ÿØÿà JFIF    ÿÛ „  ( %"1!%)+...383,7(-.+  -+++--++++---+-+-----+---------------+---+-++7-----ÿÀ  ß â" ÿÄ     ÿÄ H    !1AQaq"‘¡2B±ÁÑð#R“Ò Tbr‚²á3csƒ’ÂñDS¢³$CÿÄ   ÿÄ %  !1AQa"23‘ÿÚ   ? ôÿ ¨pŸªáÿ —åYõõ\?àÒü©ŠÄï¨pŸªáÿ —åYõõ\?àÓü©ŠÄá 0Ÿªáÿ Ÿå[úƒ ú®ði~TÁbqÐ8OÕpÿ ƒOò¤Oè`–RÂáœá™êi€ßÉ< FtŸI“öÌ8úDf´°å}“¾œ6  öFá°y¥jñÇh†ˆ¢ã/ÃÐ:ªcÈ "Y¡ðÑl>ÿ ”ÏËte:qž\oäŠe÷󲍷˜HT4&ÿ ÓÐü6ö®¿øþßèô Ÿ•7Ñi’•j|“ñì>b…þS?*Óôÿ ÓÐü*h¥£ír¶ü UãSç‚Ÿ[AÐaè[ûª•õ&õj?†Éö+EzP—WeÒírJFt ‘BŒ†Ï‡%#tE Øz ¥OÛ«!1›üä±Í™%ºÍãö]°î(–:@<‹ŒÊö×òÆt¦ãº+‡¦%ÌÁ²h´OƒJŒtMÜ>ÀÜÊw3Y´•牋4ǍýʏTì>œú=Íwhyë,¾Ôò×õ¿ßÊa»«þˆѪQ|%6ž™A õ%:øj<>É—ÿ Å_ˆCbõ¥š±ý¯Ýƒï…¶|RëócÍf溪“t.СøTÿ *Ä¿-{†çàczůŽ_–^XþŒ±miB[X±d 1,é”zEù»& î9gœf™9Ð'.;—™i}!ôšåîqêÛ٤ёý£½ÆA–àôe"A$˝Úsäÿ ÷Û #°xŸëí(l »ý3—¥5m! rt`†0~'j2(]S¦¦kv,ÚÇ l¦øJA£Šƒ J3E8ÙiŽ:cÉžúeZ°€¯\®kÖ(79«Ž:¯X”¾³Š&¡* ….‰Ž(ÜíŸ2¥ª‡×Hi²TF¤ò[¨íÈRëÉ䢍mgÑ.Ÿ<öäS0í„ǹÁU´f#Vß;Õ–…P@3ío<ä-±»Ž.L|kªÀê›fÂ6@»eu‚|ÓaÞÆŸ…¨ááå>åŠ?cKü6ùTÍÆ”†sĤÚ;H2RÚ†õ\Ö·Ÿn'¾ ñ#ºI¤Å´%çÁ­‚â7›‹qT3Iï¨ÖÚ5I7Ë!ÅOóŸ¶øÝñØôת¦$Tcö‘[«Ö³šÒ';Aþ ¸èíg A2Z"i¸vdÄ÷.iõ®§)¿]¤À†–‡É&ä{V¶iŽ”.Ó×Õÿ û?h¬Mt–íª[ÿ Ñÿ ÌV(í}=ibÔ¡›¥¢±b Lô¥‡piη_Z<‡z§èŒ)iÖwiÇ 2hÙ3·=’d÷8éŽ1¦¸c¤µ€7›7Ø ð\á)} ¹fËí›pAÃL%âc2 í§æQz¿;T8sæ°qø)QFMð‰XŒÂ±N¢aF¨…8¯!U  Z©RÊ ÖPVÄÀÍin™Ì-GˆªÅËŠ›•zË}º±ŽÍFò¹}Uw×#ä5B¤{î}Ð<ÙD é©¤&‡ïDbàÁôMÁ." ¤‡ú*õ'VŽ|¼´Úgllº¼klz[Æüï÷Aób‡Eÿ dÑ»Xx9ÃÜ£ÁT/`¼¸vI±Ýµ·Ë‚“G³þ*Ÿû´r|*}<¨îºœ @¦mÄ’M¹”.œ«Y–|6ÏU¤jç¥ÕÞqO ˜kDÆÁ¨5ÿ š;Њ¦¦€GÙk \ –Þ=â¼=SͧµªS°ÚÍpÜãQűÀõ¬?ÃÁ1Ñ•õZà?hóœ€ L¦l{Y*K˜Ù›zc˜–ˆâ ø+¾ ­-Ök¥%ùEÜA'}ˆ><ÊIè“bpÍ/qÞâvoX€w,\úªò6Z[XdÒæ­@Ö—€$òJí#é>'°Ú ôª˜<)4ryÙ£|óAÅn5žêŸyÒäMÝ2{"}‰–¤l÷ûWX\l¾Á¸góÉOÔ /óñB¤f¸çñ[.P˜ZsÊË*ßT܈§QN¢’¡¨§V¼(Üù*eÕ“”5T¨‹Âê¥FŒã½Dü[8'Ò¥a…Ú¶k7a *•›¼'Ò·\8¨ª\@\õ¢¦íq+DÙrmÎ…_ªæ»ŠÓœ¡¯’Ré9MÅ×D™lælffc+ŒÑ,ý™ÿ ¯þǤ=Å’Á7µ÷ÚÛ/“Ü€ñýã¼àí¾ÕÑ+ƒ,uµMâÀÄbm:ÒÎPæ{˜Gz[ƒ¯«® KHà`ßØŠéí¯P8Aq.C‰ à€kòpj´kN¶qô€…Õ,ÜNŠª-­{Zö’æû44‰sŽè‰îVíRœÕm" 6?³D9¡ÇTíÅꋇ`4«¸ÝÁô ï’ýorqКÇZ«x4Žâéþuïf¹µö[P ,Q£éaX±`PÉÍZ ¸äYúg üAx ’6Lê‚xÝÓ*äQ  Ï’¨hÍ =²,6ï#rÃ<¯–£»ƒ‹,–ê•€ aÛsñ'%Æ"®ÛüìBᝠHÚ3ß°©$“XnœÖ’î2ËTeûìxîß ¦å¿çÉ ðK§þ{‘t‚Ϋ¬jéîZ[ ”š7L¥4VÚCE×]m¤Øy”ä4-dz£œ§¸x.*ãÊÊ b÷•h:©‡¦s`BTÁRû¾g⻩‹jø sF¢àJøFl‘È•Xᓁà~*j¯ +(ÚÕ6-£¯÷GŠØy‚<Ç’.F‹Hœw(+)ÜÜâÈzÄäT§FߘãÏ;DmVœ3Àu@mÚüXÝü•3B¨òÌÁÛ<·ÃÜ z,Ì@õÅ·d2]ü8s÷IôÞ¯^Ç9¢u„~ëAŸï4«M? K]­ÅàPl@s_ p:°¬ZR”´›JC[CS.h‹ƒïËœ«Æ]–÷ó‚wR×k7X‰k›‘´ù¦=¡«‰¨¨Â')—71ó’c‡Ðúµ `é.{§p¹ój\Ž{1h{o±Ý=áUÊïGÖŒõ–-BÄm+AZX¶¡ ïHðæ¥JmÙ;…ä¡Ÿˆ¦ ° äšiÉg«$üMk5¤L“’çÊvïâï ,=f“"íἊ5ô¬x6{ɏžID0e¸vçmi'︧ºð9$ò¹÷*£’9ÿ ²TÔ…×>JV¥}Œ}$p[bÔ®*[jzS*8 ”·T›Í–ñUîƒwo$áè=LT™ç—~ô·¤ÈÚ$榍q‰„+´kFm)ž‹©i–ËqÞŠ‰à¶ü( ‚•§ •°ò·‡#5ª•µÊ﯅¡X¨šÁ*F#TXJÊ ušJVÍ&=iÄs1‚3•'fý§5Ñ<=[íÞ­ PÚ;ѱÌ_~Ä££8rÞ ²w;’hDT°>ÈG¬8Á²ÚzŽ®ò®qZcqJêäÞ-ö[ܘbň±çb“Š¶31²n×iƒðÕ;1¶þÉ ªX‰,ßqÏ$>•î íZ¥Z 1{ç൵+ƒÕµ¥°T$§K]á»Ûï*·¤tMI’ÂZbŽÕiÒ˜}bÓ0£ª5›¨ [5Ž^ÝœWøÂÝh° ¢OWun£¤5 a2Z.G2³YL]jåtì”ä ÁÓ‘%"©<ÔúÊ°sº UZvä‡ÄiÆÒM .÷V·™ø#kèýiíÌ–ª)µT[)BˆõÑ xB¾B€ÖT¨.¥~ð@VĶr#¸ü*åZNDŽH;âi ],©£öØpù(šºãö¼T.uCê•4@ÿ GÕÛ)Cx›®0ø#:ÏðFÒbR\(€€Ä®fã4Þ‰Fä¯HXƒÅ,†öEÑÔÜ]Öv²?tLÃvBY£ú6Êu5ÅAQ³1‘’¬x–HŒÐ‡ ^ ¸KwJôÖŽ5×CÚ¨vÜ«/B0$×k°=ðbÇ(Ï)w±A†Á† 11Í=èQšµ626ŒÜ/`G«µ<}—-Ö7KEHÈÉðóȤmݱû±·ø«Snmá=“ä«šmݱŸ¡¶~ó·“äUóJæúòB|E LêŽy´jDÔ$G¢þÐñ7óR8ýÒ…Ç› WVe#·Ÿ p·Fx~•ݤF÷0Èÿ K¯æS<6’¡WШ; ´ÿ ¥Êø\Òuî†åÝ–VNœkÒ7oòX¨Á­Ø÷FÎÑä±g÷ÿ M~Çî=p,X´ ÝÌÚÅ‹’ÃjÖ.ØöÏñ qïQ¤ÓZE†° =6·]܈ s¸>v•Ž^Ý\wq9r‰Î\¸¡kURÒ$­*‹Nq?Þª*!sŠÆ:TU_u±T+øX¡ ®¹¡,ÄâÃBTsÜ$Ø›4m椴zÜK]’’›Pƒ @€#â˜`é¹=I‡fiV•Ôî“nRm+µFPOhÍ0B£ €+¬5c v•:P'ÒyÎ ‰V~‚Ó†ÖuókDoh$å\*ö%Ю=£«…aȼ½÷Û.-½VŒŠ¼'lyî±1¬3ó#ÞE¿ÔS¤gV£m›=§\û"—WU¤ÚǼÿ ÂnÁGŒÃ ‚õN D³õNÚíŒÕ;HôyÄÈ©P¹Ä{:?R‘Ô¨âF÷ø£bÅó® JS|‚R÷ivýáâ€Æé¡è³´IئÑT!§˜•Øª‚¬â@q€wnïCWÄ@JU€ê¯m6]Ï:£âx'+ÒðXvÓ¦Úm=–´7œ $ì“B£~p%ÕŸUþ« N@¼üï~w˜ñø5®—'Ôe»¤5ã//€ž~‰Tþ›Å7•#¤× Íö pÄ$ùeåì*«ÓŠEØWEÈsßg ¦ûvžSsLpºÊW–âµEWöˬH; ™!CYõZ ÃÄf æ#1W. \uWâ\,\Çf j’<qTbên›Î[vxx£ë 'ö¨1›˜ÀM¼Pÿ H)ƒêêŒA7s,|F“ 꺸k³9Ìö*ç®;Ö!Ö$Eiž•¹ÒÚ†ýóéÝû¾ÕS®ó$’NÝäŸz¤5r¦ãÄÃD÷Üø!°ø‡Ô&@m™Ì^Ãä­d q5Lnÿ N;.6½·N|#ä"1Nƒx“ã<3('&ñßt  ~ªu”1Tb㫨9ê–›–bìd$ߣ=#ÕãÒmU¯eí$EFù5ýYô櫨æ왍Ǘ±ssM]·á¿0ÕåJRÓªîiƒ+O58ÖñªŠÒx" \µâá¨i’¤i —Ö ” M+M¤ë9‚‰A¦°Qõ¾ßøK~¼Ã‘g…Ö´~÷Ï[3GUœÒ½#…kàÔ®Ò”‰³·dWV‰IP‰Ú8u¹”E ÖqLj¾êÕCBš{A^Âß;–¨`¯¬ìö ˼ ×tìø.tƐm*n¨y4o&Àx¥n¦×î‡aupáÛj8¿m›è¶ã!o½;ß0y^ý×^EÑ¿ÒjzŒ­)vÚÑnÄL …^ªô× ‡—‚3k Îý­hï]içå–îÏ*÷ñþ»Ô CÒjøjÍznˆ´ ¹#b'Fô‹ ‰v¥'’à'T´ƒHýÍ%M‰ ƒ&ÆÇŒï1 ‘ –Þ ‰i¬s žR-Ÿ kŠ¬á¬7:þ 0ŒÅÒÕ/aÙ¬ÃÝ#Úøœ ©aiVc‰. ¹¦ãµ” ›Yg¦›ÆÎýº°f³7ƒhá·¸­}&D9¡ÂsÉÙÞèŠõØàC™¨ñbFC|´Ü(ŸƒÚÒ-%»'a Ì¿)ËÇn¿úÿ ÞŽX…4ÊÅH^ôΑí@ù¹Eh¶“L8Çjù ¼ÎåVªóR©Ï5uà V4lZß®=€xÖŸ–ÑÈ ÷”¨°¾__yM1tÉ?uÆþIkÄgæ@þ[¢†°XÃJ£j·:nkÅ¢u ‘}âGzö­/IµèŠ¬¼48q¦F°ŽR¼=ûì{´¯RýicS ÕÛ íNtÍÙï£,w4rêì®»~x(©Uñ§#Ñ&œÕ¤>ÎåÍÓ9’Ö{9eV­[Öjâ²ãu]˜å2›qÑšÕJç0€sÄ|Êëè0튔bÁ>“{×_F`Ø©ºê:µä,v¤ðfc1±"«ÔÍän1#=· Âøv~H½ÐßA¾¿Ü€Óš]Õ; I¾÷ç‚Qi†î¹9ywÔKG˜áñ zQY—§ÃÕZ07§X‚ Áh;ÁM)iÌCH-¯T‘ë|A0{Ò½LÚ–TâÖkÜ’dÀ“rmm»”جPF³ÖcbE§T€ÒxKºû’Ó®7±²(\4ŽÃ¸Uu@j™yĵ;³µ!Á¢b.W¤=mõ´êµK k ¸K^ÜÛ#p*Ü14qkZç5ïë †°5Ï%ÍÛ<Õ¤×Ô¥ê†C Õ´¼ú$ƒÖ“”]Ù¬qÞÚ[4©ý!ûÏ—Áb쳐XµA¬â~`›Çr¸8ìùÝ䫦<>ä÷«?xs´ÇÑ /á;¹øüÊÈÙà{"@Žïzâ¬[âß‚ U_<ÇŸ½4èN˜ú61®qŠu ¦þF£»äJ_ˆÙÎ~ ÞAã–Ý„Ï—rŠD;xTž‘ô`É«…suãO`?³à™ô Lý#Íc5öoæØ‚y´´÷«ZR§<&JÇ+éâô´€i!Àˆ0æAoàðLèÖ-2ŸõW.’t^–(KÁmHµV@xÜÇy®Ñø­â^:Ú3w· 7½¹°ñ¸â¹®:',«Mœ—n­Á+Ãbš LÈ‘ÄnRÓÅœ%¦²‰¨ùQ:¤f‚ "PÕtô¸…cæl…&˜Ú˜Ôkv‹ž+vŠ,=¢v­6—Xy*¥t£«<™:“aîϲ=¦6rO]XI¿Œ÷¤zÚ­›¶ 6÷”w\d ü~v®ˆÌk«^m<ÿ ¢‰Õ\)ùºŽ;… lîÙÅEŠ®cѾ@vnMÏ,¼“ñ•ŽBxðÃzãÇç%3ˆ"}Ù•Åî> BÉú;Ò]V+P˜F_´ßé> Øše|ï‡ÄOmFæÇ ãqÞ$/xÐx­z`ï9"œÜij‚!7.\Td…9M‡•iŽ‹¾‘50ÞŽn¥ß4ÉôO ¹*í^QêËÜÇÌ8=Ž§s‰'ÂëÙ«á%Pú[O †ÅP¯VsŽ°.‰,kc¶ ¬A9n˜XÎ-ÞšN["¹QÕ‰ƒMýÁߺXJæÍaLj¾×Ãmã¾ãÚ uñÒþåQô¦¥ /ÄUx:‚ÍÜ’ Đ©ØÝ3V¨‰ÕnÐ6ó*óúK­«…c ¯U òhsý­jóÔj#,ímŒRµ«lbïUTŒÑ8†Ä0œÏr`ð¡¬É Ї ë"À² ™ 6¥ f¶ ¢ÚoܱԷ-<Àî)†a¶ž'Ú»¨TXqØæ¶÷YÄHy˜9ÈIW­YÀuMFë ºÏ’AqÌ4·/Ú †ô'i$øä­=Ä Ý|öK×40è|È6p‘0§)o¥ctî§H+CA-“ xØ|ÐXŠç l8íºð3Ø:³¤¬KX¯UÿÙ # -*- test-case-name: twisted.web.test.test_xml -*- # # Copyright (c) Twisted Matrix Laboratories. # See LICENSE for details. """ *S*mall, *U*ncomplicated *X*ML. This is a very simple implementation of XML/HTML as a network protocol. It is not at all clever. Its main features are that it does not: - support namespaces - mung mnemonic entity references - validate - perform *any* external actions (such as fetching URLs or writing files) under *any* circumstances - has lots and lots of horrible hacks for supporting broken HTML (as an option, they're not on by default). """ from __future__ import print_function from twisted.internet.protocol import Protocol from twisted.python.compat import unicode from twisted.python.reflect import prefixedMethodNames # Elements of the three-tuples in the state table. BEGIN_HANDLER = 0 DO_HANDLER = 1 END_HANDLER = 2 identChars = '.-_:' lenientIdentChars = identChars + ';+#/%~' def nop(*args, **kw): "Do nothing." def unionlist(*args): l = [] for x in args: l.extend(x) d = dict([(x, 1) for x in l]) return d.keys() def zipfndict(*args, **kw): default = kw.get('default', nop) d = {} for key in unionlist(*[fndict.keys() for fndict in args]): d[key] = tuple([x.get(key, default) for x in args]) return d def prefixedMethodClassDict(clazz, prefix): return dict([(name, getattr(clazz, prefix + name)) for name in prefixedMethodNames(clazz, prefix)]) def prefixedMethodObjDict(obj, prefix): return dict([(name, getattr(obj, prefix + name)) for name in prefixedMethodNames(obj.__class__, prefix)]) class ParseError(Exception): def __init__(self, filename, line, col, message): self.filename = filename self.line = line self.col = col self.message = message def __str__(self): return "%s:%s:%s: %s" % (self.filename, self.line, self.col, self.message) class XMLParser(Protocol): state = None encodings = None filename = "" beExtremelyLenient = 0 _prepend = None # _leadingBodyData will sometimes be set before switching to the # 'bodydata' state, when we "accidentally" read a byte of bodydata # in a different state. _leadingBodyData = None def connectionMade(self): self.lineno = 1 self.colno = 0 self.encodings = [] def saveMark(self): '''Get the line number and column of the last character parsed''' # This gets replaced during dataReceived, restored afterwards return (self.lineno, self.colno) def _parseError(self, message): raise ParseError(*((self.filename,)+self.saveMark()+(message,))) def _buildStateTable(self): '''Return a dictionary of begin, do, end state function tuples''' # _buildStateTable leaves something to be desired but it does what it # does.. probably slowly, so I'm doing some evil caching so it doesn't # get called more than once per class. stateTable = getattr(self.__class__, '__stateTable', None) if stateTable is None: stateTable = self.__class__.__stateTable = zipfndict( *[prefixedMethodObjDict(self, prefix) for prefix in ('begin_', 'do_', 'end_')]) return stateTable def _decode(self, data): if 'UTF-16' in self.encodings or 'UCS-2' in self.encodings: assert not len(data) & 1, 'UTF-16 must come in pairs for now' if self._prepend: data = self._prepend + data for encoding in self.encodings: data = unicode(data, encoding) return data def maybeBodyData(self): if self.endtag: return 'bodydata' # Get ready for fun! We're going to allow # to work! # We do this by making everything between a Text # BUT # -radix if (self.tagName == 'script' and 'src' not in self.tagAttributes): # we do this ourselves rather than having begin_waitforendscript # because that can get called multiple times and we don't want # bodydata to get reset other than the first time. self.begin_bodydata(None) return 'waitforendscript' return 'bodydata' def dataReceived(self, data): stateTable = self._buildStateTable() if not self.state: # all UTF-16 starts with this string if data.startswith((b'\xff\xfe', b'\xfe\xff')): self._prepend = data[0:2] self.encodings.append('UTF-16') data = data[2:] self.state = 'begin' if self.encodings: data = self._decode(data) else: data = data.decode("utf-8") # bring state, lineno, colno into local scope lineno, colno = self.lineno, self.colno curState = self.state # replace saveMark with a nested scope function _saveMark = self.saveMark def saveMark(): return (lineno, colno) self.saveMark = saveMark # fetch functions from the stateTable beginFn, doFn, endFn = stateTable[curState] try: for byte in data: # do newline stuff if byte == u'\n': lineno += 1 colno = 0 else: colno += 1 newState = doFn(byte) if newState is not None and newState != curState: # this is the endFn from the previous state endFn() curState = newState beginFn, doFn, endFn = stateTable[curState] beginFn(byte) finally: self.saveMark = _saveMark self.lineno, self.colno = lineno, colno # state doesn't make sense if there's an exception.. self.state = curState def connectionLost(self, reason): """ End the last state we were in. """ stateTable = self._buildStateTable() stateTable[self.state][END_HANDLER]() # state methods def do_begin(self, byte): if byte.isspace(): return if byte != '<': if self.beExtremelyLenient: self._leadingBodyData = byte return 'bodydata' self._parseError("First char of document [%r] wasn't <" % (byte,)) return 'tagstart' def begin_comment(self, byte): self.commentbuf = '' def do_comment(self, byte): self.commentbuf += byte if self.commentbuf.endswith('-->'): self.gotComment(self.commentbuf[:-3]) return 'bodydata' def begin_tagstart(self, byte): self.tagName = '' # name of the tag self.tagAttributes = {} # attributes of the tag self.termtag = 0 # is the tag self-terminating self.endtag = 0 def do_tagstart(self, byte): if byte.isalnum() or byte in identChars: self.tagName += byte if self.tagName == '!--': return 'comment' elif byte.isspace(): if self.tagName: if self.endtag: # properly strict thing to do here is probably to only # accept whitespace return 'waitforgt' return 'attrs' else: self._parseError("Whitespace before tag-name") elif byte == '>': if self.endtag: self.gotTagEnd(self.tagName) return 'bodydata' else: self.gotTagStart(self.tagName, {}) return (not self.beExtremelyLenient) and 'bodydata' or self.maybeBodyData() elif byte == '/': if self.tagName: return 'afterslash' else: self.endtag = 1 elif byte in '!?': if self.tagName: if not self.beExtremelyLenient: self._parseError("Invalid character in tag-name") else: self.tagName += byte self.termtag = 1 elif byte == '[': if self.tagName == '!': return 'expectcdata' else: self._parseError("Invalid '[' in tag-name") else: if self.beExtremelyLenient: self.bodydata = '<' return 'unentity' self._parseError('Invalid tag character: %r'% byte) def begin_unentity(self, byte): self.bodydata += byte def do_unentity(self, byte): self.bodydata += byte return 'bodydata' def end_unentity(self): self.gotText(self.bodydata) def begin_expectcdata(self, byte): self.cdatabuf = byte def do_expectcdata(self, byte): self.cdatabuf += byte cdb = self.cdatabuf cd = '[CDATA[' if len(cd) > len(cdb): if cd.startswith(cdb): return elif self.beExtremelyLenient: ## WHAT THE CRAP!? MSWord9 generates HTML that includes these ## bizarre chunks, so I've gotta ignore ## 'em as best I can. this should really be a separate parse ## state but I don't even have any idea what these _are_. return 'waitforgt' else: self._parseError("Mal-formed CDATA header") if cd == cdb: self.cdatabuf = '' return 'cdata' self._parseError("Mal-formed CDATA header") def do_cdata(self, byte): self.cdatabuf += byte if self.cdatabuf.endswith("]]>"): self.cdatabuf = self.cdatabuf[:-3] return 'bodydata' def end_cdata(self): self.gotCData(self.cdatabuf) self.cdatabuf = '' def do_attrs(self, byte): if byte.isalnum() or byte in identChars: # XXX FIXME really handle !DOCTYPE at some point if self.tagName == '!DOCTYPE': return 'doctype' if self.tagName[0] in '!?': return 'waitforgt' return 'attrname' elif byte.isspace(): return elif byte == '>': self.gotTagStart(self.tagName, self.tagAttributes) return (not self.beExtremelyLenient) and 'bodydata' or self.maybeBodyData() elif byte == '/': return 'afterslash' elif self.beExtremelyLenient: # discard and move on? Only case I've seen of this so far was: # return self._parseError("Unexpected character: %r" % byte) def begin_doctype(self, byte): self.doctype = byte def do_doctype(self, byte): if byte == '>': return 'bodydata' self.doctype += byte def end_doctype(self): self.gotDoctype(self.doctype) self.doctype = None def do_waitforgt(self, byte): if byte == '>': if self.endtag or not self.beExtremelyLenient: return 'bodydata' return self.maybeBodyData() def begin_attrname(self, byte): self.attrname = byte self._attrname_termtag = 0 def do_attrname(self, byte): if byte.isalnum() or byte in identChars: self.attrname += byte return elif byte == '=': return 'beforeattrval' elif byte.isspace(): return 'beforeeq' elif self.beExtremelyLenient: if byte in '"\'': return 'attrval' if byte in lenientIdentChars or byte.isalnum(): self.attrname += byte return if byte == '/': self._attrname_termtag = 1 return if byte == '>': self.attrval = 'True' self.tagAttributes[self.attrname] = self.attrval self.gotTagStart(self.tagName, self.tagAttributes) if self._attrname_termtag: self.gotTagEnd(self.tagName) return 'bodydata' return self.maybeBodyData() # something is really broken. let's leave this attribute where it # is and move on to the next thing return self._parseError("Invalid attribute name: %r %r" % (self.attrname, byte)) def do_beforeattrval(self, byte): if byte in '"\'': return 'attrval' elif byte.isspace(): return elif self.beExtremelyLenient: if byte in lenientIdentChars or byte.isalnum(): return 'messyattr' if byte == '>': self.attrval = 'True' self.tagAttributes[self.attrname] = self.attrval self.gotTagStart(self.tagName, self.tagAttributes) return self.maybeBodyData() if byte == '\\': # I saw this in actual HTML once: # SM return self._parseError("Invalid initial attribute value: %r; Attribute values must be quoted." % byte) attrname = '' attrval = '' def begin_beforeeq(self,byte): self._beforeeq_termtag = 0 def do_beforeeq(self, byte): if byte == '=': return 'beforeattrval' elif byte.isspace(): return elif self.beExtremelyLenient: if byte.isalnum() or byte in identChars: self.attrval = 'True' self.tagAttributes[self.attrname] = self.attrval return 'attrname' elif byte == '>': self.attrval = 'True' self.tagAttributes[self.attrname] = self.attrval self.gotTagStart(self.tagName, self.tagAttributes) if self._beforeeq_termtag: self.gotTagEnd(self.tagName) return 'bodydata' return self.maybeBodyData() elif byte == '/': self._beforeeq_termtag = 1 return self._parseError("Invalid attribute") def begin_attrval(self, byte): self.quotetype = byte self.attrval = '' def do_attrval(self, byte): if byte == self.quotetype: return 'attrs' self.attrval += byte def end_attrval(self): self.tagAttributes[self.attrname] = self.attrval self.attrname = self.attrval = '' def begin_messyattr(self, byte): self.attrval = byte def do_messyattr(self, byte): if byte.isspace(): return 'attrs' elif byte == '>': endTag = 0 if self.attrval.endswith('/'): endTag = 1 self.attrval = self.attrval[:-1] self.tagAttributes[self.attrname] = self.attrval self.gotTagStart(self.tagName, self.tagAttributes) if endTag: self.gotTagEnd(self.tagName) return 'bodydata' return self.maybeBodyData() else: self.attrval += byte def end_messyattr(self): if self.attrval: self.tagAttributes[self.attrname] = self.attrval def begin_afterslash(self, byte): self._after_slash_closed = 0 def do_afterslash(self, byte): # this state is only after a self-terminating slash, e.g. if self._after_slash_closed: self._parseError("Mal-formed")#XXX When does this happen?? if byte != '>': if self.beExtremelyLenient: return else: self._parseError("No data allowed after '/'") self._after_slash_closed = 1 self.gotTagStart(self.tagName, self.tagAttributes) self.gotTagEnd(self.tagName) # don't need maybeBodyData here because there better not be # any javascript code after a , we need to # remember all the data we've been through so we can append it # to bodydata self.temptagdata += byte # 1 if byte == '/': self.endtag = True elif not self.endtag: self.bodydata += "<" + self.temptagdata return 'waitforendscript' # 2 elif byte.isalnum() or byte in identChars: self.tagName += byte if not 'script'.startswith(self.tagName): self.bodydata += "<" + self.temptagdata return 'waitforendscript' elif self.tagName == 'script': self.gotText(self.bodydata) self.gotTagEnd(self.tagName) return 'waitforgt' # 3 elif byte.isspace(): return 'waitscriptendtag' # 4 else: self.bodydata += "<" + self.temptagdata return 'waitforendscript' def begin_entityref(self, byte): self.erefbuf = '' self.erefextra = '' # extra bit for lenient mode def do_entityref(self, byte): if byte.isspace() or byte == "<": if self.beExtremelyLenient: # '&foo' probably was '&foo' if self.erefbuf and self.erefbuf != "amp": self.erefextra = self.erefbuf self.erefbuf = "amp" if byte == "<": return "tagstart" else: self.erefextra += byte return 'spacebodydata' self._parseError("Bad entity reference") elif byte != ';': self.erefbuf += byte else: return 'bodydata' def end_entityref(self): self.gotEntityReference(self.erefbuf) # hacky support for space after & in entityref in beExtremelyLenient # state should only happen in that case def begin_spacebodydata(self, byte): self.bodydata = self.erefextra self.erefextra = None do_spacebodydata = do_bodydata end_spacebodydata = end_bodydata # Sorta SAX-ish API def gotTagStart(self, name, attributes): '''Encountered an opening tag. Default behaviour is to print.''' print('begin', name, attributes) def gotText(self, data): '''Encountered text Default behaviour is to print.''' print('text:', repr(data)) def gotEntityReference(self, entityRef): '''Encountered mnemonic entity reference Default behaviour is to print.''' print('entityRef: &%s;' % entityRef) def gotComment(self, comment): '''Encountered comment. Default behaviour is to ignore.''' pass def gotCData(self, cdata): '''Encountered CDATA Default behaviour is to call the gotText method''' self.gotText(cdata) def gotDoctype(self, doctype): """Encountered DOCTYPE This is really grotty: it basically just gives you everything between '' as an argument. """ print('!DOCTYPE', repr(doctype)) def gotTagEnd(self, name): '''Encountered closing tag Default behaviour is to print.''' print('end', name)