ashb commented on a change in pull request #8962:
URL: https://github.com/apache/airflow/pull/8962#discussion_r439361771
##########
File path: airflow/operators/python.py
##########
@@ -145,6 +149,145 @@ 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 op_kwargs: a dictionary of keyword arguments that will get unpacked
+ in your function (templated)
+ :type op_kwargs: dict
+ :param op_args: a list of positional arguments that will get unpacked when
+ calling your callable (templated)
+ :type op_args: list
+ :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 = PythonOperator.ui_color
+
+ # 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,
+ task_id: str,
+ op_args: Tuple[Any],
+ op_kwargs: Dict[str, Any],
+ multiple_outputs: bool = False,
+ **kwargs
+ ) -> None:
+ kwargs['task_id'] = self._get_unique_task_id(task_id,
kwargs.get('dag', None))
+ super().__init__(**kwargs)
+ self.python_callable = python_callable
+
+ # Check that arguments can be binded
+ signature(python_callable).bind(*op_args, **op_kwargs)
+ self.multiple_outputs = multiple_outputs
+ self.op_args = op_args
+ self.op_kwargs = op_kwargs
+
+ @staticmethod
+ def _get_unique_task_id(task_id: str, dag: Optional[DAG] = None) -> str:
+ """
+ Generate unique task id given a DAG (or if run in a DAG context)
+ Ids are generated by appending a unique number to the end of
+ the original task id.
+
+ Example:
+ task_id
+ task_id__1
+ task_id__2
+ ...
+ task_id__20
+ """
+ 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):
+ """
+ Validate that python callable can be wrapped by operator.
+ Raises exception if invalid.
+
+ :param python_callable: Python object to be validated
+ :raises: TypeError, AirflowException
+ """
+ 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 execute(self, context: Dict):
+ return_value = self.python_callable(*self.op_args, **self.op_kwargs)
+ self.log.debug("Done. Returned value was: %s", return_value)
+ if not self.multiple_outputs:
+ return return_value
+ if isinstance(return_value, dict):
+ for key in return_value.keys():
+ if not isinstance(key, str):
+ raise AirflowException('Returned dictionary keys must be
strings when using '
+ f'multiple_outputs, found {key}
({type(key)}) instead')
+ for key, value in return_value.items():
+ self.xcom_push(context, key, value)
+ else:
+ raise AirflowException(f'Returned output was type
{type(return_value)} expected dictionary '
+ 'for multiple_outputs')
+ return return_value
+
+
+def task(python_callable: Optional[Callable] = None, multiple_outputs: bool =
False, **kwargs):
+ """
+ Python operator decorator. Wraps a function into an Airflow operator.
+ Accepts kwargs for operator kwarg. Can be reused in a single DAG.
+
+ :param python_callable: Function to decorate
+ :type python_callable: Optional[Callable]
+ :param multiple_outputs: if set, function return value will be
+ unrolled to multiple XCom values. List/Tuples will unroll to xcom
values
+ with index as key. Dict will unroll to xcom values with keys as XCom
keys.
+ Defaults to False.
+ :type multiple_outputs: bool
+
+ """
+ def wrapper(f):
+ """
+ Python wrapper to generate PythonFunctionalOperator out of simple
python functions.
+ Used for Airflow functional interface
+ """
+ _PythonFunctionalOperator.validate_python_callable(f)
+ kwargs['task_id'] = kwargs.get('task_id', None) or f.__name__
Review comment:
Unimportant change but:
```suggestion
kwargs.setdefault('task_id', f.__name__)
```
----------------------------------------------------------------
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:
[email protected]
