mirror of
https://github.com/modelscope/modelscope.git
synced 2026-07-10 12:33:28 +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>
210 lines
8.1 KiB
Python
210 lines
8.1 KiB
Python
# Copyright (c) Alibaba, Inc. and its affiliates.
|
|
import os
|
|
import shutil
|
|
import tempfile
|
|
import unittest
|
|
import uuid
|
|
from shutil import rmtree
|
|
|
|
import requests
|
|
|
|
from modelscope.hub.api import HubApi, ModelScopeConfig
|
|
from modelscope.hub.constants import Licenses, ModelVisibility
|
|
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.logger import get_logger
|
|
from modelscope.utils.test_utils import (TEST_ACCESS_TOKEN1,
|
|
TEST_MODEL_CHINESE_NAME,
|
|
TEST_MODEL_ORG)
|
|
|
|
logger = get_logger()
|
|
|
|
DEFAULT_GIT_PATH = 'git'
|
|
|
|
download_model_file_name = 'test.bin'
|
|
|
|
|
|
class HubOperationTest(unittest.TestCase):
|
|
|
|
def setUp(self):
|
|
self.api = HubApi()
|
|
self.api.login(TEST_ACCESS_TOKEN1)
|
|
self.model_name = 'op-%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.PUBLIC,
|
|
license=Licenses.APACHE_V2,
|
|
chinese_name=TEST_MODEL_CHINESE_NAME,
|
|
)
|
|
|
|
def tearDown(self):
|
|
try:
|
|
self.api.delete_model(model_id=self.model_id)
|
|
except Exception as e:
|
|
logger.warning(f'delete model {self.model_id} failed, {e}')
|
|
|
|
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 test_model_repo_creation(self):
|
|
# change to proper model names before use.
|
|
try:
|
|
info = self.api.get_model(model_id=self.model_id)
|
|
assert info['Name'] == self.model_name
|
|
except KeyError as ke:
|
|
if ke.args[0] == 'name':
|
|
print(f'model {self.model_name} already exists, ignore')
|
|
else:
|
|
raise
|
|
|
|
def test_download_single_file(self):
|
|
self.prepare_case()
|
|
downloaded_file = model_file_download(
|
|
model_id=self.model_id,
|
|
file_path=download_model_file_name,
|
|
revision=self.revision)
|
|
assert os.path.exists(downloaded_file)
|
|
mdtime1 = os.path.getmtime(downloaded_file)
|
|
# download again with same revision to verify cache hit
|
|
downloaded_file = model_file_download(
|
|
model_id=self.model_id,
|
|
file_path=download_model_file_name,
|
|
revision=self.revision)
|
|
mdtime2 = os.path.getmtime(downloaded_file)
|
|
assert mdtime1 == mdtime2
|
|
|
|
def test_snapshot_download(self):
|
|
self.prepare_case()
|
|
snapshot_path = snapshot_download(model_id=self.model_id)
|
|
downloaded_file_path = os.path.join(snapshot_path,
|
|
download_model_file_name)
|
|
assert os.path.exists(downloaded_file_path)
|
|
mdtime1 = os.path.getmtime(downloaded_file_path)
|
|
# download again
|
|
snapshot_path = snapshot_download(
|
|
model_id=self.model_id, revision=self.revision)
|
|
mdtime2 = os.path.getmtime(downloaded_file_path)
|
|
assert mdtime1 == mdtime2
|
|
|
|
def test_download_public_without_login(self):
|
|
try:
|
|
self.prepare_case()
|
|
rmtree(ModelScopeConfig.path_credential)
|
|
snapshot_path = snapshot_download(
|
|
model_id=self.model_id, revision=self.revision)
|
|
downloaded_file_path = os.path.join(snapshot_path,
|
|
download_model_file_name)
|
|
assert os.path.exists(downloaded_file_path)
|
|
temporary_dir = tempfile.mkdtemp()
|
|
downloaded_file = model_file_download(
|
|
model_id=self.model_id,
|
|
file_path=download_model_file_name,
|
|
revision=self.revision,
|
|
cache_dir=temporary_dir)
|
|
assert os.path.exists(downloaded_file)
|
|
finally:
|
|
self.api.login(TEST_ACCESS_TOKEN1)
|
|
|
|
def test_snapshot_delete_download_cache_file(self):
|
|
self.prepare_case()
|
|
snapshot_path = snapshot_download(
|
|
model_id=self.model_id, revision=self.revision)
|
|
downloaded_file_path = os.path.join(snapshot_path,
|
|
download_model_file_name)
|
|
assert os.path.exists(downloaded_file_path)
|
|
os.remove(downloaded_file_path)
|
|
# download again in cache
|
|
file_download_path = model_file_download(
|
|
model_id=self.model_id,
|
|
file_path=ModelFile.README,
|
|
revision=self.revision)
|
|
assert os.path.exists(file_download_path)
|
|
# deleted file need download again
|
|
file_download_path = model_file_download(
|
|
model_id=self.model_id,
|
|
file_path=download_model_file_name,
|
|
revision=self.revision)
|
|
assert os.path.exists(file_download_path)
|
|
|
|
def test_snapshot_download_default_revision(self):
|
|
pass # TOTO
|
|
|
|
def test_file_download_default_revision(self):
|
|
pass # TODO
|
|
|
|
def get_model_download_times(self):
|
|
url = f'{self.api.endpoint}/api/v1/models/{self.model_id}/downloads'
|
|
cookies = ModelScopeConfig.get_cookies()
|
|
r = requests.get(url, cookies=cookies)
|
|
if r.status_code == 200:
|
|
return r.json()['Data']['Downloads']
|
|
else:
|
|
r.raise_for_status()
|
|
return None
|
|
|
|
@unittest.skip('temp skip')
|
|
def test_list_model(self):
|
|
data = self.api.list_models(TEST_MODEL_ORG)
|
|
assert len(data['Models']) >= 1
|
|
|
|
def test_snapshot_download_location(self):
|
|
self.prepare_case()
|
|
snapshot_download_path = snapshot_download(
|
|
model_id=self.model_id, revision=self.revision)
|
|
print(snapshot_download_path)
|
|
assert os.path.exists(snapshot_download_path)
|
|
assert 'models' in snapshot_download_path
|
|
shutil.rmtree(snapshot_download_path)
|
|
# download with cache_dir
|
|
cache_dir = '/tmp/snapshot_download_cache_test'
|
|
snapshot_download_path = snapshot_download(
|
|
self.model_id, revision=self.revision, cache_dir=cache_dir)
|
|
safe_id = self.model_id.replace('/', '--')
|
|
expect_path = os.path.join(cache_dir, 'models', safe_id, 'snapshots',
|
|
self.revision)
|
|
assert snapshot_download_path == expect_path
|
|
assert os.path.exists(
|
|
os.path.join(snapshot_download_path, ModelFile.README))
|
|
shutil.rmtree(cache_dir)
|
|
# download with local_dir
|
|
local_dir = '/tmp/snapshot_download_local_dir'
|
|
snapshot_download_path = snapshot_download(
|
|
self.model_id, revision=self.revision, local_dir=local_dir)
|
|
assert snapshot_download_path == local_dir
|
|
assert os.path.exists(os.path.join(local_dir, ModelFile.README))
|
|
shutil.rmtree(local_dir)
|
|
# download with local_dir and cache dir, with local first.
|
|
local_dir = '/tmp/snapshot_download_local_dir'
|
|
snapshot_download_path = snapshot_download(
|
|
self.model_id,
|
|
revision=self.revision,
|
|
cache_dir=cache_dir,
|
|
local_dir=local_dir)
|
|
assert snapshot_download_path == local_dir
|
|
assert os.path.exists(os.path.join(local_dir, ModelFile.README))
|
|
|
|
def test_snapshot_download_ignore_file_pattern_test(self):
|
|
self.prepare_case()
|
|
snapshot_download_path = snapshot_download(
|
|
model_id=self.model_id,
|
|
revision=self.revision,
|
|
ignore_file_pattern=['.*.pt', '.*.safetensors', '.*.bin'])
|
|
for _, _, files in os.walk(snapshot_download_path):
|
|
for file in files:
|
|
assert not file.endswith('pt') and not file.endswith(
|
|
'safetensors') and not file.endswith('bin')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|