mAi
fdac496a6f
tools/anti-ai-lint.py: Python-Linter (stdlib + yq) prueft jede build/<domain>/index.html gegen die Blacklist in tools/anti-ai-blacklist.yaml. HTML wird via html.parser auf sichtbaren Text reduziert (Skripte/Styles werden ignoriert), dann werden Vokabel- Substrings (DE+EN, case-insensitive) und Regex-Patterns gematcht. Severity warn = Build geht durch, fail = Build bricht ab. Whitelist-Mechanismen: - HTML-Kommentar im Markup: <!-- anti-ai-allow: term1, term2 --> - Per-Site in site.yaml: anti_ai_allow: [term1, term2] Integration in build.sh als Schritt 4/4, mit --skip-lint fuer Notfaelle. Dockerfile installiert python3 zusaetzlich; nur im Builder-Stage, kein Effekt aufs Caddy-Image. Tests via tools/test-anti-ai-lint.sh: synthetische AI-Fixture wird korrekt geflagged, Whitelists unterdruecken Hits, fail-Severity triggert exit 1, neutraler Text exit 0. Initial-Lauf auf 59 bestehenden Sites: 2 warn (killusion.de "revolutionaer" in ironischem Kontext, kilofant.de "robust"), 0 fail. Cleanup ist Folge-Issue. README + docs/geo-seo-guideline.md aktualisiert mit der konkreten Tool-Position.
108 lines
3.4 KiB
Bash
Executable File
108 lines
3.4 KiB
Bash
Executable File
#!/bin/bash
|
|
# Self-test for tools/anti-ai-lint.py.
|
|
# Builds a synthetic AI-text fixture in a temp dir, asserts the linter
|
|
# flags it, then verifies whitelist comments suppress the hit.
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR=$(cd "$(dirname "$0")" && pwd)
|
|
LINT="$SCRIPT_DIR/anti-ai-lint.py"
|
|
|
|
tmp=$(mktemp -d)
|
|
trap 'rm -rf "$tmp"' EXIT
|
|
|
|
mkdir -p "$tmp/build/synthetic-ai.test"
|
|
|
|
cat > "$tmp/build/synthetic-ai.test/index.html" <<'HTML'
|
|
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<title>Synthetic AI sample</title>
|
|
<style>.foo { color: red; } /* leverage in CSS comment must be ignored */</style>
|
|
<script>const x = "leverage"; // in JS, must be ignored</script>
|
|
</head>
|
|
<body>
|
|
<h1>In today's evolving landscape</h1>
|
|
<p>This is a comprehensive, robust, holistic solution that lets us leverage emerging trends.</p>
|
|
<p>We delve into the intricate tapestry of AI to navigate this pivotal moment.</p>
|
|
<h2>Challenges and Future Prospects</h2>
|
|
<ul>
|
|
<li>Effizienz: hoch — Skalierbarkeit: gut — Sicherheit: solide</li>
|
|
</ul>
|
|
</body>
|
|
</html>
|
|
HTML
|
|
|
|
expect_finding() {
|
|
# expect_finding <json> <name>
|
|
python3 -c '
|
|
import json, sys
|
|
data = json.loads(sys.argv[1])
|
|
target = sys.argv[2]
|
|
hits = [f for site in data["sites"] for f in site["findings"] if f["name"] == target]
|
|
if len(hits) != 1:
|
|
print(f"expected exactly 1 finding for {target!r}, got {len(hits)}", file=sys.stderr)
|
|
sys.exit(1)
|
|
' "$1" "$2"
|
|
}
|
|
|
|
expect_no_finding() {
|
|
python3 -c '
|
|
import json, sys
|
|
data = json.loads(sys.argv[1])
|
|
target = sys.argv[2]
|
|
hits = [f for site in data["sites"] for f in site["findings"] if f["name"] == target]
|
|
if hits:
|
|
print(f"unexpected finding for {target!r}: {hits}", file=sys.stderr)
|
|
sys.exit(1)
|
|
' "$1" "$2"
|
|
}
|
|
|
|
echo "[1] expecting FAIL on synthetic AI fixture..."
|
|
report=$(python3 "$LINT" --json "$tmp/build" 2>/dev/null) && rc=0 || rc=$?
|
|
if [ "$rc" -ne 1 ]; then
|
|
echo "FAIL: expected exit 1, got $rc" >&2
|
|
echo "$report" >&2
|
|
exit 1
|
|
fi
|
|
for term in "in today's evolving landscape" "Challenges and Future Prospects" \
|
|
"leverage" "comprehensive" "delve" "em-dash-3-bullet"; do
|
|
expect_finding "$report" "$term" || exit 1
|
|
done
|
|
echo " OK"
|
|
|
|
echo "[2] expecting whitelist comment to suppress hits..."
|
|
sed -i '4a\ <!-- anti-ai-allow: leverage, comprehensive, delve, em-dash-3-bullet -->' \
|
|
"$tmp/build/synthetic-ai.test/index.html"
|
|
report=$(python3 "$LINT" --json "$tmp/build" 2>/dev/null) || true
|
|
for term in "leverage" "comprehensive" "delve" "em-dash-3-bullet"; do
|
|
expect_no_finding "$report" "$term" || exit 1
|
|
done
|
|
# fail-level "in today's evolving landscape" should still be reported
|
|
expect_finding "$report" "in today's evolving landscape" || exit 1
|
|
echo " OK"
|
|
|
|
echo "[3] expecting fail-level hit still triggers exit 1..."
|
|
python3 "$LINT" "$tmp/build" >/dev/null 2>&1 && rc=0 || rc=$?
|
|
if [ "$rc" -ne 1 ]; then
|
|
echo "FAIL: expected exit 1, got $rc" >&2
|
|
exit 1
|
|
fi
|
|
echo " OK"
|
|
|
|
echo "[4] expecting clean exit on neutral fixture..."
|
|
rm "$tmp/build/synthetic-ai.test/index.html"
|
|
mkdir -p "$tmp/build/clean.test"
|
|
echo '<!DOCTYPE html><html lang="de"><body><p>Ein einfacher Satz ohne KI-Vokabular.</p></body></html>' \
|
|
> "$tmp/build/clean.test/index.html"
|
|
rm -rf "$tmp/build/synthetic-ai.test"
|
|
out=$(python3 "$LINT" "$tmp/build" 2>&1) && rc=0 || rc=$?
|
|
if [ "$rc" -ne 0 ]; then
|
|
echo "FAIL: clean fixture should exit 0, got $rc" >&2
|
|
echo "$out"
|
|
exit 1
|
|
fi
|
|
echo " OK"
|
|
|
|
echo
|
|
echo "all tests passed"
|