def repo_isempty(repo: github.Repository) -> bool:
"""
is a GitHub repo empty?
Parameters
----------
repo : github.Repository
handle to GitHub repo
Results
-------
empty : bool
GitHub repo empty
"""
try:
repo.get_contents('/')
empty = False
except github.GithubException as e:
logging.error(f'{repo.name} is empty. \n')
empty = True
logging.info(str(e))
return empty
def guess_title(repo: Repository, path: str, branch_name: str):
"""Guesses the title of a file in a repo or branch."""
if path.endswith('.md'):
# If we are dealing with a markdown file, then we will interpret
# the first header in the file as the file's title.
contents = repo.get_contents(path, ref=branch_name)
text = base64.b64decode(contents.content).decode('UTF-8')
lines = text.split('\n')
for line in lines:
stripped = line.strip()
if stripped.startswith('#'):
return stripped.strip('#').strip()
# Turn the file name into a title.
return path.split('/')[-1].split('.')[0].replace('-', ' ').replace(
'_', ' ').capitalize()
def copy_markdown_images(root: str, file: str, repo: Repository,
markdown: str) -> str:
template = ""
paths = [result["path"] for result in parse.findall(template, markdown)]
parent = Path(file).parent
for path in paths:
if path.startswith("http"):
continue
img_path = Path(parent / path).resolve().relative_to(
Path(".").resolve())
img = repo.get_contents(str(img_path))
destination = os.path.realpath(f"{root}/gen_/{img_path}")
os.makedirs(os.path.dirname(destination), exist_ok=True)
urllib.request.urlretrieve(img.download_url, destination)
markdown = markdown.replace(path, f"gen_/{img_path}")
return markdown
def _scan_file(self,
results: ScanResults,
user: NamedUser,
org: Organization,
repo: Repository,
commitsha: str,
filename: str,
filelist: List[str]) -> None:
file: Optional(ContentFile) = None
content: str = None
for scanner in self._scanners:
if scanner.want(filename):
if not file:
file = repo.get_contents(filename, ref=commitsha)
content = file.decoded_content.decode("utf-8")
reposlug = "{}/{}".format(org.login, repo.name)
result = scanner.check(reposlug, commitsha, file.sha, file.path, content, filelist)
results.add(result)
def update_changelog(version: str, github_repository: Repository) -> None:
"""
Add a version title to the changelog.
"""
changelog_path = Path('CHANGELOG.rst')
branch = 'master'
changelog_content_file = github_repository.get_contents(
path=str(changelog_path),
ref=branch,
)
changelog_bytes = changelog_content_file.decoded_content
changelog_contents = changelog_bytes.decode('utf-8')
new_changelog_contents = changelog_contents.replace(
'Next\n----',
f'Next\n----\n\n{version}\n------------',
)
github_repository.update_file(
path=str(changelog_path),
message=f'Update for release {version}',
content=new_changelog_contents,
sha=changelog_content_file.sha,
)
def _explore_repo(self,
repo: Repository,
release_ids: Optional[list[int]] = None):
logging.info("Explore {}".format(repo.name))
repo_object = self._extract_existing_repo(repo)
releases = self._repo_releases(repo, release_ids)
if not repo_object and releases:
content = {c.name for c in repo.get_contents("")}
repo_name = repo.name
for repo_class, check_func in self._repo_type_dict.items():
if check_func(content, repo_name):
repo_object = repo_class(repo_name, repo.html_url)
logging.info("Added {}".format(repo_object))
break
if not repo_object or not releases:
return
if releases[0] not in repo_object.releases:
repo_object.releases = self._filter_releases_by_py_ver(
repo, releases, repo_object.releases)
if isinstance(repo_object, Package):
self._packages.add(repo_object)
else:
self._shells.add(repo_object)
def analyze_github_file(repo: Repository, path_to_file: str,
context: DocCheckerContext) -> FileAnalysis:
"""
This will actually load the file and the commit information to get things like if it was changed recently
and who the owner (is taken from the frontmatter).
:param context:
:param repo: The repo object in the API client
:param path_to_file: The path to the file in the repo (as in "lib/myfile.md")
:return:
"""
analysis = FileAnalysis()
info(f"Checking file {path_to_file}...")
try:
commits = repo.get_commits(path=path_to_file)
no_earlier_than = datetime.datetime.now() - datetime.timedelta(
days=context.doc_is_stale_after_days)
if commits.totalCount > 0:
commit_date = commits[0].commit.committer.date
analysis.file_changed_recently = commit_date >= no_earlier_than
analysis.last_change = commit_date
analysis.changed_by_email = commits[0].commit.committer.email
analysis.changed_by_name = commits[0].commit.committer.name
content = repo.get_contents(path_to_file, ref=context.github_branch)
analysis.file_link = content.html_url
analysis.file_identifier = path_to_file
if content.decoded_content:
doc = frontmatter.loads(content.decoded_content)
if not doc and not doc.metadata:
error(
f"There was a problem when reading the frontmatter for {path_to_file}",
1)
else:
if 'title' in doc.metadata:
analysis.doc_name = doc.metadata['title']
else:
analysis.doc_name = path_to_file
if 'owner' in doc.metadata:
analysis.owner = doc.metadata['owner']
try:
valid = validate_email(analysis.owner)
analysis.owner = valid.email
except EmailNotValidError as e:
warning(
f"Found an owner but the email {analysis.owner} is not valid: "
+ str(e), 1)
analysis.owner = None
info(f"Owner: {analysis.owner if analysis.owner else 'Not found'}", 1)
info(
f"Changed On: {analysis.last_change if analysis.last_change else 'Not found'}",
1)
info(f"Is Stale: {'No' if analysis.file_changed_recently else 'Yes'}",
1)
info(
f"Changed By: {analysis.changed_by_email if analysis.changed_by_email else 'Not found'}",
1)
except Exception as e:
error(f"Unable to load analysis due to exception: {str(e)} ", 1)
return analysis