generated from osc/skins-template
Update .gitea/workflows/test-skins.yml
This commit is contained in:
@@ -23,17 +23,7 @@ jobs:
|
|||||||
ERRORS=()
|
ERRORS=()
|
||||||
|
|
||||||
############################################################
|
############################################################
|
||||||
# Remove all NUL/control characters BEFORE any decoding
|
# Safe unicode URL decode (never produces NULL bytes)
|
||||||
############################################################
|
|
||||||
sanitize_url() {
|
|
||||||
printf '%s' "$1" \
|
|
||||||
| tr -d '\000' \
|
|
||||||
| tr -d '\r' \
|
|
||||||
| sed 's/[[:cntrl:]]//g'
|
|
||||||
}
|
|
||||||
|
|
||||||
############################################################
|
|
||||||
# Safe unicode URL decode (no null bytes)
|
|
||||||
############################################################
|
############################################################
|
||||||
urldecode() {
|
urldecode() {
|
||||||
local url="$1"
|
local url="$1"
|
||||||
@@ -42,7 +32,7 @@ jobs:
|
|||||||
}
|
}
|
||||||
|
|
||||||
############################################################
|
############################################################
|
||||||
# Detect Gitea "soft 404" even when status=200 OK
|
# Detect Gitea "soft 404" even when HTTP=200 OK
|
||||||
############################################################
|
############################################################
|
||||||
check_http() {
|
check_http() {
|
||||||
local url="$1"
|
local url="$1"
|
||||||
@@ -50,21 +40,19 @@ jobs:
|
|||||||
|
|
||||||
local status body
|
local status body
|
||||||
|
|
||||||
# Try HEAD first
|
|
||||||
status=$(curl -Is --max-time 10 "$url" | head -n1 | awk '{print $2}')
|
status=$(curl -Is --max-time 10 "$url" | head -n1 | awk '{print $2}')
|
||||||
if [[ "$status" =~ ^2|3 ]]; then
|
if [[ "$status" =~ ^2|3 ]]; then
|
||||||
body=$(curl -Ls --max-time 10 "$url")
|
body=$(curl -Ls --max-time 10 "$url")
|
||||||
if echo "$body" | grep -qiE "404 Not Found|Path .* doesn't exist|File not found|does not exist|Not Found"; then
|
if echo "$body" | grep -qiE "404 Not Found|doesn't exist|File not found|Not Found"; then
|
||||||
return 1
|
return 1
|
||||||
fi
|
fi
|
||||||
return 0
|
return 0
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# Try GET fallback
|
|
||||||
status=$(curl -Is --max-time 10 -X GET "$url" | head -n1 | awk '{print $2}')
|
status=$(curl -Is --max-time 10 -X GET "$url" | head -n1 | awk '{print $2}')
|
||||||
if [[ "$status" =~ ^2|3 ]]; then
|
if [[ "$status" =~ ^2|3 ]]; then
|
||||||
body=$(curl -Ls --max-time 10 "$url")
|
body=$(curl -Ls --max-time 10 "$url")
|
||||||
if echo "$body" | grep -qiE "404 Not Found|Path .* doesn't exist|File not found|does not exist|Not Found"; then
|
if echo "$body" | grep -qiE "404 Not Found|doesn't exist|File not found|Not Found"; then
|
||||||
return 1
|
return 1
|
||||||
fi
|
fi
|
||||||
return 0
|
return 0
|
||||||
@@ -74,7 +62,7 @@ jobs:
|
|||||||
}
|
}
|
||||||
|
|
||||||
############################################################
|
############################################################
|
||||||
# Local file existence check
|
# Local file check
|
||||||
############################################################
|
############################################################
|
||||||
check_local() {
|
check_local() {
|
||||||
local path="$1"
|
local path="$1"
|
||||||
@@ -88,27 +76,22 @@ jobs:
|
|||||||
}
|
}
|
||||||
|
|
||||||
############################################################
|
############################################################
|
||||||
# Extract URLs from Markdown + HTML
|
# Extract links from markdown + HTML
|
||||||
############################################################
|
############################################################
|
||||||
extract_links() {
|
extract_links() {
|
||||||
local f="$1"
|
local f="$1"
|
||||||
|
|
||||||
# Markdown links
|
|
||||||
grep -oE '\[[^]]*\]\([^)]*\)' "$f" \
|
grep -oE '\[[^]]*\]\([^)]*\)' "$f" \
|
||||||
| sed -E 's/.*\((.*)\).*/\1/'
|
| sed -E 's/.*\((.*)\).*/\1/'
|
||||||
|
|
||||||
# Markdown images
|
|
||||||
grep -oE '!\[[^]]*\]\([^)]*\)' "$f" \
|
grep -oE '!\[[^]]*\]\([^)]*\)' "$f" \
|
||||||
| sed -E 's/.*\((.*)\).*/\1/'
|
| sed -E 's/.*\((.*)\).*/\1/'
|
||||||
|
|
||||||
# Raw URLs
|
|
||||||
grep -oE 'https?://[^ )"]+' "$f"
|
grep -oE 'https?://[^ )"]+' "$f"
|
||||||
|
|
||||||
# <img src="">
|
|
||||||
grep -oE '<img[^>]*src="[^"]+"' "$f" \
|
grep -oE '<img[^>]*src="[^"]+"' "$f" \
|
||||||
| sed -E 's/.*src="([^"]*)".*/\1/'
|
| sed -E 's/.*src="([^"]*)".*/\1/'
|
||||||
|
|
||||||
# <video src="">
|
|
||||||
grep -oE '<video[^>]*src="[^"]+"' "$f" \
|
grep -oE '<video[^>]*src="[^"]+"' "$f" \
|
||||||
| sed -E 's/.*src="([^"]*)".*/\1/'
|
| sed -E 's/.*src="([^"]*)".*/\1/'
|
||||||
}
|
}
|
||||||
@@ -116,6 +99,9 @@ jobs:
|
|||||||
echo "🔍 Scanning Markdown files..."
|
echo "🔍 Scanning Markdown files..."
|
||||||
echo
|
echo
|
||||||
|
|
||||||
|
############################################################
|
||||||
|
# Process all markdown files
|
||||||
|
############################################################
|
||||||
find . -type f -name '*.md' | while IFS= read -r mdfile; do
|
find . -type f -name '*.md' | while IFS= read -r mdfile; do
|
||||||
echo "📄 Checking: $mdfile"
|
echo "📄 Checking: $mdfile"
|
||||||
|
|
||||||
@@ -123,40 +109,36 @@ jobs:
|
|||||||
[[ -z "$url" ]] && continue
|
[[ -z "$url" ]] && continue
|
||||||
[[ "$url" == mailto:* ]] && continue
|
[[ "$url" == mailto:* ]] && continue
|
||||||
|
|
||||||
# Clean input BEFORE use
|
# Skip versioned docs tag links
|
||||||
cleaned=$(sanitize_url "$url")
|
if [[ "$mdfile" == ./docs/* ]] && [[ "$url" == *"/src/tag/"* ]]; then
|
||||||
|
|
||||||
# Skip tag-version links in docs
|
|
||||||
if [[ "$mdfile" == ./docs/* ]] && [[ "$cleaned" == *"/src/tag/"* ]]; then
|
|
||||||
continue
|
continue
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# external
|
# External links
|
||||||
if [[ "$cleaned" == http* ]]; then
|
if [[ "$url" == http* ]]; then
|
||||||
if ! check_http "$cleaned"; then
|
if ! check_http "$url"; then
|
||||||
ERRORS+=("❌ Broken external link: $cleaned (in $mdfile)")
|
ERRORS+=("❌ Broken external link: $url (in $mdfile)")
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# local file
|
|
||||||
else
|
else
|
||||||
if ! check_local "$cleaned"; then
|
# Local links
|
||||||
ERRORS+=("❌ Missing local file: $cleaned (in $mdfile)")
|
if ! check_local "$url"; then
|
||||||
|
ERRORS+=("❌ Missing local file: $url (in $mdfile)")
|
||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
done < <(extract_links "$mdfile")
|
# 🌟 FULL FIX: sanitize extract_links output BEFORE loop
|
||||||
|
done < <(extract_links "$mdfile" | tr -d '\000' | tr -d '\r' | sed 's/[[:cntrl:]]//g')
|
||||||
|
|
||||||
echo
|
echo
|
||||||
done
|
done
|
||||||
|
|
||||||
############################################################
|
############################################################
|
||||||
# Final result
|
# Final report
|
||||||
############################################################
|
############################################################
|
||||||
echo
|
echo
|
||||||
if (( ${#ERRORS[@]} > 0 )); then
|
if (( ${#ERRORS[@]} > 0 )); then
|
||||||
echo -e "${RED}✖ Errors found:${RESET}"
|
echo -e "${RED}✖ Errors found:${RESET}"
|
||||||
printf "%s\n" "${ERRORS[@]}"
|
printf "%s\n" "${ERRORS[@]}"
|
||||||
|
|
||||||
echo
|
echo
|
||||||
echo -e "${RED}❌ Failing job because broken links were found.${RESET}"
|
echo -e "${RED}❌ Failing job because broken links were found.${RESET}"
|
||||||
exit 1
|
exit 1
|
||||||
|
|||||||
Reference in New Issue
Block a user