pycompat: add bytestr wrapper which mostly acts as a Python 2 str
This allows us to handle bytes in mostly the same manner as Python 2 str,
so we can get rid of ugly s[i:i + 1] hacks:
s = bytestr(s)
while i < len(s):
c = s[i]
...
This is the simpler version of the previous RFC patch which tried to preserve
the bytestr type if possible. New version simply drops the bytestr wrapping
so we aren't likely to pass a bytestr to a function that expects Python 3
bytes.
#!/usr/bin/env python
#
# docchecker - look for problematic markup
#
# Copyright 2016 timeless <timeless@mozdev.org> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function
import re
import sys
leadingline = re.compile(r'(^\s*)(\S.*)$')
checks = [
(r""":hg:`[^`]*'[^`]*`""",
"""warning: please avoid nesting ' in :hg:`...`"""),
(r'\w:hg:`',
'warning: please have a space before :hg:'),
(r"""(?:[^a-z][^'.])hg ([^,;"`]*'(?!hg)){2}""",
'''warning: please use " instead of ' for hg ... "..."'''),
]
def check(line):
messages = []
for match, msg in checks:
if re.search(match, line):
messages.append(msg)
if messages:
print(line)
for msg in messages:
print(msg)
def work(file):
(llead, lline) = ('', '')
for line in file:
# this section unwraps lines
match = leadingline.match(line)
if not match:
check(lline)
(llead, lline) = ('', '')
continue
lead, line = match.group(1), match.group(2)
if (lead == llead):
if (lline != ''):
lline += ' ' + line
else:
lline = line
else:
check(lline)
(llead, lline) = (lead, line)
check(lline)
def main():
for f in sys.argv[1:]:
try:
with open(f) as file:
work(file)
except BaseException as e:
print("failed to process %s: %s" % (f, e))
main()