Python charset.UNKNOWN8BIT属性代码示例

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import UNKNOWN8BIT [as 别名]
def __str__(self):
        """Return the string value of the header."""
        self._normalize()
        uchunks = []
        lastcs = None
        lastspace = None
        for string, charset in self._chunks:
            # We must preserve spaces between encoded and non-encoded word
            # boundaries, which means for us we need to add a space when we go
            # from a charset to None/us-ascii, or from None/us-ascii to a
            # charset.  Only do this for the second and subsequent chunks.
            # Don't add a space if the None/us-ascii string already has
            # a space (trailing or leading depending on transition)
            nextcs = charset
            if nextcs == _charset.UNKNOWN8BIT:
                original_bytes = string.encode('ascii', 'surrogateescape')
                string = original_bytes.decode('ascii', 'replace')
            if uchunks:
                hasspace = string and self._nonctext(string[0])
                if lastcs not in (None, 'us-ascii'):
                    if nextcs in (None, 'us-ascii') and not hasspace:
                        uchunks.append(SPACE)
                        nextcs = None
                elif nextcs not in (None, 'us-ascii') and not lastspace:
                    uchunks.append(SPACE)
            lastspace = string and self._nonctext(string[-1])
            lastcs = nextcs
            uchunks.append(string)
        return EMPTYSTRING.join(uchunks)

    # Rich comparison operators for equality only.  BAW: does it make sense to
    # have or explicitly disable <, <=, >, >= operators? 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import UNKNOWN8BIT [as 别名]
def _sanitize_header(self, name, value):
        # If the header value contains surrogates, return a Header using
        # the unknown-8bit charset to encode the bytes as encoded words.
        if not isinstance(value, str):
            # Assume it is already a header object
            return value
        if _has_surrogates(value):
            return header.Header(value, charset=_charset.UNKNOWN8BIT,
                                 header_name=name)
        else:
            return value 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import UNKNOWN8BIT [as 别名]
def _fold(self, name, value, sanitize):
        parts = []
        parts.append('%s: ' % name)
        if isinstance(value, str):
            if _has_surrogates(value):
                if sanitize:
                    h = header.Header(value,
                                      charset=_charset.UNKNOWN8BIT,
                                      header_name=name)
                else:
                    # If we have raw 8bit data in a byte string, we have no idea
                    # what the encoding is.  There is no safe way to split this
                    # string.  If it's ascii-subset, then we could do a normal
                    # ascii split, but if it's multibyte then we could break the
                    # string.  There's no way to know so the least harm seems to
                    # be to not split the string and risk it being too long.
                    parts.append(value)
                    h = None
            else:
                h = header.Header(value, header_name=name)
        else:
            # Assume it is a Header-like object.
            h = value
        if h is not None:
            parts.append(h.encode(linesep=self.linesep,
                                  maxlinelen=self.max_line_length))
        parts.append(self.linesep)
        return ''.join(parts) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import UNKNOWN8BIT [as 别名]
def _fold(self, name, value, sanitize):
        parts = []
        parts.append('%s: ' % name)
        if isinstance(value, str):
            if _has_surrogates(value):
                if sanitize:
                    h = header.Header(value,
                                      charset=_charset.UNKNOWN8BIT,
                                      header_name=name)
                else:
                    # If we have raw 8bit data in a byte string, we have no idea
                    # what the encoding is.  There is no safe way to split this
                    # string.  If it's ascii-subset, then we could do a normal
                    # ascii split, but if it's multibyte then we could break the
                    # string.  There's no way to know so the least harm seems to
                    # be to not split the string and risk it being too long.
                    parts.append(value)
                    h = None
            else:
                h = header.Header(value, header_name=name)
        else:
            # Assume it is a Header-like object.
            h = value
        if h is not None:
            # The Header class interprets a value of None for maxlinelen as the
            # default value of 78, as recommended by RFC 2822.
            maxlinelen = 0
            if self.max_line_length is not None:
                maxlinelen = self.max_line_length
            parts.append(h.encode(linesep=self.linesep, maxlinelen=maxlinelen))
        parts.append(self.linesep)
        return ''.join(parts) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import UNKNOWN8BIT [as 别名]
def append(self, s, charset=None, errors='strict'):
        """Append a string to the MIME header.

        Optional charset, if given, should be a Charset instance or the name
        of a character set (which will be converted to a Charset instance).  A
        value of None (the default) means that the charset given in the
        constructor is used.

        s may be a byte string or a Unicode string.  If it is a byte string
        (i.e. isinstance(s, str) is false), then charset is the encoding of
        that byte string, and a UnicodeError will be raised if the string
        cannot be decoded with that charset.  If s is a Unicode string, then
        charset is a hint specifying the character set of the characters in
        the string.  In either case, when producing an RFC 2822 compliant
        header using RFC 2047 rules, the string will be encoded using the
        output codec of the charset.  If the string cannot be encoded to the
        output codec, a UnicodeError will be raised.

        Optional `errors' is passed as the errors argument to the decode
        call if s is a byte string.
        """
        if charset is None:
            charset = self._charset
        elif not isinstance(charset, Charset):
            charset = Charset(charset)
        if not isinstance(s, str):
            input_charset = charset.input_codec or 'us-ascii'
            if input_charset == _charset.UNKNOWN8BIT:
                s = s.decode('us-ascii', 'surrogateescape')
            else:
                s = s.decode(input_charset, errors)
        # Ensure that the bytes we're storing can be decoded to the output
        # character set, otherwise an early error is raised.
        output_charset = charset.output_codec or 'us-ascii'
        if output_charset != _charset.UNKNOWN8BIT:
            try:
                s.encode(output_charset, errors)
            except UnicodeEncodeError:
                if output_charset!='us-ascii':
                    raise
                charset = UTF8
        self._chunks.append((s, charset))