feat(dataflow): add OpenMetadata governance node + catalog edges + UI link

Data Flow graph now shows OpenMetadata as a governance node linked to all
sources and Trino (catalog edges); node inspector exposes an 'Open in
OpenMetadata' deep link and PII-columns-cataloged metric.
This commit is contained in:
mo
2026-06-27 02:43:22 +02:00
parent 3b247fa2bd
commit c70639c46d
3 changed files with 22 additions and 0 deletions
+8
View File
@@ -37,6 +37,8 @@ NODES: list[dict[str, Any]] = [
{"id": "iceberg_hadoop", "label": "Iceberg · hadoop", "sub": "historical_sales_hdfs", "kind": "lakehouse", "x": 72, "y": 60},
{"id": "iceberg_curated", "label": "Iceberg · curated_masked", "sub": "masked PII", "kind": "lakehouse", "x": 72, "y": 86},
{"id": "trino", "label": "Trino", "sub": "query engine", "kind": "engine", "x": 90, "y": 52},
{"id": "openmetadata", "label": "OpenMetadata", "sub": "catalog · lineage · PII", "kind": "governance",
"x": 50, "y": 92, "url": "http://10.0.21.47:8585"},
]
# Edges. movement_id (optional) links to movements.py so the edge is triggerable.
@@ -55,6 +57,10 @@ EDGES: list[dict[str, Any]] = [
{"from": "iceberg_hadoop", "to": "trino", "kind": "query"},
{"from": "iceberg_curated", "to": "trino", "kind": "query"},
{"from": "kafka", "to": "trino", "kind": "query"},
{"from": "postgres", "to": "openmetadata", "kind": "catalog"},
{"from": "mysql", "to": "openmetadata", "kind": "catalog"},
{"from": "mongodb", "to": "openmetadata", "kind": "catalog"},
{"from": "trino", "to": "openmetadata", "kind": "catalog"},
]
_cache: dict[str, Any] = {"ts": 0.0, "data": None}
@@ -121,6 +127,8 @@ def _build() -> dict[str, Any]:
node = dict(n)
node["level"] = "ok"
metric = None
if n["id"] == "openmetadata":
metric = f"{pii.get('summary', {}).get('pii_columns', 0)} PII cols cataloged"
if n["id"] == "kafka":
metric = f"{cdc.get('window_total', 0)} chg/15m · {cdc.get('consumed', 0)} total"
node["level"] = "ok" if cdc.get("connected") else "warn"