feat(table-catalog): expose backing migration contract (#3574)

* feat(table-catalog): expose backing migration contract

* fix(table-catalog): require register auth for external sync

---------

Co-authored-by: Henry Guo <marshawcoco@users.noreply.github.com>
This commit is contained in:
Henry Guo
2026-06-18 21:14:40 +08:00
committed by GitHub
parent 7b0cb9e725
commit 5d9fee5c0c
5 changed files with 437 additions and 1 deletions
+4
View File
@@ -125,6 +125,7 @@ PyIceberg, PyArrow, or boto3:
python3 scripts/table-catalog/pyiceberg_smoke.py --print-client-matrix
python3 scripts/table-catalog/pyiceberg_smoke.py --print-vendor-profiles
python3 scripts/table-catalog/pyiceberg_smoke.py --print-unsupported-inventory
python3 scripts/table-catalog/pyiceberg_smoke.py --print-production-readiness
```
Use these outputs when updating release notes, PR descriptions, or follow-up
@@ -143,6 +144,9 @@ The smoke test also probes catalog-backed advanced Iceberg surfaces:
execution checks
- catalog diagnostics exposes the table recovery and consistency state used by
operators
- catalog export and diagnostics expose the current catalog backing manifest,
recoverable commit-log WAL state, strong backing migration target, single
active writer HA policy, and scale validation matrix
## Client Matrix
+30
View File
@@ -178,6 +178,24 @@ UNSUPPORTED_INVENTORY: list[dict[str, str]] = [
},
]
PRODUCTION_READINESS_INVENTORY: list[dict[str, str]] = [
{
"capability": "strong-catalog-backing",
"status": "migration-contract-supported",
"validation": "catalog export and diagnostics expose an object-backed manifest, recoverable commit-log WAL state, strong-kv-wal migration target, required migration steps, and recovery blockers before cutover",
},
{
"capability": "single-active-writer-ha",
"status": "policy-published",
"validation": "diagnostics publish single-active-writer-region semantics, linearizable leader-read requirements for commits, read-only replica limits, and explicit no active-active support",
},
{
"capability": "scale-validation-matrix",
"status": "matrix-published",
"validation": "required validation scenarios are machine-readable: concurrent commit CAS, commit-log recovery replay, migration snapshot replay, stale replica read guards, and long-running client conformance",
},
]
@dataclass(frozen=True)
class RuntimeDeps:
@@ -225,6 +243,10 @@ def unsupported_inventory() -> list[dict[str, str]]:
return [entry.copy() for entry in UNSUPPORTED_INVENTORY]
def production_readiness_inventory() -> list[dict[str, str]]:
return [entry.copy() for entry in PRODUCTION_READINESS_INVENTORY]
def normalized_rest_path(rest_path: str) -> str:
stripped = rest_path.strip()
if not stripped:
@@ -278,6 +300,11 @@ def parse_args() -> argparse.Namespace:
parser.add_argument("--print-client-matrix", action="store_true", help="Print the current client conformance matrix as JSON and exit.")
parser.add_argument("--print-vendor-profiles", action="store_true", help="Print vendor connection profile references as JSON and exit.")
parser.add_argument("--print-unsupported-inventory", action="store_true", help="Print unsupported capability inventory as JSON and exit.")
parser.add_argument(
"--print-production-readiness",
action="store_true",
help="Print catalog backing, HA, and scale-readiness inventory as JSON and exit.",
)
return apply_profile_defaults(parser.parse_args())
@@ -700,6 +727,9 @@ def printed_metadata(args: argparse.Namespace) -> bool:
if args.print_unsupported_inventory:
print_json_document({"unsupported_inventory": unsupported_inventory()})
printed = True
if args.print_production_readiness:
print_json_document({"production_readiness": production_readiness_inventory()})
printed = True
return printed
@@ -753,11 +753,25 @@ class PyIcebergSmokeConfigTest(unittest.TestCase):
self.assertIn("status", entry)
self.assertIn("roadmap_area", entry)
def test_production_readiness_inventory_tracks_catalog_backing(self) -> None:
inventory = pyiceberg_smoke.production_readiness_inventory()
capabilities = {entry["capability"] for entry in inventory}
self.assertIn("strong-catalog-backing", capabilities)
self.assertIn("single-active-writer-ha", capabilities)
self.assertIn("scale-validation-matrix", capabilities)
strong_backing = next(entry for entry in inventory if entry["capability"] == "strong-catalog-backing")
self.assertEqual(strong_backing["status"], "migration-contract-supported")
for entry in inventory:
self.assertIn("status", entry)
self.assertIn("validation", entry)
def test_published_table_catalog_docs_do_not_use_internal_roadmap_labels(self) -> None:
readme = (SCRIPT_DIR / "README.md").read_text(encoding="utf-8")
self.assertIsNone(INTERNAL_ROADMAP_LABEL_RE.search(readme))
self.assertIsNone(INTERNAL_ROADMAP_LABEL_RE.search(str(pyiceberg_smoke.unsupported_inventory())))
self.assertIsNone(INTERNAL_ROADMAP_LABEL_RE.search(str(pyiceberg_smoke.production_readiness_inventory())))
if __name__ == "__main__":