py3: fix str vs bytes in enough places to run `hg version` on Windows

I don't have Visual Studio 2015 at home, but this now works with a handful of
extensions (blackbox, extdiff, patchbomb, phabricator and rebase, but not
evolve):

    $ HGMODULEPOLICY=py py -3 ../hg version

Enabling the evolve extension causes the usual "failed to import ..." line, but
then print this before the usual version output:

    ('commit', '[b'debugancestor', b'debugapplystreamclonebundle', ...,
     b'verify', b'version']')

... where the elided part seems to be every command and alias known.

mercurial/color.py

@@ -1,537 +1,537
 # utility for color output for Mercurial commands
 #
 # Copyright (C) 2007 Kevin Christen <[e-mail]> and other
 #
 # 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 re
 
 from .i18n import _
 
 from . import (
     encoding,
     pycompat,
 )
 
 from .utils import (
     stringutil,
 )
 
 try:
     import curses
     # Mapping from effect name to terminfo attribute name (or raw code) or
     # color number.  This will also force-load the curses module.
     _baseterminfoparams = {
         'none': (True, 'sgr0', ''),
         'standout': (True, 'smso', ''),
         'underline': (True, 'smul', ''),
         'reverse': (True, 'rev', ''),
         'inverse': (True, 'rev', ''),
         'blink': (True, 'blink', ''),
         'dim': (True, 'dim', ''),
         'bold': (True, 'bold', ''),
         'invisible': (True, 'invis', ''),
         'italic': (True, 'sitm', ''),
         'black': (False, curses.COLOR_BLACK, ''),
         'red': (False, curses.COLOR_RED, ''),
         'green': (False, curses.COLOR_GREEN, ''),
         'yellow': (False, curses.COLOR_YELLOW, ''),
         'blue': (False, curses.COLOR_BLUE, ''),
         'magenta': (False, curses.COLOR_MAGENTA, ''),
         'cyan': (False, curses.COLOR_CYAN, ''),
         'white': (False, curses.COLOR_WHITE, ''),
     }
 except ImportError:
     curses = None
     _baseterminfoparams = {}
 
 # start and stop parameters for effects
 _effects = {
     'none': 0,
     'black': 30,
     'red': 31,
     'green': 32,
     'yellow': 33,
     'blue': 34,
     'magenta': 35,
     'cyan': 36,
     'white': 37,
     'bold': 1,
     'italic': 3,
     'underline': 4,
     'inverse': 7,
     'dim': 2,
     'black_background': 40,
     'red_background': 41,
     'green_background': 42,
     'yellow_background': 43,
     'blue_background': 44,
     'purple_background': 45,
     'cyan_background': 46,
     'white_background': 47,
     }
 
 _defaultstyles = {
     'grep.match': 'red bold',
     'grep.linenumber': 'green',
     'grep.rev': 'green',
     'grep.change': 'green',
     'grep.sep': 'cyan',
     'grep.filename': 'magenta',
     'grep.user': 'magenta',
     'grep.date': 'magenta',
     'addremove.added': 'green',
     'addremove.removed': 'red',
     'bookmarks.active': 'green',
     'branches.active': 'none',
     'branches.closed': 'black bold',
     'branches.current': 'green',
     'branches.inactive': 'none',
     'diff.changed': 'white',
     'diff.deleted': 'red',
     'diff.deleted.changed': 'red bold underline',
     'diff.deleted.unchanged': 'red',
     'diff.diffline': 'bold',
     'diff.extended': 'cyan bold',
     'diff.file_a': 'red bold',
     'diff.file_b': 'green bold',
     'diff.hunk': 'magenta',
     'diff.inserted': 'green',
     'diff.inserted.changed': 'green bold underline',
     'diff.inserted.unchanged': 'green',
     'diff.tab': '',
     'diff.trailingwhitespace': 'bold red_background',
     'changeset.public': '',
     'changeset.draft': '',
     'changeset.secret': '',
     'diffstat.deleted': 'red',
     'diffstat.inserted': 'green',
     'formatvariant.name.mismatchconfig': 'red',
     'formatvariant.name.mismatchdefault': 'yellow',
     'formatvariant.name.uptodate': 'green',
     'formatvariant.repo.mismatchconfig': 'red',
     'formatvariant.repo.mismatchdefault': 'yellow',
     'formatvariant.repo.uptodate': 'green',
     'formatvariant.config.special': 'yellow',
     'formatvariant.config.default': 'green',
     'formatvariant.default': '',
     'histedit.remaining': 'red bold',
     'ui.error': 'red',
     'ui.prompt': 'yellow',
     'log.changeset': 'yellow',
     'patchbomb.finalsummary': '',
     'patchbomb.from': 'magenta',
     'patchbomb.to': 'cyan',
     'patchbomb.subject': 'green',
     'patchbomb.diffstats': '',
     'rebase.rebased': 'blue',
     'rebase.remaining': 'red bold',
     'resolve.resolved': 'green bold',
     'resolve.unresolved': 'red bold',
     'shelve.age': 'cyan',
     'shelve.newest': 'green bold',
     'shelve.name': 'blue bold',
     'status.added': 'green bold',
     'status.clean': 'none',
     'status.copied': 'none',
     'status.deleted': 'cyan bold underline',
     'status.ignored': 'black bold',
     'status.modified': 'blue bold',
     'status.removed': 'red bold',
     'status.unknown': 'magenta bold underline',
     'tags.normal': 'green',
     'tags.local': 'black bold',
 }
 
 def loadcolortable(ui, extname, colortable):
     _defaultstyles.update(colortable)
 
 def _terminfosetup(ui, mode, formatted):
     '''Initialize terminfo data and the terminal if we're in terminfo mode.'''
 
     # If we failed to load curses, we go ahead and return.
     if curses is None:
         return
     # Otherwise, see what the config file says.
     if mode not in ('auto', 'terminfo'):
         return
     ui._terminfoparams.update(_baseterminfoparams)
 
     for key, val in ui.configitems('color'):
         if key.startswith('color.'):
             newval = (False, int(val), '')
             ui._terminfoparams[key[6:]] = newval
         elif key.startswith('terminfo.'):
             newval = (True, '', val.replace('\\E', '\x1b'))
             ui._terminfoparams[key[9:]] = newval
     try:
         curses.setupterm()
     except curses.error as e:
         ui._terminfoparams.clear()
         return
 
     for key, (b, e, c) in ui._terminfoparams.copy().items():
         if not b:
             continue
         if not c and not curses.tigetstr(pycompat.sysstr(e)):
             # Most terminals don't support dim, invis, etc, so don't be
             # noisy and use ui.debug().
             ui.debug("no terminfo entry for %s\n" % e)
             del ui._terminfoparams[key]
     if not curses.tigetstr(r'setaf') or not curses.tigetstr(r'setab'):
         # Only warn about missing terminfo entries if we explicitly asked for
         # terminfo mode and we're in a formatted terminal.
         if mode == "terminfo" and formatted:
             ui.warn(_("no terminfo entry for setab/setaf: reverting to "
               "ECMA-48 color\n"))
         ui._terminfoparams.clear()
 
 def setup(ui):
     """configure color on a ui
 
     That function both set the colormode for the ui object and read
     the configuration looking for custom colors and effect definitions."""
     mode = _modesetup(ui)
     ui._colormode = mode
     if mode and mode != 'debug':
         configstyles(ui)
 
 def _modesetup(ui):
     if ui.plain('color'):
         return None
     config = ui.config('ui', 'color')
     if config == 'debug':
         return 'debug'
 
     auto = (config == 'auto')
     always = False
     if not auto and stringutil.parsebool(config):
         # We want the config to behave like a boolean, "on" is actually auto,
         # but "always" value is treated as a special case to reduce confusion.
         if ui.configsource('ui', 'color') == '--color' or config == 'always':
             always = True
         else:
             auto = True
 
     if not always and not auto:
         return None
 
     formatted = (always or (encoding.environ.get('TERM') != 'dumb'
                  and ui.formatted()))
 
     mode = ui.config('color', 'mode')
 
     # If pager is active, color.pagermode overrides color.mode.
     if getattr(ui, 'pageractive', False):
         mode = ui.config('color', 'pagermode', mode)
 
     realmode = mode
     if pycompat.iswindows:
         from . import win32
 
         term = encoding.environ.get('TERM')
         # TERM won't be defined in a vanilla cmd.exe environment.
 
         # UNIX-like environments on Windows such as Cygwin and MSYS will
         # set TERM. They appear to make a best effort attempt at setting it
         # to something appropriate. However, not all environments with TERM
         # defined support ANSI.
         ansienviron = term and 'xterm' in term
 
         if mode == 'auto':
             # Since "ansi" could result in terminal gibberish, we error on the
             # side of selecting "win32". However, if w32effects is not defined,
             # we almost certainly don't support "win32", so don't even try.
             # w32ffects is not populated when stdout is redirected, so checking
             # it first avoids win32 calls in a state known to error out.
             if ansienviron or not w32effects or win32.enablevtmode():
                 realmode = 'ansi'
             else:
                 realmode = 'win32'
         # An empty w32effects is a clue that stdout is redirected, and thus
         # cannot enable VT mode.
         elif mode == 'ansi' and w32effects and not ansienviron:
             win32.enablevtmode()
     elif mode == 'auto':
         realmode = 'ansi'
 
     def modewarn():
         # only warn if color.mode was explicitly set and we're in
         # a formatted terminal
         if mode == realmode and formatted:
             ui.warn(_('warning: failed to set color mode to %s\n') % mode)
 
     if realmode == 'win32':
         ui._terminfoparams.clear()
         if not w32effects:
             modewarn()
             return None
     elif realmode == 'ansi':
         ui._terminfoparams.clear()
     elif realmode == 'terminfo':
         _terminfosetup(ui, mode, formatted)
         if not ui._terminfoparams:
             ## FIXME Shouldn't we return None in this case too?
             modewarn()
             realmode = 'ansi'
     else:
         return None
 
     if always or (auto and formatted):
         return realmode
     return None
 
 def configstyles(ui):
     ui._styles.update(_defaultstyles)
     for status, cfgeffects in ui.configitems('color'):
         if '.' not in status or status.startswith(('color.', 'terminfo.')):
             continue
         cfgeffects = ui.configlist('color', status)
         if cfgeffects:
             good = []
             for e in cfgeffects:
                 if valideffect(ui, e):
                     good.append(e)
                 else:
                     ui.warn(_("ignoring unknown color/effect %r "
                               "(configured in color.%s)\n")
                             % (e, status))
             ui._styles[status] = ' '.join(good)
 
 def _activeeffects(ui):
     '''Return the effects map for the color mode set on the ui.'''
     if ui._colormode == 'win32':
         return w32effects
     elif ui._colormode is not None:
         return _effects
     return {}
 
 def valideffect(ui, effect):
     'Determine if the effect is valid or not.'
     return ((not ui._terminfoparams and effect in _activeeffects(ui))
              or (effect in ui._terminfoparams
                  or effect[:-11] in ui._terminfoparams))
 
 def _effect_str(ui, effect):
     '''Helper function for render_effects().'''
 
     bg = False
     if effect.endswith('_background'):
         bg = True
         effect = effect[:-11]
     try:
         attr, val, termcode = ui._terminfoparams[effect]
     except KeyError:
         return ''
     if attr:
         if termcode:
             return termcode
         else:
             return curses.tigetstr(pycompat.sysstr(val))
     elif bg:
         return curses.tparm(curses.tigetstr(r'setab'), val)
     else:
         return curses.tparm(curses.tigetstr(r'setaf'), val)
 
 def _mergeeffects(text, start, stop):
     """Insert start sequence at every occurrence of stop sequence
 
     >>> s = _mergeeffects(b'cyan', b'[C]', b'|')
     >>> s = _mergeeffects(s + b'yellow', b'[Y]', b'|')
     >>> s = _mergeeffects(b'ma' + s + b'genta', b'[M]', b'|')
     >>> s = _mergeeffects(b'red' + s, b'[R]', b'|')
     >>> s
     '[R]red[M]ma[Y][C]cyan|[R][M][Y]yellow|[R][M]genta|'
     """
     parts = []
     for t in text.split(stop):
         if not t:
             continue
         parts.extend([start, t, stop])
     return ''.join(parts)
 
 def _render_effects(ui, text, effects):
     'Wrap text in commands to turn on each effect.'
     if not text:
         return text
     if ui._terminfoparams:
         start = ''.join(_effect_str(ui, effect)
                         for effect in ['none'] + effects.split())
         stop = _effect_str(ui, 'none')
     else:
         activeeffects = _activeeffects(ui)
         start = [pycompat.bytestr(activeeffects[e])
                  for e in ['none'] + effects.split()]
         start = '\033[' + ';'.join(start) + 'm'
         stop = '\033[' + pycompat.bytestr(activeeffects['none']) + 'm'
     return _mergeeffects(text, start, stop)
 
 _ansieffectre = re.compile(br'\x1b\[[0-9;]*m')
 
 def stripeffects(text):
     """Strip ANSI control codes which could be inserted by colorlabel()"""
     return _ansieffectre.sub('', text)
 
 def colorlabel(ui, msg, label):
     """add color control code according to the mode"""
     if ui._colormode == 'debug':
         if label and msg:
             if msg.endswith('\n'):
                 msg = "[%s|%s]\n" % (label, msg[:-1])
             else:
                 msg = "[%s|%s]" % (label, msg)
     elif ui._colormode is not None:
         effects = []
         for l in label.split():
             s = ui._styles.get(l, '')
             if s:
                 effects.append(s)
             elif valideffect(ui, l):
                 effects.append(l)
         effects = ' '.join(effects)
         if effects:
             msg = '\n'.join([_render_effects(ui, line, effects)
                              for line in msg.split('\n')])
     return msg
 
 w32effects = None
 if pycompat.iswindows:
     import ctypes
 
     _kernel32 = ctypes.windll.kernel32
 
     _WORD = ctypes.c_ushort
 
     _INVALID_HANDLE_VALUE = -1
 
     class _COORD(ctypes.Structure):
-        _fields_ = [('X', ctypes.c_short),
-                    ('Y', ctypes.c_short)]
+        _fields_ = [(r'X', ctypes.c_short),
+                    (r'Y', ctypes.c_short)]
 
     class _SMALL_RECT(ctypes.Structure):
-        _fields_ = [('Left', ctypes.c_short),
-                    ('Top', ctypes.c_short),
-                    ('Right', ctypes.c_short),
-                    ('Bottom', ctypes.c_short)]
+        _fields_ = [(r'Left', ctypes.c_short),
+                    (r'Top', ctypes.c_short),
+                    (r'Right', ctypes.c_short),
+                    (r'Bottom', ctypes.c_short)]
 
     class _CONSOLE_SCREEN_BUFFER_INFO(ctypes.Structure):
-        _fields_ = [('dwSize', _COORD),
-                    ('dwCursorPosition', _COORD),
-                    ('wAttributes', _WORD),
-                    ('srWindow', _SMALL_RECT),
-                    ('dwMaximumWindowSize', _COORD)]
+        _fields_ = [(r'dwSize', _COORD),
+                    (r'dwCursorPosition', _COORD),
+                    (r'wAttributes', _WORD),
+                    (r'srWindow', _SMALL_RECT),
+                    (r'dwMaximumWindowSize', _COORD)]
 
     _STD_OUTPUT_HANDLE = 0xfffffff5 # (DWORD)-11
     _STD_ERROR_HANDLE = 0xfffffff4  # (DWORD)-12
 
     _FOREGROUND_BLUE = 0x0001
     _FOREGROUND_GREEN = 0x0002
     _FOREGROUND_RED = 0x0004
     _FOREGROUND_INTENSITY = 0x0008
 
     _BACKGROUND_BLUE = 0x0010
     _BACKGROUND_GREEN = 0x0020
     _BACKGROUND_RED = 0x0040
     _BACKGROUND_INTENSITY = 0x0080
 
     _COMMON_LVB_REVERSE_VIDEO = 0x4000
     _COMMON_LVB_UNDERSCORE = 0x8000
 
     # http://msdn.microsoft.com/en-us/library/ms682088%28VS.85%29.aspx
     w32effects = {
         'none': -1,
         'black': 0,
         'red': _FOREGROUND_RED,
         'green': _FOREGROUND_GREEN,
         'yellow': _FOREGROUND_RED | _FOREGROUND_GREEN,
         'blue': _FOREGROUND_BLUE,
         'magenta': _FOREGROUND_BLUE | _FOREGROUND_RED,
         'cyan': _FOREGROUND_BLUE | _FOREGROUND_GREEN,
         'white': _FOREGROUND_RED | _FOREGROUND_GREEN | _FOREGROUND_BLUE,
         'bold': _FOREGROUND_INTENSITY,
         'black_background': 0x100,                  # unused value > 0x0f
         'red_background': _BACKGROUND_RED,
         'green_background': _BACKGROUND_GREEN,
         'yellow_background': _BACKGROUND_RED | _BACKGROUND_GREEN,
         'blue_background': _BACKGROUND_BLUE,
         'purple_background': _BACKGROUND_BLUE | _BACKGROUND_RED,
         'cyan_background': _BACKGROUND_BLUE | _BACKGROUND_GREEN,
         'white_background': (_BACKGROUND_RED | _BACKGROUND_GREEN |
                              _BACKGROUND_BLUE),
         'bold_background': _BACKGROUND_INTENSITY,
         'underline': _COMMON_LVB_UNDERSCORE,  # double-byte charsets only
         'inverse': _COMMON_LVB_REVERSE_VIDEO, # double-byte charsets only
     }
 
     passthrough = {_FOREGROUND_INTENSITY,
                    _BACKGROUND_INTENSITY,
                    _COMMON_LVB_UNDERSCORE,
                    _COMMON_LVB_REVERSE_VIDEO}
 
     stdout = _kernel32.GetStdHandle(
                   _STD_OUTPUT_HANDLE)  # don't close the handle returned
     if stdout is None or stdout == _INVALID_HANDLE_VALUE:
         w32effects = None
     else:
         csbi = _CONSOLE_SCREEN_BUFFER_INFO()
         if not _kernel32.GetConsoleScreenBufferInfo(
                     stdout, ctypes.byref(csbi)):
             # stdout may not support GetConsoleScreenBufferInfo()
             # when called from subprocess or redirected
             w32effects = None
         else:
             origattr = csbi.wAttributes
-            ansire = re.compile('\033\[([^m]*)m([^\033]*)(.*)',
+            ansire = re.compile(b'\033\[([^m]*)m([^\033]*)(.*)',
                                 re.MULTILINE | re.DOTALL)
 
     def win32print(ui, writefunc, *msgs, **opts):
         for text in msgs:
             _win32print(ui, text, writefunc, **opts)
 
     def _win32print(ui, text, writefunc, **opts):
         label = opts.get(r'label', '')
         attr = origattr
 
         def mapcolor(val, attr):
             if val == -1:
                 return origattr
             elif val in passthrough:
                 return attr | val
             elif val > 0x0f:
                 return (val & 0x70) | (attr & 0x8f)
             else:
                 return (val & 0x07) | (attr & 0xf8)
 
         # determine console attributes based on labels
         for l in label.split():
             style = ui._styles.get(l, '')
             for effect in style.split():
                 try:
                     attr = mapcolor(w32effects[effect], attr)
                 except KeyError:
                     # w32effects could not have certain attributes so we skip
                     # them if not found
                     pass
         # hack to ensure regexp finds data
-        if not text.startswith('\033['):
-            text = '\033[m' + text
+        if not text.startswith(b'\033['):
+            text = b'\033[m' + text
 
         # Look for ANSI-like codes embedded in text
         m = re.match(ansire, text)
 
         try:
             while m:
-                for sattr in m.group(1).split(';'):
+                for sattr in m.group(1).split(b';'):
                     if sattr:
                         attr = mapcolor(int(sattr), attr)
                 ui.flush()
                 _kernel32.SetConsoleTextAttribute(stdout, attr)
                 writefunc(m.group(2), **opts)
                 m = re.match(ansire, m.group(3))
         finally:
             # Explicitly reset original attributes
             ui.flush()
             _kernel32.SetConsoleTextAttribute(stdout, origattr)

mercurial/pure/osutil.py

@@ -1,271 +1,273
 # osutil.py - pure Python version of osutil.c
 #
 #  Copyright 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.
 
 from __future__ import absolute_import
 
 import ctypes
 import ctypes.util
 import os
 import socket
 import stat as statmod
 
 from .. import (
+    encoding,
     pycompat,
 )
 
 def _mode_to_kind(mode):
     if statmod.S_ISREG(mode):
         return statmod.S_IFREG
     if statmod.S_ISDIR(mode):
         return statmod.S_IFDIR
     if statmod.S_ISLNK(mode):
         return statmod.S_IFLNK
     if statmod.S_ISBLK(mode):
         return statmod.S_IFBLK
     if statmod.S_ISCHR(mode):
         return statmod.S_IFCHR
     if statmod.S_ISFIFO(mode):
         return statmod.S_IFIFO
     if statmod.S_ISSOCK(mode):
         return statmod.S_IFSOCK
     return mode
 
 def listdir(path, stat=False, skip=None):
     '''listdir(path, stat=False) -> list_of_tuples
 
     Return a sorted list containing information about the entries
     in the directory.
 
     If stat is True, each element is a 3-tuple:
 
       (name, type, stat object)
 
     Otherwise, each element is a 2-tuple:
 
       (name, type)
     '''
     result = []
     prefix = path
     if not prefix.endswith(pycompat.ossep):
         prefix += pycompat.ossep
     names = os.listdir(path)
     names.sort()
     for fn in names:
         st = os.lstat(prefix + fn)
         if fn == skip and statmod.S_ISDIR(st.st_mode):
             return []
         if stat:
             result.append((fn, _mode_to_kind(st.st_mode), st))
         else:
             result.append((fn, _mode_to_kind(st.st_mode)))
     return result
 
 if not pycompat.iswindows:
     posixfile = open
 
     _SCM_RIGHTS = 0x01
     _socklen_t = ctypes.c_uint
 
     if pycompat.sysplatform.startswith('linux'):
         # socket.h says "the type should be socklen_t but the definition of
         # the kernel is incompatible with this."
         _cmsg_len_t = ctypes.c_size_t
         _msg_controllen_t = ctypes.c_size_t
         _msg_iovlen_t = ctypes.c_size_t
     else:
         _cmsg_len_t = _socklen_t
         _msg_controllen_t = _socklen_t
         _msg_iovlen_t = ctypes.c_int
 
     class _iovec(ctypes.Structure):
         _fields_ = [
             (u'iov_base', ctypes.c_void_p),
             (u'iov_len', ctypes.c_size_t),
         ]
 
     class _msghdr(ctypes.Structure):
         _fields_ = [
             (u'msg_name', ctypes.c_void_p),
             (u'msg_namelen', _socklen_t),
             (u'msg_iov', ctypes.POINTER(_iovec)),
             (u'msg_iovlen', _msg_iovlen_t),
             (u'msg_control', ctypes.c_void_p),
             (u'msg_controllen', _msg_controllen_t),
             (u'msg_flags', ctypes.c_int),
         ]
 
     class _cmsghdr(ctypes.Structure):
         _fields_ = [
             (u'cmsg_len', _cmsg_len_t),
             (u'cmsg_level', ctypes.c_int),
             (u'cmsg_type', ctypes.c_int),
             (u'cmsg_data', ctypes.c_ubyte * 0),
         ]
 
     _libc = ctypes.CDLL(ctypes.util.find_library(u'c'), use_errno=True)
     _recvmsg = getattr(_libc, 'recvmsg', None)
     if _recvmsg:
         _recvmsg.restype = getattr(ctypes, 'c_ssize_t', ctypes.c_long)
         _recvmsg.argtypes = (ctypes.c_int, ctypes.POINTER(_msghdr),
                              ctypes.c_int)
     else:
         # recvmsg isn't always provided by libc; such systems are unsupported
         def _recvmsg(sockfd, msg, flags):
             raise NotImplementedError('unsupported platform')
 
     def _CMSG_FIRSTHDR(msgh):
         if msgh.msg_controllen < ctypes.sizeof(_cmsghdr):
             return
         cmsgptr = ctypes.cast(msgh.msg_control, ctypes.POINTER(_cmsghdr))
         return cmsgptr.contents
 
     # The pure version is less portable than the native version because the
     # handling of socket ancillary data heavily depends on C preprocessor.
     # Also, some length fields are wrongly typed in Linux kernel.
     def recvfds(sockfd):
         """receive list of file descriptors via socket"""
         dummy = (ctypes.c_ubyte * 1)()
         iov = _iovec(ctypes.cast(dummy, ctypes.c_void_p), ctypes.sizeof(dummy))
         cbuf = ctypes.create_string_buffer(256)
         msgh = _msghdr(None, 0,
                        ctypes.pointer(iov), 1,
                        ctypes.cast(cbuf, ctypes.c_void_p), ctypes.sizeof(cbuf),
                        0)
         r = _recvmsg(sockfd, ctypes.byref(msgh), 0)
         if r < 0:
             e = ctypes.get_errno()
             raise OSError(e, os.strerror(e))
         # assumes that the first cmsg has fds because it isn't easy to write
         # portable CMSG_NXTHDR() with ctypes.
         cmsg = _CMSG_FIRSTHDR(msgh)
         if not cmsg:
             return []
         if (cmsg.cmsg_level != socket.SOL_SOCKET or
             cmsg.cmsg_type != _SCM_RIGHTS):
             return []
         rfds = ctypes.cast(cmsg.cmsg_data, ctypes.POINTER(ctypes.c_int))
         rfdscount = ((cmsg.cmsg_len - _cmsghdr.cmsg_data.offset) /
                      ctypes.sizeof(ctypes.c_int))
         return [rfds[i] for i in pycompat.xrange(rfdscount)]
 
 else:
     import msvcrt
 
     _kernel32 = ctypes.windll.kernel32
 
     _DWORD = ctypes.c_ulong
     _LPCSTR = _LPSTR = ctypes.c_char_p
     _HANDLE = ctypes.c_void_p
 
     _INVALID_HANDLE_VALUE = _HANDLE(-1).value
 
     # CreateFile
     _FILE_SHARE_READ = 0x00000001
     _FILE_SHARE_WRITE = 0x00000002
     _FILE_SHARE_DELETE = 0x00000004
 
     _CREATE_ALWAYS = 2
     _OPEN_EXISTING = 3
     _OPEN_ALWAYS = 4
 
     _GENERIC_READ = 0x80000000
     _GENERIC_WRITE = 0x40000000
 
     _FILE_ATTRIBUTE_NORMAL = 0x80
 
     # open_osfhandle flags
     _O_RDONLY = 0x0000
     _O_RDWR = 0x0002
     _O_APPEND = 0x0008
 
     _O_TEXT = 0x4000
     _O_BINARY = 0x8000
 
     # types of parameters of C functions used (required by pypy)
 
     _kernel32.CreateFileA.argtypes = [_LPCSTR, _DWORD, _DWORD, ctypes.c_void_p,
         _DWORD, _DWORD, _HANDLE]
     _kernel32.CreateFileA.restype = _HANDLE
 
     def _raiseioerror(name):
         err = ctypes.WinError()
-        raise IOError(err.errno, '%s: %s' % (name, err.strerror))
+        raise IOError(err.errno, r'%s: %s' % (encoding.strfromlocal(name),
+                                              err.strerror))
 
     class posixfile(object):
         '''a file object aiming for POSIX-like semantics
 
         CPython's open() returns a file that was opened *without* setting the
         _FILE_SHARE_DELETE flag, which causes rename and unlink to abort.
         This even happens if any hardlinked copy of the file is in open state.
         We set _FILE_SHARE_DELETE here, so files opened with posixfile can be
         renamed and deleted while they are held open.
         Note that if a file opened with posixfile is unlinked, the file
         remains but cannot be opened again or be recreated under the same name,
         until all reading processes have closed the file.'''
 
-        def __init__(self, name, mode='r', bufsize=-1):
-            if 'b' in mode:
+        def __init__(self, name, mode=b'r', bufsize=-1):
+            if b'b' in mode:
                 flags = _O_BINARY
             else:
                 flags = _O_TEXT
 
-            m0 = mode[0]
-            if m0 == 'r' and '+' not in mode:
+            m0 = mode[0:1]
+            if m0 == b'r' and b'+' not in mode:
                 flags |= _O_RDONLY
                 access = _GENERIC_READ
             else:
                 # work around http://support.microsoft.com/kb/899149 and
                 # set _O_RDWR for 'w' and 'a', even if mode has no '+'
                 flags |= _O_RDWR
                 access = _GENERIC_READ | _GENERIC_WRITE
 
-            if m0 == 'r':
+            if m0 == b'r':
                 creation = _OPEN_EXISTING
-            elif m0 == 'w':
+            elif m0 == b'w':
                 creation = _CREATE_ALWAYS
-            elif m0 == 'a':
+            elif m0 == b'a':
                 creation = _OPEN_ALWAYS
                 flags |= _O_APPEND
             else:
-                raise ValueError("invalid mode: %s" % mode)
+                raise ValueError(r"invalid mode: %s" % pycompat.sysstr(mode))
 
             fh = _kernel32.CreateFileA(name, access,
                     _FILE_SHARE_READ | _FILE_SHARE_WRITE | _FILE_SHARE_DELETE,
                     None, creation, _FILE_ATTRIBUTE_NORMAL, None)
             if fh == _INVALID_HANDLE_VALUE:
                 _raiseioerror(name)
 
             fd = msvcrt.open_osfhandle(fh, flags)
             if fd == -1:
                 _kernel32.CloseHandle(fh)
                 _raiseioerror(name)
 
             f = os.fdopen(fd, pycompat.sysstr(mode), bufsize)
             # unfortunately, f.name is '<fdopen>' at this point -- so we store
             # the name on this wrapper. We cannot just assign to f.name,
             # because that attribute is read-only.
             object.__setattr__(self, r'name', name)
             object.__setattr__(self, r'_file', f)
 
         def __iter__(self):
             return self._file
 
         def __getattr__(self, name):
             return getattr(self._file, name)
 
         def __setattr__(self, name, value):
             '''mimics the read-only attributes of Python file objects
             by raising 'TypeError: readonly attribute' if someone tries:
               f = posixfile('foo.txt')
               f.name = 'bla'  '''
             return self._file.__setattr__(name, value)
 
         def __enter__(self):
             return self._file.__enter__()
 
         def __exit__(self, exc_type, exc_value, exc_tb):
             return self._file.__exit__(exc_type, exc_value, exc_tb)

mercurial/windows.py

@@ -1,594 +1,594
 # windows.py - Windows utility function implementations 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.
 
 from __future__ import absolute_import
 
 import errno
 import msvcrt
 import os
 import re
 import stat
 import string
 import sys
 
 from .i18n import _
 from . import (
     encoding,
     error,
     policy,
     pycompat,
     win32,
 )
 
 try:
     import _winreg as winreg
     winreg.CloseKey
 except ImportError:
     import winreg
 
 osutil = policy.importmod(r'osutil')
 
 getfsmountpoint = win32.getvolumename
 getfstype = win32.getfstype
 getuser = win32.getuser
 hidewindow = win32.hidewindow
 makedir = win32.makedir
 nlinks = win32.nlinks
 oslink = win32.oslink
 samedevice = win32.samedevice
 samefile = win32.samefile
 setsignalhandler = win32.setsignalhandler
 spawndetached = win32.spawndetached
 split = os.path.split
 testpid = win32.testpid
 unlink = win32.unlink
 
 umask = 0o022
 
 class mixedfilemodewrapper(object):
     """Wraps a file handle when it is opened in read/write mode.
 
     fopen() and fdopen() on Windows have a specific-to-Windows requirement
     that files opened with mode r+, w+, or a+ make a call to a file positioning
     function when switching between reads and writes. Without this extra call,
     Python will raise a not very intuitive "IOError: [Errno 0] Error."
 
     This class wraps posixfile instances when the file is opened in read/write
     mode and automatically adds checks or inserts appropriate file positioning
     calls when necessary.
     """
     OPNONE = 0
     OPREAD = 1
     OPWRITE = 2
 
     def __init__(self, fp):
         object.__setattr__(self, r'_fp', fp)
         object.__setattr__(self, r'_lastop', 0)
 
     def __enter__(self):
         return self._fp.__enter__()
 
     def __exit__(self, exc_type, exc_val, exc_tb):
         self._fp.__exit__(exc_type, exc_val, exc_tb)
 
     def __getattr__(self, name):
         return getattr(self._fp, name)
 
     def __setattr__(self, name, value):
         return self._fp.__setattr__(name, value)
 
     def _noopseek(self):
         self._fp.seek(0, os.SEEK_CUR)
 
     def seek(self, *args, **kwargs):
         object.__setattr__(self, r'_lastop', self.OPNONE)
         return self._fp.seek(*args, **kwargs)
 
     def write(self, d):
         if self._lastop == self.OPREAD:
             self._noopseek()
 
         object.__setattr__(self, r'_lastop', self.OPWRITE)
         return self._fp.write(d)
 
     def writelines(self, *args, **kwargs):
         if self._lastop == self.OPREAD:
             self._noopeseek()
 
         object.__setattr__(self, r'_lastop', self.OPWRITE)
         return self._fp.writelines(*args, **kwargs)
 
     def read(self, *args, **kwargs):
         if self._lastop == self.OPWRITE:
             self._noopseek()
 
         object.__setattr__(self, r'_lastop', self.OPREAD)
         return self._fp.read(*args, **kwargs)
 
     def readline(self, *args, **kwargs):
         if self._lastop == self.OPWRITE:
             self._noopseek()
 
         object.__setattr__(self, r'_lastop', self.OPREAD)
         return self._fp.readline(*args, **kwargs)
 
     def readlines(self, *args, **kwargs):
         if self._lastop == self.OPWRITE:
             self._noopseek()
 
         object.__setattr__(self, r'_lastop', self.OPREAD)
         return self._fp.readlines(*args, **kwargs)
 
 def posixfile(name, mode='r', buffering=-1):
     '''Open a file with even more POSIX-like semantics'''
     try:
         fp = osutil.posixfile(name, mode, buffering) # may raise WindowsError
 
         # The position when opening in append mode is implementation defined, so
         # make it consistent with other platforms, which position at EOF.
         if 'a' in mode:
             fp.seek(0, os.SEEK_END)
 
         if '+' in mode:
             return mixedfilemodewrapper(fp)
 
         return fp
     except WindowsError as err:
         # convert to a friendlier exception
         raise IOError(err.errno, '%s: %s' % (
             name, encoding.strtolocal(err.strerror)))
 
 # may be wrapped by win32mbcs extension
 listdir = osutil.listdir
 
 class winstdout(object):
     '''stdout on windows misbehaves if sent through a pipe'''
 
     def __init__(self, fp):
         self.fp = fp
 
     def __getattr__(self, key):
         return getattr(self.fp, key)
 
     def close(self):
         try:
             self.fp.close()
         except IOError:
             pass
 
     def write(self, s):
         try:
             # This is workaround for "Not enough space" error on
             # writing large size of data to console.
             limit = 16000
             l = len(s)
             start = 0
             self.softspace = 0
             while start < l:
                 end = start + limit
                 self.fp.write(s[start:end])
                 start = end
         except IOError as inst:
             if inst.errno != 0 and not win32.lasterrorwaspipeerror(inst):
                 raise
             self.close()
             raise IOError(errno.EPIPE, 'Broken pipe')
 
     def flush(self):
         try:
             return self.fp.flush()
         except IOError as inst:
             if not win32.lasterrorwaspipeerror(inst):
                 raise
             raise IOError(errno.EPIPE, 'Broken pipe')
 
 def _is_win_9x():
     '''return true if run on windows 95, 98 or me.'''
     try:
         return sys.getwindowsversion()[3] == 1
     except AttributeError:
         return 'command' in encoding.environ.get('comspec', '')
 
 def openhardlinks():
     return not _is_win_9x()
 
 def parsepatchoutput(output_line):
     """parses the output produced by patch and returns the filename"""
     pf = output_line[14:]
     if pf[0] == '`':
         pf = pf[1:-1] # Remove the quotes
     return pf
 
 def sshargs(sshcmd, host, user, port):
     '''Build argument list for ssh or Plink'''
     pflag = 'plink' in sshcmd.lower() and '-P' or '-p'
     args = user and ("%s@%s" % (user, host)) or host
     if args.startswith('-') or args.startswith('/'):
         raise error.Abort(
             _('illegal ssh hostname or username starting with - or /: %s') %
             args)
     args = shellquote(args)
     if port:
         args = '%s %s %s' % (pflag, shellquote(port), args)
     return args
 
 def setflags(f, l, x):
     pass
 
 def copymode(src, dst, mode=None):
     pass
 
 def checkexec(path):
     return False
 
 def checklink(path):
     return False
 
 def setbinary(fd):
     # When run without console, pipes may expose invalid
     # fileno(), usually set to -1.
     fno = getattr(fd, 'fileno', None)
     if fno is not None and fno() >= 0:
         msvcrt.setmode(fno(), os.O_BINARY)
 
 def pconvert(path):
     return path.replace(pycompat.ossep, '/')
 
 def localpath(path):
     return path.replace('/', '\\')
 
 def normpath(path):
     return pconvert(os.path.normpath(path))
 
 def normcase(path):
     return encoding.upper(path) # NTFS compares via upper()
 
 # see posix.py for definitions
 normcasespec = encoding.normcasespecs.upper
 normcasefallback = encoding.upperfallback
 
 def samestat(s1, s2):
     return False
 
 def shelltocmdexe(path, env):
     r"""Convert shell variables in the form $var and ${var} inside ``path``
     to %var% form.  Existing Windows style variables are left unchanged.
 
     The variables are limited to the given environment.  Unknown variables are
     left unchanged.
 
     >>> e = {b'var1': b'v1', b'var2': b'v2', b'var3': b'v3'}
     >>> # Only valid values are expanded
     >>> shelltocmdexe(b'cmd $var1 ${var2} %var3% $missing ${missing} %missing%',
     ...               e)
     'cmd %var1% %var2% %var3% $missing ${missing} %missing%'
     >>> # Single quote prevents expansion, as does \$ escaping
     >>> shelltocmdexe(b"cmd '$var1 ${var2} %var3%' \$var1 \${var2} \\", e)
     'cmd "$var1 ${var2} %var3%" $var1 ${var2} \\'
     >>> # $$ is not special. %% is not special either, but can be the end and
     >>> # start of consecutive variables
     >>> shelltocmdexe(b"cmd $$ %% %var1%%var2%", e)
     'cmd $$ %% %var1%%var2%'
     >>> # No double substitution
     >>> shelltocmdexe(b"$var1 %var1%", {b'var1': b'%var2%', b'var2': b'boom'})
     '%var1% %var1%'
     >>> # Tilde expansion
     >>> shelltocmdexe(b"~/dir ~\dir2 ~tmpfile \~/", {})
     '%USERPROFILE%/dir %USERPROFILE%\\dir2 ~tmpfile ~/'
     """
     if not any(c in path for c in b"$'~"):
         return path
 
     varchars = pycompat.sysbytes(string.ascii_letters + string.digits) + b'_-'
 
     res = b''
     index = 0
     pathlen = len(path)
     while index < pathlen:
         c = path[index]
         if c == b'\'':   # no expansion within single quotes
             path = path[index + 1:]
             pathlen = len(path)
             try:
                 index = path.index(b'\'')
                 res += b'"' + path[:index] + b'"'
             except ValueError:
                 res += c + path
                 index = pathlen - 1
         elif c == b'%':  # variable
             path = path[index + 1:]
             pathlen = len(path)
             try:
                 index = path.index(b'%')
             except ValueError:
                 res += b'%' + path
                 index = pathlen - 1
             else:
                 var = path[:index]
                 res += b'%' + var + b'%'
         elif c == b'$':  # variable
             if path[index + 1:index + 2] == b'{':
                 path = path[index + 2:]
                 pathlen = len(path)
                 try:
                     index = path.index(b'}')
                     var = path[:index]
 
                     # See below for why empty variables are handled specially
                     if env.get(var, '') != '':
                         res += b'%' + var + b'%'
                     else:
                         res += b'${' + var + b'}'
                 except ValueError:
                     res += b'${' + path
                     index = pathlen - 1
             else:
                 var = b''
                 index += 1
                 c = path[index:index + 1]
                 while c != b'' and c in varchars:
                     var += c
                     index += 1
                     c = path[index:index + 1]
                 # Some variables (like HG_OLDNODE) may be defined, but have an
                 # empty value.  Those need to be skipped because when spawning
                 # cmd.exe to run the hook, it doesn't replace %VAR% for an empty
                 # VAR, and that really confuses things like revset expressions.
                 # OTOH, if it's left in Unix format and the hook runs sh.exe, it
                 # will substitute to an empty string, and everything is happy.
                 if env.get(var, '') != '':
                     res += b'%' + var + b'%'
                 else:
                     res += b'$' + var
 
                 if c != '':
                     index -= 1
         elif (c == b'~' and index + 1 < pathlen
               and path[index + 1] in (b'\\', b'/')):
             res += "%USERPROFILE%"
         elif (c == b'\\' and index + 1 < pathlen
               and path[index + 1] in (b'$', b'~')):
             # Skip '\', but only if it is escaping $ or ~
             res += path[index + 1]
             index += 1
         else:
             res += c
 
         index += 1
     return res
 
 # A sequence of backslashes is special iff it precedes a double quote:
 # - if there's an even number of backslashes, the double quote is not
 #   quoted (i.e. it ends the quoted region)
 # - if there's an odd number of backslashes, the double quote is quoted
 # - in both cases, every pair of backslashes is unquoted into a single
 #   backslash
 # (See http://msdn2.microsoft.com/en-us/library/a1y7w461.aspx )
 # So, to quote a string, we must surround it in double quotes, double
 # the number of backslashes that precede double quotes and add another
 # backslash before every double quote (being careful with the double
 # quote we've appended to the end)
 _quotere = None
 _needsshellquote = None
 def shellquote(s):
     r"""
     >>> shellquote(br'C:\Users\xyz')
     '"C:\\Users\\xyz"'
     >>> shellquote(br'C:\Users\xyz/mixed')
     '"C:\\Users\\xyz/mixed"'
     >>> # Would be safe not to quote too, since it is all double backslashes
     >>> shellquote(br'C:\\Users\\xyz')
     '"C:\\\\Users\\\\xyz"'
     >>> # But this must be quoted
     >>> shellquote(br'C:\\Users\\xyz/abc')
     '"C:\\\\Users\\\\xyz/abc"'
     """
     global _quotere
     if _quotere is None:
-        _quotere = re.compile(r'(\\*)("|\\$)')
+        _quotere = re.compile(br'(\\*)("|\\$)')
     global _needsshellquote
     if _needsshellquote is None:
         # ":" is also treated as "safe character", because it is used as a part
         # of path name on Windows.  "\" is also part of a path name, but isn't
         # safe because shlex.split() (kind of) treats it as an escape char and
         # drops it.  It will leave the next character, even if it is another
         # "\".
-        _needsshellquote = re.compile(r'[^a-zA-Z0-9._:/-]').search
+        _needsshellquote = re.compile(br'[^a-zA-Z0-9._:/-]').search
     if s and not _needsshellquote(s) and not _quotere.search(s):
         # "s" shouldn't have to be quoted
         return s
-    return '"%s"' % _quotere.sub(r'\1\1\\\2', s)
+    return b'"%s"' % _quotere.sub(br'\1\1\\\2', s)
 
 def _unquote(s):
     if s.startswith(b'"') and s.endswith(b'"'):
         return s[1:-1]
     return s
 
 def shellsplit(s):
     """Parse a command string in cmd.exe way (best-effort)"""
     return pycompat.maplist(_unquote, pycompat.shlexsplit(s, posix=False))
 
 def quotecommand(cmd):
     """Build a command string suitable for os.popen* calls."""
     if sys.version_info < (2, 7, 1):
         # Python versions since 2.7.1 do this extra quoting themselves
         return '"' + cmd + '"'
     return cmd
 
 # if you change this stub into a real check, please try to implement the
 # username and groupname functions above, too.
 def isowner(st):
     return True
 
 def findexe(command):
     '''Find executable for command searching like cmd.exe does.
     If command is a basename then PATH is searched for command.
     PATH isn't searched if command is an absolute or relative path.
     An extension from PATHEXT is found and added if not present.
     If command isn't found None is returned.'''
     pathext = encoding.environ.get('PATHEXT', '.COM;.EXE;.BAT;.CMD')
     pathexts = [ext for ext in pathext.lower().split(pycompat.ospathsep)]
     if os.path.splitext(command)[1].lower() in pathexts:
         pathexts = ['']
 
     def findexisting(pathcommand):
         'Will append extension (if needed) and return existing file'
         for ext in pathexts:
             executable = pathcommand + ext
             if os.path.exists(executable):
                 return executable
         return None
 
     if pycompat.ossep in command:
         return findexisting(command)
 
     for path in encoding.environ.get('PATH', '').split(pycompat.ospathsep):
         executable = findexisting(os.path.join(path, command))
         if executable is not None:
             return executable
     return findexisting(os.path.expanduser(os.path.expandvars(command)))
 
 _wantedkinds = {stat.S_IFREG, stat.S_IFLNK}
 
 def statfiles(files):
     '''Stat each file in files. Yield each stat, or None if a file
     does not exist or has a type we don't care about.
 
     Cluster and cache stat per directory to minimize number of OS stat calls.'''
     dircache = {} # dirname -> filename -> status | None if file does not exist
     getkind = stat.S_IFMT
     for nf in files:
         nf  = normcase(nf)
         dir, base = os.path.split(nf)
         if not dir:
             dir = '.'
         cache = dircache.get(dir, None)
         if cache is None:
             try:
                 dmap = dict([(normcase(n), s)
                              for n, k, s in listdir(dir, True)
                              if getkind(s.st_mode) in _wantedkinds])
             except OSError as err:
                 # Python >= 2.5 returns ENOENT and adds winerror field
                 # EINVAL is raised if dir is not a directory.
                 if err.errno not in (errno.ENOENT, errno.EINVAL,
                                      errno.ENOTDIR):
                     raise
                 dmap = {}
             cache = dircache.setdefault(dir, dmap)
         yield cache.get(base, None)
 
 def username(uid=None):
     """Return the name of the user with the given uid.
 
     If uid is None, return the name of the current user."""
     return None
 
 def groupname(gid=None):
     """Return the name of the group with the given gid.
 
     If gid is None, return the name of the current group."""
     return None
 
 def removedirs(name):
     """special version of os.removedirs that does not remove symlinked
     directories or junction points if they actually contain files"""
     if listdir(name):
         return
     os.rmdir(name)
     head, tail = os.path.split(name)
     if not tail:
         head, tail = os.path.split(head)
     while head and tail:
         try:
             if listdir(head):
                 return
             os.rmdir(head)
         except (ValueError, OSError):
             break
         head, tail = os.path.split(head)
 
 def rename(src, dst):
     '''atomically rename file src to dst, replacing dst if it exists'''
     try:
         os.rename(src, dst)
     except OSError as e:
         if e.errno != errno.EEXIST:
             raise
         unlink(dst)
         os.rename(src, dst)
 
 def gethgcmd():
     return [sys.executable] + sys.argv[:1]
 
 def groupmembers(name):
     # Don't support groups on Windows for now
     raise KeyError
 
 def isexec(f):
     return False
 
 class cachestat(object):
     def __init__(self, path):
         pass
 
     def cacheable(self):
         return False
 
 def lookupreg(key, valname=None, scope=None):
     ''' Look up a key/value name in the Windows registry.
 
     valname: value name. If unspecified, the default value for the key
     is used.
     scope: optionally specify scope for registry lookup, this can be
     a sequence of scopes to look up in order. Default (CURRENT_USER,
     LOCAL_MACHINE).
     '''
     if scope is None:
         scope = (winreg.HKEY_CURRENT_USER, winreg.HKEY_LOCAL_MACHINE)
     elif not isinstance(scope, (list, tuple)):
         scope = (scope,)
     for s in scope:
         try:
             with winreg.OpenKey(s, encoding.strfromlocal(key)) as hkey:
                 val = winreg.QueryValueEx(hkey, valname)[0]
                 # never let a Unicode string escape into the wild
                 return encoding.unitolocal(val)
         except EnvironmentError:
             pass
 
 expandglobs = True
 
 def statislink(st):
     '''check whether a stat result is a symlink'''
     return False
 
 def statisexec(st):
     '''check whether a stat result is an executable file'''
     return False
 
 def poll(fds):
     # see posix.py for description
     raise NotImplementedError()
 
 def readpipe(pipe):
     """Read all available data from a pipe."""
     chunks = []
     while True:
         size = win32.peekpipe(pipe)
         if not size:
             break
 
         s = pipe.read(size)
         if not s:
             break
         chunks.append(s)
 
     return ''.join(chunks)
 
 def bindunixsocket(sock, path):
     raise NotImplementedError('unsupported platform')