ashb commented on code in PR #25972:
URL: https://github.com/apache/airflow/pull/25972#discussion_r958623252
##########
airflow/models/dataset.py:
##########
@@ -100,6 +98,55 @@ def __hash__(self):
def __repr__(self):
return f"{self.__class__.__name__}(uri={self.uri!r},
extra={self.extra!r})"
+ @property
+ def canonical_uri(self):
+ """
+ Resolve the canonical uri for a dataset.
+
+ If the uri doesn't have an `airflow` scheme, return it as-is.
+
+ If it does have an `airflow` scheme, it takes the connection id from
+ the netloc. It then will combine the connection uri and dataset uri to
+ form the canonical uri. It does this by:
+
+ * Using the scheme from the connection, unless an override is provided
+ in the dataset scheme (e.g. airflow+override://)
+ * Combine the path, connection first followed by the dataset path
+ * Merge the query args
+
+ # airflow://conn_id/...
+ # airflow+override://conn_id/...
+ # airflow://conn_id/some_extra_path?query
+ """
+ parsed = urlparse(self.uri)
+
+ if not parsed.scheme.startswith("airflow"):
+ return self.uri
+
+ conn_id = parsed.hostname
+ conn =
urlparse(Connection.get_connection_from_secrets(conn_id).get_uri())
Review Comment:
Oh https://github.com/apache/airflow/pull/25972/files#r958616778
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
