首页
学习
活动
专区
工具
TVP
发布
社区首页 >问答首页 >Windows cmd编码更改导致Python崩溃怎么办?

Windows cmd编码更改导致Python崩溃怎么办?
EN

Stack Overflow用户
提问于 2018-03-16 00:45:19
回答 2查看 0关注 0票数 0

首先,我将Windows CMD编码更改为utf-8并运行Python解释器:

代码语言:javascript
复制
chcp 65001
python

然后,我尝试打印一个unicode,在它的内部进行刺探,当我这样做的时候,Python以一种奇怪的方式崩溃(我只是在同一个窗口中得到一个cmd提示符)。

代码语言:javascript
复制
>>> import sys
>>> print u'ëèæîð'.encode(sys.stdin.encoding)
EN

Stack Overflow用户

发布于 2018-03-16 09:18:22

以下是如何cp65001不改变UTF-8的别名encodings\aliases.py

代码语言:javascript
复制
import codecs
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)

使控制台输出工作不管了的chcp代码页,并读取Unicode的命令行参数。

代码语言:javascript
复制
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
票数 0
EN
查看全部 2 条回答
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接:

https://stackoverflow.com/questions/-100007636

复制
相关文章

相似问题

领券
问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档