You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by GitBox <gi...@apache.org> on 2019/11/18 09:13:26 UTC
[GitHub] [airflow] bolkedebruin commented on a change in pull request #6564:
[AIRFLOW-5911] Simplify lineage API and improve robustness
bolkedebruin commented on a change in pull request #6564: [AIRFLOW-5911] Simplify lineage API and improve robustness
URL: https://github.com/apache/airflow/pull/6564#discussion_r347265086
##########
File path: airflow/lineage/__init__.py
##########
@@ -92,51 +115,43 @@ def prepare_lineage(func):
* "auto" -> picks up any outlets from direct upstream tasks that have outlets defined, as such that
if A -> B -> C and B does not have outlets but A does, these are provided as inlets.
* "list of task_ids" -> picks up outlets from the upstream task_ids
- * "list of datasets" -> manually defined list of DataSet
+ * "list of datasets" -> manually defined list of data
"""
@wraps(func)
def wrapper(self, context, *args, **kwargs):
self.log.debug("Preparing lineage inlets and outlets")
- task_ids = set(self._inlets['task_ids']).intersection( # pylint:disable=protected-access
- self.get_flat_relative_ids(upstream=True)
- )
- if task_ids:
- inlets = self.xcom_pull(context,
- task_ids=task_ids,
- dag_id=self.dag_id,
- key=PIPELINE_OUTLETS)
- inlets = [item for sublist in inlets if sublist for item in sublist]
- inlets = [DataSet.map_type(i['typeName'])(data=i['attributes'])
- for i in inlets]
- self.inlets.extend(inlets)
+ if isinstance(self._inlets, str):
+ self._inlets = [self._inlets, ]
+
+ if isinstance(self._inlets, list):
+ task_ids = set(
+ filter(lambda x: isinstance(x, str) and x != AUTO, self._inlets)
+ ).intersection(self.get_flat_relative_ids(upstream=True))
- if self._inlets['auto']: # pylint:disable=protected-access
- # dont append twice
- task_ids = set(self._inlets['task_ids']).symmetric_difference( # pylint:disable=protected-access
- self.upstream_task_ids
- )
- inlets = self.xcom_pull(context,
- task_ids=task_ids,
- dag_id=self.dag_id,
- key=PIPELINE_OUTLETS)
- inlets = [item for sublist in inlets if sublist for item in sublist]
- inlets = [DataSet.map_type(i['typeName'])(data=i['attributes'])
- for i in inlets]
+ if 'auto' in self._inlets:
+ task_ids = task_ids.union(task_ids.symmetric_difference(self.upstream_task_ids))
+
+ inlets = self.xcom_pull(context, task_ids=task_ids,
+ dag_id=self.dag_id, key=PIPELINE_OUTLETS)
+ inlets = [_get_instance(item) for sublist in inlets if sublist for item in sublist]
self.inlets.extend(inlets)
- if self._inlets['datasets']: # pylint:disable=protected-access
- self.inlets.extend(self._inlets['datasets']) # pylint:disable=protected-access
+ self.inlets.extend([_get_instance(_as_rendered_dict(i, context))
+ for i in self._inlets if isinstance(i, Dataset)])
+ elif self._inlets:
+ raise AttributeError("inlets is not a list or a string")
- # outlets
- if self._outlets['datasets']: # pylint:disable=protected-access
- self.outlets.extend(self._outlets['datasets']) # pylint:disable=protected-access
+ if not isinstance(self._outlets, list):
+ self._outlets = [self._outlets, ]
- self.log.debug("inlets: %s, outlets: %s", self.inlets, self.outlets)
+ self.outlets.extend(list(filter(lambda x: isinstance(x, Dataset), self._outlets)))
- for dataset in chain(self.inlets, self.outlets):
- dataset.set_context(context)
+ self.outlets = [_get_instance(_as_rendered_dict(i, context))
Review comment:
Oh let me try that. Didnt think about it
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services