[DOCS] Enable hosted docs preview (#2803)

Enables builds for documentation on every PR

Also optionally will upload this to netlify and generate a preview link
if:

1. This is a PR from the current repo (not a fork) since it needs access
to netlify secrets
2. Some files in `docs/` were modified OR the `documentation` tag is on
the PR

---------

Co-authored-by: Jay Chia <[email protected]@users.noreply.github.com>

.github/workflows/build-docs.yml

@@ -0,0 +1,95 @@
+# This workflow will build the Daft docs and optionally publishes them to Netlify
+# for easy previews.
+
+name: daft-docs
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  docgen:
+    runs-on: ubuntu-latest
+    continue-on-error: true
+    env:
+      python-version: '3.10'
+    steps:
+    - uses: actions/checkout@v4
+    - uses: moonrepo/setup-rust@v1
+      with:
+        cache: false
+    - uses: Swatinem/rust-cache@v2
+      with:
+        key: ${{ runner.os }}-build
+        cache-all-crates: 'true'
+    - name: Set up Python ${{ env.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ env.python-version }}
+        cache: pip
+        cache-dependency-path: |
+          pyproject.toml
+          requirements-dev.txt
+    - name: Setup Virtual Env
+      run: |
+        python -m venv venv
+        echo "$GITHUB_WORKSPACE/venv/bin" >> $GITHUB_PATH
+        pip install uv
+    - name: Install dependencies
+      run: |
+        uv pip install -r requirements-dev.txt
+    - name: Build Daft in development mode and generate docs
+      # TODO: Break on any Sphinx warnings
+      # make html SPHINXOPTS="-W --keep-going -n"
+      # See: https://stackoverflow.com/questions/38048945/how-to-turn-warnings-into-errors-when-building-sphinx-documentation-with-setupto
+      run: |
+        source activate
+        maturin develop
+        cd docs/
+        make html
+    - name: Upload built docs
+      uses: actions/upload-artifact@v4
+      with:
+        name: html-docs
+        path: docs/build/html
+  docpublish:
+    runs-on: ubuntu-latest
+    needs: docgen
+    # Only publish to netlify on:
+    # 1. If the previous doc building step didn't fail
+    # 2. If this is a PR from the current repo (since it needs access to secrets)
+    # 3. If some of the documentation files changed or it has the `documentation` label
+    if: |
+      ${{ success() }} &&
+      github.event.pull_request != null &&
+      github.event.pull_request.head.repo.full_name == github.repository &&
+      (
+        contains(github.event.pull_request.changed_files, 'docs/') ||
+        contains(github.event.pull_request.labels.*.name, 'documentation')
+      )
+    steps:
+    - name: Download built HTML docs
+      uses: actions/download-artifact@v4
+      with:
+        name: html-docs
+        path: ./built_html
+    - name: Add a robots.txt to disable indexing of docs
+      run: |
+        echo "User-agent: *" > ./built_html/robots.txt
+        echo "Disallow: /" >> ./built_html/robots.txt
+    - name: Deploy to Netlify
+      uses: nwtgck/[email protected]
+      with:
+        publish-dir: ./built_html
+        production-branch: main
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        deploy-message: Deploy from GitHub Actions
+        enable-pull-request-comment: true
+        enable-commit-comment: false
+        overwrites-pull-request-comment: true
+    env:
+      NETLIFY_AUTH_TOKEN: ${{ secrets.NETLIFY_AUTH_TOKEN }}
+      NETLIFY_SITE_ID: ${{ secrets.NETLIFY_SITE_ID }}
+    timeout-minutes: 1

.github/workflows/python-package.yml

@@ -789,7 +789,6 @@ jobs:
         maturin develop
         pytest --doctest-modules --continue-on-collection-errors daft/dataframe/dataframe.py daft/expressions/expressions.py daft/convert.py daft/udf.py
 
-
   publish-coverage-reports:
     name: Publish coverage reports to CodeCov
     runs-on: ubuntu-latest