Skip to content

Documentation validation #2

Documentation validation

Documentation validation #2

name: Documentation validation
on:
pull_request:
push:
branches: [mainline]
schedule:
- cron: "17 8 * * 2"
workflow_dispatch:
permissions: {}
concurrency:
group: documentation-validation-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
static:
name: Unit and static checks
if: github.event_name == 'pull_request' || github.event_name == 'push'
runs-on: ubuntu-latest
timeout-minutes: 10
permissions:
contents: read
steps:
- name: Check out repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Run repository validation
run: python3 scripts/validate_repository.py
# On pull requests, only the Markdown files the PR changed have their live external
# links checked. This keeps the required PR signal fast and resilient to unrelated
# third-party outages. The whole repository is swept on the weekly schedule below.
changed-external-links:
name: Live external links (changed files)
if: github.event_name == 'pull_request'
runs-on: ubuntu-latest
timeout-minutes: 30
permissions:
contents: read
steps:
- name: Check out repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
persist-credentials: false
- name: Check changed Markdown external links
env:
BASE_SHA: ${{ github.event.pull_request.base.sha }}
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
run: |
set -euo pipefail
# NUL-delimited to stay correct for renamed or unusually named files.
changed=()
while IFS= read -r -d '' file; do
changed+=("$file")
done < <(git diff -z --name-only --diff-filter=ACMRT "$BASE_SHA" "$HEAD_SHA" -- '*.md')
if [ ${#changed[@]} -eq 0 ]; then
echo "No Markdown files changed; nothing to check."
exit 0
fi
echo "Checking changed Markdown files:"
printf ' %s\n' "${changed[@]}"
python3 scripts/check_external_links.py "${changed[@]}"
# On the weekly schedule and manual runs, every tracked Markdown file is checked.
# A failure opens (or updates) a tracking issue so link rot gets triaged instead of
# silently failing a scheduled run nobody is watching.
all-external-links:
name: Live external links (full sweep)
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
runs-on: ubuntu-latest
timeout-minutes: 30
permissions:
contents: read
issues: write
steps:
- name: Check out repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Check all external Markdown links
id: check
run: |
set +e
python3 scripts/check_external_links.py 2>&1 | tee link-report.txt
echo "exit_code=${PIPESTATUS[0]}" >> "$GITHUB_OUTPUT"
- name: Open or update link-rot issue on failure
if: steps.check.outputs.exit_code != '0'
env:
GH_TOKEN: ${{ github.token }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
run: |
label="link-rot"
title="Broken external documentation links detected"
# The label is required for de-duplication; ignore the error if it exists.
gh label create "$label" --color B60205 --description "Automated documentation link-rot tracking" 2>/dev/null || true
# Cap the embedded report so the issue body stays well under GitHub's limit.
report="$(head -c 50000 link-report.txt)"
body="$(printf 'The scheduled documentation link check failed.\n\nWorkflow run: %s\n\n```\n%s\n```\n' "$RUN_URL" "$report")"
existing="$(gh issue list --state open --label "$label" --json number --jq '.[0].number')"
if [ -n "$existing" ]; then
echo "Updating existing issue #$existing"
gh issue comment "$existing" --body "$body"
else
echo "Opening new tracking issue"
gh issue create --title "$title" --label "$label" --body "$body"
fi
- name: Fail if links are broken
if: steps.check.outputs.exit_code != '0'
run: |
echo "External link check failed; see the tracking issue." >&2
exit 1