Class EncodedString

contrib/tools/cython/Cython/Compiler/StringEncoding.py:100–133

class EncodedString(str):
    # unicode string subclass to keep track of the original encoding.
    # 'encoding' is None for unicode strings and the source encoding
    # otherwise
    encoding = None

    def __deepcopy__(self, memo):
        return self

    def byteencode(self):
        assert self.encoding is not None
        return self.encode(self.encoding)

    def utf8encode(self):
        assert self.encoding is None
        return self.encode("UTF-8")

    @property
    def is_unicode(self):
        return self.encoding is None

    def contains_surrogates(self):
        return string_contains_surrogates(self)

    def as_utf8_string(self):
        return bytes_literal(self.utf8encode(), 'utf8')

    def as_c_string_literal(self):
        # first encodes the string then produces a c string literal
        if self.encoding is None:
            s = self.as_utf8_string()
        else:
            s = bytes_literal(self.byteencode(), self.encoding)
        return s.as_c_string_literal()


def string_contains_surrogates(ustring):