generated from osc/skins-template
247 lines
11 KiB
YAML
247 lines
11 KiB
YAML
name: Check Links in README
|
||
|
||
on:
|
||
workflow_dispatch:
|
||
|
||
jobs:
|
||
check-links:
|
||
runs-on: ubuntu-latest
|
||
|
||
steps:
|
||
- name: Checkout repository
|
||
uses: actions/checkout@v4
|
||
|
||
- name: Set up Node.js
|
||
uses: actions/setup-node@v4
|
||
with:
|
||
node-version: '20'
|
||
|
||
- name: Install link checker
|
||
run: npm install -g markdown-link-check
|
||
|
||
- name: Check external links in all markdown files
|
||
continue-on-error: true
|
||
run: |
|
||
# Create config file to handle custom domains and retries
|
||
cat > .markdown-link-check.json << 'EOF'
|
||
{
|
||
"ignorePatterns": [
|
||
{
|
||
"pattern": "^/"
|
||
}
|
||
],
|
||
"replacementPatterns": [],
|
||
"httpHeaders": [
|
||
{
|
||
"urls": ["https://git.sulej.net"],
|
||
"headers": {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
|
||
}
|
||
}
|
||
],
|
||
"timeout": "20s",
|
||
"retryOn429": true,
|
||
"retryCount": 3,
|
||
"fallbackRetryDelay": "30s",
|
||
"aliveStatusCodes": [200, 206, 301, 302, 307, 308]
|
||
}
|
||
EOF
|
||
|
||
echo ""
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
echo "🌐 Checking External Links in All Markdown Files"
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
echo ""
|
||
|
||
# Find all markdown files
|
||
find . -name "*.md" -type f | sort > markdown_files.txt
|
||
total_files=$(wc -l < markdown_files.txt)
|
||
|
||
echo "📊 Found $total_files markdown files to check"
|
||
echo ""
|
||
|
||
# Extract and group all external links by context
|
||
> all_broken_links.txt
|
||
|
||
while IFS= read -r file; do
|
||
# Run markdown-link-check and capture only errors
|
||
markdown-link-check "$file" --config .markdown-link-check.json 2>&1 | grep "^\s*\[✖\]" >> all_broken_links.txt || true
|
||
done < markdown_files.txt
|
||
|
||
# Parse README.md to group links by skin/section
|
||
if [ -f "README.md" ]; then
|
||
echo "📋 Grouping broken links by context..."
|
||
echo ""
|
||
|
||
# Count total broken links
|
||
total_broken=$(wc -l < all_broken_links.txt)
|
||
|
||
if [ $total_broken -gt 0 ]; then
|
||
echo "❌ Found $total_broken broken external links"
|
||
echo ""
|
||
|
||
# Group by category
|
||
declare -A general_links
|
||
declare -A skin_links
|
||
declare -A tag_links
|
||
|
||
while IFS= read -r line; do
|
||
url=$(echo "$line" | grep -oP 'https://[^\s]+' || echo "$line" | grep -oP 'http://[^\s]+')
|
||
|
||
# Categorize links
|
||
if [[ "$url" == *"/osc/skins"* ]]; then
|
||
general_links["$url"]=1
|
||
elif [[ "$url" == *"/src/tag/"* ]] || [[ "$url" == *"/media/tag/"* ]]; then
|
||
tag_links["$url"]=1
|
||
elif [[ "$url" == *"/export/"* ]] || [[ "$url" == *"/media/"* ]]; then
|
||
# Extract skin name from URL
|
||
skin_name=$(echo "$url" | grep -oP '/export/[^/]+' | sed 's|/export/||' | head -1)
|
||
if [ -z "$skin_name" ]; then
|
||
skin_name="Unknown"
|
||
fi
|
||
skin_links["$skin_name"]+="$url"$'\n'
|
||
else
|
||
general_links["$url"]=1
|
||
fi
|
||
done < all_broken_links.txt
|
||
|
||
# Display grouped results
|
||
if [ ${#general_links[@]} -gt 0 ]; then
|
||
echo "🔗 General Links:"
|
||
for url in "${!general_links[@]}"; do
|
||
echo " ❌ $url"
|
||
done
|
||
echo ""
|
||
fi
|
||
|
||
if [ ${#skin_links[@]} -gt 0 ]; then
|
||
echo "🎨 Skin-specific Links:"
|
||
for skin in "${!skin_links[@]}"; do
|
||
echo ""
|
||
echo " $skin:"
|
||
echo "${skin_links[$skin]}" | while IFS= read -r url; do
|
||
[ -n "$url" ] && echo " ❌ $url"
|
||
done
|
||
done
|
||
echo ""
|
||
fi
|
||
|
||
if [ ${#tag_links[@]} -gt 0 ]; then
|
||
echo "🏷️ Version Tags:"
|
||
for url in "${!tag_links[@]}"; do
|
||
echo " ❌ $url"
|
||
done
|
||
echo ""
|
||
fi
|
||
else
|
||
echo "✅ All external links are valid!"
|
||
fi
|
||
fi
|
||
|
||
- name: Check all links in markdown files
|
||
run: |
|
||
#!/bin/bash
|
||
|
||
echo ""
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
echo "🔍 Checking ALL Links in All Markdown Files"
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
echo ""
|
||
|
||
# Find all markdown files
|
||
find . -name "*.md" -type f | sort > all_markdown_files.txt
|
||
total_files=$(wc -l < all_markdown_files.txt)
|
||
echo "📊 Found $total_files markdown files to check"
|
||
echo ""
|
||
|
||
has_errors=0
|
||
|
||
# Process each markdown file
|
||
while IFS= read -r md_file; do
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
echo "📄 Checking: $md_file"
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
|
||
file_has_errors=0
|
||
|
||
# Extract ALL links from the markdown file
|
||
# Match both []() and direct URLs
|
||
grep -oP '\[([^\]]+)\]\(([^\)]+)\)' "$md_file" | sed 's/\[.*\](\(.*\))/\1/' > /tmp/links_$$.txt || true
|
||
|
||
# Also extract image links
|
||
grep -oP '!\[([^\]]*)\]\(([^\)]+)\)' "$md_file" | sed 's/!\[.*\](\(.*\))/\1/' >> /tmp/links_$$.txt || true
|
||
|
||
link_count=$(wc -l < /tmp/links_$$.txt)
|
||
|
||
if [ $link_count -eq 0 ]; then
|
||
echo " ℹ️ No links found in this file"
|
||
echo ""
|
||
continue
|
||
fi
|
||
|
||
echo " 📊 Found $link_count links to check"
|
||
echo ""
|
||
|
||
# Check each link
|
||
while IFS= read -r link; do
|
||
# Decode URL-encoded characters
|
||
decoded_link=$(echo "$link" | sed 's/%20/ /g' | sed 's/%23/#/g' | sed 's/%28/(/g' | sed 's/%29/)/g' | sed 's/%E2%80%A2/•/g' | sed 's/%E1%9A%96/ᚖ/g' | sed 's/%E3%80%8A/《/g' | sed 's/%E3%80%8B/》/g' | sed 's/%E3%80%8E/『/g' | sed 's/%E3%80%8F/』/g' | sed 's/%E2%9B%94/⛔/g' | sed 's/%E2%9C%A8/✨/g' | sed 's/%7B/{/g' | sed 's/%7D/}/g' | sed 's/%2B/+/g' | sed 's/%E3%83%86/テ/g' | sed 's/%E3%83%B3/ン/g' | sed 's/%E3%83%8D/ネ/g' | sed 's/%E3%82%B9/ス/g' | sed 's/%E3%82%A4/イ/g' | sed 's/%E3%83%BB/・/g' | sed 's/%E3%83%95/フ/g' | sed 's/%E3%83%AA/リ/g' | sed 's/%E3%83%BC/ー/g' | sed 's/%E3%83%8A/ナ/g' | sed 's/%5B/[/g' | sed 's/%5D/]/g')
|
||
|
||
# Check if it's an external URL
|
||
if [[ "$decoded_link" =~ ^https?:// ]]; then
|
||
# Check external URL with curl
|
||
if curl -s -o /dev/null -w "%{http_code}" --max-time 10 "$decoded_link" | grep -q "^[23]"; then
|
||
echo " ✅ $decoded_link"
|
||
else
|
||
echo " ❌ $decoded_link (URL not accessible)"
|
||
file_has_errors=1
|
||
has_errors=1
|
||
fi
|
||
else
|
||
# Local file - remove leading slash if present
|
||
if [[ "$decoded_link" =~ ^/ ]]; then
|
||
file_path="${decoded_link#/}"
|
||
else
|
||
# Relative path - resolve from markdown file location
|
||
md_dir=$(dirname "$md_file")
|
||
file_path="$md_dir/$decoded_link"
|
||
fi
|
||
|
||
# Normalize path
|
||
file_path=$(realpath -m "$file_path" 2>/dev/null || echo "$file_path")
|
||
|
||
if [ -f "$file_path" ]; then
|
||
echo " ✅ $decoded_link"
|
||
else
|
||
echo " ❌ $decoded_link (file not found: $file_path)"
|
||
file_has_errors=1
|
||
has_errors=1
|
||
fi
|
||
fi
|
||
done < /tmp/links_$$.txt
|
||
|
||
rm -f /tmp/links_$$.txt
|
||
|
||
if [ $file_has_errors -eq 0 ]; then
|
||
echo ""
|
||
echo " ✅ All links valid in this file"
|
||
else
|
||
echo ""
|
||
echo " ❌ Some links are broken in this file"
|
||
fi
|
||
echo ""
|
||
|
||
done < all_markdown_files.txt
|
||
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
|
||
if [ $has_errors -eq 0 ]; then
|
||
echo "✅ FINAL RESULT: All links are valid across all markdown files!"
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
exit 0
|
||
else
|
||
echo "❌ FINAL RESULT: Some links are broken. Please review the output above."
|
||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||
exit 1
|
||
fi
|