chore(openmetadata): add inventory probe; full-stack ingestion verified (177 tables, +Kafka/S3/Superset)

deploy/openmetadata/om_inventory.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+"""Report what OpenMetadata currently knows vs nothing — services, dbs, schemas, tables."""
+import om_api as o
+
+st, d = o.login("admin@open-metadata.org", "admin")
+tok = d["accessToken"]
+
+
+def g(p):
+    return o.req("GET", p, token=tok)[1]
+
+
+print("=== DATABASE SERVICES ===")
+s = g("/api/v1/services/databaseServices?limit=100")
+for sv in s.get("data", []):
+    name = sv["name"]
+    # tables under this service
+    t = g("/api/v1/tables?limit=1&service=" + name)
+    print("  %-22s type=%-12s tables=%s" % (name, sv.get("serviceType"), t.get("paging", {}).get("total")))
+print("  total services:", s.get("paging", {}).get("total"))
+
+print()
+for kind in ("messagingServices", "pipelineServices", "storageServices",
+             "dashboardServices", "mlmodelServices", "searchServices", "apiServices"):
+    s = g("/api/v1/services/" + kind + "?limit=100")
+    names = [sv["name"] for sv in s.get("data", [])]
+    print("%-20s total=%s %s" % (kind, s.get("paging", {}).get("total"), names))
+
+print()
+print("=== DATABASES / SCHEMAS per service ===")
+s = g("/api/v1/services/databaseServices?limit=100")
+for sv in s.get("data", []):
+    name = sv["name"]
+    dbs = g("/api/v1/databases?service=" + name + "&limit=100")
+    for db in dbs.get("data", []):
+        dbfqn = db["fullyQualifiedName"]
+        sch = g("/api/v1/databaseSchemas?database=" + dbfqn + "&limit=100")
+        schnames = [x["name"] for x in sch.get("data", [])]
+        print("  %s.%s  schemas=%s" % (name, db["name"], schnames))
+
+print()
+print("=== TABLES total:", g("/api/v1/tables?limit=1").get("paging", {}).get("total"))