_inputstream.py 文件源码

def characterErrorsUCS2(self, data):
        # Someone picked the wrong compile option
        # You lose
        skip = False
        for match in invalid_unicode_re.finditer(data):
            if skip:
                continue
            codepoint = ord(match.group())
            pos = match.start()
            # Pretty sure there should be endianness issues here
            if _utils.isSurrogatePair(data[pos:pos + 2]):
                # We have a surrogate pair!
                char_val = _utils.surrogatePairToCodepoint(data[pos:pos + 2])
                if char_val in non_bmp_invalid_codepoints:
                    self.errors.append("invalid-codepoint")
                skip = True
            elif (codepoint >= 0xD800 and codepoint <= 0xDFFF and
                  pos == len(data) - 1):
                self.errors.append("invalid-codepoint")
            else:
                skip = False
                self.errors.append("invalid-codepoint")