tokenizer.py 文件源码

def attributeValueUnQuotedState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeAttributeNameState
        elif data == u"&":
            self.processEntityInAttribute(">")
        elif data == u">":
            self.emitCurrentToken()
        elif data in (u'"', u"'", u"=", u"<", u"`"):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
              "unexpected-character-in-unquoted-attribute-value"})
            self.currentToken["data"][-1][1] += data
        elif data == u"\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], 
                                    "data": "invalid-codepoint"})
            self.currentToken["data"][-1][1] += u"\uFFFD"
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
              "eof-in-attribute-value-no-quotes"})
            self.state = self.dataState
        else:
            self.currentToken["data"][-1][1] += data + self.stream.charsUntil(
              frozenset((u"&", u">", u'"', u"'", u"=", u"<", u"`")) | spaceCharacters)
        return True