feat: add hub runtime and extension contract

hub_core/runtime/validation.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import json
+from typing import Any
+
+from jsonschema import Draft202012Validator, FormatChecker
+
+from hub_core.contracts import extension_contract_root
+from hub_core.runtime.models import RegistryRegistration
+
+
+class ContractValidator:
+    """Validate runtime registration input against the packaged contract."""
+
+    def __init__(self) -> None:
+        contract_root = extension_contract_root()
+        schema_root = contract_root.joinpath("schemas")
+        self._descriptor = _validator(schema_root.joinpath("hub-descriptor.schema.json"))
+        self._manifest = _validator(schema_root.joinpath("hub-manifest.schema.json"))
+        catalog = json.loads(
+            contract_root.joinpath("catalogs", "event-types.json").read_text(encoding="utf-8")
+        )
+        self._event_families = {
+            entry["type"]: entry["family"] for entry in catalog["event_types"]
+        }
+
+    def validate_registration(self, registration: RegistryRegistration) -> None:
+        self._descriptor.validate(registration.descriptor)
+        self._manifest.validate(registration.manifest)
+        descriptor_id = registration.descriptor.get("reuse_surface_id")
+        manifest_id = registration.manifest.get("reuse_surface_id")
+        if descriptor_id != manifest_id:
+            raise ValueError("descriptor and manifest reuse_surface_id must match")
+
+    def validate_event_family(self, event_type: str, expected_family: str) -> None:
+        actual_family = self._event_families.get(event_type)
+        if actual_family is None:
+            raise ValueError(f"event type '{event_type}' is not cataloged")
+        if actual_family != expected_family:
+            raise ValueError(
+                f"event type '{event_type}' belongs to '{actual_family}', not '{expected_family}'"
+            )
+
+
+def _validator(resource: Any) -> Draft202012Validator:
+    schema = json.loads(resource.read_text(encoding="utf-8"))
+    Draft202012Validator.check_schema(schema)
+    return Draft202012Validator(schema, format_checker=FormatChecker())