Python charset.UNKNOWN8BIT属性代码示例

# 需要导入模块: from future.backports.email import charset [as 别名]
# 或者: from future.backports.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 future.backports.email import charset [as 别名]
# 或者: from future.backports.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 future.backports.email import charset [as 别名]
# 或者: from future.backports.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)