view mercurial/i18n.py @ 38573:050fbd9d103a

test-convert: demonstrate an unstable hash issue for bzr -> hg -> hg It looks like the manifest value changing is the only difference, but I'm not sure why it's happening. I've got a similar divergence in a production repo that was also converted from bzr and has an octopus merge[1]. Unlike here, the manifest values for the destination merge commits reflect the initial merge only, instead of all four merges agreeing like this test. $ hg -R src_repo manifest -r 310 --debug | grep file # octopus fixup merge 2d8775bc2481bd28ac87038ecdf33e1dbddc80e9 644 file1 6adb9353a55bb8be76e71382efc724ec3ccf7ed5 644 file2 $ hg -R src_repo manifest -r 309 --debug | grep file # first merge 362e7cb5163153c4989daad1a834871ae849f205 644 file1 2c65d947191938c3ea616b7ceb7648ff3843261f 644 file2 $ hg -R dst_repo manifest -r 273 --debug | grep file # octopus fixup merge 362e7cb5163153c4989daad1a834871ae849f205 644 file1 2c65d947191938c3ea616b7ceb7648ff3843261f 644 file2 $ hg -R dst_repo manifest -r 272 --debug | grep file # first merge 362e7cb5163153c4989daad1a834871ae849f205 644 file1 2c65d947191938c3ea616b7ceb7648ff3843261f 644 file2 This divergence is espcially annoying because unlike changelog differences, I haven't figured out a way to fix this in code. The only way I found to work around it is to convert up to the point of divergence, `hg bundle` the bad revision in the source, apply it to the destination, add a line to the shamap, and fire off the conversion again. But I suspect that there's more to it than just the octopus merge because I also have a commit in the same repo, done in Mercurial (well after the conversion) that is exhibiting a similar issue (and it's not a merge commit). I'm almost positive that it was created with 4.4 or later. Any ideas? [1] https://www.mercurial-scm.org/pipermail/mercurial/2018-June/050924.html
author Matt Harbison <matt_harbison@yahoo.com>
date Thu, 05 Jul 2018 15:07:29 -0400
parents 79dd61a4554f
children dd83aafdb64a
line wrap: on
line source

# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 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

import gettext as gettextmod
import locale
import os
import sys

from . import (
    encoding,
    pycompat,
)

# modelled after templater.templatepath:
if getattr(sys, 'frozen', None) is not None:
    module = pycompat.sysexecutable
else:
    module = pycompat.fsencode(__file__)

_languages = None
if (pycompat.iswindows
    and 'LANGUAGE' not in encoding.environ
    and 'LC_ALL' not in encoding.environ
    and 'LC_MESSAGES' not in encoding.environ
    and 'LANG' not in encoding.environ):
    # Try to detect UI language by "User Interface Language Management" API
    # if no locale variables are set. Note that locale.getdefaultlocale()
    # uses GetLocaleInfo(), which may be different from UI language.
    # (See http://msdn.microsoft.com/en-us/library/dd374098(v=VS.85).aspx )
    try:
        import ctypes
        langid = ctypes.windll.kernel32.GetUserDefaultUILanguage()
        _languages = [locale.windows_locale[langid]]
    except (ImportError, AttributeError, KeyError):
        # ctypes not found or unknown langid
        pass

_ugettext = None

def setdatapath(datapath):
    datapath = pycompat.fsdecode(datapath)
    localedir = os.path.join(datapath, r'locale')
    t = gettextmod.translation(r'hg', localedir, _languages, fallback=True)
    global _ugettext
    try:
        _ugettext = t.ugettext
    except AttributeError:
        _ugettext = t.gettext

_msgcache = {}  # encoding: {message: translation}

def gettext(message):
    """Translate message.

    The message is looked up in the catalog to get a Unicode string,
    which is encoded in the local encoding before being returned.

    Important: message is restricted to characters in the encoding
    given by sys.getdefaultencoding() which is most likely 'ascii'.
    """
    # If message is None, t.ugettext will return u'None' as the
    # translation whereas our callers expect us to return None.
    if message is None or not _ugettext:
        return message

    cache = _msgcache.setdefault(encoding.encoding, {})
    if message not in cache:
        if type(message) is pycompat.unicode:
            # goofy unicode docstrings in test
            paragraphs = message.split(u'\n\n')
        else:
            paragraphs = [p.decode("ascii") for p in message.split('\n\n')]
        # Be careful not to translate the empty string -- it holds the
        # meta data of the .po file.
        u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs])
        try:
            # encoding.tolocal cannot be used since it will first try to
            # decode the Unicode string. Calling u.decode(enc) really
            # means u.encode(sys.getdefaultencoding()).decode(enc). Since
            # the Python encoding defaults to 'ascii', this fails if the
            # translated string use non-ASCII characters.
            encodingstr = pycompat.sysstr(encoding.encoding)
            cache[message] = u.encode(encodingstr, "replace")
        except LookupError:
            # An unknown encoding results in a LookupError.
            cache[message] = message
    return cache[message]

def _plain():
    if ('HGPLAIN' not in encoding.environ
        and 'HGPLAINEXCEPT' not in encoding.environ):
        return False
    exceptions = encoding.environ.get('HGPLAINEXCEPT', '').strip().split(',')
    return 'i18n' not in exceptions

if _plain():
    _ = lambda message: message
else:
    _ = gettext