mirror of
https://github.com/modelscope/modelscope.git
synced 2026-08-29 10:08:40 +02:00
* refactor(hub): shim layer delegating to modelscope-hub - Replace hub/api.py (4674→250 lines) with shim inheriting LegacyHubApi - Replace hub/snapshot_download.py, callback.py with thin shims - Partial shim hub/file_download.py (retain http_get_file) - Shim hub/constants.py and errors.py with legacy aliases - Shim hub/git.py, repository.py, cache_manager.py, upload_*.py - Migrate CLI entry to modelscope_hub.cli.main:run_cmd - Adapt 6 CLI commands as modelscope_hub.cli_plugins - Delete redundant CLI files (download/upload/login/create/etc) - Add modelscope-hub>=0.2.0 dependency, Python>=3.10 - Add __getattr__ proxy for forward-compatible method access - Propagate timeout/max_retries to internal LegacyClient - Bridge MODELSCOPE_CREDENTIALS_PATH env var to HubConfig * fix lint: isort/yapf formatting + exclude hub/api.py from hooks * set modelscope-hub>=0.0.5 * remove unused code * refactor(hub): standardize token naming — git_token vs token Disambiguate git token and SDK/API token naming across the hub layer: - ModelScopeConfig: get_token/save_token → get_git_token/save_git_token (old names kept as deprecated aliases with DeprecationWarning) - GitCommandWrapper: rename token params to git_token in clone/push/config - Repository/DatasetRepository: auth_token → git_token (deprecated compat kept) - data_loader.py: update caller to use get_git_token() SDK token references (HubApi(token=...), get_cookies(access_token=...), commit_scheduler.token) remain unchanged as they correctly use `token` naming. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * remove(msdatasets): remove all Virgo-related implementation Remove the entire Virgo dataset subsystem which is no longer needed: - Remove VirgoDataset class and VirgoDownloader - Remove VirgoAuthConfig and VirgoDatasetConfig - Remove Hubs.virgo enum value - Remove fetch_virgo_meta from DataMetaManager - Remove download_virgo_files from DatasetContextConfig - Remove test_virgo_dataset.py test file - Clean up unused imports (pandas, MaxComputeUtil, valid_url, etc.) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(hub): add OSS dataset operations and meta-file download to HubApi Add methods that msdatasets depends on but don't belong in modelscope_hub: - _legacy_request: internal helper combining legacy HTTP transport with application-level envelope validation (Code/Data/Message) - list_oss_dataset_objects: list OSS storage objects for a dataset - delete_oss_dataset_object / delete_oss_dataset_dir: delete OSS objects - fetch_meta_files_from_url: download and cache meta CSV/JSONL files Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix imports issue * fix: address PR review feedback - cli/plugins.py: change --yes and --all flags to action='store_true' - hub/git.py: replace os.linesep with .splitlines() for cross-platform safety - hub/__init__.py: use is_file() with fallback for robust credentials path detection * fix lint * update ms hub version * fix(ci): add PyPI official as fallback index for pip Aliyun mirror may lag behind PyPI for newly published packages, causing dependency resolution failures (e.g. modelscope-hub>=0.0.6). Add pypi.org/simple as extra-index-url so new versions are immediately available while keeping the Aliyun mirror as the primary source. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix UTs * remove unused UTs * fix ut * update modelscope-hub installation for source code * fix UT * fix uts * fix ut --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
127 lines
5.0 KiB
Python
127 lines
5.0 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import os
|
|
import tempfile
|
|
import unittest
|
|
import uuid
|
|
|
|
from requests.exceptions import HTTPError
|
|
|
|
from modelscope.hub.api import HubApi
|
|
from modelscope.hub.constants import Licenses, ModelVisibility
|
|
from modelscope.hub.errors import (CacheNotFound, GitError, HubError,
|
|
NotExistError)
|
|
from modelscope.hub.file_download import model_file_download
|
|
from modelscope.hub.repository import Repository
|
|
from modelscope.hub.snapshot_download import snapshot_download
|
|
from modelscope.utils.constant import ModelFile
|
|
from modelscope.utils.test_utils import (TEST_ACCESS_TOKEN1,
|
|
TEST_ACCESS_TOKEN2,
|
|
TEST_MODEL_CHINESE_NAME,
|
|
TEST_MODEL_ORG, delete_credential)
|
|
|
|
download_model_file_name = 'test.bin'
|
|
|
|
|
|
class HubPrivateFileDownloadTest(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
self.old_cwd = os.getcwd()
|
|
self.api = HubApi()
|
|
self.token, _ = self.api.login(TEST_ACCESS_TOKEN1)
|
|
self.model_name = 'pf-%s' % (uuid.uuid4().hex)
|
|
self.model_id = '%s/%s' % (TEST_MODEL_ORG, self.model_name)
|
|
self.revision = 'v0.1_test_revision'
|
|
self.api.create_model(
|
|
model_id=self.model_id,
|
|
visibility=ModelVisibility.PRIVATE,
|
|
license=Licenses.APACHE_V2,
|
|
chinese_name=TEST_MODEL_CHINESE_NAME,
|
|
)
|
|
|
|
def prepare_case(self):
|
|
temporary_dir = tempfile.mkdtemp()
|
|
self.model_dir = os.path.join(temporary_dir, self.model_name)
|
|
repo = Repository(self.model_dir, clone_from=self.model_id)
|
|
os.system("echo 'testtest'>%s"
|
|
% os.path.join(self.model_dir, download_model_file_name))
|
|
repo.push('add model')
|
|
repo.tag_and_push(self.revision, 'Test revision')
|
|
|
|
def tearDown(self):
|
|
# credential may deleted or switch login name, we need re-login here
|
|
# to ensure the temporary model is deleted.
|
|
self.api.login(TEST_ACCESS_TOKEN1)
|
|
os.chdir(self.old_cwd)
|
|
try:
|
|
self.api.delete_model(model_id=self.model_id)
|
|
except Exception as e:
|
|
print(f'delete model {self.model_id} failed, {e}')
|
|
|
|
def test_snapshot_download_private_model(self):
|
|
self.prepare_case()
|
|
snapshot_path = snapshot_download(self.model_id, self.revision)
|
|
assert os.path.exists(os.path.join(snapshot_path, ModelFile.README))
|
|
|
|
def test_snapshot_download_private_model_no_permission(self):
|
|
self.prepare_case()
|
|
self.token, _ = self.api.login(TEST_ACCESS_TOKEN2)
|
|
with self.assertRaises((HTTPError, HubError)):
|
|
snapshot_download(self.model_id, self.revision)
|
|
|
|
def test_snapshot_download_private_model_without_login(self):
|
|
self.prepare_case()
|
|
delete_credential()
|
|
with self.assertRaises((HTTPError, HubError)):
|
|
snapshot_download(self.model_id, self.revision)
|
|
|
|
def test_download_file_private_model(self):
|
|
self.prepare_case()
|
|
file_path = model_file_download(self.model_id, ModelFile.README,
|
|
self.revision)
|
|
assert os.path.exists(file_path)
|
|
|
|
def test_download_file_private_model_no_permission(self):
|
|
self.prepare_case()
|
|
self.token, _ = self.api.login(TEST_ACCESS_TOKEN2)
|
|
with self.assertRaises((HTTPError, HubError)):
|
|
model_file_download(self.model_id, ModelFile.README, self.revision)
|
|
|
|
def test_download_file_private_model_without_login(self):
|
|
self.prepare_case()
|
|
delete_credential()
|
|
with self.assertRaises((HTTPError, HubError)):
|
|
model_file_download(self.model_id, ModelFile.README, self.revision)
|
|
|
|
def test_snapshot_download_local_only(self):
|
|
self.prepare_case()
|
|
with self.assertRaises((ValueError, CacheNotFound)):
|
|
snapshot_download(
|
|
self.model_id, self.revision, local_files_only=True)
|
|
snapshot_path = snapshot_download(self.model_id, self.revision)
|
|
assert os.path.exists(os.path.join(snapshot_path, ModelFile.README))
|
|
snapshot_path = snapshot_download(
|
|
self.model_id, self.revision, local_files_only=True)
|
|
assert os.path.exists(snapshot_path)
|
|
|
|
def test_file_download_local_only(self):
|
|
self.prepare_case()
|
|
with self.assertRaises((ValueError, CacheNotFound)):
|
|
model_file_download(
|
|
self.model_id,
|
|
ModelFile.README,
|
|
self.revision,
|
|
local_files_only=True)
|
|
file_path = model_file_download(self.model_id, ModelFile.README,
|
|
self.revision)
|
|
assert os.path.exists(file_path)
|
|
file_path = model_file_download(
|
|
self.model_id,
|
|
ModelFile.README,
|
|
revision=self.revision,
|
|
local_files_only=True)
|
|
assert os.path.exists(file_path)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|