Files
breakpilot-compliance/backend-compliance/compliance/services/check_snapshot.py
T
Benjamin Admin cde670617e
CI / detect-changes (push) Successful in 11s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / secret-scan (push) Has been skipped
CI / dep-audit (push) Has been skipped
CI / sbom-scan (push) Has been skipped
CI / validate-canonical-controls (push) Successful in 14s
CI / loc-budget (push) Failing after 14s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Has been skipped
CI / test-go (push) Has been skipped
CI / iace-gt-coverage (push) Has been skipped
CI / test-python-backend (push) Successful in 37s
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped
feat(audit-pipeline): P72 MC-Scope-Classifier + P80 Snapshot/Replay-Foundation [migration-approved]
P72  MC-Scope-Classifier — pro MC den ECHTEN Doc-Adressaten festlegen
     (cookie_richtlinie/dse/banner_implementation/cmp_audit/tom/avv/jc/
      impressum/agb/widerruf/process/accounting/other).
     - Migration 145: scope_doc_type Spalte + Index auf canonical_controls
     - Backfill-Script mit Regex-Heuristik (12 Regeln, Prioritaet-sortiert)
     - Erste 11k-Sample-Distribution: 76% other (Heuristik v1 zu strict —
       v2 muss lockerere Patterns fuer DSE/TOM nachschaerfen)
     - Ziel: bevor MC-Scorecard filtert, weiss jeder MC welches Dokument
       er adressiert. Bisher landeten eHealth-/HGB-MCs im Cookie-Audit.

P80  Snapshot + Replay-Foundation — Roh-Daten persistieren damit
     Audit-Pipeline ohne erneuten Crawl rebuildbar ist.
     - Migration 146: compliance_check_snapshots Tabelle (JSONB pro
       doc_entries/banner_result/profile/cmp_vendors/scan_context)
     - services.check_snapshot.save_snapshot/load_snapshot/list
     - Endpoints GET /snapshots, GET /snapshots/{id}
     - Hook in _run_compliance_check: nach Mail-Send automatischer
       Snapshot-Save via separater SessionLocal (background-task safe)
     - Replay-Endpoint folgt im naechsten PR (braucht Refactoring
       von _run_compliance_check in crawl_phase + interpret_phase)
     - Effekt: Test-Cycle 7min -> 5sec bei reinen Logik-Aenderungen
       (P73/P79/P81+ profitieren direkt). Snapshots dienen auch als
       Regression-Test-Corpus (P81 Golden-Truth-Library).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 08:53:31 +02:00

180 lines
6.0 KiB
Python

"""
P80 — Snapshot + Replay-Helper.
Persistiert die Roh-Daten eines Compliance-Check-Laufs (DSE-Text,
Banner-HTML, Cookies, CMP-Vendors, Profile), damit die Audit-Pipeline
spaeter ohne erneuten Browser-Crawl die Mail-Render-/MC-Scoring-Logik
neu laufen kann.
Use Cases:
* Logik-Iteration (MC-Filter P72, Mail-Layout, Action-Recipes) ohne
7min Re-Crawl.
* Regression-Test: Golden-Truth-Library (P81).
* Diff-Mode: "was hat sich seit letztem Snapshot geaendert" (P84).
"""
from __future__ import annotations
import json
import logging
from typing import Any
from urllib.parse import urlparse
from sqlalchemy import text
from sqlalchemy.orm import Session
logger = logging.getLogger(__name__)
def _to_jsonb(obj: Any) -> str:
"""Serialize to JSON-string for psycopg2 JSONB insertion."""
return json.dumps(obj, default=str, ensure_ascii=False)
def _derive_site_domain(doc_entries: list[dict]) -> str:
for e in doc_entries or []:
url = (e.get("url") or "").strip()
if url:
try:
netloc = urlparse(url).netloc.lower().replace("www.", "")
if netloc:
return netloc
except Exception:
continue
return "unknown"
def save_snapshot(
db: Session,
check_id: str,
doc_entries: list[dict],
banner_result: dict | None,
profile: Any,
cmp_vendors: list[dict] | None = None,
scan_context: dict | None = None,
site_label: str | None = None,
notes: str | None = None,
) -> str | None:
"""Persist scan raw data. Returns snapshot UUID on success."""
try:
profile_dict: dict = {}
if profile is not None:
if hasattr(profile, "__dict__"):
profile_dict = {k: v for k, v in profile.__dict__.items()
if not k.startswith("_")}
elif isinstance(profile, dict):
profile_dict = profile
domain = _derive_site_domain(doc_entries or [])
result = db.execute(
text("""
INSERT INTO compliance.compliance_check_snapshots
(check_id, site_domain, site_label,
doc_entries, banner_result, profile,
scan_context, cmp_vendors, notes)
VALUES (:cid, :dom, :lbl,
CAST(:de AS JSONB), CAST(:br AS JSONB), CAST(:pr AS JSONB),
CAST(:sc AS JSONB), CAST(:cv AS JSONB), :nt)
RETURNING id
"""),
{
"cid": check_id,
"dom": domain,
"lbl": site_label,
"de": _to_jsonb(doc_entries or []),
"br": _to_jsonb(banner_result) if banner_result else None,
"pr": _to_jsonb(profile_dict) if profile_dict else None,
"sc": _to_jsonb(scan_context) if scan_context else None,
"cv": _to_jsonb(cmp_vendors) if cmp_vendors else None,
"nt": notes,
},
)
snapshot_id = str(result.fetchone()[0])
db.commit()
logger.info(
"P80: snapshot saved id=%s check=%s domain=%s docs=%d",
snapshot_id, check_id, domain, len(doc_entries or []),
)
return snapshot_id
except Exception as e:
logger.warning("P80 snapshot save failed for %s: %s", check_id, e)
try:
db.rollback()
except Exception:
pass
return None
def load_snapshot(db: Session, snapshot_id: str) -> dict | None:
"""Load a snapshot by UUID. Returns dict with all fields or None."""
try:
row = db.execute(
text("""
SELECT id, check_id, site_domain, site_label,
doc_entries, banner_result, profile,
scan_context, cmp_vendors, created_at,
replay_count, notes
FROM compliance.compliance_check_snapshots
WHERE id = CAST(:sid AS uuid)
"""),
{"sid": snapshot_id},
).fetchone()
if not row:
return None
db.execute(
text("""
UPDATE compliance.compliance_check_snapshots
SET replay_count = replay_count + 1,
last_replay_at = now()
WHERE id = CAST(:sid AS uuid)
"""),
{"sid": snapshot_id},
)
db.commit()
return {
"id": str(row[0]),
"check_id": row[1],
"site_domain": row[2],
"site_label": row[3],
"doc_entries": row[4] or [],
"banner_result": row[5],
"profile": row[6] or {},
"scan_context": row[7] or {},
"cmp_vendors": row[8] or [],
"created_at": str(row[9]),
"replay_count": row[10],
"notes": row[11],
}
except Exception as e:
logger.warning("P80 snapshot load failed for %s: %s", snapshot_id, e)
return None
def list_snapshots_for_domain(db: Session, domain: str, limit: int = 20) -> list[dict]:
"""List recent snapshots for a domain (for diff-mode P84)."""
try:
rows = db.execute(
text("""
SELECT id, check_id, site_domain, created_at, replay_count, notes
FROM compliance.compliance_check_snapshots
WHERE site_domain = :dom
ORDER BY created_at DESC
LIMIT :lim
"""),
{"dom": domain.lower().replace("www.", ""), "lim": limit},
).fetchall()
return [
{
"id": str(r[0]),
"check_id": r[1],
"site_domain": r[2],
"created_at": str(r[3]),
"replay_count": r[4],
"notes": r[5],
}
for r in rows
]
except Exception as e:
logger.warning("P80 list_snapshots failed for %s: %s", domain, e)
return []