feat: Binärdateien auf Änderungen prüfen (check-assets / approve-assets)

Neue Befehle:
- `python -m scanner check-assets`    — SHA-256-Hashes aller JS/CSS/Bild-Assets
  aus dem letzten Snapshot fetchen und mit Baseline vergleichen
- `python -m scanner approve-assets`  — aktuelle Hashes als neue Baseline setzen

Scoring: geändertes JS 40 Pkt, CSS 30 Pkt, Bild/PDF 20 Pkt.
Asset-Baseline liegt in data/baseline/asset_hashes.json.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Your Name 2026-06-12 09:26:59 +02:00
commit d803f79efe
7 changed files with 506 additions and 1 deletions

View file

@ -467,6 +467,78 @@ def score_cloak_diff(cloak_diff: dict, cfg: dict) -> dict:
return {"score": score, "level": level, "reasons": reasons, "exit_code": exit_code}
# ---------------------------------------------------------------------------
# Asset hash comparison
# ---------------------------------------------------------------------------
def compare_asset_hashes(baseline: dict, current: dict) -> dict:
"""
Compare asset hash dicts {url: {sha256, size, type, error}}.
Returns {changed, new, missing, fetch_errors, total_checked}.
"""
b_hashed = {url for url, r in baseline.items() if r.get("sha256")}
c_hashed = {url for url, r in current.items() if r.get("sha256")}
changed = [
{
"url": url,
"type": current[url].get("type", "unknown"),
"old_sha256": baseline[url]["sha256"][:16] + "",
"new_sha256": current[url]["sha256"][:16] + "",
"size_diff": (current[url].get("size") or 0) - (baseline[url].get("size") or 0),
}
for url in sorted(b_hashed & c_hashed)
if baseline[url]["sha256"] != current[url]["sha256"]
]
return {
"changed": changed,
"new": sorted(c_hashed - b_hashed),
"missing": sorted(b_hashed - set(current)),
"fetch_errors": [
{"url": url, "error": r["error"]}
for url, r in sorted(current.items())
if r.get("error")
],
"total_checked": len(c_hashed),
}
def score_asset_diff(asset_diff: dict, cfg: dict) -> dict:
"""Score asset hash changes by file type."""
sc = cfg.get("scoring", {})
thr = cfg.get("thresholds", {"yellow": 20, "red": 60})
score = 0
reasons: list[str] = []
def add(pts: int, msg: str) -> None:
nonlocal score
score += pts
reasons.append(f"{msg} (+{pts})")
for entry in asset_diff.get("changed", []):
asset_type = entry.get("type", "unknown")
if asset_type == "script":
pts = sc.get("changed_script", 40)
elif asset_type == "link_rel":
pts = sc.get("changed_stylesheet", 30)
else:
pts = sc.get("changed_asset", 20)
size_info = f", {entry['size_diff']:+d} Bytes" if entry.get("size_diff") else ""
add(pts, f"Geänderte Datei [{asset_type}]{size_info}: {entry['url']}")
yellow = thr.get("yellow", 20)
red = thr.get("red", 60)
if score >= red:
level, exit_code = "red", 2
elif score >= yellow:
level, exit_code = "yellow", 1
else:
level, exit_code = "green", 0
return {"score": score, "level": level, "reasons": reasons, "exit_code": exit_code}
def _fingerprint(obj: dict | list | str) -> str:
"""Stable hash for deduplicating diff entries."""
import json as _json