diff --git a/dev/sparktestsupport/utils.py b/dev/sparktestsupport/utils.py index a66c0e70cb56..b969b96a16c5 100755 --- a/dev/sparktestsupport/utils.py +++ b/dev/sparktestsupport/utils.py @@ -34,7 +34,7 @@ def determine_modules_for_files(filenames): Given a list of filenames, return the set of modules that contain those files. If a file is not associated with a more specific submodule, then this method will consider that file to belong to the 'root' module. `.github` directory is counted only in GitHub Actions, - and `README.md` is always ignored. + and `README.md`, `AGENTS.md`, `CONTRIBUTING.md` are always ignored. >>> sorted(x.name for x in determine_modules_for_files(["python/pyspark/a.py", "sql/core/foo"])) ['pyspark-core', 'pyspark-errors', 'sql'] @@ -42,10 +42,14 @@ def determine_modules_for_files(filenames): ['root'] >>> [x.name for x in determine_modules_for_files(["sql/README.md"])] [] + >>> [x.name for x in determine_modules_for_files(["AGENTS.md"])] + [] + >>> [x.name for x in determine_modules_for_files(["CONTRIBUTING.md"])] + [] """ changed_modules = set() for filename in filenames: - if filename.endswith("README.md"): + if filename.endswith(("README.md", "AGENTS.md", "CONTRIBUTING.md")): continue if filename in ( "scalastyle-config.xml",