mirror of
https://github.com/hanzo-ml/trainer.git
synced 2026-09-24 00:31:34 +00:00
Tariq HasanandGitHub
9183dfd24f
* chore(scripts): add copyright boilerplate verification system Signed-off-by: tariq-hasan <[email protected]> * chore(ci): add boilerplate verification to CI pipeline Signed-off-by: tariq-hasan <[email protected]> * chore: regenerate files with year-less copyright headers Signed-off-by: tariq-hasan <[email protected]> * refactor(boilerplate): simplify verification logic Signed-off-by: tariq-hasan <[email protected]> * chore(boilerplate): add missing copyright headers Signed-off-by: tariq-hasan <[email protected]> * ci(boilerplate): move verifier to code-quality workflow and run unit tests Signed-off-by: tariq-hasan <[email protected]> * feat(boilerplate): accept license headers with any year and remove year validation logic Signed-off-by: tariq-hasan <[email protected]> * feat(boilerplate): add copyright headers to generated Python API Signed-off-by: tariq-hasan <[email protected]> * refactor(boilerplate): use block-comment header for generated Go files Signed-off-by: tariq-hasan <[email protected]> * feat(boilerplate): verify copyright headers in Rust files Signed-off-by: tariq-hasan <[email protected]> --------- Signed-off-by: tariq-hasan <[email protected]>
89 lines
3.1 KiB
Python
89 lines
3.1 KiB
Python
# Copyright The Kubeflow Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import os
|
|
import runpy
|
|
|
|
import pytest
|
|
from conftest import verify_downloaded_files
|
|
|
|
import pkg.initializers.utils.utils as utils
|
|
|
|
|
|
class TestDatasetIntegration:
|
|
"""Integration tests for dataset initialization"""
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def setup_teardown(self, setup_temp_path):
|
|
self.temp_dir = setup_temp_path("DATASET_PATH")
|
|
|
|
@pytest.mark.parametrize(
|
|
"test_name, provider, test_case",
|
|
[
|
|
# Public HuggingFace dataset test
|
|
(
|
|
"HuggingFace - Public dataset",
|
|
"huggingface",
|
|
{
|
|
"storage_uri": "hf://karpathy/tiny_shakespeare",
|
|
"access_token": None,
|
|
"expected_files": ["tiny_shakespeare.py"],
|
|
"expected_error": None,
|
|
},
|
|
),
|
|
(
|
|
"HuggingFace - Invalid dataset",
|
|
"huggingface",
|
|
{
|
|
"storage_uri": "hf://invalid/nonexistent-dataset",
|
|
"access_token": None,
|
|
"expected_files": None,
|
|
"expected_error": Exception,
|
|
},
|
|
),
|
|
(
|
|
"HuggingFace - Login Failure",
|
|
"huggingface",
|
|
{
|
|
"storage_uri": "hf://karpathy/tiny_shakespeare",
|
|
"access_token": "invalid token",
|
|
"expected_files": None,
|
|
"expected_error": Exception,
|
|
},
|
|
),
|
|
],
|
|
)
|
|
def test_dataset_download(self, test_name, provider, test_case):
|
|
"""Test end-to-end dataset download for different providers"""
|
|
print(f"Running Integration test for {provider}: {test_name}")
|
|
|
|
# Setup environment variables based on test case
|
|
os.environ[utils.STORAGE_URI_ENV] = test_case["storage_uri"]
|
|
expected_files = test_case.get("expected_files")
|
|
|
|
if test_case.get("access_token"):
|
|
os.environ["ACCESS_TOKEN"] = test_case["access_token"]
|
|
|
|
# Run the main script
|
|
if test_case["expected_error"]:
|
|
with pytest.raises(test_case["expected_error"]):
|
|
runpy.run_module(
|
|
"pkg.initializers.dataset.__main__", run_name="__main__"
|
|
)
|
|
else:
|
|
runpy.run_module("pkg.initializers.dataset.__main__", run_name="__main__")
|
|
verify_downloaded_files(self.temp_dir, expected_files)
|
|
|
|
print("Test execution completed")
|