uranusjr commented on code in PR #73118:
URL: https://github.com/apache/airflow/pull/73118#discussion_r4024207851
##########
task-sdk/src/airflow/sdk/importers/python_importer.py:
##########
@@ -56,12 +65,60 @@
log = logging.getLogger(__name__)
-class PythonDagImporter(AbstractDagImporter):
+class _DefinitionSourceLoader(importlib.abc.SourceLoader):
+ """
+ A SourceLoader that executes a DagDefinition straight from its bytes.
+
+ It needs no file on disk: :meth:`.get_data`` returns the definition's
+ source, and :meth:`get_filename` reports the definition's repr, so
+ ``__file__`` and tracebacks stay meaningful.
+
+ Bytecode caching is left disabled (the inherited ``path_stats`` raises
+ ``OSError``) since it's not particularly useful in dag processors.
+ """
+
+ def __init__(self, definition: DagDefinition) -> None:
+ self._definition = definition
+
+ def get_filename(self, fullname: str) -> str:
+ return repr(self._definition)
+
+ def get_data(self, path: str) -> bytes:
+ return self._definition.read_bytes()
+
+
+class _DefinitionBytecodeLoader(importlib.abc.Loader):
"""
- Importer for Python DAG files.
+ Execute a definition's compiled bytecode (``.pyc``) straight from its
bytes.
- This is the default importer registered with the DagImporterRegistry. It
handles
- .py files containing Python DAGs.
+ The bytes-based counterpart of
:class:`importlib.machinery.SourcelessFileLoader`
+ (which is file-backed); reading through the definition keeps archive
members from
+ being extracted just to run them.
+ """
+
+ def __init__(self, definition: DagDefinition) -> None:
+ self._definition = definition
+
+ def get_filename(self, fullname: str) -> str:
+ return repr(self._definition)
+
+ def get_code(self, fullname: str) -> Any:
+ data = self._definition.read_bytes()
+ if len(data) < 16 or data[:4] != importlib.util.MAGIC_NUMBER:
Review Comment:
Fixed with an additional check. (Also with test case added.)
--
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]
