Mercurial > hg
view contrib/check-config.py @ 37947:3ea3c96ada54
encoding: introduce tagging type for non-lossy non-ASCII string
This fixes the weird behavior of toutf8b(), which would convert a local
string back to UTF-8 *only if* it was lossy in the system encoding.
Before b7b26e54e37a "encoding: avoid localstr when a string can be encoded
losslessly (issue2763)", all local strings were wrapped by the localstr
class. I think this would justify the round-trip behavior of toutf8b().
ASCII strings are special-cased, so the cost of wrapping with safelocalstr
is negligible.
(with mercurial repo)
$ export HGRCPATH=/dev/null HGPLAIN= HGENCODING=latin-1
$ hg log --time --config experimental.evolution=all > /dev/null
(original)
time: real 11.340 secs (user 11.290+0.000 sys 0.060+0.000)
time: real 11.390 secs (user 11.300+0.000 sys 0.080+0.000)
time: real 11.430 secs (user 11.360+0.000 sys 0.070+0.000)
(this patch)
time: real 11.200 secs (user 11.100+0.000 sys 0.100+0.000)
time: real 11.370 secs (user 11.300+0.000 sys 0.070+0.000)
time: real 11.190 secs (user 11.130+0.000 sys 0.060+0.000)
author | Yuya Nishihara <yuya@tcha.org> |
---|---|
date | Sun, 23 Apr 2017 13:15:30 +0900 |
parents | 2912bed9b0c7 |
children | fe28267d5223 |
line wrap: on
line source
#!/usr/bin/env python # # check-config - a config flag documentation checker for Mercurial # # Copyright 2015 Matt Mackall <mpm@selenic.com> # # 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 foundopts = {} documented = {} allowinconsistent = set() configre = re.compile(br''' # Function call ui\.config(?P<ctype>|int|bool|list)\( # First argument. ['"](?P<section>\S+)['"],\s* # Second argument ['"](?P<option>\S+)['"](,\s+ (?:default=)?(?P<default>\S+?))? \)''', re.VERBOSE | re.MULTILINE) configwithre = re.compile(b''' ui\.config(?P<ctype>with)\( # First argument is callback function. This doesn't parse robustly # if it is e.g. a function call. [^,]+,\s* ['"](?P<section>\S+)['"],\s* ['"](?P<option>\S+)['"](,\s+ (?:default=)?(?P<default>\S+?))? \)''', re.VERBOSE | re.MULTILINE) configpartialre = (br"""ui\.config""") ignorere = re.compile(br''' \#\s(?P<reason>internal|experimental|deprecated|developer|inconsistent)\s config:\s(?P<config>\S+\.\S+)$ ''', re.VERBOSE | re.MULTILINE) def main(args): for f in args: sect = b'' prevname = b'' confsect = b'' carryover = b'' linenum = 0 for l in open(f, 'rb'): linenum += 1 # check topic-like bits m = re.match(b'\s*``(\S+)``', l) if m: prevname = m.group(1) if re.match(b'^\s*-+$', l): sect = prevname prevname = b'' if sect and prevname: name = sect + b'.' + prevname documented[name] = 1 # check docstring bits m = re.match(br'^\s+\[(\S+)\]', l) if m: confsect = m.group(1) continue m = re.match(br'^\s+(?:#\s*)?(\S+) = ', l) if m: name = confsect + b'.' + m.group(1) documented[name] = 1 # like the bugzilla extension m = re.match(br'^\s*(\S+\.\S+)$', l) if m: documented[m.group(1)] = 1 # like convert m = re.match(br'^\s*:(\S+\.\S+):\s+', l) if m: documented[m.group(1)] = 1 # quoted in help or docstrings m = re.match(br'.*?``(\S+\.\S+)``', l) if m: documented[m.group(1)] = 1 # look for ignore markers m = ignorere.search(l) if m: if m.group('reason') == 'inconsistent': allowinconsistent.add(m.group('config')) else: documented[m.group('config')] = 1 # look for code-like bits line = carryover + l m = configre.search(line) or configwithre.search(line) if m: ctype = m.group('ctype') if not ctype: ctype = 'str' name = m.group('section') + "." + m.group('option') default = m.group('default') if default in (None, 'False', 'None', '0', '[]', '""', "''"): default = '' if re.match(b'[a-z.]+$', default): default = '<variable>' if (name in foundopts and (ctype, default) != foundopts[name] and name not in allowinconsistent): print(l.rstrip()) print("conflict on %s: %r != %r" % (name, (ctype, default), foundopts[name])) print("at %s:%d:" % (f, linenum)) foundopts[name] = (ctype, default) carryover = '' else: m = re.search(configpartialre, line) if m: carryover = line else: carryover = '' for name in sorted(foundopts): if name not in documented: if not (name.startswith("devel.") or name.startswith("experimental.") or name.startswith("debug.")): ctype, default = foundopts[name] if default: default = ' [%s]' % default print("undocumented: %s (%s)%s" % (name, ctype, default)) if __name__ == "__main__": if len(sys.argv) > 1: sys.exit(main(sys.argv[1:])) else: sys.exit(main([l.rstrip() for l in sys.stdin]))