comparison mercurial/encoding.py @ 41836:25694a78e4a4

encoding: use raw strings for encoding arguments

This prevents the internals of Python from coercing a unicode to str
on Python 2 and makes tests run with HGUNICODEPEDANTRY=1 a lot
happier.

Differential Revision: https://phab.mercurial-scm.org/D6051

41835:ddb174511f1b

elif _nativeenviron:
    environ = os.environb  # re-exports
else:
    # preferred encoding isn't known yet; use utf-8 to avoid unicode error
    # and recreate it once encoding is settled
    environ = dict((k.encode(u'utf-8'), v.encode(u'utf-8'))
                   for k, v in os.environ.items())  # re-exports

_encodingrewrites = {
    '646': 'ascii',
    'ANSI_X3.4-1968': 'ascii',

            # make sure string is actually stored in UTF-8
            u = s.decode('UTF-8')
            if encoding == 'UTF-8':
                # fast path
                return s
            r = u.encode(_sysstr(encoding), u"replace")
            if u == r.decode(_sysstr(encoding)):
                # r is a safe, non-lossy encoding of s
                return safelocalstr(r)
            return localstr(s, r)
        except UnicodeDecodeError:
            # we should only get here if we're looking at an ancient changeset
            try:
                u = s.decode(_sysstr(fallbackencoding))
                r = u.encode(_sysstr(encoding), u"replace")
                if u == r.decode(_sysstr(encoding)):
                    # r is a safe, non-lossy encoding of s
                    return safelocalstr(r)
                return localstr(u.encode('UTF-8'), r)
            except UnicodeDecodeError:
                u = s.decode("utf-8", "replace") # last ditch
                # can't round-trip
                return u.encode(_sysstr(encoding), u"replace")
    except LookupError as k:
        raise error.Abort(k, hint="please check your locale settings")

def fromlocal(s):
    """

    strmethod = pycompat.identity

if not _nativeenviron:
    # now encoding and helper functions are available, recreate the environ
    # dict to be exported to other modules
    environ = dict((tolocal(k.encode(u'utf-8')), tolocal(v.encode(u'utf-8')))
                   for k, v in os.environ.items())  # re-exports

if pycompat.ispy3:
    # os.getcwd() on Python 3 returns string, but it has os.getcwdb() which
    # returns bytes.

_wide = _sysstr(environ.get("HGENCODINGAMBIGUOUS", "narrow") == "wide"
                and "WFA" or "WF")

def colwidth(s):
    "Find the column width of a string for display in the local encoding"
    return ucolwidth(s.decode(_sysstr(encoding), u'replace'))

def ucolwidth(d):
    "Find the column width of a Unicode string for display"
    eaw = getattr(unicodedata, 'east_asian_width', None)
    if eaw is not None:

41836:25694a78e4a4

elif _nativeenviron:
    environ = os.environb  # re-exports
else:
    # preferred encoding isn't known yet; use utf-8 to avoid unicode error
    # and recreate it once encoding is settled
    environ = dict((k.encode(r'utf-8'), v.encode(r'utf-8'))
                   for k, v in os.environ.items())  # re-exports

_encodingrewrites = {
    '646': 'ascii',
    'ANSI_X3.4-1968': 'ascii',

            # make sure string is actually stored in UTF-8
            u = s.decode('UTF-8')
            if encoding == 'UTF-8':
                # fast path
                return s
            r = u.encode(_sysstr(encoding), r"replace")
            if u == r.decode(_sysstr(encoding)):
                # r is a safe, non-lossy encoding of s
                return safelocalstr(r)
            return localstr(s, r)
        except UnicodeDecodeError:
            # we should only get here if we're looking at an ancient changeset
            try:
                u = s.decode(_sysstr(fallbackencoding))
                r = u.encode(_sysstr(encoding), r"replace")
                if u == r.decode(_sysstr(encoding)):
                    # r is a safe, non-lossy encoding of s
                    return safelocalstr(r)
                return localstr(u.encode('UTF-8'), r)
            except UnicodeDecodeError:
                u = s.decode("utf-8", "replace") # last ditch
                # can't round-trip
                return u.encode(_sysstr(encoding), r"replace")
    except LookupError as k:
        raise error.Abort(k, hint="please check your locale settings")

def fromlocal(s):
    """

    strmethod = pycompat.identity

if not _nativeenviron:
    # now encoding and helper functions are available, recreate the environ
    # dict to be exported to other modules
    environ = dict((tolocal(k.encode(r'utf-8')), tolocal(v.encode(r'utf-8')))
                   for k, v in os.environ.items())  # re-exports

if pycompat.ispy3:
    # os.getcwd() on Python 3 returns string, but it has os.getcwdb() which
    # returns bytes.

_wide = _sysstr(environ.get("HGENCODINGAMBIGUOUS", "narrow") == "wide"
                and "WFA" or "WF")

def colwidth(s):
    "Find the column width of a string for display in the local encoding"
    return ucolwidth(s.decode(_sysstr(encoding), r'replace'))

def ucolwidth(d):
    "Find the column width of a Unicode string for display"
    eaw = getattr(unicodedata, 'east_asian_width', None)
    if eaw is not None: