Skip to content

fix: Eliminate RDD usage across SynapseML for Spark 4.0 compatibility #2067

fix: Eliminate RDD usage across SynapseML for Spark 4.0 compatibility

fix: Eliminate RDD usage across SynapseML for Spark 4.0 compatibility #2067

name: "Check Dead Links"
on:
workflow_dispatch:
push:
branches: [ "master" ]
pull_request:
# The branches below must be a subset of the branches above
branches: [ "master" ]
jobs:
scan_links:
name: Scan Website for Dead Links
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Fetch sitemap URLs
run: |
curl -s https://microsoft.github.io/SynapseML/sitemap.xml \
| grep -oP '<loc>[^<]+</loc>' \
| sed 's/<\/?loc>//g' \
> urls.txt
echo "Found $(wc -l < urls.txt) URLs in sitemap"
- name: Scan for dead links
uses: lycheeverse/lychee-action@v2
with:
args: >-
--no-progress
--max-concurrency 8
--max-retries 5
--retry-wait-time 5
--timeout 30
--accept '100..=103,200..=299,503'
urls.txt