evgenyshulman commented on a change in pull request #8962:
URL: https://github.com/apache/airflow/pull/8962#discussion_r429893722
##########
File path: airflow/operators/python.py
##########
@@ -145,6 +148,144 @@ def execute_callable(self):
return self.python_callable(*self.op_args, **self.op_kwargs)
+class _PythonFunctionalOperator(BaseOperator):
+ """
+ Wraps a Python callable and captures args/kwargs when called for execution.
+
+ :param python_callable: A reference to an object that is callable
+ :type python_callable: python callable
+ :param multiple_outputs: if set, function return value will be
+ unrolled to multiple XCom values. Dict will unroll to xcom values with
keys as keys.
+ Defaults to False.
+ :type multiple_outputs: bool
+ """
+
+ template_fields = ('_op_args', '_op_kwargs')
+ ui_color = '#ffefeb'
+
+ # since we won't mutate the arguments, we should just do the shallow copy
+ # there are some cases we can't deepcopy the objects(e.g protobuf).
+ shallow_copy_attrs = ('python_callable',)
+
+ @apply_defaults
+ def __init__(
+ self,
+ python_callable: Callable,
+ multiple_outputs: bool = False,
+ *args,
+ **kwargs
+ ) -> None:
+ self._validate_python_callable(python_callable)
+ super().__init__(*args, **kwargs)
+ self.python_callable = python_callable
+ self.multiple_outputs = multiple_outputs
+ self._kwargs = kwargs
+ self._op_args: List[Any] = []
+ self._called = False
+ self._op_kwargs: Dict[str, Any] = {}
+
+ @staticmethod
+ def _get_unique_task_id(task_id: str, dag: Optional[DAG]) -> str:
+ dag = dag or DagContext.get_current_dag()
+ if not dag or task_id not in dag.task_ids:
+ return task_id
+ core = re.split(r'__\d+$', task_id)[0]
+ suffixes = sorted(
+ [int(re.split(r'^.+__', task_id)[1])
+ for task_id in dag.task_ids
+ if re.match(rf'^{core}__\d+$', task_id)]
+ )
+ if not suffixes:
+ return f'{core}__1'
+ return f'{core}__{suffixes[-1] + 1}'
+
+ @staticmethod
+ def _validate_python_callable(python_callable):
+ if not callable(python_callable):
+ raise TypeError('`python_callable` param must be callable')
+ if 'self' in signature(python_callable).parameters.keys():
+ raise AirflowException('@task does not support methods')
+
+ def __call__(self, *args, **kwargs):
+ # If args/kwargs are set, then operator has been called. Raise
exception
+ if self._called:
+ raise AirflowException('@task decorated functions can only be
called once. If you need to reuse '
+ 'it several times in a DAG, use the `copy`
method.')
+
+ # If we have no DAG, reinitialize class to capture DAGContext and DAG
default args.
+ if not self.has_dag():
+ self.__init__(python_callable=self.python_callable,
+ multiple_outputs=self.multiple_outputs,
+ **self._kwargs)
+
+ # Capture args/kwargs
+ self._op_args = args
+ self._op_kwargs = kwargs
+ self._called = True
+ return XComArg(self)
+
+ def copy(self, task_id: Optional[str] = None, **kwargs):
+ """
+ Create a copy of the task, allow to overwrite ctor kwargs if needed.
+
+ If alias is created a new DAGContext, apply defaults and set new DAG
as the operator DAG.
+
+ :param task_id: Task id for the new operator
+ :type task_id: Optional[str]
+ """
+ _old_kwargs = self._kwargs
+ if task_id:
+ _old_kwargs['task_id'] = task_id
Review comment:
[minor] there is a side affect on self._kwargs, it doesn't break
anything now but can lead to problems in the future.
----------------------------------------------------------------
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:
us...@infra.apache.org
