ephraimbuddy commented on code in PR #68518:
URL: https://github.com/apache/airflow/pull/68518#discussion_r3704651444
##########
airflow-core/src/airflow/dag_processing/manager.py:
##########
@@ -944,7 +965,10 @@ def find_zipped_dags(abs_path: os.PathLike) ->
Iterator[str]:
try:
with zipfile.ZipFile(abs_path) as z:
for info in z.infolist():
- if might_contain_dag(info.filename, True, z):
+ # Must use the same safe_mode as discovery/parsing:
with a hardcoded True a
+ # keyword-less zip member parsed under safe_mode=False
would be absent here and
+ # then deactivated immediately after being parsed
(issue #66104).
Review Comment:
Remove issue number and make this comment really short e.g use configured
discovery safe mode
##########
airflow-core/src/airflow/dag_processing/manager.py:
##########
@@ -925,8 +935,19 @@ def _find_files_in_bundle(self, bundle: BaseDagBundle) ->
list[Path]:
"""Get relative paths for dag files from bundle dir."""
# Build up a list of Python files that could contain DAGs
self.log.info("Searching for files in %s at %s", bundle.name,
bundle.path)
- rel_paths = [Path(x).relative_to(bundle.path) for x in
list_py_file_paths(bundle.path)]
- self.log.info("Found %s files for bundle %s", len(rel_paths),
bundle.name)
+ rel_paths = [
+ Path(x).relative_to(bundle.path)
+ for x in list_py_file_paths(bundle.path,
safe_mode=self.dag_discovery_safe_mode)
+ ]
+ # Logging the effective safe_mode makes a misconfigured dag-processor
diagnosable: a
+ # component left at the default safe_mode=True silently skips
keyword-less files even
+ # when the deployment set core.dag_discovery_safe_mode=False elsewhere
(issue #66104).
Review Comment:
```suggestion
```
User facing comments, not necessary in code. The below logging is enough
##########
airflow-core/src/airflow/dag_processing/manager.py:
##########
@@ -299,6 +299,16 @@ class DagFileProcessorManager(LoggingMixin):
factory=_config_get_factory("dag_processor", "file_parsing_sort_mode")
)
+ dag_discovery_safe_mode: bool = attrs.field(
+ factory=_config_bool_factory("core", "DAG_DISCOVERY_SAFE_MODE")
+ )
+ """Resolved once per process so file discovery and the deactivation scan
use the same value.
+
+ When ``False`` the keyword heuristic is bypassed and every Python file is
scanned -- this must
+ apply consistently to discovery (:meth:`_find_files_in_bundle`) and to the
set of observed
+ filelocs (:meth:`_get_observed_filelocs`); otherwise freshly-parsed
keyword-less Dags are
+ deactivated right after being parsed (issue #66104)."""
Review Comment:
```suggestion
"""Resolved once per process so file discovery and the deactivation scan
use the same value."""
```
This should just be one line comment
##########
airflow-core/tests/unit/dag_processing/test_manager.py:
##########
@@ -157,6 +157,41 @@ def
_create_zip_bundle_with_valid_and_broken_dags(zip_path: Path) -> None:
)
+def _create_zip_bundle_with_keywordless_dag(zip_path: Path) -> None:
+ """Build a zip with one keyword-bearing member and one keyword-less
("wrapped") member.
+
+ ``with_keywords.py`` contains the ``airflow``/``dag`` strings the
safe-mode heuristic looks
+ for. ``no_keywords.py`` mimics a custom wrapper whose source contains
neither ``airflow`` nor
+ ``dag``/``asset`` -- exactly the case ``dag_discovery_safe_mode=False``
exists to support
+ (issue #66104).
Review Comment:
Issue numbers shouldn't be in codes except if it's a todo
--
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]
