Skip to content

Properly support multiple submodules in git packager #154

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
titu1994 merged 1 commit into from
Feb 15, 2025
Merged

Properly support multiple submodules in git packager #154

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion src/nemo_run/core/packaging/git.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,8 +120,14 @@ def package(self, path: Path, job_dir: str, name: str) -> str:
git_archive_cmd = (
f"git archive --format=tar --output={output_file}.tmp {self.ref}:{git_sub_path}"
)
if os.uname().sysname == "Linux":
tar_submodule_cmd = f"tar Af {output_file}.tmp $sha1.tmp && rm $sha1.tmp"
else:
tar_submodule_cmd = f"cat $sha1.tmp >> {output_file}.tmp && rm $sha1.tmp"

git_submodule_cmd = f"""git submodule foreach --recursive \
'git archive --format=tar --prefix=$sm_path/ --output=$sha1.tmp HEAD && cat $sha1.tmp >> {output_file}.tmp && rm $sha1.tmp'"""
'git archive --format=tar --prefix=$sm_path/ --output=$sha1.tmp HEAD && {tar_submodule_cmd}'"""

with ctx.cd(git_base_path):
ctx.run(git_archive_cmd)
if self.include_submodules:
Expand Down
24 changes: 22 additions & 2 deletions test/core/packaging/test_git.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,17 +342,28 @@
@patch("nemo_run.core.packaging.git.Context", MockContext)
def test_package_with_include_submodules(packager, temp_repo):
temp_repo = Path(temp_repo)
# Create a submodule
# Create first submodule
submodule_path = temp_repo / "submodule"
submodule_path.mkdir()
os.chdir(str(submodule_path))
subprocess.check_call(["git", "init", "--initial-branch=main"])
open("submodule_file.txt", "w").write("Submodule file")
subprocess.check_call(["git", "add", "."])
subprocess.check_call(["git", "commit", "-m", "Initial submodule commit"])

# Create second submodule
submodule2_path = temp_repo / "submodule2"
submodule2_path.mkdir()
os.chdir(str(submodule2_path))
subprocess.check_call(["git", "init", "--initial-branch=main"])
open("submodule2_file.txt", "w").write("Second submodule file")
subprocess.check_call(["git", "add", "."])
subprocess.check_call(["git", "commit", "-m", "Initial submodule2 commit"])

os.chdir(str(temp_repo))
subprocess.check_call(["git", "submodule", "add", str(submodule_path)])
subprocess.check_call(["git", "commit", "-m", "Add submodule"])
subprocess.check_call(["git", "submodule", "add", str(submodule2_path)])
subprocess.check_call(["git", "commit", "-m", "Add submodules"])

packager = GitArchivePackager(ref="HEAD", include_submodules=True)
with tempfile.TemporaryDirectory() as job_dir:
Expand All @@ -364,13 +375,22 @@
f"tar -xvzf {output_file} -C {os.path.join(job_dir, 'extracted_output')} --ignore-zeros"
),
)
# Check first submodule
cmp = filecmp.dircmp(
os.path.join(temp_repo, "submodule"),
os.path.join(job_dir, "extracted_output", "submodule"),
)
assert cmp.left_list == cmp.right_list
assert not cmp.diff_files

# Check second submodule
cmp2 = filecmp.dircmp(
os.path.join(temp_repo, "submodule2"),
os.path.join(job_dir, "extracted_output", "submodule2"),
)
assert cmp2.left_list == cmp2.right_list
assert not cmp2.diff_files


@patch("nemo_run.core.packaging.git.Context", MockContext)
def test_package_without_include_submodules(packager, temp_repo):
Expand Down
Loading