This is an automated email from the ASF dual-hosted git repository.
asf-gitbox-commits pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/spark-website.git
The following commit(s) were added to refs/heads/asf-site by this push:
new a697a9eb65 Revert "Add workflow to automatically generate and commit
site HTML (…
a697a9eb65 is described below
commit a697a9eb650bd086a93cee2a73cf45de53804d26
Author: Nicholas Chammas <[email protected]>
AuthorDate: Sat Jul 11 23:28:10 2026 -0700
Revert "Add workflow to automatically generate and commit site HTML (…
…#697)"
This reverts commit 59719624d8f4bb548e1042654e60cb787b2824cf, which appears
to have broken the site.
Author: Nicholas Chammas <[email protected]>
Closes #698 from nchammas/revert-automated-html.
---
.github/CONTRIBUTING.md | 6 +--
.github/PULL_REQUEST_TEMPLATE.md | 1 +
.github/actions/build-html/action.yml | 21 ----------
.github/workflows/doc_gen.yml | 76 +++++++++++++++++++++++++++++++++++
.github/workflows/html-build.yml | 16 --------
.github/workflows/html-push.yml | 43 --------------------
.gitignore | 2 +-
README.md | 28 ++++++++-----
_config.yml | 2 +-
content | 1 +
site/sitemap.xml | 39 +++++++++---------
sitemap.xml | 15 ++-----
12 files changed, 123 insertions(+), 127 deletions(-)
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
index ab2057b8e7..7b5dc0b348 100644
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@@ -1,5 +1 @@
-# Contributing to this repo
-
-Build and test your changes locally according to the instructions in
[README](../README.md).
-
-Once you've done that, submit a pull request with your changes. You only need
to commit your changes to the Markdown source. A GitHub Actions workflow will
[generate the corresponding HTML and push it for
you](./workflows/html-push.yml).
+Make sure that you generate site HTML with `jekyll build`, and include the
changes to the HTML in your pull request also. See README.md for more
information.
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
new file mode 100644
index 0000000000..9e1ffb348a
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1 @@
+<!-- *Make sure that you generate site HTML with `bundle exec jekyll build`,
and include the changes to the HTML in your pull request. See README.md for
more information.* -->
diff --git a/.github/actions/build-html/action.yml
b/.github/actions/build-html/action.yml
deleted file mode 100644
index 76f7767416..0000000000
--- a/.github/actions/build-html/action.yml
+++ /dev/null
@@ -1,21 +0,0 @@
-name: Build HTML
-
-description: Set up Ruby and run the Jekyll build.
-
-inputs:
- ruby-version:
- description: Ruby version to use.
- required: false
- default: "3.4"
-
-runs:
- using: composite
- steps:
- - name: Set up Ruby and Bundler
- uses: ruby/setup-ruby@v1
- with:
- ruby-version: ${{ inputs.ruby-version }}
- bundler-cache: true
- - name: Run documentation build
- shell: bash
- run: bundle exec jekyll build
diff --git a/.github/workflows/doc_gen.yml b/.github/workflows/doc_gen.yml
new file mode 100644
index 0000000000..01478f9273
--- /dev/null
+++ b/.github/workflows/doc_gen.yml
@@ -0,0 +1,76 @@
+name: Check document generation
+
+on:
+ push:
+ branches:
+ - asf-site
+ pull_request:
+ branches:
+ - asf-site
+
+jobs:
+ lint:
+ name: check whether all documentation was generated with the right Jekyll
version
+ runs-on: ubuntu-24.04
+ steps:
+ - name: Free up disk space
+ shell: 'script -q -e -c "bash {0}"'
+ run: |
+ echo "=================================="
+ echo "Free up disk space on CI system"
+ echo "=================================="
+
+ echo "Listing top 100 largest packages (from large to small)"
+ printf "Installed-Size\tPackage\n"
+ dpkg-query -Wf '${Installed-Size}\t${Package}\n' | sort -n -r | head
-n 100
+ df -h
+
+ echo "Removing large packages"
+ rm -rf /__t/CodeQL
+ rm -rf /__t/go
+ rm -rf /__t/node
+
+ apt-get remove --purge -y '^aspnet.*' || true
+ apt-get remove --purge -y '^dotnet-.*' || true
+ apt-get remove --purge -y '^llvm-.*' || true
+ apt-get remove --purge -y 'php.*' || true
+ apt-get remove --purge -y '^mongodb-.*' || true
+ apt-get remove --purge -y 'gfortran-11' || true
+ apt-get remove --purge -y 'humanity-icon-theme' || true
+ apt-get remove --purge -y 'nodejs-doc' || true
+ apt-get remove --purge -y snapd google-chrome-stable
microsoft-edge-stable firefox || true
+ apt-get remove --purge -y azure-cli google-cloud-sdk mono-devel
powershell libgl1-mesa-dri || true
+ apt-get autoremove --purge -y
+ apt-get clean
+
+ df -h
+ - name: Checkout Spark Website repository
+ uses: actions/checkout@v2
+ - name: Install dependencies for documentation generation
+ run: |
+ sudo apt-get update -y
+ sudo apt-get install -y ruby ruby-dev
+ sudo gem install bundler --version 2.4.19
+ bundle install
+ - name: Run documentation build
+ run: |
+ export LC_ALL=C.UTF-8
+ export LANG=C.UTF-8
+ OLD_IFS=$IFS
+ IFS=
+ GEN_ERRORS=$(bundle exec jekyll build 3>&2 2>&1 1>&3)
+ if [ $(echo $GEN_ERRORS| grep -v -e '^$'| grep -c -v
"rubygems_integration") -ne 0 ]; then
+ echo "Error during document generation:"
+ echo $GEN_ERRORS
+ exit 1
+ fi
+ IFS=$OLD_IFS
+ CHANGED_FILE=( $(git ls-files --modified --other --exclude-standard
--directory | grep -v sitemap.xml | grep -v llms.txt) )
+ if [ ${#CHANGED_FILE[@]} -ne 0 ]; then
+ echo "Not all documentation was generated and/or not the right
Jekyll version was used! Modified / untracked files (excluding sitemap.xml):"
+ echo ${CHANGED_FILE[*]}
+ echo "Git diff (excluding sitemap.xml):"
+ git diff -- . ':(exclude)site/sitemap.xml'
+ exit 1
+ fi
+ shell: /bin/bash {0}
diff --git a/.github/workflows/html-build.yml b/.github/workflows/html-build.yml
deleted file mode 100644
index b94dfebe2b..0000000000
--- a/.github/workflows/html-build.yml
+++ /dev/null
@@ -1,16 +0,0 @@
-name: Build HTML
-
-on:
- pull_request:
- branches:
- - asf-site
-
-jobs:
- build:
- name: Build HTML
- runs-on: ubuntu-24.04
- steps:
- - name: Checkout Spark Website repository
- uses: actions/checkout@v7
- - name: Build HTML
- uses: ./.github/actions/build-html
diff --git a/.github/workflows/html-push.yml b/.github/workflows/html-push.yml
deleted file mode 100644
index 15160e7b4c..0000000000
--- a/.github/workflows/html-push.yml
+++ /dev/null
@@ -1,43 +0,0 @@
-name: Build and Push HTML
-
-on:
- push:
- branches:
- - asf-site
-
-jobs:
- commit:
- name: Build and commit HTML to `asf-site`
- # This condition is important. We don't want to trigger this job if the
last
- # commit was created _by_ this job!
- if: >-
- !(
- contains(github.event.head_commit.message, '[html]') &&
- github.event.head_commit.author.name == 'github-actions[bot]'
- )
- # Not technically necessary, but helps avoid spurious failures if multiple
- # commits are pushed in rapid succession.
- concurrency:
- group: html-push-${{ github.ref }}
- cancel-in-progress: true
- runs-on: ubuntu-24.04
- permissions:
- contents: write
- steps:
- - name: Checkout Spark Website repository
- uses: actions/checkout@v7
- - name: Build HTML
- uses: ./.github/actions/build-html
- - name: Commit and push generated HTML
- run: |
- git config user.name "github-actions[bot]"
- git config user.email "github-actions[bot]@users.noreply.github.com"
- # `-f` because we told git to otherwise ignore `site/`
- git add -f site/
- if git diff --cached --quiet; then
- echo "No changes to commit."
- else
- COMMIT_TITLE=$(git log -1 --pretty=%s)
- git commit -m "[html] $COMMIT_TITLE"
- git push
- fi
diff --git a/.gitignore b/.gitignore
index 90ef9e9205..d0d5f1c267 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,4 +4,4 @@ target/
.jekyll-cache/
.jekyll-metadata
.local_ruby_bundle
-site/
+site/python
diff --git a/README.md b/README.md
index 7b77603936..bef477a201 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,4 @@
-# Apache Spark Main Website
-
-This repository captures the main Apache Spark website located at
https://spark.apache.org. The programming docs are [in the main Spark repo][1],
not here.
-
-[1]: https://github.com/apache/spark/tree/master/docs
-
-To contribute changes, see [CONTRIBUTING](.github/CONTRIBUTING.md).
-
-## Generating the website HTML locally
+## Generating the website HTML
In this directory you will find text files formatted using Markdown, with an
`.md` suffix.
@@ -36,6 +28,22 @@ of Spark from the Spark source repository and then copied to
the website under t
directory. See the instructions for building those in the readme in the Spark
project's `/docs` directory.
+## Rouge and Pygments
+
+We also use [Rouge](https://github.com/rouge-ruby/rouge) for syntax
highlighting in documentation Markdown pages.
+Its HTML output is compatible with CSS files designed for
[Pygments](https://pygments.org/).
+
+To mark a block of code in your Markdown to be syntax highlighted by `jekyll`
during the
+compile phase, use the following syntax:
+
+ {% highlight scala %}
+ // Your Scala code goes here, you can replace Scala with many other
+ // supported languages too.
+ {% endhighlight %}
+
+You probably don't need to install that unless you want to regenerate the
Pygments CSS file.
+It requires Python, and can be installed by running `sudo easy_install
Pygments`.
+
## Merge PR
-To merge a pull request, use the `merge_pr.py` script. This script also
squashes the commits.
+To merge pull request, use the `merge_pr.py` script which also squashes the
commits.
diff --git a/_config.yml b/_config.yml
index 5e5be4c0c8..98f05068c0 100644
--- a/_config.yml
+++ b/_config.yml
@@ -4,6 +4,6 @@ kramdown:
entity_output: symbol
permalink: none
destination: site
-exclude: ['README.md', 'LICENSE', 'merge_pr.py', 'Gemfile', 'Gemfile.lock']
+exclude: ['README.md', 'content', 'LICENSE', 'merge_pr.py', 'Gemfile',
'Gemfile.lock']
keep_files: ['docs', 'static', 'llms.txt']
url: https://spark.apache.org
diff --git a/content b/content
new file mode 120000
index 0000000000..d97e100637
--- /dev/null
+++ b/content
@@ -0,0 +1 @@
+site
\ No newline at end of file
diff --git a/site/sitemap.xml b/site/sitemap.xml
index 19f2ddf2f1..3ef7e411a1 100644
--- a/site/sitemap.xml
+++ b/site/sitemap.xml
@@ -1163,10 +1163,7 @@
<loc>https://spark.apache.org/releases/spark-release-0-3.html</loc>
<changefreq>weekly</changefreq>
</url>
-<url>
- <loc>https://spark.apache.org/</loc>
- <changefreq>weekly</changefreq>
-</url>
+
<url>
<loc>https://spark.apache.org/404.html</loc>
<changefreq>weekly</changefreq>
@@ -1208,19 +1205,23 @@
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/graphx/</loc>
+ <loc>https://spark.apache.org/history.html</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/history.html</loc>
+ <loc>https://spark.apache.org/improvement-proposals.html</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/improvement-proposals.html</loc>
+ <loc>https://spark.apache.org/spark-connect/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/mailing-lists.html</loc>
+ <loc>https://spark.apache.org/pandas-on-spark/</loc>
+ <changefreq>weekly</changefreq>
+</url>
+<url>
+ <loc>https://spark.apache.org/graphx/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
@@ -1228,45 +1229,46 @@
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/news/</loc>
+ <loc>https://spark.apache.org/streaming/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/pandas-on-spark/</loc>
+ <loc>https://spark.apache.org/news/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/powered-by.html</loc>
+ <loc>https://spark.apache.org/screencasts/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/release-process.html</loc>
+ <loc>https://spark.apache.org/sql/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/research.html</loc>
+ <loc>https://spark.apache.org/</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/screencasts/</loc>
+ <loc>https://spark.apache.org/mailing-lists.html</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/security.html</loc>
+ <loc>https://spark.apache.org/powered-by.html</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/spark-connect/</loc>
+ <loc>https://spark.apache.org/release-process.html</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/sql/</loc>
+ <loc>https://spark.apache.org/research.html</loc>
<changefreq>weekly</changefreq>
</url>
<url>
- <loc>https://spark.apache.org/streaming/</loc>
+ <loc>https://spark.apache.org/security.html</loc>
<changefreq>weekly</changefreq>
</url>
+
<url>
<loc>https://spark.apache.org/third-party-projects.html</loc>
<changefreq>weekly</changefreq>
@@ -1279,4 +1281,5 @@
<loc>https://spark.apache.org/versioning-policy.html</loc>
<changefreq>weekly</changefreq>
</url>
+
</urlset>
diff --git a/sitemap.xml b/sitemap.xml
index 71fb8b093d..257359ef91 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -151,18 +151,9 @@ sitemap: false
<changefreq>weekly</changefreq>
</url>
{% endfor %}
-{%- comment -%}
-Explicitly sort `site.pages` so that the order is consistent and we don't get
spurious git diffs.
-`site.posts` doesn't have this issue because it's already sorted.
-See: https://jekyllrb.com/docs/variables/#site-variables
-{%- endcomment -%}
-{%- assign sorted_pages = site.pages | sort: "url" -%}
-{%- for page in sorted_pages -%}
-{%- if page.sitemap != false -%}
-<url>
+{% for page in site.pages %}{% if page.sitemap != false %}<url>
<loc>{{ site.url }}{{ page.url }}</loc>
<changefreq>weekly</changefreq>
-</url>
-{% endif %}
-{%- endfor -%}
+</url>{% endif %}
+{% endfor %}
</urlset>
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
