我正在开发一个python应用程序，它可以在多个平台上以多种语言将文本打印到控制台。 该程序适用于所有UNIX平台，但在Windows中，在命令行中打印unicode字符串时出错。
已经有一个相关的线索： （Windows cmd encoding change causes Python crash） 但我在那里找不到具体的答案。
例如，对于以下亚洲文本，在Linux中，我可以运行：
>>> print u"\u5f15\u8d77\u7684\u6216".encode("utf-8")
引起的或
但在Windows中，我得到了：
>>> print u"\u5f15\u8d77\u7684\u6216".encode("utf-8")
σ╝ץΦ╡╖τתהµטצ
在做类似的事情时，我成功地用消息框显示了正确的文字：
>>> 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控制台中执行此操作，并且最好 - 在我的python代码之外不需要太多配置（因为我的应用程序将分发给许多主机）。
这可能吗？
编辑：如果不可能 - 我很乐意接受在显示unicode的Windows中编写控制台应用程序的其他一些建议，例如：另一个Windows控制台的python实现
答案 0 :(得分：2)
有一个WriteConsoleW解决方案，提供unicode argv和stdout（print）但不提供stdin：Windows cmd encoding change causes Python crash
我修改的唯一东西是sys.argv来保持unicode。由于某种原因，原始版本utf-8对其进行了编码。
#!/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
答案 1 :(得分：1)
使用其他控制台程序。以下工作在mintty中，即Cygwin中的默认终端模拟器。
>>> print u"\u5f15\u8d77\u7684\u6216"
引起的或
Windows还有其他可用的控制台替代方案，但我还没有评估他们的Unicode支持。
答案 2 :(得分：0)
它仅来自于cmd和powershell consoel不支持可变宽度字体。固定字体不包含中文脚本。 Cygwin的情况也是如此 Putty更先进，支持带有西里尔语，越南语，阿拉伯语脚本的可变宽度字体，但到目前为止还没有中文。
HTH
答案 3 :(得分：-2)
您可以尝试在Windows上使用程序iconv，并通过它管道您的Python输出吗？它会是这样的：
python foo.py | iconv -f utf-8 -t utf-16
您可能需要做一些工作才能在Windows上获得iconv - 它是Cygwin的一部分，但如果需要，您可能会以某种方式单独构建它。
答案 4 :(得分：-3)
问题已在PrintFails article中解答。
默认情况下，Microsoft Windows中的控制台仅显示256 字符（Code page 437的cp437，原始的IBM-PC 1981扩展ASCII字符 集。）
对俄罗斯而言，这意味着CP866，其他国家也使用自己的代码页。这意味着要正确读取Windows控制台中的Python输出，您应该将Windows配置与本机代码页配置为显示打印的符号。
我建议您始终打印Unicode文本而不进行任何编码，以确保与各种平台的最大兼容性。
如果您尝试打印不可打印的字符，您将收到UnicodeEncodeError或查看扭曲的文本。
在某些情况下，如果Python无法正确确定输出编码，您可能会尝试设置PYTHONIOENCODING环境变量，请注意，这可能不适用于您的示例，因为您的控制台无法在当前显示亚洲文本配置。
要重新配置控制台，请使用控制面板 - >语言和区域设置 - >高级（选项卡） - ＆gt;非Unicode程序语言（部分）。请注意，菜单名称由我从俄语翻译。
另请参阅very similar question的答案。