Non-UTF-8 extension catalog aborts the whole merge #5195

 4690  
 4691          Returns:
 4692              URL of the primary catalog
 4693  
 4694          Raises:
 4695              ValidationError: If a catalog URL is invalid
 4696          """
 4697          active = self.get_active_catalogs()
 4698          return active[0].url if active else self.DEFAULT_CATALOG_URL
 4699  
 4700      def _fetch_single_catalog(
 4701          self, entry: CatalogEntry, force_refresh: bool = False
 4702      ) -> Dict[str, Any]:
 4703          """Fetch a single catalog with per-URL caching.
 4704  
 4705          For the DEFAULT_CATALOG_URL, uses legacy cache files (self.cache_file /
 4706          self.cache_metadata_file) for backward compatibility. For all other URLs,
 4707          uses URL-hash-based cache files in self.cache_dir.
 4708  
 4709          Args:
 4710              entry: CatalogEntry describing the catalog to fetch
 4711              force_refresh: If True, bypass cache
 4712  
 4713          Returns:
 4714              Catalog data dictionary
 4715  
 4716          Raises:
 4717              ExtensionError: If catalog cannot be fetched or has invalid format
 4718          """
 4719          import urllib.error
 4720  
 4721          # Determine cache file paths (backward compat for default catalog)
 4722          if entry.url == self.DEFAULT_CATALOG_URL:
 4723              cache_file = self.cache_file
 4724              cache_meta_file = self.cache_metadata_file
 4725              is_valid = not force_refresh and self.is_cache_valid()
 4726          else:
 4727              url_hash = hashlib.sha256(entry.url.encode()).hexdigest()[:16]
 4728              cache_file = self.cache_dir / f"catalog-{url_hash}.json"
 4729              cache_meta_file = self.cache_dir / f"catalog-{url_hash}-metadata.json"
 4730              is_valid = False
 4731              if not force_refresh and cache_file.exists() and cache_meta_file.exists():
 4732                  try:
 4733                      metadata = json.loads(cache_meta_file.read_text(encoding="utf-8"))
 4734                      cached_at = datetime.fromisoformat(metadata.get("cached_at", ""))
 4735                      if cached_at.tzinfo is None:
 4736                          cached_at = cached_at.replace(tzinfo=timezone.utc)
 4737                      age = (datetime.now(timezone.utc) - cached_at).total_seconds()
 4738                      is_valid = age < self.CACHE_DURATION
 4739                  except (
 4740                      json.JSONDecodeError,
 4741                      OSError,
 4742                      UnicodeError,
 4743                      ValueError,
 4744                      KeyError,
 4745                      TypeError,
 4746                      AttributeError,
 4747                  ):
 4748                      # Cache validity is best-effort: invalid/missing metadata
 4749                      # fields, an unreadable metadata file (permissions / disk),
 4750                      # a wrongly-encoded metadata file (written by a tool using