def consumeNumberEntity()

in bleach/_vendor/html5lib/_tokenizer.py [0:0]
51 lines of code
7 McCabe index (conditional complexity)

    def consumeNumberEntity(self, isHex):
        """This function returns either U+FFFD or the character based on the
        decimal or hexadecimal representation. It also discards ";" if present.
        If not present self.tokenQueue.append({"type": tokenTypes["ParseError"]}) is invoked.
        """

        allowed = digits
        radix = 10
        if isHex:
            allowed = hexDigits
            radix = 16

        charStack = []

        # Consume all the characters that are in range while making sure we
        # don't hit an EOF.
        c = self.stream.char()
        while c in allowed and c is not EOF:
            charStack.append(c)
            c = self.stream.char()

        # Convert the set of characters consumed to an int.
        charAsInt = int("".join(charStack), radix)

        # Certain characters get replaced with others
        if charAsInt in replacementCharacters:
            char = replacementCharacters[charAsInt]
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "illegal-codepoint-for-numeric-entity",
                                    "datavars": {"charAsInt": charAsInt}})
        elif ((0xD800 <= charAsInt <= 0xDFFF) or
              (charAsInt > 0x10FFFF)):
            char = "\uFFFD"
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "illegal-codepoint-for-numeric-entity",
                                    "datavars": {"charAsInt": charAsInt}})
        else:
            # Should speed up this check somehow (e.g. move the set to a constant)
            if ((0x0001 <= charAsInt <= 0x0008) or
                (0x000E <= charAsInt <= 0x001F) or
                (0x007F <= charAsInt <= 0x009F) or
                (0xFDD0 <= charAsInt <= 0xFDEF) or
                charAsInt in frozenset([0x000B, 0xFFFE, 0xFFFF, 0x1FFFE,
                                        0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
                                        0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE,
                                        0x5FFFF, 0x6FFFE, 0x6FFFF, 0x7FFFE,
                                        0x7FFFF, 0x8FFFE, 0x8FFFF, 0x9FFFE,
                                        0x9FFFF, 0xAFFFE, 0xAFFFF, 0xBFFFE,
                                        0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE,
                                        0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE,
                                        0xFFFFF, 0x10FFFE, 0x10FFFF])):
                self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                        "data":
                                        "illegal-codepoint-for-numeric-entity",
                                        "datavars": {"charAsInt": charAsInt}})
            try:
                # Try/except needed as UCS-2 Python builds' unichar only works
                # within the BMP.
                char = chr(charAsInt)
            except ValueError:
                v = charAsInt - 0x10000
                char = chr(0xD800 | (v >> 10)) + chr(0xDC00 | (v & 0x3FF))

        # Discard the ; if present. Otherwise, put it back on the queue and
        # invoke parseError on parser.
        if c != ";":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "numeric-entity-without-semicolon"})
            self.stream.unget(c)

        return char