如何在Windows控制台打印Python中的unicode字符串
我正在开发一个Python应用程序，可以在多个平台上将文本以多种语言打印到控制台。这个程序在所有UNIX平台上运行得很好，但在Windows上打印Unicode字符串时出现了错误。
已经有一个相关的讨论帖，内容是关于这个问题的：Windows cmd编码变化导致Python崩溃，但我在里面找不到我具体的问题的答案。
举个例子，对于以下的亚洲文字，在Linux上我可以运行：
>>> print u"\u5f15\u8d77\u7684\u6216".encode("utf-8")
引起的或
但在Windows上我得到的是：
>>> print u"\u5f15\u8d77\u7684\u6216".encode("utf-8")
σ╝ץΦ╡╖τתהµטצ
我成功地通过消息框显示了正确的文本，当我这样做的时候：
>>> file("bla.vbs", "w").write(u'MsgBox "\u5f15\u8d77\u7684\u6216", 4, "MyTitle"'.encode("utf-16"))
>>> os.system("cscript //U //NoLogo bla.vbs")
但是，我希望能够在Windows控制台中做到这一点，并且最好是不要在我的Python代码之外进行太多配置（因为我的应用程序将会分发到很多主机上）。
这可能吗？
编辑：如果这不可能，我也很乐意接受一些其他建议，比如在Windows中编写一个能够显示Unicode的控制台应用程序，例如一个Python实现的替代Windows控制台。
5 个回答
0
这主要是因为命令提示符和PowerShell控制台不支持可变宽度的字体。固定宽度的字体里没有包含中文字符。Cygwin也是一样的情况。
Putty更先进一些，支持可变宽度的字体，并且可以显示西里尔字母、越南语和阿拉伯语，但目前还不支持中文。
希望这对你有帮助。
1
可以试试其他的控制台程序。下面的代码在Cygwin的默认终端模拟器mintty中可以正常运行。
>>> print u"\u5f15\u8d77\u7684\u6216"
引起的或
Windows上还有其他的控制台选择，不过我没有检查过它们对Unicode的支持情况。
3
这里有一个使用WriteConsoleW的方法，它可以处理unicode格式的命令行参数和输出（打印），但是不能处理输入：Windows cmd编码变化导致Python崩溃
我唯一修改的就是让sys.argv保持unicode格式。原来的版本出于某种原因把它编码成了utf-8。
#!/usr/bin/env python
# -*- coding: utf-8 -*-
""" https://stackoverflow.com/questions/878972/windows-cmd-encoding-change-causes-python-crash#answer-3259271
"""
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
# <https://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] for i in xrange(0, argc.value)]
# 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