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 +1,69 @@
+"""BMW Group ePaaS (Enterprise Privacy as a Service).
+
+URL: /epaas/prod/policypage/<tenant>/<config>/<locale>.epaas.json
+Schema: policyPageMetadata + categories + providers
+"""
+
+import re
+
+MATCHER = re.compile(r"/epaas/prod/policypage/.+\.epaas\.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;", "&")
+               .replace("&lt;", "<").replace("&gt;", ">")
+               .replace("&quot;", '"').replace("&#39;", "'"))
+    return _WS_RE.sub(" ", no_tags).strip()
+
+
+def reconstruct(d: dict) -> str:
+    meta = d.get("policyPageMetadata", {}) or {}
+    parts: list[str] = ["# Cookie-Richtlinie"]
+
+    for key in ("heading", "subHeading", "prologue", "dataController", "epilogue"):
+        val = meta.get(key)
+        if val:
+            parts.append("")
+            parts.append(_clean(str(val)))
+
+    cats = d.get("categories", []) or []
+    if cats:
+        parts.append("")
+        parts.append("## Cookie-Kategorien")
+        for c in cats:
+            name = c.get("name") or c.get("id") or ""
+            desc = c.get("description") or c.get("descriptionHtml") or ""
+            parts.append("")
+            parts.append(f"### {name}")
+            parts.append(_clean(str(desc)))
+
+    providers = d.get("providers", []) or []
+    if providers:
+        parts.append("")
+        parts.append(f"## Anbieter ({len(providers)})")
+        for p in providers:
+            name = p.get("name") or p.get("id") or ""
+            purpose = (p.get("purpose") or "").strip()
+            country = (p.get("country") or "").strip()
+            persistence = (p.get("persistencePurposeDescription") or "").strip()
+            line = f"- {name}"
+            if purpose:
+                line += f" — Zweck: {purpose}"
+            if country:
+                line += f" — Sitz: {country}"
+            if persistence:
+                line += f" — Speicherdauer: {persistence[:120]}"
+            parts.append(line)
+
+    if meta.get("expiresAfter"):
+        parts.append("")
+        parts.append(f"Speicherdauer: {meta['expiresAfter']}")
+    if meta.get("persistencePurposeText"):
+        parts.append(_clean(str(meta["persistencePurposeText"])))
+
+    return "\n".join(parts)