Skip to content

fix(core): place repack dependencies in code root #6460

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

Open
lucasjia-aws wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix(core): place repack dependencies in code root #6460

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
7 changes: 2 additions & 5 deletions sagemaker-core/src/sagemaker/core/common_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -744,13 +744,10 @@ def _create_or_update_code_dir(
for dependency in dependencies:
# Validate dependency path for security
_validate_dependency_path(dependency)
lib_dir = os.path.join(code_dir, "lib")
if os.path.isdir(dependency):
shutil.copytree(dependency, os.path.join(lib_dir, os.path.basename(dependency)))
shutil.copytree(dependency, os.path.join(code_dir, os.path.basename(dependency)))
else:
if not os.path.exists(lib_dir):
os.mkdir(lib_dir)
shutil.copy2(dependency, lib_dir)
shutil.copy2(dependency, code_dir)


def _extract_model(model_uri, sagemaker_session, tmp):
Expand Down
116 changes: 94 additions & 22 deletions sagemaker-core/tests/unit/test_common_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2660,37 +2660,109 @@ def test_create_or_update_code_dir_with_source_directory(self):
assert os.path.exists(code_dir)
assert os.path.exists(os.path.join(code_dir, "app.py"))

def test_create_or_update_code_dir_with_dependencies(self):
"""Test code directory creation with dependencies."""
def test_create_or_update_code_dir_copies_directory_dependency_to_code_root(self, tmp_path):
"""Test directory dependencies are importable from the code root."""
from sagemaker.core.common_utils import _create_or_update_code_dir

with tempfile.TemporaryDirectory() as tmpdir:
model_dir = os.path.join(tmpdir, "model")
os.makedirs(model_dir)
model_dir = tmp_path / "model"
model_dir.mkdir()
inference_script = tmp_path / "inference.py"
inference_script.write_text("# inference code")
dependency = tmp_path / "my_lib"
dependency.mkdir()
(dependency / "helper.py").write_text("# helper code")

_create_or_update_code_dir(
str(model_dir), str(inference_script), None, [str(dependency)], None, str(tmp_path)
)

inference_script = os.path.join(tmpdir, "inference.py")
with open(inference_script, "w") as f:
f.write("# inference code")
assert (model_dir / "code" / "my_lib" / "helper.py").exists()
assert not (model_dir / "code" / "lib").exists()

def test_create_or_update_code_dir_copies_file_dependency_to_code_root(self, tmp_path):
"""Test single-file dependencies are importable from the code root."""
from sagemaker.core.common_utils import _create_or_update_code_dir

model_dir = tmp_path / "model"
model_dir.mkdir()
inference_script = tmp_path / "inference.py"
inference_script.write_text("# inference code")
dependency = tmp_path / "helper.py"
dependency.write_text("# helper code")

_create_or_update_code_dir(
str(model_dir), str(inference_script), None, [str(dependency)], None, str(tmp_path)
)

assert (model_dir / "code" / "helper.py").exists()
assert not (model_dir / "code" / "lib").exists()

def test_create_or_update_code_dir_dependency_coexists_with_source_directory(self, tmp_path):
"""Test dependencies and source-directory files share the code root."""
from sagemaker.core.common_utils import _create_or_update_code_dir

model_dir = tmp_path / "model"
model_dir.mkdir()
source_dir = tmp_path / "source"
source_dir.mkdir()
(source_dir / "inference.py").write_text("# inference code")
dependency = tmp_path / "my_lib"
dependency.mkdir()
(dependency / "helper.py").write_text("# helper code")

_create_or_update_code_dir(
str(model_dir), "inference.py", str(source_dir), [str(dependency)], None, str(tmp_path)
)

dep_dir = os.path.join(tmpdir, "my_lib")
os.makedirs(dep_dir)
with open(os.path.join(dep_dir, "helper.py"), "w") as f:
f.write("# helper code")
assert (model_dir / "code" / "inference.py").exists()
assert (model_dir / "code" / "my_lib" / "helper.py").exists()

def test_create_or_update_code_dir_rejects_directory_dependency_collision(self, tmp_path):
"""Test directory dependencies do not silently merge with source code."""
from sagemaker.core.common_utils import _create_or_update_code_dir

# Should create code directory with dependencies
model_dir = tmp_path / "model"
model_dir.mkdir()
source_dir = tmp_path / "source"
(source_dir / "my_lib").mkdir(parents=True)
(source_dir / "my_lib" / "source.py").write_text("# source code")
dependency_parent = tmp_path / "dependency"
dependency = dependency_parent / "my_lib"
dependency.mkdir(parents=True)
(dependency / "helper.py").write_text("# helper code")

with pytest.raises(FileExistsError):
_create_or_update_code_dir(
model_dir,
inference_script,
None,
[dep_dir],
str(model_dir),
"inference.py",
str(source_dir),
[str(dependency)],
None,
tmpdir,
str(tmp_path),
)

code_dir = os.path.join(model_dir, "code")
lib_dir = os.path.join(code_dir, "lib")
assert os.path.exists(lib_dir)
assert os.path.exists(os.path.join(lib_dir, "my_lib", "helper.py"))
assert (model_dir / "code" / "my_lib" / "source.py").exists()
assert not (model_dir / "code" / "my_lib" / "helper.py").exists()

def test_create_or_update_code_dir_file_dependency_overwrites_collision(self, tmp_path):
"""Test a file dependency preserves copy2 overwrite semantics."""
from sagemaker.core.common_utils import _create_or_update_code_dir

model_dir = tmp_path / "model"
model_dir.mkdir()
source_dir = tmp_path / "source"
source_dir.mkdir()
(source_dir / "helper.py").write_text("source")
dependency_parent = tmp_path / "dependency"
dependency_parent.mkdir()
dependency = dependency_parent / "helper.py"
dependency.write_text("dependency")

_create_or_update_code_dir(
str(model_dir), "inference.py", str(source_dir), [str(dependency)], None, str(tmp_path)
)

assert (model_dir / "code" / "helper.py").read_text() == "dependency"

def test_create_or_update_code_dir_rejects_sensitive_paths(self):
"""Test that code_dir validation rejects sensitive system paths."""
Expand Down
Loading