def consumeEntity()

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

    def consumeEntity(self, allowedChar=None, fromAttribute=False):
        # Initialise to the default output for when no entity is matched
        output = "&"

        charStack = [self.stream.char()]
        if (charStack[0] in spaceCharacters or charStack[0] in (EOF, "<", "&") or
                (allowedChar is not None and allowedChar == charStack[0])):
            self.stream.unget(charStack[0])

        elif charStack[0] == "#":
            # Read the next character to see if it's hex or decimal
            hex = False
            charStack.append(self.stream.char())
            if charStack[-1] in ("x", "X"):
                hex = True
                charStack.append(self.stream.char())

            # charStack[-1] should be the first digit
            if (hex and charStack[-1] in hexDigits) \
                    or (not hex and charStack[-1] in digits):
                # At least one digit found, so consume the whole number
                self.stream.unget(charStack[-1])
                output = self.consumeNumberEntity(hex)
            else:
                # No digits found
                self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                        "data": "expected-numeric-entity"})
                self.stream.unget(charStack.pop())
                output = "&" + "".join(charStack)

        else:
            # At this point in the process might have named entity. Entities
            # are stored in the global variable "entities".
            #
            # Consume characters and compare to these to a substring of the
            # entity names in the list until the substring no longer matches.
            while (charStack[-1] is not EOF):
                if not entitiesTrie.has_keys_with_prefix("".join(charStack)):
                    break
                charStack.append(self.stream.char())

            # At this point we have a string that starts with some characters
            # that may match an entity
            # Try to find the longest entity the string will match to take care
            # of &noti for instance.
            try:
                entityName = entitiesTrie.longest_prefix("".join(charStack[:-1]))
                entityLength = len(entityName)
            except KeyError:
                entityName = None

            if entityName is not None:
                if entityName[-1] != ";":
                    self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                            "named-entity-without-semicolon"})
                if (entityName[-1] != ";" and fromAttribute and
                    (charStack[entityLength] in asciiLetters or
                     charStack[entityLength] in digits or
                     charStack[entityLength] == "=")):
                    self.stream.unget(charStack.pop())
                    output = "&" + "".join(charStack)
                else:
                    output = entities[entityName]
                    self.stream.unget(charStack.pop())
                    output += "".join(charStack[entityLength:])
            else:
                self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                        "expected-named-entity"})
                self.stream.unget(charStack.pop())
                output = "&" + "".join(charStack)

        if fromAttribute:
            self.currentToken["data"][-1][1] += output
        else:
            if output in spaceCharacters:
                tokenType = "SpaceCharacters"
            else:
                tokenType = "Characters"
            self.tokenQueue.append({"type": tokenTypes[tokenType], "data": output})