def test_Pep8(self):
text = self.text
GP = gs.Github_Profile()
gf.get_pep8_errs(text, GP)
assert GP.pep8['E1'] == 1
assert GP.pep8['E2'] == 1
assert GP.pep8['E5'] == 1
assert GP.pep8['E7'] == 1
assert GP.pep8['W2'] == 3
def pickle_repo(repo):
"""
Basic function that scrapes repo data using the Github API and
saves it locally as a pickled file, to be used by test_classify()
above.
"""
GP = gs.Github_Profile()
url = 'https://api.github.com/repos/%s' % repo
repo_path = 'GP_%s.pkl' % (repo.replace('/', '_'))
r = gf.get_request(url)
if r.ok:
item = json.loads(r.text or r.content)
gs.get_features(item, GP)
joblib.dump(GP, repo_path)
def get_features(item):
"""
Top-level function that scrapes features for each python file
and stores it in a Github_Profile class.
"""
GP = gs.Github_Profile()
contents_url = '%s/contents' % item['url']
# scrape readme
gf.get_readme_length(contents_url, GP)
# scrape file-by-file stats
digest_repo(contents_url, GP)
# scrape commit history
gf.get_repo_commit_history(item, GP)
# scrape stargazers
GP.n_stars = item['stargazers_count']
# scrape forks
GP.n_forks = item['forks_count']
return GP
def test_readme(self):
GP = gs.Github_Profile()
url = 'https://api.github.com/repos/silburt/DeepMoon/contents'
gf.get_readme_length(url, GP)
assert GP.readme_lines == 99