����JFIFXX�����    $.' ",#(7),01444'9=82<.342  2!!22222222222222222222222222222222222222222222222222����"��4�� ���,�PG"Z_�4�˷����kjز�Z�,F+��_z�,�© �����zh6�٨�ic�fu���#ډb���_�N�?��wQ���5-�~�I���8����TK<5o�Iv-�����k�_U_�����~b�M��d����Ӝ�U�Hh��?]��E�w��Q���k�{��_}qFW7HTՑ��Y��F�?_�'ϔ��_�Ջt��=||I ��6�έ"�����D���/[�k�9���Y�8ds|\���Ҿp6�Ҵ���]��.����6�z<�v��@]�i%��$j��~�g��J>��no����pM[me�i$[����s�o�ᘨ�˸ nɜG-�ĨU�ycP�3.DB�li�;��hj���x7Z^�N�h������N3u{�:j�x�힞��#M&��jL P@_���� P��&��o8������9�����@Sz6�t7#O�ߋ �s}Yf�T���lmr����Z)'N��k�۞p����w\�Tȯ?�8`�O��i{wﭹW�[�r�� ��Q4F�׊���3m&L�=��h3����z~��#�\�l :�F,j@�� ʱ�wQT����8�"kJO���6�֚l����}���R�>ډK���]��y����&����p�}b��;N�1�m�r$�|��7�>e�@B�TM*-iH��g�D�)� E�m�|�ؘbҗ�a��Ҿ����t4���o���G��*oCN�rP���Q��@z,|?W[0�����:�n,jWiE��W��$~/�hp\��?��{(�0���+�Y8rΟ�+����>S-S����VN;�}�s?.����� w�9��˟<���Mq4�Wv'��{)0�1mB��V����W[�����8�/<� �%���wT^�5���b��)iM� pg�N�&ݝ��VO~�q���u���9� ����!��J27����$O-���! �:�%H��� ـ����y�ΠM=t{!S�� oK8������t<����è:a������[�����ա�H���~��w��Qz`�po�^ ����Q��n� �,uu�C�$ ^���,������8�#��:�6��e�|~���!�3�3.�\0��q��o�4`.|� ����y�Q�`~;�d�ׯ,��O�Zw�������`73�v�܋�<���Ȏ�� ـ4k��5�K�a�u�=9Yd��$>x�A�&�� j0� ���vF��� Y�|�y��� ~�6�@c��1vOp�Ig����4��l�OD���L����� R���c���j�_�uX6��3?nk��Wy�f;^*B� ��@�~a�`��Eu������+���6�L��.ü>��}y���}_�O�6�͐�:�YrG�X��kG�����l^w���~㒶sy��Iu�!� W ��X��N�7BV��O��!X�2����wvG�R�f�T#�����t�/?���%8�^�W�aT��G�cL�M���I��(J����1~�8�?aT ���]����AS�E��(��*E}� 2��#I/�׍qz��^t�̔���b�Yz4x���t�){ OH��+(E��A&�N�������XT��o��"�XC��'���)}�J�z�p� ��~5�}�^����+�6����w��c��Q�|Lp�d�H��}�(�.|����k��c4^�"�����Z?ȕ ��a<�L�!039C� �Eu�C�F�Ew�ç ;�n?�*o���B�8�bʝ���'#Rqf���M}7����]����s2tcS{�\icTx;�\��7K���P���ʇ Z O-��~��c>"��?�������P��E��O�8��@�8��G��Q�g�a�Վ���󁶠�䧘��_%#r�>�1�z�a��eb��qcPѵ��n���#L��� =��׀t� L�7�`��V���A{�C:�g���e@�w1 Xp3�c3�ġ����p��M"'-�@n4���fG��B3�DJ�8[Jo�ߐ���gK)ƛ��$���� ���8�3�����+���� �����6�ʻ���� ���S�kI�*KZlT _`���?��K����QK�d����B`�s}�>���`��*�>��,*@J�d�oF*����弝��O}�k��s��]��y�ߘ��c1G�V���<=�7��7����6�q�PT��tXԀ�!9*4�4Tހ3XΛex�46���Y��D ����� �BdemDa����\�_l,��G�/���֌7���Y�](�xTt^%�GE�����4�}bT���ڹ�����;Y)���B�Q��u��>J/J �⮶.�XԄ��j�ݳ�+E��d ��r�5�_D�1 ��o�� �B�x�΢�#���<��W�����8���R6�@g�M�.��� dr�D��>(otU��@x=��~v���2� ӣ�d�oBd��3�eO�6�㣷�����ݜ6��6Y��Qz`��S��{���\P�~z m5{J/L��1������<�e�ͅPu�b�]�ϔ���'������f�b� Zpw��c`"��i���BD@:)ִ�:�]��hv�E�w���T�l��P���"Ju�}��وV J��G6��. J/�Qgl߭�e�����@�z�Zev2u�)]կ�����7x���s�M�-<ɯ�c��r�v�����@��$�ޮ}lk���a���'����>x��O\�ZFu>�����ck#��&:��`�$�ai�>2Δ����l���oF[h��lE�ܺ�Πk:)���`�� $[6�����9�����kOw�\|���8}������ބ:��񶐕��I�A1/�=�2[�,�!��.}gN#�u����b��� ~��݊��}34q����d�E��Lc��$��"�[q�U�硬g^��%B �z���r�pJ�ru%v\h1Y�ne`ǥ:g���pQM~�^�Xi� ��`S�:V29.�P���V�?B�k�� AEvw%�_�9C�Q����wKekPؠ�\�;Io d�{ ߞo�c1eP����\� `����E=���@K<�Y���eڼ�J���w����{av�F�'�M�@/J��+9p���|]�����Iw &`��8���&M�hg��[�{��Xj��%��Ӓ�$��(����ʹN���<>�I���RY���K2�NPlL�ɀ)��&e����B+ь����( � �JTx���_?EZ� }@ 6�U���뙢ط�z��dWI�n` D����噥�[��uV��"�G&Ú����2g�}&m��?ċ�"����Om#��������� ��{�ON��"S�X��Ne��ysQ���@Fn��Vg���dX�~nj�]J�<�K]:��FW��b�������62�=��5f����JKw��bf�X�55��~J �%^����:�-�QIE��P��v�nZum� z � ~ə ���� ���ة����;�f��\v���g�8�1��f24;�V���ǔ�)����9���1\��c��v�/'Ƞ�w�������$�4�R-��t���� e�6�/�ġ �̕Ecy�J���u�B���<�W�ַ~�w[B1L۲�-JS΂�{���΃������A��20�c#��@ 0!1@AP"#2Q`$3V�%45a6�FRUq��� ����^7ׅ,$n�������+��F�`��2X'��0vM��p�L=������5��8������u�p~���.�`r�����\���O��,ư�0oS ��_�M�����l���4�kv\JSd���x���SW�<��Ae�IX����������$I���w�:S���y���›R��9�Q[���,�5�;�@]�%���u�@ *ro�lbI �� ��+���%m:�͇ZV�����u�̉����θau<�fc�.����{�4Ա� �Q����*�Sm��8\ujqs]{kN���)qO�y�_*dJ�b�7���yQqI&9�ԌK!�M}�R�;������S�T���1���i[U�ɵz�]��U)V�S6���3$K{�ߊ<�(� E]Զ[ǼENg�����'�\?#)Dkf��J���o��v���'�%ƞ�&K�u�!��b�35LX�Ϸ��63$K�a�;�9>,R��W��3�3� d�JeTYE.Mϧ��-�o�j3+y��y^�c�������VO�9NV\nd�1 ��!͕_)a�v;����թ�M�lWR1��)El��P;��yوÏ�u 3�k�5Pr6<�⒲l�!˞*��u־�n�!�l:����UNW ��%��Chx8vL'��X�@��*��)���̮��ˍ��� ���D-M�+J�U�kvK����+�x8��cY������?�Ԡ��~3mo��|�u@[XeY�C�\Kp�x8�oC�C�&����N�~3-H���� ��MX�s�u<`���~"WL��$8ξ��3���a�)|:@�m�\���^�`�@ҷ)�5p+��6���p�%i)P M���ngc�����#0Aruz���RL+xSS?���ʮ}()#�t��mˇ!��0}}y����<�e� �-ή�Ԩ��X������ MF���ԙ~l L.3���}�V뽺�v�����멬��Nl�)�2����^�Iq��a��M��qG��T�����c3#������3U�Ǎ���}��לS�|qa��ڃ�+���-��2�f����/��bz��ڐ�� �ݼ[2�ç����k�X�2�* �Z�d���J�G����M*9W���s{��w���T��x��y,�in�O�v��]���n����P�$�JB@=4�OTI�n��e�22a\����q�d���%�$��(���:���: /*�K[PR�fr\nڙdN���F�n�$�4�[�� U�zƶ����� �mʋ���,�ao�u 3�z� �x��Kn����\[��VFmbE;�_U��&V�Gg�]L�۪&#n%�$ɯ�dG���D�TI=�%+AB�Ru#��b4�1�»x�cs�YzڙJG��f��Il��d�eF'T� iA��T���uC�$����Y��H?����[!G`}���ͪ� �纤Hv\������j�Ex�K���!���OiƸ�Yj�+u-<���'q����uN�*�r\��+�]���<�wOZ.fp�ێ��,-*)V?j-kÊ#�`�r��dV����(�ݽBk�����G�ƛk�QmUڗe��Z���f}|����8�8��a���i��3'J�����~G_�^���d�8w������ R�`(�~�.��u���l�s+g�bv���W���lGc}��u���afE~1�Ue������Z�0�8�=e�� f@/�jqEKQQ�J��oN��J���W5~M>$6�Lt�;$ʳ{���^��6�{����v6���ķܰg�V�cnn �~z�x�«�,2�u�?cE+Ș�H؎�%�Za�)���X>uW�Tz�Nyo����s���FQƤ��$��*�&�LLXL)�1�" L��eO��ɟ�9=���:t��Z���c��Ž���Y?�ӭV�wv�~,Y��r�ۗ�|�y��GaF�����C�����.�+� ���v1���fήJ�����]�S��T��B��n5sW}y�$��~z�'�c ��8 ��� ,! �p��VN�S��N�N�q��y8z˱�A��4��*��'������2n<�s���^ǧ˭P�Jޮɏ�U�G�L�J�*#��<�V��t7�8����TĜ>��i}K%,���)[��z�21z ?�N�i�n1?T�I�R#��m-�����������������1����lA�`��fT5+��ܐ�c�q՝��ʐ��,���3�f2U�եmab��#ŠdQ�y>\��)�SLY����w#��.���ʑ�f��� ,"+�w�~�N�'�c�O�3F�������N<���)j��&��,-� �љ���֊�_�zS���TǦ����w�>��?�������n��U仆�V���e�����0���$�C�d���rP �m�׈e�Xm�Vu� �L��.�bֹ��� �[Դaզ���*��\y�8�Է:�Ez\�0�Kq�C b��̘��cө���Q��=0Y��s�N��S.���3.���O�o:���#���v7�[#߫ ��5�܎�L���Er4���9n��COWlG�^��0k�%<���ZB���aB_���������'=��{i�v�l�$�uC���mƎҝ{�c㱼�y]���W�i ��ߧc��m�H� m�"�"�����;Y�ߝ�Z�Ǔ�����:S#��|}�y�,/k�Ld� TA�(�AI$+I3��;Y*���Z��}|��ӧO��d�v��..#:n��f>�>���ȶI�TX��� 8��y����"d�R�|�)0���=���n4��6ⲑ�+��r<�O�܂~zh�z����7ܓ�HH�Ga롏���nCo�>������a ���~]���R���̲c?�6(�q�;5%� |�uj�~z8R=X��I�V=�|{v�Gj\gc��q����z�؋%M�ߍ����1y��#��@f^���^�>N�����#x#۹��6�Y~�?�dfPO��{��P�4��V��u1E1J �*|���%���JN��`eWu�zk M6���q t[�� ��g�G���v��WIG��u_ft����5�j�"�Y�:T��ɐ���*�;� e5���4����q$C��2d�}���� _S�L#m�Yp��O�.�C�;��c����Hi#֩%+) �Ӎ��ƲV���SYź��g |���tj��3�8���r|���V��1#;.SQ�A[���S������#���`n�+���$��$I �P\[�@�s��(�ED�z���P��])8�G#��0B��[ى��X�II�q<��9�~[Z멜�Z�⊔IWU&A>�P~�#��dp<�?����7���c��'~���5 ��+$���lx@�M�dm��n<=e�dyX��?{�|Aef ,|n3�<~z�ƃ�uۧ�����P��Y,�ӥQ�*g�#먙R�\���;T��i,��[9Qi歉����c>]9�� ��"�c��P�� �Md?٥��If�ت�u��k��/����F��9�c*9��Ǎ:�ØF���z�n*�@|I�ށ9����N3{'��[�'ͬ�Ҳ4��#}��!�V� Fu��,�,mTIk���v C�7v���B�6k�T9��1�*l� '~��ƞF��lU��'�M ����][ΩũJ_�{�i�I�n��$���L�� j��O�dx�����kza۪��#�E��Cl����x˘�o�����V���ɞ�ljr��)�/,�߬h�L��#��^��L�ф�,íMƁe�̩�NB�L�����iL����q�}��(��q��6IçJ$�W�E$��:������=#����(�K�B����zђ <��K(�N�۫K�w��^O{!����)�H���>x�������lx�?>Պ�+�>�W���,Ly!_�D���Ō�l���Q�!�[ �S����J��1��Ɛ�Y}��b,+�Lo�x�ɓ)����=�y�oh�@�꥟/��I��ѭ=��P�y9��� �ۍYӘ�e+�p�Jnϱ?V\SO%�(�t� ���=?MR�[Ș�����d�/ ��n�l��B�7j� ��!�;ӥ�/�[-���A�>�dN�sLj ��,ɪv��=1c�.SQ�O3�U���ƀ�ܽ�E����������̻��9G�ϷD�7(�}��Ävӌ\�y�_0[w ���<΍>����a_��[0+�L��F.�޺��f�>oN�T����q;���y\��bՃ��y�jH�<|q-eɏ�_?_9+P���Hp$�����[ux�K w�Mw��N�ی'$Y2�=��q���KB��P��~������Yul:�[<����F1�2�O���5=d����]Y�sw:���Ϯ���E��j,_Q��X��z`H1,#II ��d�wr��P˂@�ZJV����y$�\y�{}��^~���[:N����ߌ�U�������O��d�����ؾe��${p>G��3c���Ė�lʌ�� ת��[��`ϱ�-W����dg�I��ig2��� ��}s ��ؤ(%#sS@���~���3�X�nRG�~\jc3�v��ӍL��M[JB�T��s3}��j�Nʖ��W����;7��ç?=X�F=-�=����q�ߚ���#���='�c��7���ڑW�I(O+=:uxq�������������e2�zi+�kuG�R��������0�&e�n���iT^J����~\jy���p'dtG��s����O��3����9* �b#Ɋ�� p������[Bws�T�>d4�ۧs���nv�n���U���_�~,�v����ƜJ1��s�� �QIz��)�(lv8M���U=�;����56��G���s#�K���MP�=��LvyGd��}�VwWBF�'�à �?MH�U�g2�� ����!�p�7Q��j��ڴ����=��j�u��� Jn�A s���uM������e��Ɔ�Ҕ�!)'��8Ϣ�ٔ��ޝ(��Vp���צ֖d=�IC�J�Ǡ{q������kԭ�߸���i��@K����u�|�p=..�*+����x�����z[Aqġ#s2a�Ɗ���RR�)*HRsi�~�a &f��M��P����-K�L@��Z��Xy�'x�{}��Zm+���:�)�) IJ�-i�u���� ���ܒH��'�L(7�y�GӜq���� j��� 6ߌg1�g�o���,kر���tY�?W,���p���e���f�OQS��!K�۟cҒA�|ս�j�>��=⬒��˧L[�� �߿2JaB~R��u�:��Q�] �0H~���]�7��Ƽ�I���(}��cq '�ήET���q�?f�ab���ӥvr� �)o��-Q��_'����ᴎo��K������;��V���o��%���~OK ����*��b�f:���-ťIR��`B�5!RB@���ï�� �u �̯e\�_U�_������� g�ES��3�������QT��a����x����U<~�c?�*�#]�MW,[8O�a�x��]�1bC|踤�P��lw5V%�)�{t�<��d��5���0i�XSU��m:��Z�┵�i�"��1�^B�-��P�hJ��&)O��*�D��c�W��vM��)����}���P��ܗ-q����\mmζZ-l@�}��a��E�6��F�@��&Sg@���ݚ�M����� ȹ 4����#p�\H����dYDo�H���"��\��..R�B�H�z_�/5˘����6��KhJR��P�mƶi�m���3�,#c�co��q�a)*Pt����R�m�k�7x�D�E�\Y�閣_X�<���~�)���c[[�BP����6�Yq���S��0����%_����;��Àv�~�| VS؇ ��'O0��F0��\���U�-�d@�����7�SJ*z��3n��y��P����O���������m�~�P�3|Y��ʉr#�C�<�G~�.,! ���bqx���h~0=��!ǫ�jy����l�O,�[B��~��|9��ٱ����Xly�#�i�B��g%�S��������tˋ���e���ې��\[d�t)��.+u�|1 ������#�~Oj����hS�%��i.�~X���I�H�m��0n���c�1uE�q��cF�RF�o���7� �O�ꮧ� ���ۛ{��ʛi5�rw?׌#Qn�TW��~?y$��m\�\o����%W� ?=>S�N@�� �Ʈ���R����N�)�r"C�:��:����� �����#��qb��Y�. �6[��2K����2u�Ǧ�HYR��Q�MV��� �G�$��Q+.>�����nNH��q�^��� ����q��mM��V��D�+�-�#*�U�̒ ���p욳��u:�������IB���m���PV@O���r[b= �� ��1U�E��_Nm�yKbN�O���U�}�the�`�|6֮P>�\2�P�V���I�D�i�P�O;�9�r�mAHG�W�S]��J*�_�G��+kP�2����Ka�Z���H�'K�x�W�MZ%�O�YD�Rc+o��?�q��Ghm��d�S�oh�\�D�|:W������UA�Qc yT�q������~^�H��/��#p�CZ���T�I�1�ӏT����4��"�ČZ�����}��`w�#�*,ʹ�� ��0�i��課�Om�*�da��^gJ݅{���l�e9uF#T�ֲ��̲�ٞC"�q���ߍ ոޑ�o#�XZTp����@ o�8��(jd��xw�]�,f���`~�|,s��^����f�1���t��|��m�򸄭/ctr��5s��7�9Q�4�H1꠲BB@l9@���C�����+�wp�xu�£Yc�9��?`@#�o�mH�s2��)�=��2�.�l����jg�9$�Y�S�%*L������R�Y������7Z���,*=�䷘$�������arm�o�ϰ���UW.|�r�uf����IGw�t����Zwo��~5 ��YյhO+=8fF�)�W�7�L9lM�̘·Y���֘YLf�큹�pRF���99.A �"wz��=E\Z���'a� 2��Ǚ�#;�'}�G���*��l��^"q��+2FQ� hj��kŦ��${���ޮ-�T�٭cf�|�3#~�RJ����t��$b�(R��(����r���dx� >U b�&9,>���%E\� Ά�e�$��'�q't��*�א���ެ�b��-|d���SB�O�O��$�R+�H�)�܎�K��1m`;�J�2�Y~9��O�g8=vqD`K[�F)k�[���1m޼c��n���]s�k�z$@��)!I �x՝"v��9=�ZA=`Ɠi �:�E��)`7��vI��}d�YI�_ �o�:ob���o ���3Q��&D&�2=�� �Ά��;>�h����y.*ⅥS������Ӭ�+q&����j|UƧ����}���J0��WW< ۋS�)jQR�j���Ư��rN)�Gű�4Ѷ(�S)Ǣ�8��i��W52���No˓� ۍ%�5brOn�L�;�n��\G����=�^U�dI���8$�&���h��'���+�(������cȁ߫k�l��S^���cƗjԌE�ꭔ��gF���Ȓ��@���}O���*;e�v�WV���YJ\�]X'5��ղ�k�F��b 6R�o՜m��i N�i����>J����?��lPm�U��}>_Z&�KK��q�r��I�D�Չ~�q�3fL�:S�e>���E���-G���{L�6p�e,8��������QI��h��a�Xa��U�A'���ʂ���s�+טIjP�-��y�8ۈZ?J$��W�P� ��R�s�]��|�l(�ԓ��sƊi��o(��S0��Y� 8�T97.�����WiL��c�~�dxc�E|�2!�X�K�Ƙਫ਼�$((�6�~|d9u+�qd�^3�89��Y�6L�.I�����?���iI�q���9�)O/뚅����O���X��X�V��ZF[�یgQ�L��K1���RҖr@v�#��X�l��F���Нy�S�8�7�kF!A��sM���^rkp�jP�DyS$N���q��nxҍ!U�f�!eh�i�2�m���`�Y�I�9r�6� �TF���C}/�y�^���Η���5d�'��9A-��J��>{�_l+�`��A���[�'��յ�ϛ#w:݅�%��X�}�&�PSt�Q�"�-��\縵�/����$Ɨh�Xb�*�y��BS����;W�ջ_mc�����vt?2}1�;qS�d�d~u:2k5�2�R�~�z+|HE!)�Ǟl��7`��0�<�,�2*���Hl-��x�^����'_TV�gZA�'j� ^�2Ϊ��N7t�����?w�� �x1��f��Iz�C-Ȗ��K�^q�;���-W�DvT�7��8�Z�������� hK�(P:��Q- �8�n�Z���܃e貾�<�1�YT<�,�����"�6{/ �?�͟��|1�:�#g��W�>$����d��J��d�B��=��jf[��%rE^��il:��B���x���Sּ�1հ��,�=��*�7 fcG��#q� �eh?��2�7�����,�!7x��6�n�LC�4x��},Geǝ�tC.��vS �F�43��zz\��;QYC,6����~;RYS/6���|2���5���v��T��i����������mlv��������&� �nRh^ejR�LG�f���? �ۉҬܦƩ��|��Ȱ����>3����!v��i�ʯ�>�v��オ�X3e���_1z�Kȗ\<������!�8���V��]��?b�k41�Re��T�q��mz��TiOʦ�Z��Xq���L������q"+���2ۨ��8}�&N7XU7Ap�d�X��~�׿��&4e�o�F��� �H����O���č�c�� 懴�6���͉��+)��v;j��ݷ�� �UV�� i��� j���Y9GdÒJ1��詞�����V?h��l����l�cGs�ځ�������y�Ac�����\V3�? �� ܙg�>qH�S,�E�W�[�㺨�uch�⍸�O�}���a��>�q�6�n6����N6�q������N ! 1AQaq�0@����"2BRb�#Pr���3C`��Scst���$4D���%Td�� ?���N����a��3��m���C���w��������xA�m�q�m���m������$����4n淿t'��C"w��zU=D�\R+w�p+Y�T�&�պ@��ƃ��3ޯ?�Aﶂ��aŘ���@-�����Q�=���9D��ռ�ѻ@��M�V��P��܅�G5�f�Y<�u=,EC)�<�Fy'�"�&�չ�X~f��l�KԆV��?�� �W�N����=(� �;���{�r����ٌ�Y���h{�١������jW����P���Tc�����X�K�r��}���w�R��%��?���E��m�� �Y�q|����\lEE4���r���}�lsI�Y������f�$�=�d�yO����p�����yBj8jU�o�/�S��?�U��*������ˍ�0������u�q�m [�?f����a�� )Q�>����6#������� ?����0UQ����,IX���(6ڵ[�DI�MNލ�c&���υ�j\��X�R|,4��� j������T�hA�e��^���d���b<����n�� �즇�=!���3�^�`j�h�ȓr��jẕ�c�,ٞX����-����a�ﶔ���#�$��]w�O��Ӫ�1y%��L�Y<�wg#�ǝ�̗`�x�xa�t�w��»1���o7o5��>�m뭛C���Uƃߜ}�C���y1Xνm�F8�jI���]����H���ۺиE@I�i;r�8ӭ����V�F�Շ| ��&?�3|x�B�MuS�Ge�=Ӕ�#BE5G�����Y!z��_e��q�р/W>|-�Ci߇�t�1ޯќd�R3�u��g�=0 5��[?�#͏��q�cf���H��{ ?u�=?�?ǯ���}Z��z���hmΔ�BFTW�����<�q�(v� ��!��z���iW]*�J�V�z��gX֧A�q�&��/w���u�gYӘa���; �i=����g:��?2�dž6�ى�k�4�>�Pxs����}������G�9��3 ���)gG�R<>r h�$��'nc�h�P��Bj��J�ҧH� -��N1���N��?��~��}-q!=��_2hc�M��l�vY%UE�@|�v����M2�.Y[|y�"Eï��K�ZF,�ɯ?,q�?v�M 80jx�"�;�9vk�����+ ֧�� �ȺU��?�%�vcV��mA�6��Qg^M����A}�3�nl� QRN�l8�kkn�'�����(��M�7m9و�q���%ޟ���*h$Zk"��$�9��: �?U8�Sl��,,|ɒ��xH(ѷ����Gn�/Q�4�P��G�%��Ա8�N��!� �&�7�;���eKM7�4��9R/%����l�c>�x;������>��C�:�����t��h?aKX�bhe�ᜋ^�$�Iհ �hr7%F$�E��Fd���t��5���+�(M6�t����Ü�UU|zW�=a�Ts�Tg������dqP�Q����b'�m���1{|Y����X�N��b �P~��F^F:����k6�"�j!�� �I�r�`��1&�-$�Bevk:y���#yw��I0��x��=D�4��tU���P�ZH��ڠ底taP��6����b>�xa����Q�#� WeF��ŮNj�p�J* mQ�N����*I�-*�ȩ�F�g�3 �5��V�ʊ�ɮ�a��5F���O@{���NX��?����H�]3��1�Ri_u��������ѕ�� ����0��� F��~��:60�p�͈�S��qX#a�5>���`�o&+�<2�D����: �������ڝ�$�nP���*)�N�|y�Ej�F�5ټ�e���ihy�Z �>���k�bH�a�v��h�-#���!�Po=@k̆IEN��@��}Ll?j�O������߭�ʞ���Q|A07x���wt!xf���I2?Z��<ץ�T���cU�j��]��陎Ltl �}5�ϓ��$�,��O�mˊ�;�@O��jE��j(�ا,��LX���LO���Ц�90�O �.����a��nA���7������j4 ��W��_ٓ���zW�jcB������y՗+EM�)d���N�g6�y1_x��p�$Lv:��9�"z��p���ʙ$��^��JԼ*�ϭ����o���=x�Lj�6�J��u82�A�H�3$�ٕ@�=Vv�]�'�qEz�;I˼��)��=��ɯ���x �/�W(V���p�����$ �m�������u�����񶤑Oqˎ�T����r��㠚x�sr�GC��byp�G��1ߠ�w e�8�$⿄����/�M{*}��W�]˷.�CK\�ުx���/$�WPw���r� |i���&�}�{�X� �>��$-��l���?-z���g����lΆ���(F���h�vS*���b���߲ڡn,|)mrH[���a�3�ר�[1��3o_�U�3�TC�$��(�=�)0�kgP���� ��u�^=��4 �WYCҸ:��vQ�ר�X�à��tk�m,�t*��^�,�}D*� �"(�I��9R����>`�`��[~Q]�#af��i6l��8���6�:,s�s�N6�j"�A4���IuQ��6E,�GnH��zS�HO�uk�5$�I�4��ؤ�Q9�@��C����wp�BGv[]�u�Ov���0I4���\��y�����Q�Ѹ��~>Z��8�T��a��q�ޣ;z��a���/��S��I:�ܫ_�|������>=Z����8:�S��U�I�J��"IY���8%b8���H��:�QO�6�;7�I�S��J��ҌAά3��>c���E+&jf$eC+�z�;��V����� �r���ʺ������my�e���aQ�f&��6�ND��.:��NT�vm�<- u���ǝ\MvZY�N�NT��-A�>jr!S��n�O 1�3�Ns�%�3D@���`������ܟ 1�^c<���� �a�ɽ�̲�Xë#�w�|y�cW�=�9I*H8�p�^(4���՗�k��arOcW�tO�\�ƍR��8����'�K���I�Q�����?5�>[�}��yU�ײ -h��=��% q�ThG�2�)���"ו3]�!kB��*p�FDl�A���,�eEi�H�f�Ps�����5�H:�Փ~�H�0Dت�D�I����h�F3�������c��2���E��9�H��5�zԑ�ʚ�i�X�=:m�xg�hd(�v����׊�9iS��O��d@0ڽ���:�p�5�h-��t�&���X�q�ӕ,��ie�|���7A�2���O%P��E��htj��Y1��w�Ѓ!����  ���� ࢽ��My�7�\�a�@�ţ�J �4�Ȼ�F�@o�̒?4�wx��)��]�P��~�����u�����5�����7X ��9��^ܩ�U;Iꭆ 5 �������eK2�7(�{|��Y׎ �V��\"���Z�1� Z�����}��(�Ǝ"�1S���_�vE30>���p;� ΝD��%x�W�?W?v����o�^V�i�d��r[��/&>�~`�9Wh��y�;���R��� ;;ɮT��?����r$�g1�K����A��C��c��K��l:�'��3 c�ﳯ*"t8�~l��)���m��+U,z��`(�>yJ�?����h>��]��v��ЍG*�{`��;y]��I�T� ;c��NU�fo¾h���/$���|NS���1�S�"�H��V���T���4��uhǜ�]�v;���5�͠x��'C\�SBpl���h}�N����� A�Bx���%��ޭ�l��/����T��w�ʽ]D�=����K���ž�r㻠l4�S�O?=�k �M:� ��c�C�a�#ha���)�ѐxc�s���gP�iG��{+���x���Q���I= �� z��ԫ+ �8"�k�ñ�j=|����c ��y��CF��/��*9ж�h{ �?4�o� ��k�m�Q�N�x��;�Y��4膚�a�w?�6�>e]�����Q�r�:����g�,i"�����ԩA�*M�<�G��b�if��l^M��5� �Ҩ�{����6J��ZJ�����P�*�����Y���ݛu�_4�9�I8�7���������,^ToR���m4�H��?�N�S�ѕw��/S��甍�@�9H�S�T��t�ƻ���ʒU��*{Xs�@����f�����֒Li�K{H�w^���������Ϥm�tq���s� ���ք��f:��o~s��g�r��ט� �S�ѱC�e]�x���a��) ���(b-$(�j>�7q�B?ӕ�F��hV25r[7 Y� }L�R��}����*sg+��x�r�2�U=�*'WS��ZDW]�WǞ�<��叓���{�$�9Ou4��y�90-�1�'*D`�c�^o?(�9��u���ݐ��'PI&� f�Jݮ�������:wS����jfP1F:X �H�9dԯ���˝[�_54 �}*;@�ܨ�� ð�yn�T���?�ןd�#���4rG�ͨ��H�1�|-#���Mr�S3��G�3�����)�.᧏3v�z֑��r����$G"�`j �1t��x0<Ɔ�Wh6�y�6��,œ�Ga��gA����y��b��)��h�D��ß�_�m��ü �gG;��e�v��ݝ�nQ� ��C����-�*��o���y�a��M��I�>�<���]obD��"�:���G�A��-\%LT�8���c�)��+y76���o�Q�#*{�(F�⽕�y����=���rW�\p���۩�c���A���^e6��K������ʐ�cVf5$�'->���ՉN"���F�"�UQ@�f��Gb~��#�&�M=��8�ט�JNu9��D��[̤�s�o�~������ G��9T�tW^g5y$b��Y'��س�Ǵ�=��U-2 #�MC�t(�i� �lj�@Q 5�̣i�*�O����s�x�K�f��}\��M{E�V�{�υ��Ƈ�����);�H����I��fe�Lȣr�2��>��W�I�Ȃ6������i��k�� �5�YOxȺ����>��Y�f5'��|��H+��98pj�n�.O�y�������jY��~��i�w'������l�;�s�2��Y��:'lg�ꥴ)o#'Sa�a�K��Z� �m��}�`169�n���"���x��I ��*+� }F<��cГ���F�P�������ֹ*�PqX�x۩��,� ��N�� �4<-����%����:��7����W���u�`����� $�?�I��&����o��o��`v�>��P��"��l���4��5'�Z�gE���8���?��[�X�7(��.Q�-��*���ތL@̲����v��.5���[��=�t\+�CNܛ��,g�SQnH����}*F�G16���&:�t��4ُ"A��̣��$�b �|����#rs��a�����T�� ]�<�j��BS�('$�ɻ� �wP;�/�n��?�ݜ��x�F��yUn�~mL*-�������Xf�wd^�a�}��f�,=t�׵i�.2/wpN�Ep8�OР���•��R�FJ� 55TZ��T �ɭ�<��]��/�0�r�@�f��V��V����Nz�G��^���7hZi����k��3�,kN�e|�vg�1{9]_i��X5y7� 8e]�U����'�-2,���e"����]ot�I��Y_��n�(JҼ��1�O ]bXc���Nu�No��pS���Q_���_�?i�~�x h5d'�(qw52] ��'ޤ�q��o1�R!���`ywy�A4u���h<קy���\[~�4�\ X�Wt/� 6�����n�F�a8��f���z �3$�t(���q��q�x��^�XWeN'p<-v�!�{�(>ӽDP7��ո0�y)�e$ٕv�Ih'Q�EA�m*�H��RI��=:��� ���4牢) �%_iN�ݧ�l]� �Nt���G��H�L��� ɱ�g<���1V�,�J~�ٹ�"K��Q�� 9�HS�9�?@��k����r�;we݁�]I�!{ �@�G�[�"��`���J:�n]�{�cA�E����V��ʆ���#��U9�6����j�#Y�m\��q�e4h�B�7��C�������d<�?J����1g:ٳ���=Y���D�p�ц� ׈ǔ��1�]26؜oS�'��9�V�FVu�P�h�9�xc�oq�X��p�o�5��Ա5$�9W�V(�[Ak�aY錎qf;�'�[�|���b�6�Ck��)��#a#a˙��8���=äh�4��2��C��4tm^ �n'c���]GQ$[Wҿ��i���vN�{Fu ��1�gx��1┷���N�m��{j-,��x�� Ūm�ЧS�[�s���Gna���䑴�� x�p 8<������97�Q���ϴ�v�aϚG��Rt�Һ׈�f^\r��WH�JU�7Z���y)�vg=����n��4�_)y��D'y�6�]�c�5̪�\� �PF�k����&�c;��cq�$~T�7j ���nç]�<�g ":�to�t}�159�<�/�8������m�b�K#g'I'.W�����6��I/��>v��\�MN��g���m�A�yQL�4u�Lj�j9��#44�t��l^�}L����n��R��!��t��±]��r��h6ٍ>�yҏ�N��fU�� ���� Fm@�8}�/u��jb9������he:A�y�ծw��GpΧh�5����l}�3p468��)U��d��c����;Us/�֔�YX�1�O2��uq�s��`hwg�r~�{ R��mhN��؎*q 42�*th��>�#���E����#��Hv�O����q�}�����6�e��\�,Wk�#���X��b>��p}�դ��3���T5��†��6��[��@�P�y*n��|'f�֧>�lư΂�̺����SU�'*�q�p�_S�����M�� '��c�6�����m�� ySʨ;M��r���Ƌ�m�Kxo,���Gm�P��A�G�:��i��w�9�}M(�^�V��$ǒ�ѽ�9���|���� �a����J�SQ�a���r�B;����}���ٻ֢�2�%U���c�#�g���N�a�ݕ�'�v�[�OY'��3L�3�;,p�]@�S��{ls��X�'���c�jw�k'a�.��}�}&�� �dP�*�bK=ɍ!����;3n�gΊU�ߴmt�'*{,=SzfD� A��ko~�G�aoq�_mi}#�m�������P�Xhύ����mxǍ�΂���巿zf��Q���c���|kc�����?���W��Y�$���_Lv����l߶��c���`?����l�j�ݲˏ!V��6����U�Ђ(A���4y)H���p�Z_�x��>���e��R��$�/�`^'3qˏ�-&Q�=?��CFVR �D�fV�9��{�8g�������n�h�(P"��6�[�D���< E�����~0<@�`�G�6����Hг�cc�� �c�K.5��D��d�B���`?�XQ��2��ٿyqo&+�1^� DW�0�ꊩ���G�#��Q�nL3��c���������/��x ��1�1[y�x�პCW��C�c�UĨ80�m�e�4.{�m��u���I=��f�����0QRls9���f���������9���~f�����Ǩ��a�"@�8���ȁ�Q����#c�ic������G��$���G���r/$W�(��W���V�"��m�7�[m�A�m����bo��D� j����۳� l���^�k�h׽����� ��#� iXn�v��eT�k�a�^Y�4�BN��ĕ��0 !01@Q"2AaPq3BR������?���@4�Q�����T3,���㺠�W�[=JK�Ϟ���2�r^7��vc�:�9 �E�ߴ�w�S#d���Ix��u��:��Hp��9E!�� V 2;73|F��9Y���*ʬ�F��D����u&���y؟��^EA��A��(ɩ���^��GV:ݜDy�`��Jr29ܾ�㝉��[���E;Fzx��YG��U�e�Y�C���� ����v-tx����I�sם�Ę�q��Eb�+P\ :>�i�C'�;�����k|z�رn�y]�#ǿb��Q��������w�����(�r|ӹs��[�D��2v-%��@;�8<a���[\o[ϧw��I!��*0�krs)�[�J9^��ʜ��p1)� "��/_>��o��<1����A�E�y^�C��`�x1'ܣn�p��s`l���fQ��):�l����b>�Me�jH^?�kl3(�z:���1ŠK&?Q�~�{�ٺ�h�y���/�[��V�|6��}�KbX����mn[-��7�5q�94�������dm���c^���h� X��5��<�eޘ>G���-�}�دB�ޟ� ��|�rt�M��V+�]�c?�-#ڛ��^ǂ}���Lkr���O��u�>�-D�ry� D?:ޞ�U��ǜ�7�V��?瓮�"�#���r��չģVR;�n���/_� ؉v�ݶe5d�b9��/O��009�G���5n�W����JpA�*�r9�>�1��.[t���s�F���nQ� V 77R�]�ɫ8����_0<՜�IF�u(v��4��F�k�3��E)��N:��yڮe��P�`�1}�$WS��J�SQ�N�j�ٺ��޵�#l���ј(�5=��5�lǏmoW�v-�1����v,W�mn��߀$x�<����v�j(����c]��@#��1������Ǔ���o'��u+����;G�#�޸��v-lη��/(`i⣍Pm^���ԯ̾9Z��F��������n��1��� ��]�[��)�'������:�֪�W��FC����� �B9،!?���]��V��A�Վ�M��b�w��G F>_DȬ0¤�#�QR�[V��kz���m�w�"��9ZG�7'[��=�Q����j8R?�zf�\a�=��O�U����*oB�A�|G���2�54 �p��.w7� �� ��&������ξxGHp� B%��$g�����t�Џ򤵍z���HN�u�Я�-�'4��0��;_��3 !01"@AQa2Pq#3BR������?��ʩca��en��^��8���<�u#��m*08r��y�N"�<�Ѳ0��@\�p��� �����Kv�D��J8�Fҽ� �f�Y��-m�ybX�NP����}�!*8t(�OqѢ��Q�wW�K��ZD��Δ^e��!� ��B�K��p~�����e*l}z#9ң�k���q#�Ft�o��S�R����-�w�!�S���Ӥß|M�l޶V��!eˈ�8Y���c�ЮM2��tk���� ������J�fS����Ö*i/2�����n]�k�\���|4yX�8��U�P.���Ы[���l��@"�t�<������5�lF���vU�����W��W��;�b�cД^6[#7@vU�xgZv��F�6��Q,K�v��� �+Ъ��n��Ǣ��Ft���8��0��c�@�!�Zq s�v�t�;#](B��-�nῃ~���3g������5�J�%���O������n�kB�ĺ�.r��+���#�N$?�q�/�s�6��p��a����a��J/��M�8��6�ܰ"�*������ɗud"\w���aT(����[��F��U՛����RT�b���n�*��6���O��SJ�.�ij<�v�MT��R\c��5l�sZB>F��<7�;EA��{��E���Ö��1U/�#��d1�a�n.1ě����0�ʾR�h��|�R��Ao�3�m3 ��%�� ���28Q� ��y��φ���H�To�7�lW>����#i`�q���c����a��� �m,B�-j����݋�'mR1Ήt�>��V��p���s�0IbI�C.���1R�ea�����]H�6����������4B>��o��](��$B���m�����a�!=��?�B� K�Ǿ+�Ծ"�n���K��*��+��[T#�{E�J�S����Q�����s�5�:�U�\wĐ�f�3����܆&�)����I���Ԇw��E T�lrTf6Q|R�h:��[K�� �z��c֧�G�C��%\��_�a�84��HcO�bi��ؖV��7H �)*ģK~Xhչ0��4?�0��� �E<���}3���#���u�?�� ��|g�S�6ꊤ�|�I#Hڛ� �ա��w�X��9��7���Ŀ%�SL��y6č��|�F�a 8���b��$�sק�h���b9RAu7�˨p�Č�_\*w��묦��F ����4D~�f����|(�"m���NK��i�S�>�$d7SlA��/�²����SL��|6N�}���S�˯���g��]6��; �#�.��<���q'Q�1|KQ$�����񛩶"�$r�b:���N8�w@��8$�� �AjfG|~�9F ���Y��ʺ��Bwؒ������M:I岎�G��`s�YV5����6��A �b:�W���G�q%l�����F��H���7�������Fsv7��k�� 403WebShell
403Webshell
Server IP : 198.54.115.249  /  Your IP : 216.73.216.224
Web Server : LiteSpeed
System : Linux server66.web-hosting.com 4.18.0-553.44.1.lve.el8.x86_64 #1 SMP Thu Mar 13 14:29:12 UTC 2025 x86_64
User : digigcnj ( 11081)
PHP Version : 8.0.30
Disable Function : NONE
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : ON  |  Sudo : OFF  |  Pkexec : OFF
Directory :  /opt/alt/python35/lib/python3.5/site-packages/pip/_vendor/html5lib/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :


[ Back ]     

Current File : /opt/alt/python35/lib/python3.5/site-packages/pip/_vendor/html5lib/_tokenizer.py
from __future__ import absolute_import, division, unicode_literals

from pip._vendor.six import unichr as chr

from collections import deque, OrderedDict
from sys import version_info

from .constants import spaceCharacters
from .constants import entities
from .constants import asciiLetters, asciiUpper2Lower
from .constants import digits, hexDigits, EOF
from .constants import tokenTypes, tagTokenTypes
from .constants import replacementCharacters

from ._inputstream import HTMLInputStream

from ._trie import Trie

entitiesTrie = Trie(entities)

if version_info >= (3, 7):
    attributeMap = dict
else:
    attributeMap = OrderedDict


class HTMLTokenizer(object):
    """ This class takes care of tokenizing HTML.

    * self.currentToken
      Holds the token that is currently being processed.

    * self.state
      Holds a reference to the method to be invoked... XXX

    * self.stream
      Points to HTMLInputStream object.
    """

    def __init__(self, stream, parser=None, **kwargs):

        self.stream = HTMLInputStream(stream, **kwargs)
        self.parser = parser

        # Setup the initial tokenizer state
        self.escapeFlag = False
        self.lastFourChars = []
        self.state = self.dataState
        self.escape = False

        # The current token being created
        self.currentToken = None
        super(HTMLTokenizer, self).__init__()

    def __iter__(self):
        """ This is where the magic happens.

        We do our usually processing through the states and when we have a token
        to return we yield the token which pauses processing until the next token
        is requested.
        """
        self.tokenQueue = deque([])
        # Start processing. When EOF is reached self.state will return False
        # instead of True and the loop will terminate.
        while self.state():
            while self.stream.errors:
                yield {"type": tokenTypes["ParseError"], "data": self.stream.errors.pop(0)}
            while self.tokenQueue:
                yield self.tokenQueue.popleft()

    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

    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})

    def processEntityInAttribute(self, allowedChar):
        """This method replaces the need for "entityInAttributeValueState".
        """
        self.consumeEntity(allowedChar=allowedChar, fromAttribute=True)

    def emitCurrentToken(self):
        """This method is a generic handler for emitting the tags. It also sets
        the state to "data" because that's what's needed after a token has been
        emitted.
        """
        token = self.currentToken
        # Add token to the queue to be yielded
        if (token["type"] in tagTokenTypes):
            token["name"] = token["name"].translate(asciiUpper2Lower)
            if token["type"] == tokenTypes["StartTag"]:
                raw = token["data"]
                data = attributeMap(raw)
                if len(raw) > len(data):
                    # we had some duplicated attribute, fix so first wins
                    data.update(raw[::-1])
                token["data"] = data

            if token["type"] == tokenTypes["EndTag"]:
                if token["data"]:
                    self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                            "data": "attributes-in-end-tag"})
                if token["selfClosing"]:
                    self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                            "data": "self-closing-flag-on-end-tag"})
        self.tokenQueue.append(token)
        self.state = self.dataState

    # Below are the various tokenizer states worked out.
    def dataState(self):
        data = self.stream.char()
        if data == "&":
            self.state = self.entityDataState
        elif data == "<":
            self.state = self.tagOpenState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\u0000"})
        elif data is EOF:
            # Tokenization ends.
            return False
        elif data in spaceCharacters:
            # Directly after emitting a token you switch back to the "data
            # state". At that point spaceCharacters are important so they are
            # emitted separately.
            self.tokenQueue.append({"type": tokenTypes["SpaceCharacters"], "data":
                                    data + self.stream.charsUntil(spaceCharacters, True)})
            # No need to update lastFourChars here, since the first space will
            # have already been appended to lastFourChars and will have broken
            # any <!-- or --> sequences
        else:
            chars = self.stream.charsUntil(("&", "<", "\u0000"))
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data":
                                    data + chars})
        return True

    def entityDataState(self):
        self.consumeEntity()
        self.state = self.dataState
        return True

    def rcdataState(self):
        data = self.stream.char()
        if data == "&":
            self.state = self.characterReferenceInRcdata
        elif data == "<":
            self.state = self.rcdataLessThanSignState
        elif data == EOF:
            # Tokenization ends.
            return False
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
        elif data in spaceCharacters:
            # Directly after emitting a token you switch back to the "data
            # state". At that point spaceCharacters are important so they are
            # emitted separately.
            self.tokenQueue.append({"type": tokenTypes["SpaceCharacters"], "data":
                                    data + self.stream.charsUntil(spaceCharacters, True)})
            # No need to update lastFourChars here, since the first space will
            # have already been appended to lastFourChars and will have broken
            # any <!-- or --> sequences
        else:
            chars = self.stream.charsUntil(("&", "<", "\u0000"))
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data":
                                    data + chars})
        return True

    def characterReferenceInRcdata(self):
        self.consumeEntity()
        self.state = self.rcdataState
        return True

    def rawtextState(self):
        data = self.stream.char()
        if data == "<":
            self.state = self.rawtextLessThanSignState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
        elif data == EOF:
            # Tokenization ends.
            return False
        else:
            chars = self.stream.charsUntil(("<", "\u0000"))
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data":
                                    data + chars})
        return True

    def scriptDataState(self):
        data = self.stream.char()
        if data == "<":
            self.state = self.scriptDataLessThanSignState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
        elif data == EOF:
            # Tokenization ends.
            return False
        else:
            chars = self.stream.charsUntil(("<", "\u0000"))
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data":
                                    data + chars})
        return True

    def plaintextState(self):
        data = self.stream.char()
        if data == EOF:
            # Tokenization ends.
            return False
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data":
                                    data + self.stream.charsUntil("\u0000")})
        return True

    def tagOpenState(self):
        data = self.stream.char()
        if data == "!":
            self.state = self.markupDeclarationOpenState
        elif data == "/":
            self.state = self.closeTagOpenState
        elif data in asciiLetters:
            self.currentToken = {"type": tokenTypes["StartTag"],
                                 "name": data, "data": [],
                                 "selfClosing": False,
                                 "selfClosingAcknowledged": False}
            self.state = self.tagNameState
        elif data == ">":
            # XXX In theory it could be something besides a tag name. But
            # do we really care?
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-tag-name-but-got-right-bracket"})
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<>"})
            self.state = self.dataState
        elif data == "?":
            # XXX In theory it could be something besides a tag name. But
            # do we really care?
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-tag-name-but-got-question-mark"})
            self.stream.unget(data)
            self.state = self.bogusCommentState
        else:
            # XXX
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-tag-name"})
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.stream.unget(data)
            self.state = self.dataState
        return True

    def closeTagOpenState(self):
        data = self.stream.char()
        if data in asciiLetters:
            self.currentToken = {"type": tokenTypes["EndTag"], "name": data,
                                 "data": [], "selfClosing": False}
            self.state = self.tagNameState
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-closing-tag-but-got-right-bracket"})
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-closing-tag-but-got-eof"})
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "</"})
            self.state = self.dataState
        else:
            # XXX data can be _'_...
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-closing-tag-but-got-char",
                                    "datavars": {"data": data}})
            self.stream.unget(data)
            self.state = self.bogusCommentState
        return True

    def tagNameState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeAttributeNameState
        elif data == ">":
            self.emitCurrentToken()
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-tag-name"})
            self.state = self.dataState
        elif data == "/":
            self.state = self.selfClosingStartTagState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["name"] += "\uFFFD"
        else:
            self.currentToken["name"] += data
            # (Don't use charsUntil here, because tag names are
            # very short and it's faster to not do anything fancy)
        return True

    def rcdataLessThanSignState(self):
        data = self.stream.char()
        if data == "/":
            self.temporaryBuffer = ""
            self.state = self.rcdataEndTagOpenState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.stream.unget(data)
            self.state = self.rcdataState
        return True

    def rcdataEndTagOpenState(self):
        data = self.stream.char()
        if data in asciiLetters:
            self.temporaryBuffer += data
            self.state = self.rcdataEndTagNameState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "</"})
            self.stream.unget(data)
            self.state = self.rcdataState
        return True

    def rcdataEndTagNameState(self):
        appropriate = self.currentToken and self.currentToken["name"].lower() == self.temporaryBuffer.lower()
        data = self.stream.char()
        if data in spaceCharacters and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.beforeAttributeNameState
        elif data == "/" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.selfClosingStartTagState
        elif data == ">" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.emitCurrentToken()
            self.state = self.dataState
        elif data in asciiLetters:
            self.temporaryBuffer += data
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "</" + self.temporaryBuffer})
            self.stream.unget(data)
            self.state = self.rcdataState
        return True

    def rawtextLessThanSignState(self):
        data = self.stream.char()
        if data == "/":
            self.temporaryBuffer = ""
            self.state = self.rawtextEndTagOpenState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.stream.unget(data)
            self.state = self.rawtextState
        return True

    def rawtextEndTagOpenState(self):
        data = self.stream.char()
        if data in asciiLetters:
            self.temporaryBuffer += data
            self.state = self.rawtextEndTagNameState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "</"})
            self.stream.unget(data)
            self.state = self.rawtextState
        return True

    def rawtextEndTagNameState(self):
        appropriate = self.currentToken and self.currentToken["name"].lower() == self.temporaryBuffer.lower()
        data = self.stream.char()
        if data in spaceCharacters and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.beforeAttributeNameState
        elif data == "/" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.selfClosingStartTagState
        elif data == ">" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.emitCurrentToken()
            self.state = self.dataState
        elif data in asciiLetters:
            self.temporaryBuffer += data
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "</" + self.temporaryBuffer})
            self.stream.unget(data)
            self.state = self.rawtextState
        return True

    def scriptDataLessThanSignState(self):
        data = self.stream.char()
        if data == "/":
            self.temporaryBuffer = ""
            self.state = self.scriptDataEndTagOpenState
        elif data == "!":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<!"})
            self.state = self.scriptDataEscapeStartState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.stream.unget(data)
            self.state = self.scriptDataState
        return True

    def scriptDataEndTagOpenState(self):
        data = self.stream.char()
        if data in asciiLetters:
            self.temporaryBuffer += data
            self.state = self.scriptDataEndTagNameState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "</"})
            self.stream.unget(data)
            self.state = self.scriptDataState
        return True

    def scriptDataEndTagNameState(self):
        appropriate = self.currentToken and self.currentToken["name"].lower() == self.temporaryBuffer.lower()
        data = self.stream.char()
        if data in spaceCharacters and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.beforeAttributeNameState
        elif data == "/" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.selfClosingStartTagState
        elif data == ">" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.emitCurrentToken()
            self.state = self.dataState
        elif data in asciiLetters:
            self.temporaryBuffer += data
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "</" + self.temporaryBuffer})
            self.stream.unget(data)
            self.state = self.scriptDataState
        return True

    def scriptDataEscapeStartState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
            self.state = self.scriptDataEscapeStartDashState
        else:
            self.stream.unget(data)
            self.state = self.scriptDataState
        return True

    def scriptDataEscapeStartDashState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
            self.state = self.scriptDataEscapedDashDashState
        else:
            self.stream.unget(data)
            self.state = self.scriptDataState
        return True

    def scriptDataEscapedState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
            self.state = self.scriptDataEscapedDashState
        elif data == "<":
            self.state = self.scriptDataEscapedLessThanSignState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
        elif data == EOF:
            self.state = self.dataState
        else:
            chars = self.stream.charsUntil(("<", "-", "\u0000"))
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data":
                                    data + chars})
        return True

    def scriptDataEscapedDashState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
            self.state = self.scriptDataEscapedDashDashState
        elif data == "<":
            self.state = self.scriptDataEscapedLessThanSignState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
            self.state = self.scriptDataEscapedState
        elif data == EOF:
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            self.state = self.scriptDataEscapedState
        return True

    def scriptDataEscapedDashDashState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
        elif data == "<":
            self.state = self.scriptDataEscapedLessThanSignState
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": ">"})
            self.state = self.scriptDataState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
            self.state = self.scriptDataEscapedState
        elif data == EOF:
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            self.state = self.scriptDataEscapedState
        return True

    def scriptDataEscapedLessThanSignState(self):
        data = self.stream.char()
        if data == "/":
            self.temporaryBuffer = ""
            self.state = self.scriptDataEscapedEndTagOpenState
        elif data in asciiLetters:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<" + data})
            self.temporaryBuffer = data
            self.state = self.scriptDataDoubleEscapeStartState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.stream.unget(data)
            self.state = self.scriptDataEscapedState
        return True

    def scriptDataEscapedEndTagOpenState(self):
        data = self.stream.char()
        if data in asciiLetters:
            self.temporaryBuffer = data
            self.state = self.scriptDataEscapedEndTagNameState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "</"})
            self.stream.unget(data)
            self.state = self.scriptDataEscapedState
        return True

    def scriptDataEscapedEndTagNameState(self):
        appropriate = self.currentToken and self.currentToken["name"].lower() == self.temporaryBuffer.lower()
        data = self.stream.char()
        if data in spaceCharacters and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.beforeAttributeNameState
        elif data == "/" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.state = self.selfClosingStartTagState
        elif data == ">" and appropriate:
            self.currentToken = {"type": tokenTypes["EndTag"],
                                 "name": self.temporaryBuffer,
                                 "data": [], "selfClosing": False}
            self.emitCurrentToken()
            self.state = self.dataState
        elif data in asciiLetters:
            self.temporaryBuffer += data
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "</" + self.temporaryBuffer})
            self.stream.unget(data)
            self.state = self.scriptDataEscapedState
        return True

    def scriptDataDoubleEscapeStartState(self):
        data = self.stream.char()
        if data in (spaceCharacters | frozenset(("/", ">"))):
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            if self.temporaryBuffer.lower() == "script":
                self.state = self.scriptDataDoubleEscapedState
            else:
                self.state = self.scriptDataEscapedState
        elif data in asciiLetters:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            self.temporaryBuffer += data
        else:
            self.stream.unget(data)
            self.state = self.scriptDataEscapedState
        return True

    def scriptDataDoubleEscapedState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
            self.state = self.scriptDataDoubleEscapedDashState
        elif data == "<":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.state = self.scriptDataDoubleEscapedLessThanSignState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
        elif data == EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-script-in-script"})
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
        return True

    def scriptDataDoubleEscapedDashState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
            self.state = self.scriptDataDoubleEscapedDashDashState
        elif data == "<":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.state = self.scriptDataDoubleEscapedLessThanSignState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
            self.state = self.scriptDataDoubleEscapedState
        elif data == EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-script-in-script"})
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            self.state = self.scriptDataDoubleEscapedState
        return True

    def scriptDataDoubleEscapedDashDashState(self):
        data = self.stream.char()
        if data == "-":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "-"})
        elif data == "<":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "<"})
            self.state = self.scriptDataDoubleEscapedLessThanSignState
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": ">"})
            self.state = self.scriptDataState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": "\uFFFD"})
            self.state = self.scriptDataDoubleEscapedState
        elif data == EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-script-in-script"})
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            self.state = self.scriptDataDoubleEscapedState
        return True

    def scriptDataDoubleEscapedLessThanSignState(self):
        data = self.stream.char()
        if data == "/":
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": "/"})
            self.temporaryBuffer = ""
            self.state = self.scriptDataDoubleEscapeEndState
        else:
            self.stream.unget(data)
            self.state = self.scriptDataDoubleEscapedState
        return True

    def scriptDataDoubleEscapeEndState(self):
        data = self.stream.char()
        if data in (spaceCharacters | frozenset(("/", ">"))):
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            if self.temporaryBuffer.lower() == "script":
                self.state = self.scriptDataEscapedState
            else:
                self.state = self.scriptDataDoubleEscapedState
        elif data in asciiLetters:
            self.tokenQueue.append({"type": tokenTypes["Characters"], "data": data})
            self.temporaryBuffer += data
        else:
            self.stream.unget(data)
            self.state = self.scriptDataDoubleEscapedState
        return True

    def beforeAttributeNameState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.stream.charsUntil(spaceCharacters, True)
        elif data in asciiLetters:
            self.currentToken["data"].append([data, ""])
            self.state = self.attributeNameState
        elif data == ">":
            self.emitCurrentToken()
        elif data == "/":
            self.state = self.selfClosingStartTagState
        elif data in ("'", '"', "=", "<"):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "invalid-character-in-attribute-name"})
            self.currentToken["data"].append([data, ""])
            self.state = self.attributeNameState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"].append(["\uFFFD", ""])
            self.state = self.attributeNameState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-attribute-name-but-got-eof"})
            self.state = self.dataState
        else:
            self.currentToken["data"].append([data, ""])
            self.state = self.attributeNameState
        return True

    def attributeNameState(self):
        data = self.stream.char()
        leavingThisState = True
        emitToken = False
        if data == "=":
            self.state = self.beforeAttributeValueState
        elif data in asciiLetters:
            self.currentToken["data"][-1][0] += data +\
                self.stream.charsUntil(asciiLetters, True)
            leavingThisState = False
        elif data == ">":
            # XXX If we emit here the attributes are converted to a dict
            # without being checked and when the code below runs we error
            # because data is a dict not a list
            emitToken = True
        elif data in spaceCharacters:
            self.state = self.afterAttributeNameState
        elif data == "/":
            self.state = self.selfClosingStartTagState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"][-1][0] += "\uFFFD"
            leavingThisState = False
        elif data in ("'", '"', "<"):
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data":
                                    "invalid-character-in-attribute-name"})
            self.currentToken["data"][-1][0] += data
            leavingThisState = False
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "eof-in-attribute-name"})
            self.state = self.dataState
        else:
            self.currentToken["data"][-1][0] += data
            leavingThisState = False

        if leavingThisState:
            # Attributes are not dropped at this stage. That happens when the
            # start tag token is emitted so values can still be safely appended
            # to attributes, but we do want to report the parse error in time.
            self.currentToken["data"][-1][0] = (
                self.currentToken["data"][-1][0].translate(asciiUpper2Lower))
            for name, _ in self.currentToken["data"][:-1]:
                if self.currentToken["data"][-1][0] == name:
                    self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                            "duplicate-attribute"})
                    break
            # XXX Fix for above XXX
            if emitToken:
                self.emitCurrentToken()
        return True

    def afterAttributeNameState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.stream.charsUntil(spaceCharacters, True)
        elif data == "=":
            self.state = self.beforeAttributeValueState
        elif data == ">":
            self.emitCurrentToken()
        elif data in asciiLetters:
            self.currentToken["data"].append([data, ""])
            self.state = self.attributeNameState
        elif data == "/":
            self.state = self.selfClosingStartTagState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"].append(["\uFFFD", ""])
            self.state = self.attributeNameState
        elif data in ("'", '"', "<"):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "invalid-character-after-attribute-name"})
            self.currentToken["data"].append([data, ""])
            self.state = self.attributeNameState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-end-of-tag-but-got-eof"})
            self.state = self.dataState
        else:
            self.currentToken["data"].append([data, ""])
            self.state = self.attributeNameState
        return True

    def beforeAttributeValueState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.stream.charsUntil(spaceCharacters, True)
        elif data == "\"":
            self.state = self.attributeValueDoubleQuotedState
        elif data == "&":
            self.state = self.attributeValueUnQuotedState
            self.stream.unget(data)
        elif data == "'":
            self.state = self.attributeValueSingleQuotedState
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-attribute-value-but-got-right-bracket"})
            self.emitCurrentToken()
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"][-1][1] += "\uFFFD"
            self.state = self.attributeValueUnQuotedState
        elif data in ("=", "<", "`"):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "equals-in-unquoted-attribute-value"})
            self.currentToken["data"][-1][1] += data
            self.state = self.attributeValueUnQuotedState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-attribute-value-but-got-eof"})
            self.state = self.dataState
        else:
            self.currentToken["data"][-1][1] += data
            self.state = self.attributeValueUnQuotedState
        return True

    def attributeValueDoubleQuotedState(self):
        data = self.stream.char()
        if data == "\"":
            self.state = self.afterAttributeValueState
        elif data == "&":
            self.processEntityInAttribute('"')
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"][-1][1] += "\uFFFD"
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-attribute-value-double-quote"})
            self.state = self.dataState
        else:
            self.currentToken["data"][-1][1] += data +\
                self.stream.charsUntil(("\"", "&", "\u0000"))
        return True

    def attributeValueSingleQuotedState(self):
        data = self.stream.char()
        if data == "'":
            self.state = self.afterAttributeValueState
        elif data == "&":
            self.processEntityInAttribute("'")
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"][-1][1] += "\uFFFD"
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-attribute-value-single-quote"})
            self.state = self.dataState
        else:
            self.currentToken["data"][-1][1] += data +\
                self.stream.charsUntil(("'", "&", "\u0000"))
        return True

    def attributeValueUnQuotedState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeAttributeNameState
        elif data == "&":
            self.processEntityInAttribute(">")
        elif data == ">":
            self.emitCurrentToken()
        elif data in ('"', "'", "=", "<", "`"):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-character-in-unquoted-attribute-value"})
            self.currentToken["data"][-1][1] += data
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"][-1][1] += "\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(("&", ">", '"', "'", "=", "<", "`", "\u0000")) | spaceCharacters)
        return True

    def afterAttributeValueState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeAttributeNameState
        elif data == ">":
            self.emitCurrentToken()
        elif data == "/":
            self.state = self.selfClosingStartTagState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-EOF-after-attribute-value"})
            self.stream.unget(data)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-character-after-attribute-value"})
            self.stream.unget(data)
            self.state = self.beforeAttributeNameState
        return True

    def selfClosingStartTagState(self):
        data = self.stream.char()
        if data == ">":
            self.currentToken["selfClosing"] = True
            self.emitCurrentToken()
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data":
                                    "unexpected-EOF-after-solidus-in-tag"})
            self.stream.unget(data)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-character-after-solidus-in-tag"})
            self.stream.unget(data)
            self.state = self.beforeAttributeNameState
        return True

    def bogusCommentState(self):
        # Make a new comment token and give it as value all the characters
        # until the first > or EOF (charsUntil checks for EOF automatically)
        # and emit it.
        data = self.stream.charsUntil(">")
        data = data.replace("\u0000", "\uFFFD")
        self.tokenQueue.append(
            {"type": tokenTypes["Comment"], "data": data})

        # Eat the character directly after the bogus comment which is either a
        # ">" or an EOF.
        self.stream.char()
        self.state = self.dataState
        return True

    def markupDeclarationOpenState(self):
        charStack = [self.stream.char()]
        if charStack[-1] == "-":
            charStack.append(self.stream.char())
            if charStack[-1] == "-":
                self.currentToken = {"type": tokenTypes["Comment"], "data": ""}
                self.state = self.commentStartState
                return True
        elif charStack[-1] in ('d', 'D'):
            matched = True
            for expected in (('o', 'O'), ('c', 'C'), ('t', 'T'),
                             ('y', 'Y'), ('p', 'P'), ('e', 'E')):
                charStack.append(self.stream.char())
                if charStack[-1] not in expected:
                    matched = False
                    break
            if matched:
                self.currentToken = {"type": tokenTypes["Doctype"],
                                     "name": "",
                                     "publicId": None, "systemId": None,
                                     "correct": True}
                self.state = self.doctypeState
                return True
        elif (charStack[-1] == "[" and
              self.parser is not None and
              self.parser.tree.openElements and
              self.parser.tree.openElements[-1].namespace != self.parser.tree.defaultNamespace):
            matched = True
            for expected in ["C", "D", "A", "T", "A", "["]:
                charStack.append(self.stream.char())
                if charStack[-1] != expected:
                    matched = False
                    break
            if matched:
                self.state = self.cdataSectionState
                return True

        self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                "expected-dashes-or-doctype"})

        while charStack:
            self.stream.unget(charStack.pop())
        self.state = self.bogusCommentState
        return True

    def commentStartState(self):
        data = self.stream.char()
        if data == "-":
            self.state = self.commentStartDashState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"] += "\uFFFD"
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "incorrect-comment"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-comment"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["data"] += data
            self.state = self.commentState
        return True

    def commentStartDashState(self):
        data = self.stream.char()
        if data == "-":
            self.state = self.commentEndState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"] += "-\uFFFD"
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "incorrect-comment"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-comment"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["data"] += "-" + data
            self.state = self.commentState
        return True

    def commentState(self):
        data = self.stream.char()
        if data == "-":
            self.state = self.commentEndDashState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"] += "\uFFFD"
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "eof-in-comment"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["data"] += data + \
                self.stream.charsUntil(("-", "\u0000"))
        return True

    def commentEndDashState(self):
        data = self.stream.char()
        if data == "-":
            self.state = self.commentEndState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"] += "-\uFFFD"
            self.state = self.commentState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-comment-end-dash"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["data"] += "-" + data
            self.state = self.commentState
        return True

    def commentEndState(self):
        data = self.stream.char()
        if data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"] += "--\uFFFD"
            self.state = self.commentState
        elif data == "!":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-bang-after-double-dash-in-comment"})
            self.state = self.commentEndBangState
        elif data == "-":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-dash-after-double-dash-in-comment"})
            self.currentToken["data"] += data
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-comment-double-dash"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            # XXX
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-comment"})
            self.currentToken["data"] += "--" + data
            self.state = self.commentState
        return True

    def commentEndBangState(self):
        data = self.stream.char()
        if data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data == "-":
            self.currentToken["data"] += "--!"
            self.state = self.commentEndDashState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["data"] += "--!\uFFFD"
            self.state = self.commentState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-comment-end-bang-state"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["data"] += "--!" + data
            self.state = self.commentState
        return True

    def doctypeState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeDoctypeNameState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-doctype-name-but-got-eof"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "need-space-after-doctype"})
            self.stream.unget(data)
            self.state = self.beforeDoctypeNameState
        return True

    def beforeDoctypeNameState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            pass
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-doctype-name-but-got-right-bracket"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["name"] = "\uFFFD"
            self.state = self.doctypeNameState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-doctype-name-but-got-eof"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["name"] = data
            self.state = self.doctypeNameState
        return True

    def doctypeNameState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.currentToken["name"] = self.currentToken["name"].translate(asciiUpper2Lower)
            self.state = self.afterDoctypeNameState
        elif data == ">":
            self.currentToken["name"] = self.currentToken["name"].translate(asciiUpper2Lower)
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["name"] += "\uFFFD"
            self.state = self.doctypeNameState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype-name"})
            self.currentToken["correct"] = False
            self.currentToken["name"] = self.currentToken["name"].translate(asciiUpper2Lower)
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["name"] += data
        return True

    def afterDoctypeNameState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            pass
        elif data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.currentToken["correct"] = False
            self.stream.unget(data)
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            if data in ("p", "P"):
                matched = True
                for expected in (("u", "U"), ("b", "B"), ("l", "L"),
                                 ("i", "I"), ("c", "C")):
                    data = self.stream.char()
                    if data not in expected:
                        matched = False
                        break
                if matched:
                    self.state = self.afterDoctypePublicKeywordState
                    return True
            elif data in ("s", "S"):
                matched = True
                for expected in (("y", "Y"), ("s", "S"), ("t", "T"),
                                 ("e", "E"), ("m", "M")):
                    data = self.stream.char()
                    if data not in expected:
                        matched = False
                        break
                if matched:
                    self.state = self.afterDoctypeSystemKeywordState
                    return True

            # All the characters read before the current 'data' will be
            # [a-zA-Z], so they're garbage in the bogus doctype and can be
            # discarded; only the latest character might be '>' or EOF
            # and needs to be ungetted
            self.stream.unget(data)
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "expected-space-or-right-bracket-in-doctype", "datavars":
                                    {"data": data}})
            self.currentToken["correct"] = False
            self.state = self.bogusDoctypeState

        return True

    def afterDoctypePublicKeywordState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeDoctypePublicIdentifierState
        elif data in ("'", '"'):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.stream.unget(data)
            self.state = self.beforeDoctypePublicIdentifierState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.stream.unget(data)
            self.state = self.beforeDoctypePublicIdentifierState
        return True

    def beforeDoctypePublicIdentifierState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            pass
        elif data == "\"":
            self.currentToken["publicId"] = ""
            self.state = self.doctypePublicIdentifierDoubleQuotedState
        elif data == "'":
            self.currentToken["publicId"] = ""
            self.state = self.doctypePublicIdentifierSingleQuotedState
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-end-of-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["correct"] = False
            self.state = self.bogusDoctypeState
        return True

    def doctypePublicIdentifierDoubleQuotedState(self):
        data = self.stream.char()
        if data == "\"":
            self.state = self.afterDoctypePublicIdentifierState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["publicId"] += "\uFFFD"
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-end-of-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["publicId"] += data
        return True

    def doctypePublicIdentifierSingleQuotedState(self):
        data = self.stream.char()
        if data == "'":
            self.state = self.afterDoctypePublicIdentifierState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["publicId"] += "\uFFFD"
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-end-of-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["publicId"] += data
        return True

    def afterDoctypePublicIdentifierState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.betweenDoctypePublicAndSystemIdentifiersState
        elif data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data == '"':
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["systemId"] = ""
            self.state = self.doctypeSystemIdentifierDoubleQuotedState
        elif data == "'":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["systemId"] = ""
            self.state = self.doctypeSystemIdentifierSingleQuotedState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["correct"] = False
            self.state = self.bogusDoctypeState
        return True

    def betweenDoctypePublicAndSystemIdentifiersState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            pass
        elif data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data == '"':
            self.currentToken["systemId"] = ""
            self.state = self.doctypeSystemIdentifierDoubleQuotedState
        elif data == "'":
            self.currentToken["systemId"] = ""
            self.state = self.doctypeSystemIdentifierSingleQuotedState
        elif data == EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["correct"] = False
            self.state = self.bogusDoctypeState
        return True

    def afterDoctypeSystemKeywordState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            self.state = self.beforeDoctypeSystemIdentifierState
        elif data in ("'", '"'):
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.stream.unget(data)
            self.state = self.beforeDoctypeSystemIdentifierState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.stream.unget(data)
            self.state = self.beforeDoctypeSystemIdentifierState
        return True

    def beforeDoctypeSystemIdentifierState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            pass
        elif data == "\"":
            self.currentToken["systemId"] = ""
            self.state = self.doctypeSystemIdentifierDoubleQuotedState
        elif data == "'":
            self.currentToken["systemId"] = ""
            self.state = self.doctypeSystemIdentifierSingleQuotedState
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.currentToken["correct"] = False
            self.state = self.bogusDoctypeState
        return True

    def doctypeSystemIdentifierDoubleQuotedState(self):
        data = self.stream.char()
        if data == "\"":
            self.state = self.afterDoctypeSystemIdentifierState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["systemId"] += "\uFFFD"
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-end-of-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["systemId"] += data
        return True

    def doctypeSystemIdentifierSingleQuotedState(self):
        data = self.stream.char()
        if data == "'":
            self.state = self.afterDoctypeSystemIdentifierState
        elif data == "\u0000":
            self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                    "data": "invalid-codepoint"})
            self.currentToken["systemId"] += "\uFFFD"
        elif data == ">":
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-end-of-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.currentToken["systemId"] += data
        return True

    def afterDoctypeSystemIdentifierState(self):
        data = self.stream.char()
        if data in spaceCharacters:
            pass
        elif data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "eof-in-doctype"})
            self.currentToken["correct"] = False
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                    "unexpected-char-in-doctype"})
            self.state = self.bogusDoctypeState
        return True

    def bogusDoctypeState(self):
        data = self.stream.char()
        if data == ">":
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        elif data is EOF:
            # XXX EMIT
            self.stream.unget(data)
            self.tokenQueue.append(self.currentToken)
            self.state = self.dataState
        else:
            pass
        return True

    def cdataSectionState(self):
        data = []
        while True:
            data.append(self.stream.charsUntil("]"))
            data.append(self.stream.charsUntil(">"))
            char = self.stream.char()
            if char == EOF:
                break
            else:
                assert char == ">"
                if data[-1][-2:] == "]]":
                    data[-1] = data[-1][:-2]
                    break
                else:
                    data.append(char)

        data = "".join(data)  # pylint:disable=redefined-variable-type
        # Deal with null here rather than in the parser
        nullCount = data.count("\u0000")
        if nullCount > 0:
            for _ in range(nullCount):
                self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                        "data": "invalid-codepoint"})
            data = data.replace("\u0000", "\uFFFD")
        if data:
            self.tokenQueue.append({"type": tokenTypes["Characters"],
                                    "data": data})
        self.state = self.dataState
        return True

Youez - 2016 - github.com/yon3zu
LinuXploit