Mercurial > hg
view mercurial/diffutil.py @ 44651:00e0c5c06ed5
pycompat: change argv conversion semantics
Use of os.fsencode() to convert Python's sys.argv back to bytes
was not correct because it isn't the logically inverse operation
from what CPython was doing under the hood.
This commit changes the logic for doing the str -> bytes
conversion. This required a separate implementation for
POSIX and Windows.
The Windows behavior is arguably not ideal. The previous
behavior on Windows was leading to failing tests, such as
test-http-branchmap.t, which defines a utf-8 branch name
via a command argument. Previously, Mercurial's argument
parser looked to be receiving wchar_t bytes in some cases.
After this commit, behavior on Windows is compatible with
Python 2, where CPython did not implement `int wmain()` and
Windows was performing a Unicode to ANSI conversion on the
wchar_t native command line.
Arguably better behavior on Windows would be for Mercurial to
preserve the original Unicode sequence coming from Python and
to wrap this in a bytes-like type so we can round trip safely.
But, this would be new, backwards incompatible behavior. My
goal for this commit was to converge Mercurial behavior on
Python 3 on Windows to fix busted tests. And I believe I was
successful, as this commit fixes 9 tests on my Windows
machine and 14 tests in the AWS CI environment!
Differential Revision: https://phab.mercurial-scm.org/D8337
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sat, 28 Mar 2020 12:18:58 -0700 |
parents | 687b865b95ad |
children | 89a2afe31e82 |
line wrap: on
line source
# diffutil.py - utility functions related to diff and patch # # Copyright 2006 Brendan Cully <brendan@kublai.com> # Copyright 2007 Chris Mason <chris.mason@oracle.com> # Copyright 2018 Octobus <octobus@octobus.net> # # 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 from .i18n import _ from . import ( mdiff, pycompat, ) def diffallopts( ui, opts=None, untrusted=False, section=b'diff', configprefix=b'' ): '''return diffopts with all features supported and parsed''' return difffeatureopts( ui, opts=opts, untrusted=untrusted, section=section, git=True, whitespace=True, formatchanging=True, configprefix=configprefix, ) def difffeatureopts( ui, opts=None, untrusted=False, section=b'diff', git=False, whitespace=False, formatchanging=False, configprefix=b'', ): '''return diffopts with only opted-in features parsed Features: - git: git-style diffs - whitespace: whitespace options like ignoreblanklines and ignorews - formatchanging: options that will likely break or cause correctness issues with most diff parsers ''' def get(key, name=None, getter=ui.configbool, forceplain=None): if opts: v = opts.get(key) # diffopts flags are either None-default (which is passed # through unchanged, so we can identify unset values), or # some other falsey default (eg --unified, which defaults # to an empty string). We only want to override the config # entries from hgrc with command line values if they # appear to have been set, which is any truthy value, # True, or False. if v or isinstance(v, bool): return v if forceplain is not None and ui.plain(): return forceplain return getter( section, configprefix + (name or key), untrusted=untrusted ) # core options, expected to be understood by every diff parser buildopts = { b'nodates': get(b'nodates'), b'showfunc': get(b'show_function', b'showfunc'), b'context': get(b'unified', getter=ui.config), } buildopts[b'xdiff'] = ui.configbool(b'experimental', b'xdiff') if git: buildopts[b'git'] = get(b'git') # since this is in the experimental section, we need to call # ui.configbool directory buildopts[b'showsimilarity'] = ui.configbool( b'experimental', b'extendedheader.similarity' ) # need to inspect the ui object instead of using get() since we want to # test for an int hconf = ui.config(b'experimental', b'extendedheader.index') if hconf is not None: hlen = None try: # the hash config could be an integer (for length of hash) or a # word (e.g. short, full, none) hlen = int(hconf) if hlen < 0 or hlen > 40: msg = _(b"invalid length for extendedheader.index: '%d'\n") ui.warn(msg % hlen) except ValueError: # default value if hconf == b'short' or hconf == b'': hlen = 12 elif hconf == b'full': hlen = 40 elif hconf != b'none': msg = _(b"invalid value for extendedheader.index: '%s'\n") ui.warn(msg % hconf) finally: buildopts[b'index'] = hlen if whitespace: buildopts[b'ignorews'] = get(b'ignore_all_space', b'ignorews') buildopts[b'ignorewsamount'] = get( b'ignore_space_change', b'ignorewsamount' ) buildopts[b'ignoreblanklines'] = get( b'ignore_blank_lines', b'ignoreblanklines' ) buildopts[b'ignorewseol'] = get(b'ignore_space_at_eol', b'ignorewseol') if formatchanging: buildopts[b'text'] = opts and opts.get(b'text') binary = None if opts is None else opts.get(b'binary') buildopts[b'nobinary'] = ( not binary if binary is not None else get(b'nobinary', forceplain=False) ) buildopts[b'noprefix'] = get(b'noprefix', forceplain=False) buildopts[b'worddiff'] = get( b'word_diff', b'word-diff', forceplain=False ) return mdiff.diffopts(**pycompat.strkwargs(buildopts))