view mercurial/i18n.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

# i18n.py - internationalization support for mercurial
#
# Copyright 2005, 2006 Matt Mackall <[e-mail]>
#
# 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:
            # should be ascii, but we have unicode docstrings in test, which
            # are converted to utf-8 bytes on Python 3.
            paragraphs = [p.decode("utf-8") 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