tsi-org/tango

1# coding=utf-82# Copyright 2023 The HuggingFace Inc. team.3#4# Licensed under the Apache License, Version 2.0 (the "License");5# you may not use this file except in compliance with the License.6# You may obtain a copy of the License at7#8#     http://www.apache.org/licenses/LICENSE-2.09#10# Unless required by applicable law or agreed to in writing, software11# distributed under the License is distributed on an "AS IS" BASIS,12# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.13# See the License for the specific language governing permissions and14# limitations under the License.15 16# this script reports modified .py files under the desired list of top-level sub-dirs passed as a list of arguments, e.g.:17#   python ./utils/get_modified_files.py utils src tests examples18#19# it uses git to find the forking point and which files were modified - i.e. files not under git won't be considered20# since the output of this script is fed into Makefile commands it doesn't print a newline after the results21 22import re23import subprocess24import sys25 26 27fork_point_sha = subprocess.check_output("git merge-base main HEAD".split()).decode("utf-8")28modified_files = subprocess.check_output(f"git diff --name-only {fork_point_sha}".split()).decode("utf-8").split()29 30joined_dirs = "|".join(sys.argv[1:])31regex = re.compile(rf"^({joined_dirs}).*?\.py$")32 33relevant_modified_files = [x for x in modified_files if regex.match(x)]34print(" ".join(relevant_modified_files), end="")35