feat(consent-tester): Phase B — named CMP library + plugin architecture

cmp_extractor.py refactored to thin coordinator (123 LOC, was 223). Discovers all CMP modules via cmp_library/_registry.py:load_all() at import time. Restart consent-tester to pick up new modules. New cmp_library/ folder: - _registry.py: auto-discovers all modules with MATCHER + reconstruct() - epaas.py: BMW Group ePaaS (extracted from cmp_extractor) - onetrust.py: cdn.cookielaw.org Groups/Cookies schema - cookiebot.py: consent.cookiebot.com Categories schema - usercentrics.py: api.usercentrics.eu services schema - didomi.py: sdk.privacy-center.org notice + vendors + purposes - trustarc.py: consent.trustarc.com categories + vendors Each module: - MATCHER: re.Pattern matching the CMP JSON endpoint URL - reconstruct(d: dict) -> str: builds German Markdown cookie-policy text Phase E (self-improving) will write auto_*.py files into the same folder; _registry already picks those up via pkgutil.iter_modules.
2026-05-16 22:59:48 +02:00
parent 4f19310130
commit 7e426c31f1
9 changed files with 427 additions and 144 deletions
@@ -0,0 +1,56 @@
+"""OneTrust Cookie Consent.
+
+URL: cdn.cookielaw.org/consent/<id>/<id>.json
+     OR cdn.cookielaw.org/consent/<id>/<lang>.json
+Schema: Groups[] with GroupName, GroupDescription, Cookies[]
+"""
+
+import re
+
+MATCHER = re.compile(r"cdn\.cookielaw\.org/consent/[^/]+/[^/]+\.json", re.I)
+
+_TAG_RE = re.compile(r"<[^>]+>")
+_WS_RE = re.compile(r"\s+")
+
+
+def _clean(text: str) -> str:
+    no_tags = _TAG_RE.sub(" ", text)
+    no_tags = no_tags.replace("&nbsp;", " ").replace("&amp;", "&")
+    return _WS_RE.sub(" ", no_tags).strip()
+
+
+def reconstruct(d: dict) -> str:
+    parts: list[str] = ["# Cookie-Richtlinie (OneTrust)"]
+
+    # Optional preamble fields
+    for key in ("Description", "PolicyText", "PolicyDescription"):
+        val = d.get(key)
+        if val:
+            parts.append("")
+            parts.append(_clean(str(val)))
+
+    groups = d.get("Groups") or d.get("groups") or []
+    for g in groups:
+        name = g.get("GroupName") or g.get("name") or ""
+        desc = g.get("GroupDescription") or g.get("description") or ""
+        parts.append("")
+        parts.append(f"## {name}")
+        if desc:
+            parts.append(_clean(str(desc)))
+
+        cookies = g.get("Cookies") or g.get("cookies") or []
+        for c in cookies[:50]:
+            cn = c.get("Name") or c.get("name") or ""
+            cp = c.get("Provider") or c.get("provider") or ""
+            cd = c.get("description") or c.get("Description") or ""
+            ce = c.get("Length") or c.get("expires") or ""
+            line = f"- {cn}"
+            if cp:
+                line += f" ({cp})"
+            if cd:
+                line += f" — {cd[:120]}"
+            if ce:
+                line += f" — Speicherdauer: {ce}"
+            parts.append(line)
+
+    return "\n".join(parts)