只读模式
group, 分享
评论更多问题
博客标签总是存在一个
This commit is contained in:
lealife
2015-06-15 18:01:48 +08:00
parent 7e458bb433
commit 6987a38820
1453 changed files with 114561 additions and 91536 deletions

87
public/tinymce/classes/html/SaxParser.js Normal file → Executable file
View File

@ -8,6 +8,8 @@
* Contributing: http://www.tinymce.com/contributing
*/
/*eslint max-depth:[2, 9] */
/**
* This class parses HTML code using pure JavaScript and executes various events for each item it finds. It will
* always execute the events in the right order for tag soup code like <b><p></b></p>. It will also remove elements
@ -55,6 +57,45 @@ define("tinymce/html/SaxParser", [
], function(Schema, Entities, Tools) {
var each = Tools.each;
/**
* Returns the index of the end tag for a specific start tag. This can be
* used to skip all children of a parent element from being processed.
*
* @private
* @method findEndTag
* @param {tinymce.html.Schema} schema Schema instance to use to match short ended elements.
* @param {String} html HTML string to find the end tag in.
* @param {Number} startIndex Indext to start searching at should be after the start tag.
* @return {Number} Index of the end tag.
*/
function findEndTag(schema, html, startIndex) {
var count = 1, index, matches, tokenRegExp, shortEndedElements;
shortEndedElements = schema.getShortEndedElements();
tokenRegExp = /<([!?\/])?([A-Za-z0-9\-_\:\.]+)((?:\s+[^"\'>]+(?:(?:"[^"]*")|(?:\'[^\']*\')|[^>]*))*|\/|\s+)>/g;
tokenRegExp.lastIndex = index = startIndex;
while ((matches = tokenRegExp.exec(html))) {
index = tokenRegExp.lastIndex;
if (matches[1] === '/') { // End element
count--;
} else if (!matches[1]) { // Start element
if (matches[2] in shortEndedElements) {
continue;
}
count++;
}
if (count === 0) {
break;
}
}
return index;
}
/**
* Constructs a new SaxParser instance.
*
@ -63,8 +104,10 @@ define("tinymce/html/SaxParser", [
* @param {Object} settings Name/value collection of settings. comment, cdata, text, start and end are callbacks.
* @param {tinymce.html.Schema} schema HTML Schema class to use when parsing.
*/
return function(settings, schema) {
var self = this, noop = function() {};
function SaxParser(settings, schema) {
var self = this;
function noop() {}
settings = settings || {};
self.schema = schema = schema || new Schema();
@ -94,7 +137,8 @@ define("tinymce/html/SaxParser", [
var validate, elementRule, isValidElement, attr, attribsValue, validAttributesMap, validAttributePatterns;
var attributesRequired, attributesDefault, attributesForced;
var anyAttributesRequired, selfClosing, tokenRegExp, attrRegExp, specialElements, attrValue, idCount = 0;
var decode = Entities.decode, fixSelfClosing, filteredAttrs = Tools.makeMap('src,href');
var decode = Entities.decode, fixSelfClosing, filteredUrlAttrs = Tools.makeMap('src,href,data,background,formaction,poster');
var scriptUriRegExp = /((java|vb)script|mhtml):/i, dataUriRegExp = /^data:/i;
function processEndTag(name) {
var pos, i;
@ -160,8 +204,23 @@ define("tinymce/html/SaxParser", [
}
}
if (filteredAttrs[name] && !settings.allow_script_urls) {
if (/(java|vb)script:/i.test(decodeURIComponent(value.replace(trimRegExp, '')))) {
// Block any javascript: urls or non image data uris
if (filteredUrlAttrs[name] && !settings.allow_script_urls) {
var uri = value.replace(trimRegExp, '');
try {
// Might throw malformed URI sequence
uri = decodeURIComponent(uri);
} catch (ex) {
// Fallback to non UTF-8 decoder
uri = unescape(uri);
}
if (scriptUriRegExp.test(uri)) {
return;
}
if (!settings.allow_html_data_urls && dataUriRegExp.test(uri) && !/^data:image\//i.test(uri)) {
return;
}
}
@ -181,7 +240,7 @@ define("tinymce/html/SaxParser", [
'(?:!DOCTYPE([\\w\\W]*?)>)|' + // DOCTYPE
'(?:\\?([^\\s\\/<>]+) ?([\\w\\W]*?)[?/]>)|' + // PI
'(?:\\/([^>]+)>)|' + // End element
'(?:([A-Za-z0-9\\-\\:\\.]+)((?:\\s+[^"\'>]+(?:(?:"[^"]*")|(?:\'[^\']*\')|[^>]*))*|\\/|\\s+)>)' + // Start element
'(?:([A-Za-z0-9\\-_\\:\\.]+)((?:\\s+[^"\'>]+(?:(?:"[^"]*")|(?:\'[^\']*\')|[^>]*))*|\\/|\\s+)>)' + // Start element
')', 'g');
attrRegExp = /([\w:\-]+)(?:\s*=\s*(?:(?:\"((?:[^\"])*)\")|(?:\'((?:[^\'])*)\')|([^>\s]+)))?/g;
@ -318,7 +377,13 @@ define("tinymce/html/SaxParser", [
}
// Invalidate element if it's marked as bogus
if (attrList.map['data-mce-bogus']) {
if ((attr = attrList.map['data-mce-bogus'])) {
if (attr === 'all') {
index = findEndTag(schema, html, tokenRegExp.lastIndex);
tokenRegExp.lastIndex = index;
continue;
}
isValidElement = false;
}
}
@ -401,5 +466,9 @@ define("tinymce/html/SaxParser", [
}
}
};
};
});
}
SaxParser.findEndTag = findEndTag;
return SaxParser;
});