actions/telemetry: explain why we collect telemetry data (#3887) #874

Workflow file for this run

.github/workflows/export-edu-docs-to-gcs.yaml at 4208bd8

	name: Export Edu Documentation to GCS

	on:
	push:
	branches: [ main ]
	paths:
	- 'content/**'
	- 'data/**'
	- '**.md'
	- 'scripts/generate_image_catalog.py'
	- '.github/workflows/export-edu-docs-to-gcs.yaml'

	schedule:
	- cron: '30 1 * * 0' # Weekly on Sundays at 1:30 AM (same as other repos)

	workflow_dispatch:

	permissions: {}

	jobs:
	export-docs:
	if: github.repository == 'chainguard-dev/edu'
	runs-on: ubuntu-latest
	permissions:
	contents: write # Required for repository dispatch events
	id-token: write # Required for workload identity federation

	steps:
	- name: Harden Runner
	uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
	with:
	egress-policy: audit

	- name: Checkout repository
	uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
	with:
	persist-credentials: false # Don't persist auth token

	- name: Authenticate to Google Cloud
	uses: step-security/google-github-auth@775fc4c80760272ef389c9f9f8d98de7db0c170d # v3.0.2
	with:
	workload_identity_provider: "projects/456977358484/locations/global/workloadIdentityPools/chainguard-academy/providers/chainguard-edu"
	service_account: "github-chainguard-academy@chainguard-academy.iam.gserviceaccount.com"

	- name: Set up Cloud SDK
	uses: google-github-actions/setup-gcloud@aa5489c8933f4cc7a4f7d45035b3b1440c9c10db # v3.0.1

	- name: Prepare documentation export
	run: \|
	set -euo pipefail # Exit on error, undefined variable, or pipe failure

	echo "Preparing edu documentation export..."

	# Use mktemp for secure temp directory
	EXPORT_DIR=$(mktemp -d)
	trap 'rm -rf "$EXPORT_DIR"' EXIT # Clean up on exit

	# Copy content directory (main documentation)
	if [ -d "content" ]; then
	echo "Copying and cleaning content directory..."
	# Create content directory structure
	find content -type d \| while read -r dir; do
	mkdir -p "$EXPORT_DIR/$dir"
	done

	# Process each markdown file to remove HTML comments
	find content -name "*.md" -type f \| while read -r file; do
	# Remove HTML comments and clean up empty lines
	sed -E 's/<!--[^>]*-->//g' "$file" \| \
	sed '/^[[:space:]]$/N;/\n[[:space:]]$/d' > "$EXPORT_DIR/$file"
	done

	echo "✓ Processed $(find content -name "*.md" -type f \| wc -l) markdown files in content/"
	else
	echo "Warning: content directory not found"
	fi

	# Create a content index for reference
	echo "Creating content index..."
	find "$EXPORT_DIR" -name "*.md" -type f \| \
	sed "s\|$EXPORT_DIR/\|\|" \| \
	sort > "$EXPORT_DIR/content-index.txt"

	# Create metadata file with proper JSON escaping
	cat > "$EXPORT_DIR/metadata.json" << EOF
	{
	"repository": "chainguard-dev/edu",
	"export_time": "$(date -u +"%Y-%m-%dT%H:%M:%SZ")",
	"commit": "$GITHUB_SHA",
	"ref": "$GITHUB_REF",
	"triggered_by": "$GITHUB_EVENT_NAME",
	"files_count": $(find "$EXPORT_DIR" -name "*.md" -type f \| wc -l),
	"total_size": "$(du -sh "$EXPORT_DIR" \| cut -f1)"
	}
	EOF

	# Validate JSON
	python3 -m json.tool "$EXPORT_DIR/metadata.json" > /dev/null

	# Display summary
	echo ""
	echo "Export Summary:"
	echo "---------------"
	echo "Total markdown files: $(find "$EXPORT_DIR" -name "*.md" -type f \| wc -l)"
	echo "Total size: $(du -sh "$EXPORT_DIR" \| cut -f1)"

	# Create tarball with restricted permissions
	cd "$(dirname "$EXPORT_DIR")"
	tar --owner=0 --group=0 --mode='u+rwX,go+rX,go-w' \
	-czf /tmp/docs-export.tar.gz "$(basename "$EXPORT_DIR")"

	echo ""
	echo "Documentation bundle created:"
	ls -lh /tmp/docs-export.tar.gz

	- name: Upload to GCS
	run: \|
	set -euo pipefail

	echo "Uploading edu documentation to GCS..."

	# Upload with specific content type and cache control
	gcloud storage cp /tmp/docs-export.tar.gz \
	"gs://academy-all-docs/edu/docs-export.tar.gz" \
	--project=chainguard-academy \
	--content-type="application/gzip" \
	--cache-control="no-cache"

	# Extract for metadata upload
	EXPORT_DIR=$(mktemp -d)
	trap 'rm -rf "$EXPORT_DIR"' EXIT
	tar -xzf /tmp/docs-export.tar.gz -C "$EXPORT_DIR" --strip-components=1

	# Upload metadata
	gcloud storage cp "$EXPORT_DIR/metadata.json" \
	"gs://academy-all-docs/edu/metadata.json" \
	--project=chainguard-academy \
	--content-type="application/json" \
	--cache-control="no-cache"

	# Upload content index
	gcloud storage cp "$EXPORT_DIR/content-index.txt" \
	"gs://academy-all-docs/edu/content-index.txt" \
	--project=chainguard-academy \
	--content-type="text/plain" \
	--cache-control="no-cache"

	echo "✓ Successfully uploaded edu documentation to GCS"

	- name: Trigger compilation workflow
	if: github.event_name == 'push' \|\| github.event_name == 'schedule'
	uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
	with:
	github-token: ${{ secrets.GITHUB_TOKEN }}
	script: \|
	// Wait a moment to ensure all repos have uploaded if running on schedule
	if (context.eventName === 'schedule') {
	await new Promise(resolve => setTimeout(resolve, 60000)); // Wait 1 minute
	}

	await github.rest.repos.createDispatchEvent({
	owner: context.repo.owner,
	repo: context.repo.repo,
	event_type: 'ai-docs-source-updated',
	client_payload: {
	repository: 'chainguard-dev/edu',
	commit: context.sha,
	source: 'edu'
	}
	});

	console.log('Triggered AI docs compilation workflow');

Navigation Menu

Uh oh!

actions/telemetry: explain why we collect telemetry data (#3887) #874

Workflow file

actions/telemetry: explain why we collect telemetry data (#3887) #874

Uh oh!

Workflow file for this run