Files
modelscope/tests/cli/test_scancache_cmd.py
Xingjun.Wang 680c3638e0 [Feat & Refactor] Refactor hub and CLI modules (#1732)
* 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>
2026-06-09 22:23:14 +08:00

87 lines
3.2 KiB
Python

import os
import subprocess
import sys
import tempfile
import unittest
from argparse import Namespace
from unittest import mock
from modelscope.hub.constants import TEMPORARY_FOLDER_NAME
from modelscope.utils.file_utils import get_modelscope_cache_dir
class TestScanCacheCommand(unittest.TestCase):
"""Test cases for scancache command in ModelScope CLI."""
@classmethod
def setUpClass(cls):
"""Set up for tests."""
# download one file to ensure the cache directory exists
model_id = 'Qwen/Qwen3-0.6B'
cmd = f'python -m modelscope.cli.cli download --model {model_id} README.md'
subprocess.getstatusoutput(cmd)
def test_scan_default_dir(self):
cmd = 'python -m modelscope.cli.cli scan-cache'
stat, output = subprocess.getstatusoutput(cmd)
self.assertEqual(stat, 0)
self.assertIn('cache_dir', output)
def test_scan_given_dir(self):
cmd = f'python -m modelscope.cli.cli scan-cache --dir {get_modelscope_cache_dir()}'
stat, output = subprocess.getstatusoutput(cmd)
self.assertEqual(stat, 0)
self.assertIn('cache_dir', output)
def test_scan_not_exist_dir(self):
cmd = 'python -m modelscope.cli.cli scan-cache --dir /fake/cache/path'
stat, output = subprocess.getstatusoutput(cmd)
self.assertEqual(stat, 0)
self.assertIn('0 repo(s)', output)
class TestClearCacheCommand(unittest.TestCase):
"""clear-cache must resolve the right cache root in both scenarios:
* MODELSCOPE_CACHE set -> $MODELSCOPE_CACHE/{models,datasets}/<id>
* MODELSCOPE_CACHE unset -> ~/.cache/modelscope/hub/{models,datasets}/<id>
"""
def _clear_and_assert(self, root, kind, entity_id):
from modelscope.cli.clearcache import ClearCacheCMD
sub = {'model': 'models', 'dataset': 'datasets'}[kind]
entity_dir = os.path.join(root, sub, entity_id)
temp_dir = os.path.join(root, sub, TEMPORARY_FOLDER_NAME, entity_id)
os.makedirs(entity_dir)
os.makedirs(temp_dir)
args = Namespace(
model=entity_id if kind == 'model' else None,
dataset=entity_id if kind == 'dataset' else None)
with mock.patch('builtins.input', return_value='Y'):
ClearCacheCMD(args).execute()
self.assertFalse(os.path.exists(entity_dir))
self.assertFalse(os.path.exists(temp_dir))
def test_env_cache(self):
with tempfile.TemporaryDirectory() as tmp, \
mock.patch.dict(os.environ,
{'MODELSCOPE_CACHE': tmp}, clear=False):
for kind in ('model', 'dataset'):
with self.subTest(kind=kind):
self._clear_and_assert(tmp, kind, f'org/{kind}')
def test_default_cache(self):
with tempfile.TemporaryDirectory() as tmp:
env = {
k: v
for k, v in os.environ.items() if k != 'MODELSCOPE_CACHE'
}
env['HOME'] = tmp
with mock.patch.dict(os.environ, env, clear=True):
self._clear_and_assert(
os.path.join(tmp, '.cache', 'modelscope', 'hub'), 'model',
'org/repo')
if __name__ == '__main__':
unittest.main()