def test_prepare_filename(self):
repo_urls = [
"https://whatever.cite.com/cool/you.git",
"whatever.cite.com/cool/you.git",
"whatever.cite.com/cool/you\\\n",
"whatever.cite.com/cool/you\n",
"whatever.cite.com/cool/you",
"whatever.cite.com/cool/you.git\n",
]
with tempfile.TemporaryDirectory() as tmpdir:
for repo_url in repo_urls:
self.assertEqual(
os.path.join(tmpdir,
"source_whatever.cite.com&cool&you.asdf"),
Repo2SourceTransformer.prepare_filename(
repo_url, tmpdir, 0))
for repo_url in repo_urls:
self.assertEqual(
os.path.join(tmpdir,
"w/source_whatever.cite.com&cool&you.asdf"),
Repo2SourceTransformer.prepare_filename(
repo_url, tmpdir, 1))
for repo_url in repo_urls:
self.assertEqual(
os.path.join(
tmpdir,
"w/wh/wha/source_whatever.cite.com&cool&you.asdf"),
Repo2SourceTransformer.prepare_filename(
repo_url, tmpdir, 3))
self.assertEqual(
os.path.join(tmpdir, "a/ab/abc/source_abc.asdf"),
Repo2SourceTransformer.prepare_filename("abc", tmpdir, 10))
def test_overwrite_existing(self):
with tempfile.TemporaryDirectory() as tmpdir:
model_path = Repo2SourceTransformer.prepare_filename(
DATA_DIR_SOURCE, tmpdir)
r2cc = Repo2SourceTransformer(linguist=tests.ENRY,
overwrite_existing=False)
r2cc.transform(DATA_DIR_SOURCE, output=tmpdir, num_processes=1)
data = asdf.open(model_path)
r2cc2 = Repo2SourceTransformer(linguist=tests.ENRY,
overwrite_existing=False)
r2cc2.transform(DATA_DIR_SOURCE, output=tmpdir, num_processes=1)
data2 = asdf.open(model_path)
self.assertEqual(data.tree["meta"]["created_at"],
data2.tree["meta"]["created_at"])
r2cc2 = Repo2SourceTransformer(linguist=tests.ENRY,
overwrite_existing=True)
r2cc2.transform(DATA_DIR_SOURCE, output=tmpdir, num_processes=1)
data3 = asdf.open(model_path)
self.assertNotEqual(data.tree["meta"]["created_at"],
data3.tree["meta"]["created_at"])
def check_no_model(self, tmpdir):
path = Repo2SourceTransformer.prepare_filename(DATA_DIR_SOURCE, tmpdir)
self.assertFalse(os.path.exists(path))
def load_default_source_model(self, tmpdir):
path = Repo2SourceTransformer.prepare_filename(DATA_DIR_SOURCE, tmpdir)
validate_asdf_file(self, path)
return Source().load(source=path)
def default_source_model_transformer(self, tmpdir):
r2cc = Repo2SourceTransformer(timeout=50, linguist=tests.ENRY)
r2cc.transform(DATA_DIR_SOURCE, output=tmpdir, num_processes=1)
self.assertEqual(r2cc.dependencies(), [])