sync

apps/api/app/cli.py

@@ -8,10 +8,10 @@ from dataclasses import asdict
 from .config import settings
 from .database import SessionLocal
 from .importer import import_records
-from .community_importer import stage_observations
+from .community_importer import stage_observations, update_waterbody_detail, update_waterbody_details, upsert_waterbody_catalog
 from .retention import RetentionPolicy, apply_retention
 from .storage import delete_screenshot
-from .catalog_audit import audit_catalog
+from .catalog_audit import audit_catalog, audit_waterbody_catalog
 from .community_scheduler import run_source, configured_sources
 
 # Static registry for argparse choices — no DB required for --help
@@ -34,11 +34,20 @@ def main() -> int:
     community = sub.add_parser("stage-community-json")
     community.add_argument("--input", default="-", help="JSON array path or - for stdin")
     community.add_argument("--limit", type=int, default=500)
+    waterbodies = sub.add_parser("import-waterbody-catalog")
+    waterbodies.add_argument("--input", required=True, help="JSON snapshot path or - for stdin")
+    waterbodies.add_argument("--limit", type=int, default=100)
+    detail = sub.add_parser("import-waterbody-detail")
+    detail.add_argument("--input", required=True, help="JSON detail snapshot path")
+    details = sub.add_parser("import-waterbody-details")
+    details.add_argument("--input", required=True, help="JSON array of detail snapshots")
     fetch_community = sub.add_parser("fetch-community")
     fetch_community.add_argument("source", choices=STATIC_SOURCE_CHOICES)
     cleanup = sub.add_parser("cleanup-retention")
     cleanup.add_argument("--apply", action="store_true", help="apply changes; default is dry-run")
     sub.add_parser("audit-catalog")
+    waterbody_audit = sub.add_parser("audit-waterbody-catalog")
+    waterbody_audit.add_argument("--input", required=True, help="JSON snapshot path")
     args = parser.parse_args()
     with SessionLocal() as session:
         if args.command == "import-records":
@@ -57,6 +66,43 @@ def main() -> int:
                 parser.error("input must be a JSON array")
             created, updated = stage_observations(session, payload[:args.limit])
             print(f"staged: created={created} updated={updated}")
+        elif args.command == "import-waterbody-catalog":
+            if not 1 <= args.limit <= 500:
+                parser.error("--limit must be between 1 and 500")
+            stream = sys.stdin if args.input == "-" else open(args.input, encoding="utf-8")
+            try:
+                snapshot = json.load(stream)
+            finally:
+                if stream is not sys.stdin:
+                    stream.close()
+            if isinstance(snapshot, dict):
+                payload = snapshot.get("items")
+                source_system = snapshot.get("source_system")
+                if isinstance(payload, list) and isinstance(source_system, str):
+                    payload = [
+                        {"source_system": source_system, **item}
+                        for item in payload if isinstance(item, dict)
+                    ]
+            else:
+                payload = snapshot
+            if not isinstance(payload, list):
+                parser.error("input must be a JSON array or an object with an items array")
+            created, updated = upsert_waterbody_catalog(session, payload[:args.limit])
+            print(f"waterbodies: created={created} updated={updated}")
+        elif args.command == "import-waterbody-detail":
+            with open(args.input, encoding="utf-8") as stream:
+                payload = json.load(stream)
+            if not isinstance(payload, dict):
+                parser.error("input must be a JSON object")
+            update_waterbody_detail(session, payload)
+            print(f"waterbody detail: updated={payload.get('source_external_id', 'unknown')}")
+        elif args.command == "import-waterbody-details":
+            with open(args.input, encoding="utf-8") as stream:
+                payload = json.load(stream)
+            if not isinstance(payload, list):
+                parser.error("input must be a JSON array")
+            created, updated = update_waterbody_details(session, payload)
+            print(f"waterbody details: created={created} updated={updated}")
         elif args.command == "fetch-community":
             # A09: Verify source is enabled at runtime (not just in static choices)
             enabled = configured_sources()
@@ -76,6 +122,24 @@ def main() -> int:
             )
             counts = apply_retention(session, policy=policy, dry_run=not args.apply, delete_object=delete_screenshot)
             print(json.dumps({"mode": "apply" if args.apply else "dry-run", "policy": asdict(policy), "counts": counts}, ensure_ascii=False))
+        elif args.command == "audit-waterbody-catalog":
+            stream = sys.stdin if args.input == "-" else open(args.input, encoding="utf-8")
+            try:
+                snapshot = json.load(stream)
+            finally:
+                if stream is not sys.stdin:
+                    stream.close()
+            items = snapshot.get("items") if isinstance(snapshot, dict) else snapshot
+            if not isinstance(items, list):
+                parser.error("input must be a JSON array or an object with an items array")
+            expected_ids = {
+                str(item["source_external_id"])
+                for item in items
+                if isinstance(item, dict) and item.get("source_external_id")
+            }
+            result = audit_waterbody_catalog(session, expected_ids)
+            print(json.dumps(result, ensure_ascii=False))
+            return 1 if result["failures"] else 0
         else:
             result = audit_catalog(session)
             print(json.dumps(result, ensure_ascii=False))