Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add --additional-github-domain to check-vcs-permalinks #530

Merged
merged 1 commit into from Nov 18, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
4 changes: 4 additions & 0 deletions README.md
Expand Up @@ -66,6 +66,10 @@ Attempts to load all TOML files to verify syntax.

#### `check-vcs-permalinks`
Ensures that links to vcs websites are permalinks.
- `--additional-github-domain DOMAIN` - Add check for specified domain.
Can be repeated multiple times. for example, if your company uses
GitHub Enterprise you may use something like
`--additional-github-domain github.example.com`

#### `check-xml`
Attempts to load all xml files to verify syntax.
Expand Down
35 changes: 25 additions & 10 deletions pre_commit_hooks/check_vcs_permalinks.py
@@ -1,35 +1,50 @@
import argparse
import re
import sys
from typing import List
from typing import Optional
from typing import Pattern
from typing import Sequence


GITHUB_NON_PERMALINK = re.compile(
br'https://github.com/[^/ ]+/[^/ ]+/blob/master/[^# ]+#L\d+',
)
def _get_pattern(domain: str) -> Pattern[bytes]:
regex = rf'https://{domain}/[^/ ]+/[^/ ]+/blob/master/[^# ]+#L\d+'
return re.compile(regex.encode())


def _check_filename(filename: str) -> int:
def _check_filename(filename: str, patterns: List[Pattern[bytes]]) -> int:
retv = 0
with open(filename, 'rb') as f:
for i, line in enumerate(f, 1):
if GITHUB_NON_PERMALINK.search(line):
sys.stdout.write(f'{filename}:{i}:')
sys.stdout.flush()
sys.stdout.buffer.write(line)
retv = 1
for pattern in patterns:
if pattern.search(line):
sys.stdout.write(f'{filename}:{i}:')
sys.stdout.flush()
sys.stdout.buffer.write(line)
retv = 1
return retv


def main(argv: Optional[Sequence[str]] = None) -> int:
parser = argparse.ArgumentParser()
parser.add_argument('filenames', nargs='*')
parser.add_argument(
'--additional-github-domain',
dest='additional_github_domains',
action='append',
default=['github.com'],
)
args = parser.parse_args(argv)

patterns = [
_get_pattern(domain)
for domain in args.additional_github_domains
]

retv = 0

for filename in args.filenames:
retv |= _check_filename(filename)
retv |= _check_filename(filename, patterns)

if retv:
print()
Expand Down
6 changes: 4 additions & 2 deletions tests/check_vcs_permalinks_test.py
Expand Up @@ -22,13 +22,15 @@ def test_passing(tmpdir):
def test_failing(tmpdir, capsys):
with tmpdir.as_cwd():
tmpdir.join('f.txt').write_binary(
b'https://github.com/asottile/test/blob/master/foo#L1\n',
b'https://github.com/asottile/test/blob/master/foo#L1\n'
b'https://example.com/asottile/test/blob/master/foo#L1\n',
)

assert main(('f.txt',))
assert main(('f.txt', '--additional-github-domain', 'example.com'))
out, _ = capsys.readouterr()
assert out == (
'f.txt:1:https://github.com/asottile/test/blob/master/foo#L1\n'
'f.txt:2:https://example.com/asottile/test/blob/master/foo#L1\n'
'\n'
'Non-permanent github link detected.\n'
'On any page on github press [y] to load a permalink.\n'
Expand Down