Here's how to alias cp65001 to UTF-8 without changing encodingsaliases.py:
import codecs
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
(IMHO, don't pay any attention to the silliness about cp65001 not being identical to UTF-8 at http://bugs.python.org/issue6058#msg97731 . It's intended to be the same, even if Microsoft's codec has some minor bugs.)
Here is some code (written for Tahoe-LAFS, tahoe-lafs.org) that makes console output work regardless of the chcp code page, and also reads Unicode command-line arguments. Credit to Michael Kaplan for the idea behind this solution. If stdout or stderr are redirected, it will output UTF-8. If you want a Byte Order Mark, you'll need to write it explicitly.
[Edit: This version uses WriteConsoleW instead of the _O_U8TEXT flag in the MSVC runtime library, which is buggy. WriteConsoleW is also buggy relative to the MS documentation, but less so.]
import sys
if sys.platform == "win32":
import codecs
from ctypes import WINFUNCTYPE, windll, POINTER, byref, c_int
from ctypes.wintypes import BOOL, HANDLE, DWORD, LPWSTR, LPCWSTR, LPVOID
original_stderr = sys.stderr
# If any exception occurs in this code, we'll probably try to print it on stderr,
# which makes for frustrating debugging if stderr is directed to our wrapper.
# So be paranoid about catching errors and reporting them to original_stderr,
# so that we can at least see them.
def _complain(message):
print >>original_stderr, message if isinstance(message, str) else repr(message)
# Work around <http://bugs.python.org/issue6058>.
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
# Make Unicode console output work independently of the current code page.
# This also fixes <http://bugs.python.org/issue1602>.
# Credit to Michael Kaplan <http://www.siao2.com/2010/04/07/9989346.aspx>
# and TZOmegaTZIOY
# <http://stackoverflow.com/questions/878972/windows-cmd-encoding-change-causes-python-crash/1432462#1432462>.
try:
# <http://msdn.microsoft.com/en-us/library/ms683231(VS.85).aspx>
# HANDLE WINAPI GetStdHandle(DWORD nStdHandle);
# returns INVALID_HANDLE_VALUE, NULL, or a valid handle
#
# <http://msdn.microsoft.com/en-us/library/aa364960(VS.85).aspx>
# DWORD WINAPI GetFileType(DWORD hFile);
#
# <http://msdn.microsoft.com/en-us/library/ms683167(VS.85).aspx>
# BOOL WINAPI GetConsoleMode(HANDLE hConsole, LPDWORD lpMode);
GetStdHandle = WINFUNCTYPE(HANDLE, DWORD)(("GetStdHandle", windll.kernel32))
STD_OUTPUT_HANDLE = DWORD(-11)
STD_ERROR_HANDLE = DWORD(-12)
GetFileType = WINFUNCTYPE(DWORD, DWORD)(("GetFileType", windll.kernel32))
FILE_TYPE_CHAR = 0x0002
FILE_TYPE_REMOTE = 0x8000
GetConsoleMode = WINFUNCTYPE(BOOL, HANDLE, POINTER(DWORD))(("GetConsoleMode", windll.kernel32))
INVALID_HANDLE_VALUE = DWORD(-1).value
def not_a_console(handle):
if handle == INVALID_HANDLE_VALUE or handle is None:
return True
return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR
or GetConsoleMode(handle, byref(DWORD())) == 0)
old_stdout_fileno = None
old_stderr_fileno = None
if hasattr(sys.stdout, 'fileno'):
old_stdout_fileno = sys.stdout.fileno()
if hasattr(sys.stderr, 'fileno'):
old_stderr_fileno = sys.stderr.fileno()
STDOUT_FILENO = 1
STDERR_FILENO = 2
real_stdout = (old_stdout_fileno == STDOUT_FILENO)
real_stderr = (old_stderr_fileno == STDERR_FILENO)
if real_stdout:
hStdout = GetStdHandle(STD_OUTPUT_HANDLE)
if not_a_console(hStdout):
real_stdout = False
if real_stderr:
hStderr = GetStdHandle(STD_ERROR_HANDLE)
if not_a_console(hStderr):
real_stderr = False
if real_stdout or real_stderr:
# BOOL WINAPI WriteConsoleW(HANDLE hOutput, LPWSTR lpBuffer, DWORD nChars,
# LPDWORD lpCharsWritten, LPVOID lpReserved);
WriteConsoleW = WINFUNCTYPE(BOOL, HANDLE, LPWSTR, DWORD, POINTER(DWORD), LPVOID)(("WriteConsoleW", windll.kernel32))
class UnicodeOutput:
def __init__(self, hConsole, stream, fileno, name):
self._hConsole = hConsole
self._stream = stream
self._fileno = fileno
self.closed = False
self.softspace = False
self.mode = 'w'
self.encoding = 'utf-8'
self.name = name
self.flush()
def isatty(self):
return False
def close(self):
# don't really close the handle, that would only cause problems
self.closed = True
def fileno(self):
return self._fileno
def flush(self):
if self._hConsole is None:
try:
self._stream.flush()
except Exception as e:
_complain("%s.flush: %r from %r" % (self.name, e, self._stream))
raise
def write(self, text):
try:
if self._hConsole is None:
if isinstance(text, unicode):
text = text.encode('utf-8')
self._stream.write(text)
else:
if not isinstance(text, unicode):
text = str(text).decode('utf-8')
remaining = len(text)
while remaining:
n = DWORD(0)
# There is a shorter-than-documented limitation on the
# length of the string passed to WriteConsoleW (see
# <http://tahoe-lafs.org/trac/tahoe-lafs/ticket/1232>.
retval = WriteConsoleW(self._hConsole, text, min(remaining, 10000), byref(n), None)
if retval == 0 or n.value == 0:
raise IOError("WriteConsoleW returned %r, n.value = %r" % (retval, n.value))
remaining -= n.value
if not remaining:
break
text = text[n.value:]
except Exception as e:
_complain("%s.write: %r" % (self.name, e))
raise
def writelines(self, lines):
try:
for line in lines:
self.write(line)
except Exception as e:
_complain("%s.writelines: %r" % (self.name, e))
raise
if real_stdout:
sys.stdout = UnicodeOutput(hStdout, None, STDOUT_FILENO, '<Unicode console stdout>')
else:
sys.stdout = UnicodeOutput(None, sys.stdout, old_stdout_fileno, '<Unicode redirected stdout>')
if real_stderr:
sys.stderr = UnicodeOutput(hStderr, None, STDERR_FILENO, '<Unicode console stderr>')
else:
sys.stderr = UnicodeOutput(None, sys.stderr, old_stderr_fileno, '<Unicode redirected stderr>')
except Exception as e:
_complain("exception %r while fixing up sys.stdout and sys.stderr" % (e,))
# While we're at it, let's unmangle the command-line arguments:
# This works around <http://bugs.python.org/issue2128>.
GetCommandLineW = WINFUNCTYPE(LPWSTR)(("GetCommandLineW", windll.kernel32))
CommandLineToArgvW = WINFUNCTYPE(POINTER(LPWSTR), LPCWSTR, POINTER(c_int))(("CommandLineToArgvW", windll.shell32))
argc = c_int(0)
argv_unicode = CommandLineToArgvW(GetCommandLineW(), byref(argc))
argv = [argv_unicode[i].encode('utf-8') for i in xrange(0, argc.value)]
if not hasattr(sys, 'frozen'):
# If this is an executable produced by py2exe or bbfreeze, then it will
# have been invoked directly. Otherwise, unicode_argv[0] is the Python
# interpreter, so skip that.
argv = argv[1:]
# Also skip option arguments to the Python interpreter.
while len(argv) > 0:
arg = argv[0]
if not arg.startswith(u"-") or arg == u"-":
break
argv = argv[1:]
if arg == u'-m':
# sys.argv[0] should really be the absolute path of the module source,
# but never mind
break
if arg == u'-c':
argv[0] = u'-c'
break
# if you like:
sys.argv = argv
Finally, it is possible to grant ΤΖΩΤΖΙΟΥ's wish to use DejaVu Sans Mono, which I agree is an excellent font, for the console.
You can find information on the font requirements and how to add new fonts for the windows console in the 'Necessary criteria for fonts to be available in a command window' Microsoft KB
But basically, on Vista (probably also Win7):
- under
HKEY_LOCAL_MACHINE_SOFTWAREMicrosoftWindows NTCurrentVersionConsoleTrueTypeFont, set "0" to "DejaVu Sans Mono";
- for each of the subkeys under
HKEY_CURRENT_USERConsole, set "FaceName" to "DejaVu Sans Mono".
On XP, check the thread 'Changing Command Prompt fonts?' in LockerGnome forums.
