/** * $Id: Serializer.js 952 2008-11-03 17:56:04Z spocke $ * * @author Moxiecode * @copyright Copyright © 2004-2008, Moxiecode Systems AB, All rights reserved. */ (function() { // Shorten names var extend = tinymce.extend, each = tinymce.each, Dispatcher = tinymce.util.Dispatcher, isIE = tinymce.isIE, isGecko = tinymce.isGecko; // Returns only attribites that have values not all attributes in IE function getIEAtts(n) { var o = []; // Object will throw exception in IE if (n.nodeName == 'OBJECT') return n.attributes; n.cloneNode(false).outerHTML.replace(/([a-z0-9\:\-_]+)=/gi, function(a, b) { o.push({specified : 1, nodeName : b}); }); return o; }; function wildcardToRE(s) { return s.replace(/([?+*])/g, '.$1'); }; /**#@+ * @class This class is used to serialize DOM trees into a string. * Consult the TinyMCE Wiki API for more details and examples on how to use this class. * @member tinymce.dom.Serializer */ tinymce.create('tinymce.dom.Serializer', { /** * Constucts a new DOM serializer class. * * @constructor * @param {Object} s Optional name/Value collection of settings for the serializer. */ Serializer : function(s) { var t = this; t.key = 0; t.onPreProcess = new Dispatcher(t); t.onPostProcess = new Dispatcher(t); if (tinymce.relaxedDomain && tinymce.isGecko) { // Gecko has a bug where we can't create a new XML document if domain relaxing is used t.writer = new tinymce.dom.StringWriter(); } else { try { t.writer = new tinymce.dom.XMLWriter(); } catch (ex) { // IE might throw exception if ActiveX is disabled so we then switch to the slightly slower StringWriter t.writer = new tinymce.dom.StringWriter(); } } // Default settings t.settings = s = extend({ dom : tinymce.DOM, valid_nodes : 0, node_filter : 0, attr_filter : 0, invalid_attrs : /^(mce_|_moz_)/, closed : /(br|hr|input|meta|img|link|param)/, entity_encoding : 'named', entities : '160,nbsp,161,iexcl,162,cent,163,pound,164,curren,165,yen,166,brvbar,167,sect,168,uml,169,copy,170,ordf,171,laquo,172,not,173,shy,174,reg,175,macr,176,deg,177,plusmn,178,sup2,179,sup3,180,acute,181,micro,182,para,183,middot,184,cedil,185,sup1,186,ordm,187,raquo,188,frac14,189,frac12,190,frac34,191,iquest,192,Agrave,193,Aacute,194,Acirc,195,Atilde,196,Auml,197,Aring,198,AElig,199,Ccedil,200,Egrave,201,Eacute,202,Ecirc,203,Euml,204,Igrave,205,Iacute,206,Icirc,207,Iuml,208,ETH,209,Ntilde,210,Ograve,211,Oacute,212,Ocirc,213,Otilde,214,Ouml,215,times,216,Oslash,217,Ugrave,218,Uacute,219,Ucirc,220,Uuml,221,Yacute,222,THORN,223,szlig,224,agrave,225,aacute,226,acirc,227,atilde,228,auml,229,aring,230,aelig,231,ccedil,232,egrave,233,eacute,234,ecirc,235,euml,236,igrave,237,iacute,238,icirc,239,iuml,240,eth,241,ntilde,242,ograve,243,oacute,244,ocirc,245,otilde,246,ouml,247,divide,248,oslash,249,ugrave,250,uacute,251,ucirc,252,uuml,253,yacute,254,thorn,255,yuml,402,fnof,913,Alpha,914,Beta,915,Gamma,916,Delta,917,Epsilon,918,Zeta,919,Eta,920,Theta,921,Iota,922,Kappa,923,Lambda,924,Mu,925,Nu,926,Xi,927,Omicron,928,Pi,929,Rho,931,Sigma,932,Tau,933,Upsilon,934,Phi,935,Chi,936,Psi,937,Omega,945,alpha,946,beta,947,gamma,948,delta,949,epsilon,950,zeta,951,eta,952,theta,953,iota,954,kappa,955,lambda,956,mu,957,nu,958,xi,959,omicron,960,pi,961,rho,962,sigmaf,963,sigma,964,tau,965,upsilon,966,phi,967,chi,968,psi,969,omega,977,thetasym,978,upsih,982,piv,8226,bull,8230,hellip,8242,prime,8243,Prime,8254,oline,8260,frasl,8472,weierp,8465,image,8476,real,8482,trade,8501,alefsym,8592,larr,8593,uarr,8594,rarr,8595,darr,8596,harr,8629,crarr,8656,lArr,8657,uArr,8658,rArr,8659,dArr,8660,hArr,8704,forall,8706,part,8707,exist,8709,empty,8711,nabla,8712,isin,8713,notin,8715,ni,8719,prod,8721,sum,8722,minus,8727,lowast,8730,radic,8733,prop,8734,infin,8736,ang,8743,and,8744,or,8745,cap,8746,cup,8747,int,8756,there4,8764,sim,8773,cong,8776,asymp,8800,ne,8801,equiv,8804,le,8805,ge,8834,sub,8835,sup,8836,nsub,8838,sube,8839,supe,8853,oplus,8855,otimes,8869,perp,8901,sdot,8968,lceil,8969,rceil,8970,lfloor,8971,rfloor,9001,lang,9002,rang,9674,loz,9824,spades,9827,clubs,9829,hearts,9830,diams,338,OElig,339,oelig,352,Scaron,353,scaron,376,Yuml,710,circ,732,tilde,8194,ensp,8195,emsp,8201,thinsp,8204,zwnj,8205,zwj,8206,lrm,8207,rlm,8211,ndash,8212,mdash,8216,lsquo,8217,rsquo,8218,sbquo,8220,ldquo,8221,rdquo,8222,bdquo,8224,dagger,8225,Dagger,8240,permil,8249,lsaquo,8250,rsaquo,8364,euro', bool_attrs : /(checked|disabled|readonly|selected|nowrap)/, valid_elements : '*[*]', extended_valid_elements : 0, valid_child_elements : 0, invalid_elements : 0, fix_table_elements : 0, fix_list_elements : true, fix_content_duplication : true, convert_fonts_to_spans : false, font_size_classes : 0, font_size_style_values : 0, apply_source_formatting : 0, indent_mode : 'simple', indent_char : '\t', indent_levels : 1, remove_linebreaks : 1, remove_redundant_brs : 1, element_format : 'xhtml' }, s); t.dom = s.dom; if (s.remove_redundant_brs) { t.onPostProcess.add(function(se, o) { // Remove BR elements at end of list elements since they get rendered in IE o.content = o.content.replace(/
(\s*<\/li>)/g, '$1'); }); } // Remove XHTML element endings i.e. produce crap :) XHTML is better if (s.element_format == 'html') { t.onPostProcess.add(function(se, o) { o.content = o.content.replace(/<([^>]+) \/>/g, '<$1>'); }); } if (s.fix_list_elements) { t.onPreProcess.add(function(se, o) { var nl, x, a = ['ol', 'ul'], i, n, p, r = /^(OL|UL)$/, np; function prevNode(e, n) { var a = n.split(','), i; while ((e = e.previousSibling) != null) { for (i=0; i= 0; i--) { if (i == pl.length - 1) { while (ns = pl[i - 1].nextSibling) tm.appendChild(ns.parentNode.removeChild(ns)); } else { n = pl[i].cloneNode(false); if (i != 0) { while (ns = pl[i - 1].nextSibling) n.appendChild(ns.parentNode.removeChild(ns)); } tm = tm.appendChild(n); } } e = t.dom.insertAfter(e.parentNode.removeChild(e), pa); t.dom.insertAfter(e, pa); t.dom.insertAfter(pa2, e); } }); }); } }, /**#@+ * @method */ /** * Sets a list of entities to use for the named entity encoded. * * @param {String} s List of entities in the following format: number,name,.... */ setEntities : function(s) { var t = this, a, i, l = {}, re = '', v; // No need to setup more than once if (t.entityLookup) return; // Build regex and lookup array a = s.split(','); for (i = 0; i < a.length; i += 2) { v = a[i]; // Don't add default & " etc. if (v == 34 || v == 38 || v == 60 || v == 62) continue; l[String.fromCharCode(a[i])] = a[i + 1]; v = parseInt(a[i]).toString(16); re += '\\u' + '0000'.substring(v.length) + v; } if (!re) { t.settings.entity_encoding = 'raw'; return; } t.entitiesRE = new RegExp('[' + re + ']', 'g'); t.entityLookup = l; }, /** * Sets the valid child rules. This enables you to specify what elements can be childrens of what parents. * Consult the Wiki for format description on this input. * * @param {String} s String with valid child rules. */ setValidChildRules : function(s) { this.childRules = null; this.addValidChildRules(s); }, /** * Adds valid child rules. This enables you to specify what elements can be childrens of what parents. * Consult the Wiki for format description on this input. * * @param {String} s String with valid child rules to add. */ addValidChildRules : function(s) { var t = this, inst, intr, bloc; if (!s) return; inst = 'A|BR|SPAN|BDO|MAP|OBJECT|IMG|TT|I|B|BIG|SMALL|EM|STRONG|DFN|CODE|Q|SAMP|KBD|VAR|CITE|ABBR|ACRONYM|SUB|SUP|#text|#comment'; intr = 'A|BR|SPAN|BDO|OBJECT|APPLET|IMG|MAP|IFRAME|TT|I|B|U|S|STRIKE|BIG|SMALL|FONT|BASEFONT|EM|STRONG|DFN|CODE|Q|SAMP|KBD|VAR|CITE|ABBR|ACRONYM|SUB|SUP|INPUT|SELECT|TEXTAREA|LABEL|BUTTON|#text|#comment'; bloc = 'H[1-6]|P|DIV|ADDRESS|PRE|FORM|TABLE|LI|OL|UL|TD|CAPTION|BLOCKQUOTE|CENTER|DL|DT|DD|DIR|FIELDSET|FORM|NOSCRIPT|NOFRAMES|MENU|ISINDEX|SAMP'; each(s.split(','), function(s) { var p = s.split(/\[|\]/), re; s = ''; each(p[1].split('|'), function(v) { if (s) s += '|'; switch (v) { case '%itrans': v = intr; break; case '%itrans_na': v = intr.substring(2); break; case '%istrict': v = inst; break; case '%istrict_na': v = inst.substring(2); break; case '%btrans': v = bloc; break; case '%bstrict': v = bloc; break; } s += v; }); re = new RegExp('^(' + s.toLowerCase() + ')$', 'i'); each(p[0].split('/'), function(s) { t.childRules = t.childRules || {}; t.childRules[s] = re; }); }); // Build regex s = ''; each(t.childRules, function(v, k) { if (s) s += '|'; s += k; }); t.parentElementsRE = new RegExp('^(' + s.toLowerCase() + ')$', 'i'); /*console.debug(t.parentElementsRE.toString()); each(t.childRules, function(v) { console.debug(v.toString()); });*/ }, /** * Sets the valid elements rules of the serializer this enables you to specify things like what elements should be * outputted and what attributes specific elements might have. * Consult the Wiki for more details on this format. * * @param {String} s Valid elements rules string. */ setRules : function(s) { var t = this; t._setup(); t.rules = {}; t.wildRules = []; t.validElements = {}; return t.addRules(s); }, /** * Adds valid elements rules to the serializer this enables you to specify things like what elements should be * outputted and what attributes specific elements might have. * Consult the Wiki for more details on this format. * * @param {String} s Valid elements rules string to add. */ addRules : function(s) { var t = this, dr; if (!s) return; t._setup(); each(s.split(','), function(s) { var p = s.split(/\[|\]/), tn = p[0].split('/'), ra, at, wat, va = []; // Extend with default rules if (dr) at = tinymce.extend([], dr.attribs); // Parse attributes if (p.length > 1) { each(p[1].split('|'), function(s) { var ar = {}, i; at = at || []; // Parse attribute rule s = s.replace(/::/g, '~'); s = /^([!\-])?([\w*.?~_\-]+|)([=:<])?(.+)?$/.exec(s); s[2] = s[2].replace(/~/g, ':'); // Add required attributes if (s[1] == '!') { ra = ra || []; ra.push(s[2]); } // Remove inherited attributes if (s[1] == '-') { for (i = 0; i ]*>)(.*?)(<\/script>)/g}, {pattern : /(]*>)(.*?)(<\/style>)/g}, {pattern : /(]*>)(.*?)(<\/pre>)/g, encode : 1}, {pattern : /()/g} ] }); h = p.content; // Entity encode if (s.entity_encoding !== 'raw') h = t._encode(h); // Use BR instead of   padded P elements inside editor and use

 

outside editor /* if (o.set) h = h.replace(/

\s+( | |\u00a0|
)\s+<\/p>/g, '


'); else h = h.replace(/

\s+( | |\u00a0|
)\s+<\/p>/g, '

$1

');*/ // Since Gecko and Safari keeps whitespace in the DOM we need to // remove it inorder to match other browsers. But I think Gecko and Safari is right. // This process is only done when getting contents out from the editor. if (!o.set) { // We need to replace paragraph whitespace with an nbsp before indentation to keep the \u00a0 char h = h.replace(/

\s+<\/p>|]+)>\s+<\/p>/g, s.entity_encoding == 'numeric' ? ' 

' : ' 

'); if (s.remove_linebreaks) { h = h.replace(/\r?\n|\r/g, ' '); h = h.replace(/(<[^>]+>)\s+/g, '$1 '); h = h.replace(/\s+(<\/[^>]+>)/g, ' $1'); h = h.replace(/<(p|h[1-6]|blockquote|hr|div|table|tbody|tr|td|body|head|html|title|meta|style|pre|script|link|object) ([^>]+)>\s+/g, '<$1 $2>'); // Trim block start h = h.replace(/<(p|h[1-6]|blockquote|hr|div|table|tbody|tr|td|body|head|html|title|meta|style|pre|script|link|object)>\s+/g, '<$1>'); // Trim block start h = h.replace(/\s+<\/(p|h[1-6]|blockquote|hr|div|table|tbody|tr|td|body|head|html|title|meta|style|pre|script|link|object)>/g, ''); // Trim block end } // Simple indentation if (s.apply_source_formatting && s.indent_mode == 'simple') { // Add line breaks before and after block elements h = h.replace(/<(\/?)(ul|hr|table|meta|link|tbody|tr|object|body|head|html|map)(|[^>]+)>\s*/g, '\n<$1$2$3>\n'); h = h.replace(/\s*<(p|h[1-6]|blockquote|div|title|style|pre|script|td|li|area)(|[^>]+)>/g, '\n<$1$2>'); h = h.replace(/<\/(p|h[1-6]|blockquote|div|title|style|pre|script|td|li)>\s*/g, '\n'); h = h.replace(/\n\n/g, '\n'); } } h = t._unprotect(h, p); // Restore CDATA sections h = h.replace(//g, ''); // Restore the \u00a0 character if raw mode is enabled if (s.entity_encoding == 'raw') h = h.replace(/

 <\/p>|]+)> <\/p>/g, '\u00a0

'); } o.content = h; }, _serializeNode : function(n, inn) { var t = this, s = t.settings, w = t.writer, hc, el, cn, i, l, a, at, no, v, nn, ru, ar, iv; if (!s.node_filter || s.node_filter(n)) { switch (n.nodeType) { case 1: // Element if (n.hasAttribute ? n.hasAttribute('mce_bogus') : n.getAttribute('mce_bogus')) return; iv = false; hc = n.hasChildNodes(); nn = n.getAttribute('mce_name') || n.nodeName.toLowerCase(); // Add correct prefix on IE if (isIE) { if (n.scopeName !== 'HTML' && n.scopeName !== 'html') nn = n.scopeName + ':' + nn; } // Remove mce prefix on IE needed for the abbr element if (nn.indexOf('mce:') === 0) nn = nn.substring(4); // Check if valid if (!t.validElementsRE.test(nn) || (t.invalidElementsRE && t.invalidElementsRE.test(nn)) || inn) { iv = true; break; } if (isIE) { // Fix IE content duplication (DOM can have multiple copies of the same node) if (s.fix_content_duplication) { if (n.mce_serialized == t.key) return; n.mce_serialized = t.key; } // IE sometimes adds a / infront of the node name if (nn.charAt(0) == '/') nn = nn.substring(1); } else if (isGecko) { // Ignore br elements if (n.nodeName === 'BR' && n.getAttribute('type') == '_moz') return; } // Check if valid child if (t.childRules) { if (t.parentElementsRE.test(t.elementName)) { if (!t.childRules[t.elementName].test(nn)) { iv = true; break; } } t.elementName = nn; } ru = t.findRule(nn); nn = ru.name || nn; // Skip empty nodes or empty node name in IE if ((!hc && ru.noEmpty) || (isIE && !nn)) { iv = true; break; } // Check required if (ru.requiredAttribs) { a = ru.requiredAttribs; for (i = a.length - 1; i >= 0; i--) { if (this.dom.getAttrib(n, a[i]) !== '') break; } // None of the required was there if (i == -1) { iv = true; break; } } w.writeStartElement(nn); // Add ordered attributes if (ru.attribs) { for (i=0, at = ru.attribs, l = at.length; i-1; i--) { no = at[i]; if (no.specified) { a = no.nodeName.toLowerCase(); if (s.invalid_attrs.test(a) || !ru.validAttribsRE.test(a)) continue; ar = t.findAttribRule(ru, a); v = t._getAttrib(n, ar, a); if (v !== null) w.writeAttribute(a, v); } } } // Padd empty nodes with a   if (ru.padd) { // If it has only one bogus child, padd it anyway workaround for
bug if (hc && (cn = n.firstChild) && cn.nodeType === 1 && n.childNodes.length === 1) { if (cn.hasAttribute ? cn.hasAttribute('mce_bogus') : cn.getAttribute('mce_bogus')) w.writeText('\u00a0'); } else if (!hc) w.writeText('\u00a0'); // No children then padd it } break; case 3: // Text // Check if valid child if (t.childRules && t.parentElementsRE.test(t.elementName)) { if (!t.childRules[t.elementName].test(n.nodeName)) return; } return w.writeText(n.nodeValue); case 4: // CDATA return w.writeCDATA(n.nodeValue); case 8: // Comment return w.writeComment(n.nodeValue); } } else if (n.nodeType == 1) hc = n.hasChildNodes(); if (hc) { cn = n.firstChild; while (cn) { t._serializeNode(cn); t.elementName = nn; cn = cn.nextSibling; } } // Write element end if (!iv) { if (hc || !s.closed.test(nn)) w.writeFullEndElement(); else w.writeEndElement(); } }, _protect : function(o) { var t = this; o.items = o.items || []; function enc(s) { return s.replace(/[\r\n\\]/g, function(c) { if (c === '\n') return '\\n'; else if (c === '\\') return '\\\\'; return '\\r'; }); }; function dec(s) { return s.replace(/\\[\\rn]/g, function(c) { if (c === '\\n') return '\n'; else if (c === '\\\\') return '\\'; return '\r'; }); }; each(o.patterns, function(p) { o.content = dec(enc(o.content).replace(p.pattern, function(x, a, b, c) { b = dec(b); if (p.encode) b = t._encode(b); o.items.push(b); return a + '' + c; })); }); return o; }, _unprotect : function(h, o) { h = h.replace(/\