
|
|
if: inputs.target == 'main' && runner.os == 'Linux' && inputs.deploy == true
|
|
shell: bash
|
|
run: |
|
|
echo "🔄 GitHub Pages deployment information:"
|
|
echo "📊 Deployed to: gh-pages branch"
|
|
echo "📊 Source directory: _book"
|
|
echo "✅ Deployment should be complete"
|
|
echo "🌐 Site should be available at: https://${{ github.repository_owner }}.github.io/${{ github.event.repository.name }}"
|
|
|
|
- name: 📋 Build Summary
|
|
shell: pwsh
|
|
run: |
|
|
# Create a variable for the TeX Live status
|
|
$texLiveStatus = if ("${{ inputs.format }}" -eq "pdf" -or "${{ inputs.format }}" -eq "all") {
|
|
"Installed via teatimeguest/setup-texlive-action@v3"
|
|
} else {
|
|
"Skipped (not needed for HTML only)"
|
|
}
|
|
|
|
@"
|
|
## 📊 Build Status Summary
|
|
🎯 Target: ${{ inputs.target }}
|
|
💻 OS: ${{ inputs.os }}
|
|
🔧 Environment: ${{ inputs.environment }}
|
|
📚 Quarto Version: ${{ inputs.quarto-version }}
|
|
🔬 R Version: ${{ inputs.r-version }}
|
|
📄 Format: ${{ inputs.format }}
|
|
🚀 Deploy: ${{ inputs.deploy }}
|
|
🧩 Cache Status:
|
|
- TeX Live: $texLiveStatus
|
|
- R Packages: ${{ steps.cache-r-packages.outputs.cache-hit == 'true' && '✅ Hit' || '❌ Miss' }}
|
|
⏰ Completed at: $(Get-Date -Format "yyyy-MM-dd HH:mm:ss")
|
|
"@ | Add-Content $env:GITHUB_STEP_SUMMARY |