nchammas commented on code in PR #58136: URL: https://github.com/apache/spark/pull/58136#discussion_r3816363790
########## dev/sparktestsupport/modules.py: ########## @@ -19,10 +19,88 @@ import itertools import os import re -from pathlib import Path +import sys +from pathlib import Path, PurePath all_modules = [] +# These are `pathlib.PurePath` glob-style patterns with some customization: +# - Bare patterns match a file name at any depth. +# - Leading slashes anchor at the repository root. +# - A trailing slash denotes an ignored directory subtree. +# See: https://docs.python.org/3/library/pathlib.html#pathlib.PurePath.match +# +# Rejected alternatives: +# - Regexes present a footgun in that `.` needs to be carefully escaped but +# often isn't. +# - `.gitignore`-style patterns would be ideal but don't have support in the +# standard library. +ignored_file_patterns = ( + ".asf.yaml", + ".gitignore", + "AGENTS.md", + "CONTRIBUTING.md", + "README.md", + "/LICENSE-binary", + "/NOTICE-binary", + "/scalastyle-config.xml", + "/SECURITY.md", Review Comment: I think these could be loosened to match the pattern anywhere in the path hierarchy. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
