mercurial/encoding.py

clone: only use stream when we understand the revlog format

This patch fixes issues with stream cloning in the presense of parentdelta,
lwcopy and similar additions that change the interpretation of the revlog
format, or the format itself.

Currently, the stream capability is sent like this:
stream=<version of changelog>

But the client doesn't actually check the version number; also, it only checks
the changelog and it doesn't capture the interpretation-changes and
flag-changes in parentdelta and lwcopy.

This patch removes the 'stream' capability whenever we use a non-basic revlog
format, to prevent old clients from receiving incorrect data. In those cases,
a new capability called 'streamreqs' is added instead. Instead of a revlog
version, it comes with a list of revlog-format relevant requirements, which
are a subset of the repository requirements, excluding things that are not
relevant for stream.

New clients use this to determine whether or not they can stream. Old clients
only look for the 'stream' capability, as always. New servers will still send
this when serving old repositories.

# encoding.py - character transcoding support for Mercurial
#
#  Copyright 2005-2009 Matt Mackall <[e-mail]> 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.

import error
import unicodedata, locale, os

def _getpreferredencoding():
    '''
    On darwin, getpreferredencoding ignores the locale environment and
    always returns mac-roman. http://bugs.python.org/issue6202 fixes this
    for Python 2.7 and up. This is the same corrected code for earlier
    Python versions.

    However, we can't use a version check for this method, as some distributions 
    patch Python to fix this. Instead, we use it as a 'fixer' for the mac-roman
    encoding, as it is unlikely that this encoding is the actually expected.
    '''
    try:
        locale.CODESET
    except AttributeError:
        # Fall back to parsing environment variables :-(
        return locale.getdefaultlocale()[1]

    oldloc = locale.setlocale(locale.LC_CTYPE)
    locale.setlocale(locale.LC_CTYPE, "")
    result = locale.nl_langinfo(locale.CODESET)
    locale.setlocale(locale.LC_CTYPE, oldloc)

    return result

_encodingfixers = {
    '646': lambda: 'ascii',
    'ANSI_X3.4-1968': lambda: 'ascii',
    'mac-roman': _getpreferredencoding
}

try:
    encoding = os.environ.get("HGENCODING")
    if not encoding:
        encoding = locale.getpreferredencoding() or 'ascii'
        encoding = _encodingfixers.get(encoding, lambda: encoding)()
except locale.Error:
    encoding = 'ascii'
encodingmode = os.environ.get("HGENCODINGMODE", "strict")
fallbackencoding = 'ISO-8859-1'

def tolocal(s):
    """
    Convert a string from internal UTF-8 to local encoding

    All internal strings should be UTF-8 but some repos before the
    implementation of locale support may contain latin1 or possibly
    other character sets. We attempt to decode everything strictly
    using UTF-8, then Latin-1, and failing that, we use UTF-8 and
    replace unknown characters.
    """
    for e in ('UTF-8', fallbackencoding):
        try:
            u = s.decode(e) # attempt strict decoding
            return u.encode(encoding, "replace")
        except LookupError, k:
            raise error.Abort("%s, please check your locale settings" % k)
        except UnicodeDecodeError:
            pass
    u = s.decode("utf-8", "replace") # last ditch
    return u.encode(encoding, "replace")

def fromlocal(s):
    """
    Convert a string from the local character encoding to UTF-8

    We attempt to decode strings using the encoding mode set by
    HGENCODINGMODE, which defaults to 'strict'. In this mode, unknown
    characters will cause an error message. Other modes include
    'replace', which replaces unknown characters with a special
    Unicode character, and 'ignore', which drops the character.
    """
    try:
        return s.decode(encoding, encodingmode).encode("utf-8")
    except UnicodeDecodeError, inst:
        sub = s[max(0, inst.start - 10):inst.start + 10]
        raise error.Abort("decoding near '%s': %s!" % (sub, inst))
    except LookupError, k:
        raise error.Abort("%s, please check your locale settings" % k)

def colwidth(s):
    "Find the column width of a UTF-8 string for display"
    d = s.decode(encoding, 'replace')
    if hasattr(unicodedata, 'east_asian_width'):
        w = unicodedata.east_asian_width
        return sum([w(c) in 'WFA' and 2 or 1 for c in d])
    return len(d)