loleaflet/.eslintignore | 1 loleaflet/Makefile.am | 5 loleaflet/js/Autolinker.js | 4187 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 4191 insertions(+), 2 deletions(-)
New commits: commit c537bea9389be67479f6347740fcbbe5b8ac4e87 Author: Henry Castro <hcas...@collabora.com> AuthorDate: Thu Feb 20 12:21:44 2020 -0400 Commit: Henry Castro <hcas...@collabora.com> CommitDate: Fri Feb 21 00:49:04 2020 +0100 loleaflet: import Autolinker.js library The file was imported from node_modules/autolinker/dist/Autolinker.js the main reason is to analyze the source code, debug and patch if necessary To get the source code from npm repository make libs Change-Id: I3eea7cc6e8d61623398d77ed74e751ccd861252b Reviewed-on: https://gerrit.libreoffice.org/c/online/+/89150 Tested-by: Jenkins CollaboraOffice <jenkinscollaboraoff...@gmail.com> Reviewed-by: Henry Castro <hcas...@collabora.com> diff --git a/loleaflet/.eslintignore b/loleaflet/.eslintignore index ca03adc2e..64caf1af1 100644 --- a/loleaflet/.eslintignore +++ b/loleaflet/.eslintignore @@ -1,4 +1,5 @@ # We only directly edit toolbar.js in dist/ +**/js/Autolinker.js **/js/json2.js **/js/select2.js **/js/vex.combined.js diff --git a/loleaflet/Makefile.am b/loleaflet/Makefile.am index 413ef7f66..ea6e31621 100644 --- a/loleaflet/Makefile.am +++ b/loleaflet/Makefile.am @@ -72,6 +72,7 @@ define npm_source endef NODE_MODULES_SRC =\ + autolinker@1.4.3 \ json-js@1.1.2 \ select2@4.0.1 \ vex-js@4.1.0 \ @@ -122,10 +123,10 @@ NODE_MODULES_JS =\ node_modules/jquery-mousewheel/jquery.mousewheel.js \ node_modules/jquery-contextmenu/dist/jquery.contextMenu.js \ node_modules/jquery-ui/jquery-ui.js \ - node_modules/smartmenus/dist/jquery.smartmenus.js \ - node_modules/autolinker/dist/Autolinker.js + node_modules/smartmenus/dist/jquery.smartmenus.js LOLEAFLET_LIBS_JS =\ + Autolinker.js \ json2.js \ select2.js \ vex.combined.js \ diff --git a/loleaflet/js/Autolinker.js b/loleaflet/js/Autolinker.js new file mode 100644 index 000000000..d463c331a --- /dev/null +++ b/loleaflet/js/Autolinker.js @@ -0,0 +1,4187 @@ +/*! + * Autolinker.js + * 1.4.3 + * + * Copyright(c) 2017 Gregory Jacobs <g...@greg-jacobs.com> + * MIT License + * + * https://github.com/gregjacobs/Autolinker.js + */ +;(function(root, factory) { + if (typeof define === 'function' && define.amd) { + define([], factory); + } else if (typeof exports === 'object') { + module.exports = factory(); + } else { + root.Autolinker = factory(); + } +}(this, function() { +/** + * @class Autolinker + * @extends Object + * + * Utility class used to process a given string of text, and wrap the matches in + * the appropriate anchor (<a>) tags to turn them into links. + * + * Any of the configuration options may be provided in an Object (map) provided + * to the Autolinker constructor, which will configure how the {@link #link link()} + * method will process the links. + * + * For example: + * + * var autolinker = new Autolinker( { + * newWindow : false, + * truncate : 30 + * } ); + * + * var html = autolinker.link( "Joe went to www.yahoo.com" ); + * // produces: 'Joe went to <a href="http://www.yahoo.com">yahoo.com</a>' + * + * + * The {@link #static-link static link()} method may also be used to inline + * options into a single call, which may be more convenient for one-off uses. + * For example: + * + * var html = Autolinker.link( "Joe went to www.yahoo.com", { + * newWindow : false, + * truncate : 30 + * } ); + * // produces: 'Joe went to <a href="http://www.yahoo.com">yahoo.com</a>' + * + * + * ## Custom Replacements of Links + * + * If the configuration options do not provide enough flexibility, a {@link #replaceFn} + * may be provided to fully customize the output of Autolinker. This function is + * called once for each URL/Email/Phone#/Hashtag/Mention (Twitter, Instagram) + * match that is encountered. + * + * For example: + * + * var input = "..."; // string with URLs, Email Addresses, Phone #s, Hashtags, and Mentions (Twitter, Instagram) + * + * var linkedText = Autolinker.link( input, { + * replaceFn : function( match ) { + * console.log( "href = ", match.getAnchorHref() ); + * console.log( "text = ", match.getAnchorText() ); + * + * switch( match.getType() ) { + * case 'url' : + * console.log( "url: ", match.getUrl() ); + * + * if( match.getUrl().indexOf( 'mysite.com' ) === -1 ) { + * var tag = match.buildTag(); // returns an `Autolinker.HtmlTag` instance, which provides mutator methods for easy changes + * tag.setAttr( 'rel', 'nofollow' ); + * tag.addClass( 'external-link' ); + * + * return tag; + * + * } else { + * return true; // let Autolinker perform its normal anchor tag replacement + * } + * + * case 'email' : + * var email = match.getEmail(); + * console.log( "email: ", email ); + * + * if( email === "my@own.address" ) { + * return false; // don't auto-link this particular email address; leave as-is + * } else { + * return; // no return value will have Autolinker perform its normal anchor tag replacement (same as returning `true`) + * } + * + * case 'phone' : + * var phoneNumber = match.getPhoneNumber(); + * console.log( phoneNumber ); + * + * return '<a href="http://newplace.to.link.phone.numbers.to/">' + phoneNumber + '</a>'; + * + * case 'hashtag' : + * var hashtag = match.getHashtag(); + * console.log( hashtag ); + * + * return '<a href="http://newplace.to.link.hashtag.handles.to/">' + hashtag + '</a>'; + * + * case 'mention' : + * var mention = match.getMention(); + * console.log( mention ); + * + * return '<a href="http://newplace.to.link.mention.to/">' + mention + '</a>'; + * } + * } + * } ); + * + * + * The function may return the following values: + * + * - `true` (Boolean): Allow Autolinker to replace the match as it normally + * would. + * - `false` (Boolean): Do not replace the current match at all - leave as-is. + * - Any String: If a string is returned from the function, the string will be + * used directly as the replacement HTML for the match. + * - An {@link Autolinker.HtmlTag} instance, which can be used to build/modify + * an HTML tag before writing out its HTML text. + * + * @constructor + * @param {Object} [cfg] The configuration options for the Autolinker instance, + * specified in an Object (map). + */ +var Autolinker = function( cfg ) { + cfg = cfg || {}; + + this.version = Autolinker.version; + + this.urls = this.normalizeUrlsCfg( cfg.urls ); + this.email = typeof cfg.email === 'boolean' ? cfg.email : true; + this.phone = typeof cfg.phone === 'boolean' ? cfg.phone : true; + this.hashtag = cfg.hashtag || false; + this.mention = cfg.mention || false; + this.newWindow = typeof cfg.newWindow === 'boolean' ? cfg.newWindow : true; + this.stripPrefix = this.normalizeStripPrefixCfg( cfg.stripPrefix ); + this.stripTrailingSlash = typeof cfg.stripTrailingSlash === 'boolean' ? cfg.stripTrailingSlash : true; + + // Validate the value of the `mention` cfg + var mention = this.mention; + if( mention !== false && mention !== 'twitter' && mention !== 'instagram' ) { + throw new Error( "invalid `mention` cfg - see docs" ); + } + + // Validate the value of the `hashtag` cfg + var hashtag = this.hashtag; + if( hashtag !== false && hashtag !== 'twitter' && hashtag !== 'facebook' && hashtag !== 'instagram' ) { + throw new Error( "invalid `hashtag` cfg - see docs" ); + } + + this.truncate = this.normalizeTruncateCfg( cfg.truncate ); + this.className = cfg.className || ''; + this.replaceFn = cfg.replaceFn || null; + this.context = cfg.context || this; + + this.htmlParser = null; + this.matchers = null; + this.tagBuilder = null; +}; + + + +/** + * Automatically links URLs, Email addresses, Phone Numbers, Twitter handles, + * Hashtags, and Mentions found in the given chunk of HTML. Does not link URLs + * found within HTML tags. + * + * For instance, if given the text: `You should go to http://www.yahoo.com`, + * then the result will be `You should go to <a href="http://www.yahoo.com">http://www.yahoo.com</a>` + * + * Example: + * + * var linkedText = Autolinker.link( "Go to google.com", { newWindow: false } ); + * // Produces: "Go to <a href="http://google.com">google.com</a>" + * + * @static + * @param {String} textOrHtml The HTML or text to find matches within (depending + * on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #mention}, + * {@link #hashtag}, and {@link #mention} options are enabled). + * @param {Object} [options] Any of the configuration options for the Autolinker + * class, specified in an Object (map). See the class description for an + * example call. + * @return {String} The HTML text, with matches automatically linked. + */ +Autolinker.link = function( textOrHtml, options ) { + var autolinker = new Autolinker( options ); + return autolinker.link( textOrHtml ); +}; + + + +/** + * Parses the input `textOrHtml` looking for URLs, email addresses, phone + * numbers, username handles, and hashtags (depending on the configuration + * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match} + * objects describing those matches (without making any replacements). + * + * Note that if parsing multiple pieces of text, it is slightly more efficient + * to create an Autolinker instance, and use the instance-level {@link #parse} + * method. + * + * Example: + * + * var matches = Autolinker.parse( "Hello google.com, I am a...@asdf.com", { + * urls: true, + * email: true + * } ); + * + * console.log( matches.length ); // 2 + * console.log( matches[ 0 ].getType() ); // 'url' + * console.log( matches[ 0 ].getUrl() ); // 'google.com' + * console.log( matches[ 1 ].getType() ); // 'email' + * console.log( matches[ 1 ].getEmail() ); // 'a...@asdf.com' + * + * @static + * @param {String} textOrHtml The HTML or text to find matches within + * (depending on if the {@link #urls}, {@link #email}, {@link #phone}, + * {@link #hashtag}, and {@link #mention} options are enabled). + * @param {Object} [options] Any of the configuration options for the Autolinker + * class, specified in an Object (map). See the class description for an + * example call. + * @return {Autolinker.match.Match[]} The array of Matches found in the + * given input `textOrHtml`. + */ +Autolinker.parse = function( textOrHtml, options ) { + var autolinker = new Autolinker( options ); + return autolinker.parse( textOrHtml ); +}; + + +/** + * @static + * @property {String} version (readonly) + * + * The Autolinker version number in the form major.minor.patch + * + * Ex: 0.25.1 + */ +Autolinker.version = '1.4.3'; + + +Autolinker.prototype = { + constructor : Autolinker, // fix constructor property + + /** + * @cfg {Boolean/Object} [urls] + * + * `true` if URLs should be automatically linked, `false` if they should not + * be. Defaults to `true`. + * + * Examples: + * + * urls: true + * + * // or + * + * urls: { + * schemeMatches : true, + * wwwMatches : true, + * tldMatches : true + * } + * + * As shown above, this option also accepts an Object form with 3 properties + * to allow for more customization of what exactly gets linked. All default + * to `true`: + * + * @cfg {Boolean} [urls.schemeMatches] `true` to match URLs found prefixed + * with a scheme, i.e. `http://google.com`, or `other+scheme://google.com`, + * `false` to prevent these types of matches. + * @cfg {Boolean} [urls.wwwMatches] `true` to match urls found prefixed with + * `'www.'`, i.e. `www.google.com`. `false` to prevent these types of + * matches. Note that if the URL had a prefixed scheme, and + * `schemeMatches` is true, it will still be linked. + * @cfg {Boolean} [urls.tldMatches] `true` to match URLs with known top + * level domains (.com, .net, etc.) that are not prefixed with a scheme or + * `'www.'`. This option attempts to match anything that looks like a URL + * in the given text. Ex: `google.com`, `asdf.org/?page=1`, etc. `false` + * to prevent these types of matches. + */ + + /** + * @cfg {Boolean} [email=true] + * + * `true` if email addresses should be automatically linked, `false` if they + * should not be. + */ + + /** + * @cfg {Boolean} [phone=true] + * + * `true` if Phone numbers ("(555)555-5555") should be automatically linked, + * `false` if they should not be. + */ + + /** + * @cfg {Boolean/String} [hashtag=false] + * + * A string for the service name to have hashtags (ex: "#myHashtag") + * auto-linked to. The currently-supported values are: + * + * - 'twitter' + * - 'facebook' + * - 'instagram' + * + * Pass `false` to skip auto-linking of hashtags. + */ + + /** + * @cfg {String/Boolean} [mention=false] + * + * A string for the service name to have mentions (ex: "@myuser") + * auto-linked to. The currently supported values are: + * + * - 'twitter' + * - 'instagram' + * + * Defaults to `false` to skip auto-linking of mentions. + */ + + /** + * @cfg {Boolean} [newWindow=true] + * + * `true` if the links should open in a new window, `false` otherwise. + */ + + /** + * @cfg {Boolean/Object} [stripPrefix] + * + * `true` if 'http://' (or 'https://') and/or the 'www.' should be stripped + * from the beginning of URL links' text, `false` otherwise. Defaults to + * `true`. + * + * Examples: + * + * stripPrefix: true + * + * // or + * + * stripPrefix: { + * scheme : true, + * www : true + * } + * + * As shown above, this option also accepts an Object form with 2 properties + * to allow for more customization of what exactly is prevented from being + * displayed. Both default to `true`: + * + * @cfg {Boolean} [stripPrefix.scheme] `true` to prevent the scheme part of + * a URL match from being displayed to the user. Example: + * `'http://google.com'` will be displayed as `'google.com'`. `false` to + * not strip the scheme. NOTE: Only an `'http://'` or `'https://'` scheme + * will be removed, so as not to remove a potentially dangerous scheme + * (such as `'file://'` or `'javascript:'`) + * @cfg {Boolean} [stripPrefix.www] www (Boolean): `true` to prevent the + * `'www.'` part of a URL match from being displayed to the user. Ex: + * `'www.google.com'` will be displayed as `'google.com'`. `false` to not + * strip the `'www'`. + */ + + /** + * @cfg {Boolean} [stripTrailingSlash=true] + * + * `true` to remove the trailing slash from URL matches, `false` to keep + * the trailing slash. + * + * Example when `true`: `http://google.com/` will be displayed as + * `http://google.com`. + */ + + /** + * @cfg {Number/Object} [truncate=0] + * + * ## Number Form + * + * A number for how many characters matched text should be truncated to + * inside the text of a link. If the matched text is over this number of + * characters, it will be truncated to this length by adding a two period + * ellipsis ('..') to the end of the string. + * + * For example: A url like 'http://www.yahoo.com/some/long/path/to/a/file' + * truncated to 25 characters might look something like this: + * 'yahoo.com/some/long/pat..' + * + * Example Usage: + * + * truncate: 25 + * + * + * Defaults to `0` for "no truncation." + * + * + * ## Object Form + * + * An Object may also be provided with two properties: `length` (Number) and + * `location` (String). `location` may be one of the following: 'end' + * (default), 'middle', or 'smart'. + * + * Example Usage: + * + * truncate: { length: 25, location: 'middle' } + * + * @cfg {Number} [truncate.length=0] How many characters to allow before + * truncation will occur. Defaults to `0` for "no truncation." + * @cfg {"end"/"middle"/"smart"} [truncate.location="end"] + * + * - 'end' (default): will truncate up to the number of characters, and then + * add an ellipsis at the end. Ex: 'yahoo.com/some/long/pat..' + * - 'middle': will truncate and add the ellipsis in the middle. Ex: + * 'yahoo.com/s..th/to/a/file' + * - 'smart': for URLs where the algorithm attempts to strip out unnecessary + * parts first (such as the 'www.', then URL scheme, hash, etc.), + * attempting to make the URL human-readable before looking for a good + * point to insert the ellipsis if it is still too long. Ex: + * 'yahoo.com/some..to/a/file'. For more details, see + * {@link Autolinker.truncate.TruncateSmart}. + */ + + /** + * @cfg {String} className + * + * A CSS class name to add to the generated links. This class will be added + * to all links, as well as this class plus match suffixes for styling + * url/email/phone/hashtag/mention links differently. + * + * For example, if this config is provided as "myLink", then: + * + * - URL links will have the CSS classes: "myLink myLink-url" + * - Email links will have the CSS classes: "myLink myLink-email", and + * - Phone links will have the CSS classes: "myLink myLink-phone" + * - Hashtag links will have the CSS classes: "myLink myLink-hashtag" + * - Mention links will have the CSS classes: "myLink myLink-mention myLink-[type]" + * where [type] is either "instagram" or "twitter" + */ + + /** + * @cfg {Function} replaceFn + * + * A function to individually process each match found in the input string. + * + * See the class's description for usage. + * + * The `replaceFn` can be called with a different context object (`this` + * reference) using the {@link #context} cfg. + * + * This function is called with the following parameter: + * + * @cfg {Autolinker.match.Match} replaceFn.match The Match instance which + * can be used to retrieve information about the match that the `replaceFn` + * is currently processing. See {@link Autolinker.match.Match} subclasses + * for details. + */ + + /** + * @cfg {Object} context + * + * The context object (`this` reference) to call the `replaceFn` with. + * + * Defaults to this Autolinker instance. + */ + + + /** + * @property {String} version (readonly) + * + * The Autolinker version number in the form major.minor.patch + * + * Ex: 0.25.1 + */ + + /** + * @private + * @property {Autolinker.htmlParser.HtmlParser} htmlParser + * + * The HtmlParser instance used to skip over HTML tags, while finding text + * nodes to process. This is lazily instantiated in the {@link #getHtmlParser} + * method. + */ + + /** + * @private + * @property {Autolinker.matcher.Matcher[]} matchers + * + * The {@link Autolinker.matcher.Matcher} instances for this Autolinker + * instance. + * + * This is lazily created in {@link #getMatchers}. + */ + + /** + * @private + * @property {Autolinker.AnchorTagBuilder} tagBuilder + * + * The AnchorTagBuilder instance used to build match replacement anchor tags. + * Note: this is lazily instantiated in the {@link #getTagBuilder} method. + */ + + + /** + * Normalizes the {@link #urls} config into an Object with 3 properties: + * `schemeMatches`, `wwwMatches`, and `tldMatches`, all Booleans. + * + * See {@link #urls} config for details. + * + * @private + * @param {Boolean/Object} urls + * @return {Object} + */ + normalizeUrlsCfg : function( urls ) { + if( urls == null ) urls = true; // default to `true` + + if( typeof urls === 'boolean' ) { + return { schemeMatches: urls, wwwMatches: urls, tldMatches: urls }; + + } else { // object form + return { + schemeMatches : typeof urls.schemeMatches === 'boolean' ? urls.schemeMatches : true, + wwwMatches : typeof urls.wwwMatches === 'boolean' ? urls.wwwMatches : true, + tldMatches : typeof urls.tldMatches === 'boolean' ? urls.tldMatches : true + }; + } + }, + + + /** + * Normalizes the {@link #stripPrefix} config into an Object with 2 + * properties: `scheme`, and `www` - both Booleans. + * + * See {@link #stripPrefix} config for details. + * + * @private + * @param {Boolean/Object} stripPrefix + * @return {Object} + */ + normalizeStripPrefixCfg : function( stripPrefix ) { + if( stripPrefix == null ) stripPrefix = true; // default to `true` + + if( typeof stripPrefix === 'boolean' ) { + return { scheme: stripPrefix, www: stripPrefix }; + + } else { // object form + return { + scheme : typeof stripPrefix.scheme === 'boolean' ? stripPrefix.scheme : true, + www : typeof stripPrefix.www === 'boolean' ? stripPrefix.www : true + }; + } + }, + + + /** + * Normalizes the {@link #truncate} config into an Object with 2 properties: + * `length` (Number), and `location` (String). + * + * See {@link #truncate} config for details. + * + * @private + * @param {Number/Object} truncate + * @return {Object} + */ + normalizeTruncateCfg : function( truncate ) { + if( typeof truncate === 'number' ) { + return { length: truncate, location: 'end' }; + + } else { // object, or undefined/null + return Autolinker.Util.defaults( truncate || {}, { + length : Number.POSITIVE_INFINITY, + location : 'end' + } ); + } + }, + + + /** + * Parses the input `textOrHtml` looking for URLs, email addresses, phone + * numbers, username handles, and hashtags (depending on the configuration + * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match} + * objects describing those matches (without making any replacements). + * + * This method is used by the {@link #link} method, but can also be used to + * simply do parsing of the input in order to discover what kinds of links + * there are and how many. + * + * Example usage: + * + * var autolinker = new Autolinker( { + * urls: true, + * email: true + * } ); + * + * var matches = autolinker.parse( "Hello google.com, I am a...@asdf.com" ); + * + * console.log( matches.length ); // 2 + * console.log( matches[ 0 ].getType() ); // 'url' + * console.log( matches[ 0 ].getUrl() ); // 'google.com' + * console.log( matches[ 1 ].getType() ); // 'email' + * console.log( matches[ 1 ].getEmail() ); // 'a...@asdf.com' + * + * @param {String} textOrHtml The HTML or text to find matches within + * (depending on if the {@link #urls}, {@link #email}, {@link #phone}, + * {@link #hashtag}, and {@link #mention} options are enabled). + * @return {Autolinker.match.Match[]} The array of Matches found in the + * given input `textOrHtml`. + */ + parse : function( textOrHtml ) { + var htmlParser = this.getHtmlParser(), + htmlNodes = htmlParser.parse( textOrHtml ), + anchorTagStackCount = 0, // used to only process text around anchor tags, and any inner text/html they may have; + matches = []; + + // Find all matches within the `textOrHtml` (but not matches that are + // already nested within <a> tags) + for( var i = 0, len = htmlNodes.length; i < len; i++ ) { + var node = htmlNodes[ i ], + nodeType = node.getType(); + + if( nodeType === 'element' && node.getTagName() === 'a' ) { // Process HTML anchor element nodes in the input `textOrHtml` to find out when we're within an <a> tag + if( !node.isClosing() ) { // it's the start <a> tag + anchorTagStackCount++; + } else { // it's the end </a> tag + anchorTagStackCount = Math.max( anchorTagStackCount - 1, 0 ); // attempt to handle extraneous </a> tags by making sure the stack count never goes below 0 + } + + } else if( nodeType === 'text' && anchorTagStackCount === 0 ) { // Process text nodes that are not within an <a> tag + var textNodeMatches = this.parseText( node.getText(), node.getOffset() ); + + matches.push.apply( matches, textNodeMatches ); + } + } + + + // After we have found all matches, remove subsequent matches that + // overlap with a previous match. This can happen for instance with URLs, + // where the url 'google.com/#link' would match '#link' as a hashtag. + matches = this.compactMatches( matches ); + + // And finally, remove matches for match types that have been turned + // off. We needed to have all match types turned on initially so that + // things like hashtags could be filtered out if they were really just + // part of a URL match (for instance, as a named anchor). + matches = this.removeUnwantedMatches( matches ); + + return matches; + }, + + + /** + * After we have found all matches, we need to remove subsequent matches + * that overlap with a previous match. This can happen for instance with + * URLs, where the url 'google.com/#link' would match '#link' as a hashtag. + * + * @private + * @param {Autolinker.match.Match[]} matches + * @return {Autolinker.match.Match[]} + */ + compactMatches : function( matches ) { + // First, the matches need to be sorted in order of offset + matches.sort( function( a, b ) { return a.getOffset() - b.getOffset(); } ); + + for( var i = 0; i < matches.length - 1; i++ ) { + var match = matches[ i ], + offset = match.getOffset(), + matchedTextLength = match.getMatchedText().length, + endIdx = offset + matchedTextLength; + + if( i + 1 < matches.length ) { + // Remove subsequent matches that equal offset with current match + if( matches[ i + 1 ].getOffset() === offset ) { + var removeIdx = matches[ i + 1 ].getMatchedText().length > matchedTextLength ? i : i + 1; + matches.splice( removeIdx, 1 ); + continue; + } + + // Remove subsequent matches that overlap with the current match + if( matches[ i + 1 ].getOffset() <= endIdx ) { + matches.splice( i + 1, 1 ); + } + } + } + + return matches; + }, + + + /** + * Removes matches for matchers that were turned off in the options. For + * example, if {@link #hashtag hashtags} were not to be matched, we'll + * remove them from the `matches` array here. + * + * @private + * @param {Autolinker.match.Match[]} matches The array of matches to remove + * the unwanted matches from. Note: this array is mutated for the + * removals. + * @return {Autolinker.match.Match[]} The mutated input `matches` array. + */ + removeUnwantedMatches : function( matches ) { + var remove = Autolinker.Util.remove; + + if( !this.hashtag ) remove( matches, function( match ) { return match.getType() === 'hashtag'; } ); + if( !this.email ) remove( matches, function( match ) { return match.getType() === 'email'; } ); + if( !this.phone ) remove( matches, function( match ) { return match.getType() === 'phone'; } ); + if( !this.mention ) remove( matches, function( match ) { return match.getType() === 'mention'; } ); + if( !this.urls.schemeMatches ) { + remove( matches, function( m ) { return m.getType() === 'url' && m.getUrlMatchType() === 'scheme'; } ); + } + if( !this.urls.wwwMatches ) { + remove( matches, function( m ) { return m.getType() === 'url' && m.getUrlMatchType() === 'www'; } ); + } + if( !this.urls.tldMatches ) { + remove( matches, function( m ) { return m.getType() === 'url' && m.getUrlMatchType() === 'tld'; } ); + } + + return matches; + }, + + + /** + * Parses the input `text` looking for URLs, email addresses, phone + * numbers, username handles, and hashtags (depending on the configuration + * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match} + * objects describing those matches. + * + * This method processes a **non-HTML string**, and is used to parse and + * match within the text nodes of an HTML string. This method is used + * internally by {@link #parse}. + * + * @private + * @param {String} text The text to find matches within (depending on if the + * {@link #urls}, {@link #email}, {@link #phone}, + * {@link #hashtag}, and {@link #mention} options are enabled). This must be a non-HTML string. + * @param {Number} [offset=0] The offset of the text node within the + * original string. This is used when parsing with the {@link #parse} + * method to generate correct offsets within the {@link Autolinker.match.Match} + * instances, but may be omitted if calling this method publicly. + * @return {Autolinker.match.Match[]} The array of Matches found in the + * given input `text`. + */ + parseText : function( text, offset ) { + offset = offset || 0; + var matchers = this.getMatchers(), + matches = []; + + for( var i = 0, numMatchers = matchers.length; i < numMatchers; i++ ) { + var textMatches = matchers[ i ].parseMatches( text ); + + // Correct the offset of each of the matches. They are originally + // the offset of the match within the provided text node, but we + // need to correct them to be relative to the original HTML input + // string (i.e. the one provided to #parse). + for( var j = 0, numTextMatches = textMatches.length; j < numTextMatches; j++ ) { + textMatches[ j ].setOffset( offset + textMatches[ j ].getOffset() ); + } + + matches.push.apply( matches, textMatches ); + } + return matches; + }, + + + /** + * Automatically links URLs, Email addresses, Phone numbers, Hashtags, + * and Mentions (Twitter, Instagram) found in the given chunk of HTML. Does not link + * URLs found within HTML tags. + * + * For instance, if given the text: `You should go to http://www.yahoo.com`, + * then the result will be `You should go to + * <a href="http://www.yahoo.com">http://www.yahoo.com</a>` + * + * This method finds the text around any HTML elements in the input + * `textOrHtml`, which will be the text that is processed. Any original HTML + * elements will be left as-is, as well as the text that is already wrapped + * in anchor (<a>) tags. + * + * @param {String} textOrHtml The HTML or text to autolink matches within + * (depending on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #hashtag}, and {@link #mention} options are enabled). + * @return {String} The HTML, with matches automatically linked. + */ + link : function( textOrHtml ) { + if( !textOrHtml ) { return ""; } // handle `null` and `undefined` + + var matches = this.parse( textOrHtml ), + newHtml = [], + lastIndex = 0; + + for( var i = 0, len = matches.length; i < len; i++ ) { + var match = matches[ i ]; + + newHtml.push( textOrHtml.substring( lastIndex, match.getOffset() ) ); + newHtml.push( this.createMatchReturnVal( match ) ); + + lastIndex = match.getOffset() + match.getMatchedText().length; + } + newHtml.push( textOrHtml.substring( lastIndex ) ); // handle the text after the last match + + return newHtml.join( '' ); + }, + + + /** + * Creates the return string value for a given match in the input string. + * + * This method handles the {@link #replaceFn}, if one was provided. + * + * @private + * @param {Autolinker.match.Match} match The Match object that represents + * the match. + * @return {String} The string that the `match` should be replaced with. + * This is usually the anchor tag string, but may be the `matchStr` itself + * if the match is not to be replaced. + */ + createMatchReturnVal : function( match ) { + // Handle a custom `replaceFn` being provided + var replaceFnResult; + if( this.replaceFn ) { + replaceFnResult = this.replaceFn.call( this.context, match ); // Autolinker instance is the context + } + + if( typeof replaceFnResult === 'string' ) { + return replaceFnResult; // `replaceFn` returned a string, use that + + } else if( replaceFnResult === false ) { + return match.getMatchedText(); // no replacement for the match + + } else if( replaceFnResult instanceof Autolinker.HtmlTag ) { + return replaceFnResult.toAnchorString(); + + } else { // replaceFnResult === true, or no/unknown return value from function + // Perform Autolinker's default anchor tag generation + var anchorTag = match.buildTag(); // returns an Autolinker.HtmlTag instance + + return anchorTag.toAnchorString(); + } + }, + + + /** + * Lazily instantiates and returns the {@link #htmlParser} instance for this + * Autolinker instance. + * + * @protected + * @return {Autolinker.htmlParser.HtmlParser} + */ + getHtmlParser : function() { + var htmlParser = this.htmlParser; + + if( !htmlParser ) { + htmlParser = this.htmlParser = new Autolinker.htmlParser.HtmlParser(); + } + + return htmlParser; + }, + + + /** + * Lazily instantiates and returns the {@link Autolinker.matcher.Matcher} + * instances for this Autolinker instance. + * + * @protected + * @return {Autolinker.matcher.Matcher[]} + */ + getMatchers : function() { + if( !this.matchers ) { + var matchersNs = Autolinker.matcher, + tagBuilder = this.getTagBuilder(); + + var matchers = [ + new matchersNs.Hashtag( { tagBuilder: tagBuilder, serviceName: this.hashtag } ), + new matchersNs.Email( { tagBuilder: tagBuilder } ), + new matchersNs.Phone( { tagBuilder: tagBuilder } ), + new matchersNs.Mention( { tagBuilder: tagBuilder, serviceName: this.mention } ), + new matchersNs.Url( { tagBuilder: tagBuilder, stripPrefix: this.stripPrefix, stripTrailingSlash: this.stripTrailingSlash } ) + ]; + + return ( this.matchers = matchers ); + + } else { + return this.matchers; + } + }, + + + /** + * Returns the {@link #tagBuilder} instance for this Autolinker instance, lazily instantiating it + * if it does not yet exist. + * + * This method may be used in a {@link #replaceFn} to generate the {@link Autolinker.HtmlTag HtmlTag} instance that + * Autolinker would normally generate, and then allow for modifications before returning it. For example: + * + * var html = Autolinker.link( "Test google.com", { + * replaceFn : function( match ) { + * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance + * tag.setAttr( 'rel', 'nofollow' ); + * + * return tag; + * } + * } ); + * + * // generated html: + * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a> + * + * @return {Autolinker.AnchorTagBuilder} + */ + getTagBuilder : function() { + var tagBuilder = this.tagBuilder; + + if( !tagBuilder ) { + tagBuilder = this.tagBuilder = new Autolinker.AnchorTagBuilder( { + newWindow : this.newWindow, + truncate : this.truncate, + className : this.className + } ); + } + + return tagBuilder; + } + +}; + + +// Autolinker Namespaces + +Autolinker.match = {}; +Autolinker.matcher = {}; +Autolinker.htmlParser = {}; +Autolinker.truncate = {}; + +/*global Autolinker */ +/*jshint eqnull:true, boss:true */ +/** + * @class Autolinker.Util + * @singleton + * + * A few utility methods for Autolinker. + */ +Autolinker.Util = { + + /** + * @property {Function} abstractMethod + * + * A function object which represents an abstract method. + */ + abstractMethod : function() { throw "abstract"; }, + + + /** + * @private + * @property {RegExp} trimRegex + * + * The regular expression used to trim the leading and trailing whitespace + * from a string. + */ + trimRegex : /^[\s\uFEFF\xA0]+|[\s\uFEFF\xA0]+$/g, + + + /** + * Assigns (shallow copies) the properties of `src` onto `dest`. + * + * @param {Object} dest The destination object. + * @param {Object} src The source object. + * @return {Object} The destination object (`dest`) + */ + assign : function( dest, src ) { + for( var prop in src ) { + if( src.hasOwnProperty( prop ) ) { + dest[ prop ] = src[ prop ]; + } + } + + return dest; + }, + + + /** + * Assigns (shallow copies) the properties of `src` onto `dest`, if the + * corresponding property on `dest` === `undefined`. + * + * @param {Object} dest The destination object. + * @param {Object} src The source object. + * @return {Object} The destination object (`dest`) + */ + defaults : function( dest, src ) { + for( var prop in src ) { + if( src.hasOwnProperty( prop ) && dest[ prop ] === undefined ) { + dest[ prop ] = src[ prop ]; + } + } + + return dest; + }, + + + /** + * Extends `superclass` to create a new subclass, adding the `protoProps` to the new subclass's prototype. + * + * @param {Function} superclass The constructor function for the superclass. + * @param {Object} protoProps The methods/properties to add to the subclass's prototype. This may contain the + * special property `constructor`, which will be used as the new subclass's constructor function. + * @return {Function} The new subclass function. + */ + extend : function( superclass, protoProps ) { + var superclassProto = superclass.prototype; + + var F = function() {}; + F.prototype = superclassProto; + + var subclass; + if( protoProps.hasOwnProperty( 'constructor' ) ) { + subclass = protoProps.constructor; + } else { + subclass = function() { superclassProto.constructor.apply( this, arguments ); }; + } + + var subclassProto = subclass.prototype = new F(); // set up prototype chain + subclassProto.constructor = subclass; // fix constructor property + subclassProto.superclass = superclassProto; + + delete protoProps.constructor; // don't re-assign constructor property to the prototype, since a new function may have been created (`subclass`), which is now already there + Autolinker.Util.assign( subclassProto, protoProps ); + + return subclass; + }, + + + /** + * Truncates the `str` at `len - ellipsisChars.length`, and adds the `ellipsisChars` to the + * end of the string (by default, two periods: '..'). If the `str` length does not exceed + * `len`, the string will be returned unchanged. + * + * @param {String} str The string to truncate and add an ellipsis to. + * @param {Number} truncateLen The length to truncate the string at. + * @param {String} [ellipsisChars=...] The ellipsis character(s) to add to the end of `str` + * when truncated. Defaults to '...' + */ + ellipsis : function( str, truncateLen, ellipsisChars ) { + var ellipsisLength; + + if( str.length > truncateLen ) { + if(ellipsisChars == null) { + ellipsisChars = '…'; + ellipsisLength = 3; + } else { + ellipsisLength = ellipsisChars.length; + } + + str = str.substring( 0, truncateLen - ellipsisLength ) + ellipsisChars; + } + return str; + }, + + + /** + * Supports `Array.prototype.indexOf()` functionality for old IE (IE8 and below). + * + * @param {Array} arr The array to find an element of. + * @param {*} element The element to find in the array, and return the index of. + * @return {Number} The index of the `element`, or -1 if it was not found. + */ + indexOf : function( arr, element ) { + if( Array.prototype.indexOf ) { + return arr.indexOf( element ); + + } else { + for( var i = 0, len = arr.length; i < len; i++ ) { + if( arr[ i ] === element ) return i; + } + return -1; + } + }, + + + /** + * Removes array elements based on a filtering function. Mutates the input + * array. + * + * Using this instead of the ES5 Array.prototype.filter() function, to allow + * Autolinker compatibility with IE8, and also to prevent creating many new + * arrays in memory for filtering. + * + * @param {Array} arr The array to remove elements from. This array is + * mutated. + * @param {Function} fn A function which should return `true` to + * remove an element. + * @return {Array} The mutated input `arr`. + */ + remove : function( arr, fn ) { + for( var i = arr.length - 1; i >= 0; i-- ) { + if( fn( arr[ i ] ) === true ) { + arr.splice( i, 1 ); + } + } + }, + + + /** + * Performs the functionality of what modern browsers do when `String.prototype.split()` is called + * with a regular expression that contains capturing parenthesis. + * + * For example: + * + * // Modern browsers: + * "a,b,c".split( /(,)/ ); // --> [ 'a', ',', 'b', ',', 'c' ] + * + * // Old IE (including IE8): + * "a,b,c".split( /(,)/ ); // --> [ 'a', 'b', 'c' ] + * + * This method emulates the functionality of modern browsers for the old IE case. + * + * @param {String} str The string to split. + * @param {RegExp} splitRegex The regular expression to split the input `str` on. The splitting + * character(s) will be spliced into the array, as in the "modern browsers" example in the + * description of this method. + * Note #1: the supplied regular expression **must** have the 'g' flag specified. + * Note #2: for simplicity's sake, the regular expression does not need + * to contain capturing parenthesis - it will be assumed that any match has them. + * @return {String[]} The split array of strings, with the splitting character(s) included. + */ + splitAndCapture : function( str, splitRegex ) { + if( !splitRegex.global ) throw new Error( "`splitRegex` must have the 'g' flag set" ); + + var result = [], + lastIdx = 0, + match; + + while( match = splitRegex.exec( str ) ) { + result.push( str.substring( lastIdx, match.index ) ); + result.push( match[ 0 ] ); // push the splitting char(s) + + lastIdx = match.index + match[ 0 ].length; + } + result.push( str.substring( lastIdx ) ); + + return result; + }, + + + /** + * Trims the leading and trailing whitespace from a string. + * + * @param {String} str The string to trim. + * @return {String} + */ + trim : function( str ) { + return str.replace( this.trimRegex, '' ); + } + +}; + +/*global Autolinker */ +/*jshint boss:true */ +/** + * @class Autolinker.HtmlTag + * @extends Object + * + * Represents an HTML tag, which can be used to easily build/modify HTML tags programmatically. + * + * Autolinker uses this abstraction to create HTML tags, and then write them out as strings. You may also use + * this class in your code, especially within a {@link Autolinker#replaceFn replaceFn}. + * + * ## Examples + * + * Example instantiation: + * + * var tag = new Autolinker.HtmlTag( { + * tagName : 'a', + * attrs : { 'href': 'http://google.com', 'class': 'external-link' }, + * innerHtml : 'Google' + * } ); + * + * tag.toAnchorString(); // <a href="http://google.com" class="external-link">Google</a> + * + * // Individual accessor methods + * tag.getTagName(); // 'a' + * tag.getAttr( 'href' ); // 'http://google.com' + * tag.hasClass( 'external-link' ); // true + * + * + * Using mutator methods (which may be used in combination with instantiation config properties): + * + * var tag = new Autolinker.HtmlTag(); + * tag.setTagName( 'a' ); + * tag.setAttr( 'href', 'http://google.com' ); + * tag.addClass( 'external-link' ); + * tag.setInnerHtml( 'Google' ); + * + * tag.getTagName(); // 'a' + * tag.getAttr( 'href' ); // 'http://google.com' + * tag.hasClass( 'external-link' ); // true + * + * tag.toAnchorString(); // <a href="http://google.com" class="external-link">Google</a> + * + * + * ## Example use within a {@link Autolinker#replaceFn replaceFn} + * + * var html = Autolinker.link( "Test google.com", { + * replaceFn : function( match ) { + * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance, configured with the Match's href and anchor text + * tag.setAttr( 'rel', 'nofollow' ); + * + * return tag; + * } + * } ); + * + * // generated html: + * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a> + * + * + * ## Example use with a new tag for the replacement + * + * var html = Autolinker.link( "Test google.com", { + * replaceFn : function( match ) { + * var tag = new Autolinker.HtmlTag( { + * tagName : 'button', + * attrs : { 'title': 'Load URL: ' + match.getAnchorHref() }, + * innerHtml : 'Load URL: ' + match.getAnchorText() + * } ); + * + * return tag; + * } + * } ); + * + * // generated html: + * // Test <button title="Load URL: http://google.com">Load URL: google.com</button> + */ +Autolinker.HtmlTag = Autolinker.Util.extend( Object, { + + /** + * @cfg {String} tagName + * + * The tag name. Ex: 'a', 'button', etc. + * + * Not required at instantiation time, but should be set using {@link #setTagName} before {@link #toAnchorString} + * is executed. + */ + + /** + * @cfg {Object.<String, String>} attrs + * + * An key/value Object (map) of attributes to create the tag with. The keys are the attribute names, and the + * values are the attribute values. + */ + + /** + * @cfg {String} innerHtml + * + * The inner HTML for the tag. + * + * Note the camel case name on `innerHtml`. Acronyms are camelCased in this utility (such as not to run into the acronym + * naming inconsistency that the DOM developers created with `XMLHttpRequest`). You may alternatively use {@link #innerHTML} + * if you prefer, but this one is recommended. + */ + + /** + * @cfg {String} innerHTML + * + * Alias of {@link #innerHtml}, accepted for consistency with the browser DOM api, but prefer the camelCased version + * for acronym names. + */ + + + /** + * @protected + * @property {RegExp} whitespaceRegex + * + * Regular expression used to match whitespace in a string of CSS classes. + */ + whitespaceRegex : /\s+/, + + + /** + * @constructor + * @param {Object} [cfg] The configuration properties for this class, in an Object (map) + */ + constructor : function( cfg ) { + Autolinker.Util.assign( this, cfg ); + + this.innerHtml = this.innerHtml || this.innerHTML; // accept either the camelCased form or the fully capitalized acronym + }, + + + /** + * Sets the tag name that will be used to generate the tag with. + * + * @param {String} tagName + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + setTagName : function( tagName ) { + this.tagName = tagName; + return this; + }, + + + /** + * Retrieves the tag name. + * + * @return {String} + */ + getTagName : function() { + return this.tagName || ""; + }, + + + /** + * Sets an attribute on the HtmlTag. + * + * @param {String} attrName The attribute name to set. + * @param {String} attrValue The attribute value to set. + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + setAttr : function( attrName, attrValue ) { + var tagAttrs = this.getAttrs(); + tagAttrs[ attrName ] = attrValue; + + return this; + }, + + + /** + * Retrieves an attribute from the HtmlTag. If the attribute does not exist, returns `undefined`. + * + * @param {String} attrName The attribute name to retrieve. + * @return {String} The attribute's value, or `undefined` if it does not exist on the HtmlTag. + */ + getAttr : function( attrName ) { + return this.getAttrs()[ attrName ]; + }, + + + /** + * Sets one or more attributes on the HtmlTag. + * + * @param {Object.<String, String>} attrs A key/value Object (map) of the attributes to set. + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + setAttrs : function( attrs ) { + var tagAttrs = this.getAttrs(); + Autolinker.Util.assign( tagAttrs, attrs ); + + return this; + }, + + + /** + * Retrieves the attributes Object (map) for the HtmlTag. + * + * @return {Object.<String, String>} A key/value object of the attributes for the HtmlTag. + */ + getAttrs : function() { + return this.attrs || ( this.attrs = {} ); + }, + + + /** + * Sets the provided `cssClass`, overwriting any current CSS classes on the HtmlTag. + * + * @param {String} cssClass One or more space-separated CSS classes to set (overwrite). + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + setClass : function( cssClass ) { + return this.setAttr( 'class', cssClass ); + }, + + + /** + * Convenience method to add one or more CSS classes to the HtmlTag. Will not add duplicate CSS classes. + * + * @param {String} cssClass One or more space-separated CSS classes to add. + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + addClass : function( cssClass ) { + var classAttr = this.getClass(), + whitespaceRegex = this.whitespaceRegex, + indexOf = Autolinker.Util.indexOf, // to support IE8 and below + classes = ( !classAttr ) ? [] : classAttr.split( whitespaceRegex ), + newClasses = cssClass.split( whitespaceRegex ), + newClass; + + while( newClass = newClasses.shift() ) { + if( indexOf( classes, newClass ) === -1 ) { + classes.push( newClass ); + } + } + + this.getAttrs()[ 'class' ] = classes.join( " " ); + return this; + }, + + + /** + * Convenience method to remove one or more CSS classes from the HtmlTag. + * + * @param {String} cssClass One or more space-separated CSS classes to remove. + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + removeClass : function( cssClass ) { + var classAttr = this.getClass(), + whitespaceRegex = this.whitespaceRegex, + indexOf = Autolinker.Util.indexOf, // to support IE8 and below + classes = ( !classAttr ) ? [] : classAttr.split( whitespaceRegex ), + removeClasses = cssClass.split( whitespaceRegex ), + removeClass; + + while( classes.length && ( removeClass = removeClasses.shift() ) ) { + var idx = indexOf( classes, removeClass ); + if( idx !== -1 ) { + classes.splice( idx, 1 ); + } + } + + this.getAttrs()[ 'class' ] = classes.join( " " ); + return this; + }, + + + /** + * Convenience method to retrieve the CSS class(es) for the HtmlTag, which will each be separated by spaces when + * there are multiple. + * + * @return {String} + */ + getClass : function() { + return this.getAttrs()[ 'class' ] || ""; + }, + + + /** + * Convenience method to check if the tag has a CSS class or not. + * + * @param {String} cssClass The CSS class to check for. + * @return {Boolean} `true` if the HtmlTag has the CSS class, `false` otherwise. + */ + hasClass : function( cssClass ) { + return ( ' ' + this.getClass() + ' ' ).indexOf( ' ' + cssClass + ' ' ) !== -1; + }, + + + /** + * Sets the inner HTML for the tag. + * + * @param {String} html The inner HTML to set. + * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained. + */ + setInnerHtml : function( html ) { + this.innerHtml = html; + + return this; + }, + + + /** + * Retrieves the inner HTML for the tag. + * + * @return {String} + */ + getInnerHtml : function() { + return this.innerHtml || ""; + }, + + + /** + * Override of superclass method used to generate the HTML string for the tag. + * + * @return {String} + */ + toAnchorString : function() { + var tagName = this.getTagName(), + attrsStr = this.buildAttrsStr(); + + attrsStr = ( attrsStr ) ? ' ' + attrsStr : ''; // prepend a space if there are actually attributes + + return [ '<', tagName, attrsStr, '>', this.getInnerHtml(), '</', tagName, '>' ].join( "" ); + }, + + + /** + * Support method for {@link #toAnchorString}, returns the string space-separated key="value" pairs, used to populate + * the stringified HtmlTag. + * + * @protected + * @return {String} Example return: `attr1="value1" attr2="value2"` + */ + buildAttrsStr : function() { + if( !this.attrs ) return ""; // no `attrs` Object (map) has been set, return empty string + + var attrs = this.getAttrs(), + attrsArr = []; + + for( var prop in attrs ) { + if( attrs.hasOwnProperty( prop ) ) { + attrsArr.push( prop + '="' + attrs[ prop ] + '"' ); + } + } + return attrsArr.join( " " ); + } + +} ); + +/*global Autolinker */ +/** + * @class Autolinker.RegexLib + * @singleton + * + * Builds and stores a library of the common regular expressions used by the + * Autolinker utility. + * + * Other regular expressions may exist ad-hoc, but these are generally the + * regular expressions that are shared between source files. + */ +Autolinker.RegexLib = (function() { + + /** + * The string form of a regular expression that would match all of the + * alphabetic ("letter") chars in the unicode character set when placed in a + * RegExp character class (`[]`). This includes all international alphabetic + * characters. + * + * These would be the characters matched by unicode regex engines `\p{L}` + * escape ("all letters"). + * + * Taken from the XRegExp library: http://xregexp.com/ + * Specifically: http://xregexp.com/v/3.0.0/unicode-categories.js + * + * @private + * @type {String} + */ + var alphaCharsStr = 'A-Za-z\\xAA\\xB5\\xBA\\xC0-\\xD6\\xD8-\\xF6\\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u052F\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0-\u08B4\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0AF9\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D \u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C39\u0C3D\u0C58-\u0C5A\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D5F-\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\ u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F5\u13F8-\u13FD\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16F1-\u16F8\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2 D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FD5\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA7AD\uA7B0-\uA7B7\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA8FD\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uA9E0-\uA9E4\uA9E6-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA7E-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB65\uAB70-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\u FB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC'; + + /** + * The string form of a regular expression that would match all of the + * decimal number chars in the unicode character set when placed in a RegExp + * character class (`[]`). + * + * These would be the characters matched by unicode regex engines `\p{Nd}` + * escape ("all decimal numbers") + * + * Taken from the XRegExp library: http://xregexp.com/ + * Specifically: http://xregexp.com/v/3.0.0/unicode-categories.js + * + * @private + * @type {String} + */ + var decimalNumbersStr = '0-9\u0660-\u0669\u06F0-\u06F9\u07C0-\u07C9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE6-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0DE6-\u0DEF\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u1040-\u1049\u1090-\u1099\u17E0-\u17E9\u1810-\u1819\u1946-\u194F\u19D0-\u19D9\u1A80-\u1A89\u1A90-\u1A99\u1B50-\u1B59\u1BB0-\u1BB9\u1C40-\u1C49\u1C50-\u1C59\uA620-\uA629\uA8D0-\uA8D9\uA900-\uA909\uA9D0-\uA9D9\uA9F0-\uA9F9\uAA50-\uAA59\uABF0-\uABF9\uFF10-\uFF19'; + + + // See documentation below + var alphaNumericCharsStr = alphaCharsStr + decimalNumbersStr; + + + // See documentation below + var domainNameRegex = new RegExp( '[' + alphaNumericCharsStr + '.\\-]*[' + alphaNumericCharsStr + '\\-]' ); + + return { + + /** + * The string form of a regular expression that would match all of the + * letters and decimal number chars in the unicode character set when placed + * in a RegExp character class (`[]`). + * + * These would be the characters matched by unicode regex engines `[\p{L}\p{Nd}]` + * escape ("all letters and decimal numbers") + * + * @property {String} alphaNumericCharsStr + */ + alphaNumericCharsStr : alphaNumericCharsStr, + + /** + * The string form of a regular expression that would match all of the + * letters and in the unicode character set when placed + * in a RegExp character class (`[]`). + * + * These would be the characters matched by unicode regex engines `[\p{L}]` + * escape ("all letters") + * + * @property {String} alphaCharsStr + */ + alphaCharsStr : alphaCharsStr, + + /** + * A regular expression to match domain names of a URL or email address. + * Ex: 'google', 'yahoo', 'some-other-company', etc. + * + * @property {RegExp} domainNameRegex + */ + domainNameRegex : domainNameRegex, + + }; + + +}() ); + +/*global Autolinker */ +/*jshint sub:true */ +/** + * @protected + * @class Autolinker.AnchorTagBuilder + * @extends Object + * + * Builds anchor (<a>) tags for the Autolinker utility when a match is + * found. + * + * Normally this class is instantiated, configured, and used internally by an + * {@link Autolinker} instance, but may actually be used indirectly in a + * {@link Autolinker#replaceFn replaceFn} to create {@link Autolinker.HtmlTag HtmlTag} + * instances which may be modified before returning from the + * {@link Autolinker#replaceFn replaceFn}. For example: + * + * var html = Autolinker.link( "Test google.com", { + * replaceFn : function( match ) { + * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance + * tag.setAttr( 'rel', 'nofollow' ); + * + * return tag; + * } + * } ); + * + * // generated html: + * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a> + */ +Autolinker.AnchorTagBuilder = Autolinker.Util.extend( Object, { + + /** + * @cfg {Boolean} newWindow + * @inheritdoc Autolinker#newWindow + */ + + /** + * @cfg {Object} truncate + * @inheritdoc Autolinker#truncate + */ + + /** + * @cfg {String} className + * @inheritdoc Autolinker#className + */ + + + /** + * @constructor + * @param {Object} [cfg] The configuration options for the AnchorTagBuilder instance, specified in an Object (map). + */ + constructor : function( cfg ) { + cfg = cfg || {}; + + this.newWindow = cfg.newWindow; + this.truncate = cfg.truncate; + this.className = cfg.className; + }, + + + /** + * Generates the actual anchor (<a>) tag to use in place of the + * matched text, via its `match` object. + * + * @param {Autolinker.match.Match} match The Match instance to generate an + * anchor tag from. + * @return {Autolinker.HtmlTag} The HtmlTag instance for the anchor tag. + */ + build : function( match ) { + return new Autolinker.HtmlTag( { + tagName : 'a', + attrs : this.createAttrs( match ), + innerHtml : this.processAnchorText( match.getAnchorText() ) + } ); + }, + + + /** + * Creates the Object (map) of the HTML attributes for the anchor (<a>) + * tag being generated. + * + * @protected + * @param {Autolinker.match.Match} match The Match instance to generate an + * anchor tag from. + * @return {Object} A key/value Object (map) of the anchor tag's attributes. + */ + createAttrs : function( match ) { + var attrs = { + 'href' : match.getAnchorHref() // we'll always have the `href` attribute + }; + + var cssClass = this.createCssClass( match ); + if( cssClass ) { + attrs[ 'class' ] = cssClass; + } + if( this.newWindow ) { + attrs[ 'target' ] = "_blank"; + attrs[ 'rel' ] = "noopener noreferrer"; + } + + if( this.truncate ) { + if( this.truncate.length && this.truncate.length < match.getAnchorText().length ) { + attrs[ 'title' ] = match.getAnchorHref(); + } + } + + return attrs; + }, + + + /** + * Creates the CSS class that will be used for a given anchor tag, based on + * the `matchType` and the {@link #className} config. + * + * Example returns: + * + * - "" // no {@link #className} + * - "myLink myLink-url" // url match + * - "myLink myLink-email" // email match + * - "myLink myLink-phone" // phone match + * - "myLink myLink-hashtag" // hashtag match + * - "myLink myLink-mention myLink-twitter" // mention match with Twitter service + * + * @private + * @param {Autolinker.match.Match} match The Match instance to generate an + * anchor tag from. + * @return {String} The CSS class string for the link. Example return: + * "myLink myLink-url". If no {@link #className} was configured, returns + * an empty string. + */ + createCssClass : function( match ) { + var className = this.className; + + if( !className ) { + return ""; + + } else { + var returnClasses = [ className ], + cssClassSuffixes = match.getCssClassSuffixes(); + + for( var i = 0, len = cssClassSuffixes.length; i < len; i++ ) { + returnClasses.push( className + '-' + cssClassSuffixes[ i ] ); + } + return returnClasses.join( ' ' ); + } + }, + + + /** + * Processes the `anchorText` by truncating the text according to the + * {@link #truncate} config. + * + * @private + * @param {String} anchorText The anchor tag's text (i.e. what will be + * displayed). + * @return {String} The processed `anchorText`. + */ + processAnchorText : function( anchorText ) { + anchorText = this.doTruncate( anchorText ); + + return anchorText; + }, + + + /** + * Performs the truncation of the `anchorText` based on the {@link #truncate} + * option. If the `anchorText` is longer than the length specified by the + * {@link #truncate} option, the truncation is performed based on the + * `location` property. See {@link #truncate} for details. + * + * @private + * @param {String} anchorText The anchor tag's text (i.e. what will be + * displayed). + * @return {String} The truncated anchor text. + */ + doTruncate : function( anchorText ) { + var truncate = this.truncate; + if( !truncate || !truncate.length ) return anchorText; + + var truncateLength = truncate.length, + truncateLocation = truncate.location; + + if( truncateLocation === 'smart' ) { + return Autolinker.truncate.TruncateSmart( anchorText, truncateLength ); + + } else if( truncateLocation === 'middle' ) { + return Autolinker.truncate.TruncateMiddle( anchorText, truncateLength ); + + } else { + return Autolinker.truncate.TruncateEnd( anchorText, truncateLength ); + } + } + +} ); + +/*global Autolinker */ +/** + * @class Autolinker.htmlParser.HtmlParser + * @extends Object + * + * An HTML parser implementation which simply walks an HTML string and returns an array of + * {@link Autolinker.htmlParser.HtmlNode HtmlNodes} that represent the basic HTML structure of the input string. + * + * Autolinker uses this to only link URLs/emails/mentions within text nodes, effectively ignoring / "walking + * around" HTML tags. + */ +Autolinker.htmlParser.HtmlParser = Autolinker.Util.extend( Object, { + + /** + * @private + * @property {RegExp} htmlRegex + * + * The regular expression used to pull out HTML tags from a string. Handles namespaced HTML tags and + * attribute names, as specified by http://www.w3.org/TR/html-markup/syntax.html. + * + * Capturing groups: + * + * 1. The "!DOCTYPE" tag name, if a tag is a <!DOCTYPE> tag. + * 2. If it is an end tag, this group will have the '/'. + * 3. If it is a comment tag, this group will hold the comment text (i.e. + * the text inside the `<!--` and `-->`. + * 4. The tag name for a tag without attributes (other than the <!DOCTYPE> tag) + * 5. The tag name for a tag with attributes (other than the <!DOCTYPE> tag) + */ + htmlRegex : (function() { + var commentTagRegex = /!--([\s\S]+?)--/, + tagNameRegex = /[0-9a-zA-Z][0-9a-zA-Z:]*/, + attrNameRegex = /[^\s"'>\/=\x00-\x1F\x7F]+/, // the unicode range accounts for excluding control chars, and the delete char + attrValueRegex = /(?:"[^"]*?"|'[^']*?'|[^'"=<>`\s]+)/, // double quoted, single quoted, or unquoted attribute values + nameEqualsValueRegex = attrNameRegex.source + '(?:\\s*=\\s*' + attrValueRegex.source + ')?'; // optional '=[value]' + + return new RegExp( [ + // for <!DOCTYPE> tag. Ex: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">) + '(?:', + '<(!DOCTYPE)', // *** Capturing Group 1 - If it's a doctype tag + + // Zero or more attributes following the tag name + '(?:', + '\\s+', // one or more whitespace chars before an attribute + + // Either: + // A. attr="value", or + // B. "value" alone (To cover example doctype tag: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">) + '(?:', nameEqualsValueRegex, '|', attrValueRegex.source + ')', + ')*', + '>', + ')', + + '|', + + // All other HTML tags (i.e. tags that are not <!DOCTYPE>) + '(?:', + '<(/)?', // Beginning of a tag or comment. Either '<' for a start tag, or '</' for an end tag. + // *** Capturing Group 2: The slash or an empty string. Slash ('/') for end tag, empty string for start or self-closing tag. + + '(?:', + commentTagRegex.source, // *** Capturing Group 3 - A Comment Tag's Text + + '|', + + // Handle tag without attributes. + // Doing this separately from a tag that has attributes + // to fix a regex time complexity issue seen with the + // example in https://github.com/gregjacobs/Autolinker.js/issues/172 + '(?:', + // *** Capturing Group 4 - The tag name for a tag without attributes + '(' + tagNameRegex.source + ')', + + '\\s*/?', // any trailing spaces and optional '/' before the closing '>' + ')', + + '|', + + // Handle tag with attributes + // Doing this separately from a tag with no attributes + // to fix a regex time complexity issue seen with the + // example in https://github.com/gregjacobs/Autolinker.js/issues/172 + '(?:', + // *** Capturing Group 5 - The tag name for a tag with attributes + '(' + tagNameRegex.source + ')', + + '\\s+', // must have at least one space after the tag name to prevent ReDoS issue (issue #172) + + // Zero or more attributes following the tag name + '(?:', + '(?:\\s+|\\b)', // any number of whitespace chars before an attribute. NOTE: Using \s* here throws Chrome into an infinite loop for some reason, so using \s+|\b instead + nameEqualsValueRegex, // attr="value" (with optional ="value" part) + ')*', + + '\\s*/?', // any trailing spaces and optional '/' before the closing '>' + ')', + ')', + '>', + ')' + ].join( "" ), 'gi' ); + } )(), + + /** + * @private + * @property {RegExp} htmlCharacterEntitiesRegex + * + * The regular expression that matches common HTML character entities. + * + * Ignoring & as it could be part of a query string -- handling it separately. + */ + htmlCharacterEntitiesRegex: /( | |<|<|>|>|"|"|')/gi, + + + /** + * Parses an HTML string and returns a simple array of {@link Autolinker.htmlParser.HtmlNode HtmlNodes} + * to represent the HTML structure of the input string. + * + * @param {String} html The HTML to parse. + * @return {Autolinker.htmlParser.HtmlNode[]} + */ + parse : function( html ) { + var htmlRegex = this.htmlRegex, + currentResult, + lastIndex = 0, + textAndEntityNodes, + nodes = []; // will be the result of the method + + while( ( currentResult = htmlRegex.exec( html ) ) !== null ) { + var tagText = currentResult[ 0 ], + commentText = currentResult[ 3 ], // if we've matched a comment + tagName = currentResult[ 1 ] || currentResult[ 4 ] || currentResult[ 5 ], // The <!DOCTYPE> tag (ex: "!DOCTYPE"), or another tag (ex: "a" or "img") + isClosingTag = !!currentResult[ 2 ], + offset = currentResult.index, + inBetweenTagsText = html.substring( lastIndex, offset ); + + // Push TextNodes and EntityNodes for any text found between tags + if( inBetweenTagsText ) { + textAndEntityNodes = this.parseTextAndEntityNodes( lastIndex, inBetweenTagsText ); + nodes.push.apply( nodes, textAndEntityNodes ); + } + + // Push the CommentNode or ElementNode + if( commentText ) { + nodes.push( this.createCommentNode( offset, tagText, commentText ) ); + } else { + nodes.push( this.createElementNode( offset, tagText, tagName, isClosingTag ) ); + } + + lastIndex = offset + tagText.length; + } + + // Process any remaining text after the last HTML element. Will process all of the text if there were no HTML elements. + if( lastIndex < html.length ) { + var text = html.substring( lastIndex ); + + // Push TextNodes and EntityNodes for any text found between tags + if( text ) { + textAndEntityNodes = this.parseTextAndEntityNodes( lastIndex, text ); + + // Note: the following 3 lines were previously: + // nodes.push.apply( nodes, textAndEntityNodes ); + // but this was causing a "Maximum Call Stack Size Exceeded" + // error on inputs with a large number of html entities. + textAndEntityNodes.forEach( function( node ) { + nodes.push( node ); + } ); + } + } + + return nodes; + }, + + + /** + * Parses text and HTML entity nodes from a given string. The input string + * should not have any HTML tags (elements) within it. + * + * @private + * @param {Number} offset The offset of the text node match within the + * original HTML string. + * @param {String} text The string of text to parse. This is from an HTML + * text node. + * @return {Autolinker.htmlParser.HtmlNode[]} An array of HtmlNodes to + * represent the {@link Autolinker.htmlParser.TextNode TextNodes} and + * {@link Autolinker.htmlParser.EntityNode EntityNodes} found. + */ + parseTextAndEntityNodes : function( offset, text ) { + var nodes = [], + textAndEntityTokens = Autolinker.Util.splitAndCapture( text, this.htmlCharacterEntitiesRegex ); // split at HTML entities, but include the HTML entities in the results array + + // Every even numbered token is a TextNode, and every odd numbered token is an EntityNode + // For example: an input `text` of "Test "this" today" would turn into the + // `textAndEntityTokens`: [ 'Test ', '"', 'this', '"', ' today' ] + for( var i = 0, len = textAndEntityTokens.length; i < len; i += 2 ) { + var textToken = textAndEntityTokens[ i ], + entityToken = textAndEntityTokens[ i + 1 ]; + + if( textToken ) { + nodes.push( this.createTextNode( offset, textToken ) ); + offset += textToken.length; + } + if( entityToken ) { + nodes.push( this.createEntityNode( offset, entityToken ) ); + offset += entityToken.length; + } + } + return nodes; + }, + + + /** + * Factory method to create an {@link Autolinker.htmlParser.CommentNode CommentNode}. + * + * @private + * @param {Number} offset The offset of the match within the original HTML + * string. + * @param {String} tagText The full text of the tag (comment) that was + * matched, including its <!-- and -->. + * @param {String} commentText The full text of the comment that was matched. + */ + createCommentNode : function( offset, tagText, commentText ) { + return new Autolinker.htmlParser.CommentNode( { + offset : offset, + text : tagText, + comment: Autolinker.Util.trim( commentText ) + } ); + }, + + + /** + * Factory method to create an {@link Autolinker.htmlParser.ElementNode ElementNode}. + * + * @private + * @param {Number} offset The offset of the match within the original HTML + * string. + * @param {String} tagText The full text of the tag (element) that was + * matched, including its attributes. + * @param {String} tagName The name of the tag. Ex: An <img> tag would + * be passed to this method as "img". + * @param {Boolean} isClosingTag `true` if it's a closing tag, false + * otherwise. + * @return {Autolinker.htmlParser.ElementNode} + */ + createElementNode : function( offset, tagText, tagName, isClosingTag ) { + return new Autolinker.htmlParser.ElementNode( { + offset : offset, + text : tagText, + tagName : tagName.toLowerCase(), + closing : isClosingTag + } ); + }, + + + /** + * Factory method to create a {@link Autolinker.htmlParser.EntityNode EntityNode}. + * + * @private + * @param {Number} offset The offset of the match within the original HTML + * string. + * @param {String} text The text that was matched for the HTML entity (such + * as '&nbsp;'). + * @return {Autolinker.htmlParser.EntityNode} + */ + createEntityNode : function( offset, text ) { + return new Autolinker.htmlParser.EntityNode( { offset: offset, text: text } ); + }, + + + /** + * Factory method to create a {@link Autolinker.htmlParser.TextNode TextNode}. + * + * @private + * @param {Number} offset The offset of the match within the original HTML + * string. + * @param {String} text The text that was matched. + * @return {Autolinker.htmlParser.TextNode} + */ + createTextNode : function( offset, text ) { + return new Autolinker.htmlParser.TextNode( { offset: offset, text: text } ); + } + +} ); + +/*global Autolinker */ +/** + * @abstract + * @class Autolinker.htmlParser.HtmlNode + * + * Represents an HTML node found in an input string. An HTML node is one of the + * following: + * + * 1. An {@link Autolinker.htmlParser.ElementNode ElementNode}, which represents + * HTML tags. + * 2. A {@link Autolinker.htmlParser.CommentNode CommentNode}, which represents + * HTML comments. + * 3. A {@link Autolinker.htmlParser.TextNode TextNode}, which represents text + * outside or within HTML tags. + * 4. A {@link Autolinker.htmlParser.EntityNode EntityNode}, which represents + * one of the known HTML entities that Autolinker looks for. This includes + * common ones such as &quot; and &nbsp; + */ +Autolinker.htmlParser.HtmlNode = Autolinker.Util.extend( Object, { + + /** + * @cfg {Number} offset (required) + * + * The offset of the HTML node in the original text that was parsed. + */ + offset : undefined, + + /** + * @cfg {String} text (required) + * + * The text that was matched for the HtmlNode. + * + * - In the case of an {@link Autolinker.htmlParser.ElementNode ElementNode}, + * this will be the tag's text. + * - In the case of an {@link Autolinker.htmlParser.CommentNode CommentNode}, + * this will be the comment's text. + * - In the case of a {@link Autolinker.htmlParser.TextNode TextNode}, this + * will be the text itself. + * - In the case of a {@link Autolinker.htmlParser.EntityNode EntityNode}, + * this will be the text of the HTML entity. + */ + text : undefined, + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match instance, + * specified in an Object (map). + */ + constructor : function( cfg ) { + Autolinker.Util.assign( this, cfg ); + + if( this.offset == null ) throw new Error( '`offset` cfg required' ); + if( this.text == null ) throw new Error( '`text` cfg required' ); + }, + + + /** + * Returns a string name for the type of node that this class represents. + * + * @abstract + * @return {String} + */ + getType : Autolinker.Util.abstractMethod, + + + /** + * Retrieves the {@link #offset} of the HtmlNode. This is the offset of the + * HTML node in the original string that was parsed. + * + * @return {Number} + */ + getOffset : function() { + return this.offset; + }, + + + /** + * Retrieves the {@link #text} for the HtmlNode. + * + * @return {String} + */ + getText : function() { + return this.text; + } + +} ); +/*global Autolinker */ +/** + * @class Autolinker.htmlParser.CommentNode + * @extends Autolinker.htmlParser.HtmlNode + * + * Represents an HTML comment node that has been parsed by the + * {@link Autolinker.htmlParser.HtmlParser}. + * + * See this class's superclass ({@link Autolinker.htmlParser.HtmlNode}) for more + * details. + */ +Autolinker.htmlParser.CommentNode = Autolinker.Util.extend( Autolinker.htmlParser.HtmlNode, { + + /** + * @cfg {String} comment (required) + * + * The text inside the comment tag. This text is stripped of any leading or + * trailing whitespace. + */ + comment : '', + + + /** + * Returns a string name for the type of node that this class represents. + * + * @return {String} + */ + getType : function() { + return 'comment'; + }, + + + /** + * Returns the comment inside the comment tag. + * + * @return {String} + */ + getComment : function() { + return this.comment; + } + +} ); +/*global Autolinker */ +/** + * @class Autolinker.htmlParser.ElementNode + * @extends Autolinker.htmlParser.HtmlNode + * + * Represents an HTML element node that has been parsed by the {@link Autolinker.htmlParser.HtmlParser}. + * + * See this class's superclass ({@link Autolinker.htmlParser.HtmlNode}) for more + * details. + */ +Autolinker.htmlParser.ElementNode = Autolinker.Util.extend( Autolinker.htmlParser.HtmlNode, { + + /** + * @cfg {String} tagName (required) + * + * The name of the tag that was matched. + */ + tagName : '', + + /** + * @cfg {Boolean} closing (required) + * + * `true` if the element (tag) is a closing tag, `false` if its an opening + * tag. + */ + closing : false, + + + /** + * Returns a string name for the type of node that this class represents. + * + * @return {String} + */ + getType : function() { + return 'element'; + }, + + + /** + * Returns the HTML element's (tag's) name. Ex: for an <img> tag, + * returns "img". + * + * @return {String} + */ + getTagName : function() { + return this.tagName; + }, + + + /** + * Determines if the HTML element (tag) is a closing tag. Ex: <div> + * returns `false`, while </div> returns `true`. + * + * @return {Boolean} + */ + isClosing : function() { + return this.closing; + } + +} ); +/*global Autolinker */ +/** + * @class Autolinker.htmlParser.EntityNode + * @extends Autolinker.htmlParser.HtmlNode + * + * Represents a known HTML entity node that has been parsed by the {@link Autolinker.htmlParser.HtmlParser}. + * Ex: '&nbsp;', or '&#160;' (which will be retrievable from the {@link #getText} + * method. + * + * Note that this class will only be returned from the HtmlParser for the set of + * checked HTML entity nodes defined by the {@link Autolinker.htmlParser.HtmlParser#htmlCharacterEntitiesRegex}. + * + * See this class's superclass ({@link Autolinker.htmlParser.HtmlNode}) for more + * details. + */ +Autolinker.htmlParser.EntityNode = Autolinker.Util.extend( Autolinker.htmlParser.HtmlNode, { + + /** + * Returns a string name for the type of node that this class represents. + * + * @return {String} + */ + getType : function() { + return 'entity'; + } + +} ); +/*global Autolinker */ +/** + * @class Autolinker.htmlParser.TextNode + * @extends Autolinker.htmlParser.HtmlNode + * + * Represents a text node that has been parsed by the {@link Autolinker.htmlParser.HtmlParser}. + * + * See this class's superclass ({@link Autolinker.htmlParser.HtmlNode}) for more + * details. + */ +Autolinker.htmlParser.TextNode = Autolinker.Util.extend( Autolinker.htmlParser.HtmlNode, { + + /** + * Returns a string name for the type of node that this class represents. + * + * @return {String} + */ + getType : function() { + return 'text'; + } + +} ); +/*global Autolinker */ +/** + * @abstract + * @class Autolinker.match.Match + * + * Represents a match found in an input string which should be Autolinked. A Match object is what is provided in a + * {@link Autolinker#replaceFn replaceFn}, and may be used to query for details about the match. + * + * For example: + * + * var input = "..."; // string with URLs, Email Addresses, and Mentions (Twitter, Instagram) + * + * var linkedText = Autolinker.link( input, { + * replaceFn : function( match ) { + * console.log( "href = ", match.getAnchorHref() ); + * console.log( "text = ", match.getAnchorText() ); + * + * switch( match.getType() ) { + * case 'url' : + * console.log( "url: ", match.getUrl() ); + * + * case 'email' : + * console.log( "email: ", match.getEmail() ); + * + * case 'mention' : + * console.log( "mention: ", match.getMention() ); + * } + * } + * } ); + * + * See the {@link Autolinker} class for more details on using the {@link Autolinker#replaceFn replaceFn}. + */ +Autolinker.match.Match = Autolinker.Util.extend( Object, { + + /** + * @cfg {Autolinker.AnchorTagBuilder} tagBuilder (required) + * + * Reference to the AnchorTagBuilder instance to use to generate an anchor + * tag for the Match. + */ + + /** + * @cfg {String} matchedText (required) + * + * The original text that was matched by the {@link Autolinker.matcher.Matcher}. + */ + + /** + * @cfg {Number} offset (required) + * + * The offset of where the match was made in the input string. + */ + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match + * instance, specified in an Object (map). + */ + constructor : function( cfg ) { + if( cfg.tagBuilder == null ) throw new Error( '`tagBuilder` cfg required' ); + if( cfg.matchedText == null ) throw new Error( '`matchedText` cfg required' ); + if( cfg.offset == null ) throw new Error( '`offset` cfg required' ); + + this.tagBuilder = cfg.tagBuilder; + this.matchedText = cfg.matchedText; + this.offset = cfg.offset; + }, + + + /** + * Returns a string name for the type of match that this class represents. + * + * @abstract + * @return {String} + */ + getType : Autolinker.Util.abstractMethod, + + + /** + * Returns the original text that was matched. + * + * @return {String} + */ + getMatchedText : function() { + return this.matchedText; + }, + + + /** + * Sets the {@link #offset} of where the match was made in the input string. + * + * A {@link Autolinker.matcher.Matcher} will be fed only HTML text nodes, + * and will therefore set an original offset that is relative to the HTML + * text node itself. However, we want this offset to be relative to the full + * HTML input string, and thus if using {@link Autolinker#parse} (rather + * than calling a {@link Autolinker.matcher.Matcher} directly), then this + * offset is corrected after the Matcher itself has done its job. + * + * @param {Number} offset + */ + setOffset : function( offset ) { + this.offset = offset; + }, + + + /** + * Returns the offset of where the match was made in the input string. This + * is the 0-based index of the match. + * + * @return {Number} + */ + getOffset : function() { + return this.offset; + }, + + + /** + * Returns the anchor href that should be generated for the match. + * + * @abstract + * @return {String} + */ + getAnchorHref : Autolinker.Util.abstractMethod, + + + /** + * Returns the anchor text that should be generated for the match. + * + * @abstract + * @return {String} + */ + getAnchorText : Autolinker.Util.abstractMethod, + + + /** + * Returns the CSS class suffix(es) for this match. + * + * A CSS class suffix is appended to the {@link Autolinker#className} in + * the {@link Autolinker.AnchorTagBuilder} when a match is translated into + * an anchor tag. + * + * For example, if {@link Autolinker#className} was configured as 'myLink', + * and this method returns `[ 'url' ]`, the final class name of the element + * will become: 'myLink myLink-url'. + * + * The match may provide multiple CSS class suffixes to be appended to the + * {@link Autolinker#className} in order to facilitate better styling + * options for different match criteria. See {@link Autolinker.match.Mention} + * for an example. + * + * By default, this method returns a single array with the match's + * {@link #getType type} name, but may be overridden by subclasses. + * + * @return {String[]} + */ + getCssClassSuffixes : function() { + return [ this.getType() ]; + }, + + + /** + * Builds and returns an {@link Autolinker.HtmlTag} instance based on the + * Match. + * + * This can be used to easily generate anchor tags from matches, and either + * return their HTML string, or modify them before doing so. + * + * Example Usage: + * + * var tag = match.buildTag(); + * tag.addClass( 'cordova-link' ); + * tag.setAttr( 'target', '_system' ); + * + * tag.toAnchorString(); // <a href="http://google.com" class="cordova-link" target="_system">Google</a> + */ + buildTag : function() { + return this.tagBuilder.build( this ); + } + +} ); + +/*global Autolinker */ +/** + * @class Autolinker.match.Email + * @extends Autolinker.match.Match + * + * Represents a Email match found in an input string which should be Autolinked. + * + * See this class's superclass ({@link Autolinker.match.Match}) for more details. + */ +Autolinker.match.Email = Autolinker.Util.extend( Autolinker.match.Match, { + + /** + * @cfg {String} email (required) + * + * The email address that was matched. + */ + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match + * instance, specified in an Object (map). + */ + constructor : function( cfg ) { + Autolinker.match.Match.prototype.constructor.call( this, cfg ); + + if( !cfg.email ) throw new Error( '`email` cfg required' ); + + this.email = cfg.email; + }, + + + /** + * Returns a string name for the type of match that this class represents. + * + * @return {String} + */ + getType : function() { + return 'email'; + }, + + + /** + * Returns the email address that was matched. + * + * @return {String} + */ + getEmail : function() { + return this.email; + }, + + + /** + * Returns the anchor href that should be generated for the match. + * + * @return {String} + */ + getAnchorHref : function() { + return 'mailto:' + this.email; + }, + + + /** + * Returns the anchor text that should be generated for the match. + * + * @return {String} + */ + getAnchorText : function() { + return this.email; + } + +} ); +/*global Autolinker */ +/** + * @class Autolinker.match.Hashtag + * @extends Autolinker.match.Match + * + * Represents a Hashtag match found in an input string which should be + * Autolinked. + * + * See this class's superclass ({@link Autolinker.match.Match}) for more + * details. + */ +Autolinker.match.Hashtag = Autolinker.Util.extend( Autolinker.match.Match, { + + /** + * @cfg {String} serviceName + * + * The service to point hashtag matches to. See {@link Autolinker#hashtag} + * for available values. + */ + + /** + * @cfg {String} hashtag (required) + * + * The Hashtag that was matched, without the '#'. + */ + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match + * instance, specified in an Object (map). + */ + constructor : function( cfg ) { + Autolinker.match.Match.prototype.constructor.call( this, cfg ); + + // TODO: if( !serviceName ) throw new Error( '`serviceName` cfg required' ); + if( !cfg.hashtag ) throw new Error( '`hashtag` cfg required' ); + + this.serviceName = cfg.serviceName; + this.hashtag = cfg.hashtag; + }, + + + /** + * Returns the type of match that this class represents. + * + * @return {String} + */ + getType : function() { + return 'hashtag'; + }, + + + /** + * Returns the configured {@link #serviceName} to point the Hashtag to. + * Ex: 'facebook', 'twitter'. + * + * @return {String} + */ + getServiceName : function() { + return this.serviceName; + }, + + + /** + * Returns the matched hashtag, without the '#' character. + * + * @return {String} + */ + getHashtag : function() { + return this.hashtag; + }, + + + /** + * Returns the anchor href that should be generated for the match. + * + * @return {String} + */ + getAnchorHref : function() { + var serviceName = this.serviceName, + hashtag = this.hashtag; + + switch( serviceName ) { + case 'twitter' : + return 'https://twitter.com/hashtag/' + hashtag; + case 'facebook' : + return 'https://www.facebook.com/hashtag/' + hashtag; + case 'instagram' : + return 'https://instagram.com/explore/tags/' + hashtag; + + default : // Shouldn't happen because Autolinker's constructor should block any invalid values, but just in case. + throw new Error( 'Unknown service name to point hashtag to: ', serviceName ); + } + }, + + + /** + * Returns the anchor text that should be generated for the match. + * + * @return {String} + */ + getAnchorText : function() { + return '#' + this.hashtag; + } + +} ); + +/*global Autolinker */ +/** + * @class Autolinker.match.Phone + * @extends Autolinker.match.Match + * + * Represents a Phone number match found in an input string which should be + * Autolinked. + * + * See this class's superclass ({@link Autolinker.match.Match}) for more + * details. + */ +Autolinker.match.Phone = Autolinker.Util.extend( Autolinker.match.Match, { + + /** + * @protected + * @property {String} number (required) + * + * The phone number that was matched, without any delimiter characters. + * + * Note: This is a string to allow for prefixed 0's. + */ + + /** + * @protected + * @property {Boolean} plusSign (required) + * + * `true` if the matched phone number started with a '+' sign. We'll include + * it in the `tel:` URL if so, as this is needed for international numbers. + * + * Ex: '+1 (123) 456 7879' + */ + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match + * instance, specified in an Object (map). + */ + constructor : function( cfg ) { + Autolinker.match.Match.prototype.constructor.call( this, cfg ); + + if( !cfg.number ) throw new Error( '`number` cfg required' ); + if( cfg.plusSign == null ) throw new Error( '`plusSign` cfg required' ); + + this.number = cfg.number; + this.plusSign = cfg.plusSign; + }, + + + /** + * Returns a string name for the type of match that this class represents. + * + * @return {String} + */ + getType : function() { + return 'phone'; + }, + + + /** + * Returns the phone number that was matched as a string, without any + * delimiter characters. + * + * Note: This is a string to allow for prefixed 0's. + * + * @return {String} + */ + getNumber: function() { + return this.number; + }, + + + /** + * Returns the anchor href that should be generated for the match. + * + * @return {String} + */ + getAnchorHref : function() { + return 'tel:' + ( this.plusSign ? '+' : '' ) + this.number; + }, + + + /** + * Returns the anchor text that should be generated for the match. + * + * @return {String} + */ + getAnchorText : function() { + return this.matchedText; + } + +} ); + +/*global Autolinker */ +/** + * @class Autolinker.match.Mention + * @extends Autolinker.match.Match + * + * Represents a Mention match found in an input string which should be Autolinked. + * + * See this class's superclass ({@link Autolinker.match.Match}) for more details. + */ +Autolinker.match.Mention = Autolinker.Util.extend( Autolinker.match.Match, { + + /** + * @cfg {String} serviceName + * + * The service to point mention matches to. See {@link Autolinker#mention} + * for available values. + */ + + /** + * @cfg {String} mention (required) + * + * The Mention that was matched, without the '@' character. + */ + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match + * instance, specified in an Object (map). + */ + constructor : function( cfg ) { + Autolinker.match.Match.prototype.constructor.call( this, cfg ); + + if( !cfg.serviceName ) throw new Error( '`serviceName` cfg required' ); + if( !cfg.mention ) throw new Error( '`mention` cfg required' ); + + this.mention = cfg.mention; + this.serviceName = cfg.serviceName; + }, + + + /** + * Returns the type of match that this class represents. + * + * @return {String} + */ + getType : function() { + return 'mention'; + }, + + + /** + * Returns the mention, without the '@' character. + * + * @return {String} + */ + getMention : function() { + return this.mention; + }, + + + /** + * Returns the configured {@link #serviceName} to point the mention to. + * Ex: 'instagram', 'twitter'. + * + * @return {String} + */ + getServiceName : function() { + return this.serviceName; + }, + + + /** + * Returns the anchor href that should be generated for the match. + * + * @return {String} + */ + getAnchorHref : function() { + switch( this.serviceName ) { + case 'twitter' : + return 'https://twitter.com/' + this.mention; + case 'instagram' : + return 'https://instagram.com/' + this.mention; + + default : // Shouldn't happen because Autolinker's constructor should block any invalid values, but just in case. + throw new Error( 'Unknown service name to point mention to: ', this.serviceName ); + } + }, + + + /** + * Returns the anchor text that should be generated for the match. + * + * @return {String} + */ + getAnchorText : function() { + return '@' + this.mention; + }, + + + /** + * Returns the CSS class suffixes that should be used on a tag built with + * the match. See {@link Autolinker.match.Match#getCssClassSuffixes} for + * details. + * + * @return {String[]} + */ + getCssClassSuffixes : function() { + var cssClassSuffixes = Autolinker.match.Match.prototype.getCssClassSuffixes.call( this ), + serviceName = this.getServiceName(); + + if( serviceName ) { + cssClassSuffixes.push( serviceName ); + } + return cssClassSuffixes; + } + +} ); + +/*global Autolinker */ +/** + * @class Autolinker.match.Url + * @extends Autolinker.match.Match + * + * Represents a Url match found in an input string which should be Autolinked. + * + * See this class's superclass ({@link Autolinker.match.Match}) for more details. + */ +Autolinker.match.Url = Autolinker.Util.extend( Autolinker.match.Match, { + + /** + * @cfg {String} url (required) + * + * The url that was matched. + */ + + /** + * @cfg {"scheme"/"www"/"tld"} urlMatchType (required) + * + * The type of URL match that this class represents. This helps to determine + * if the match was made in the original text with a prefixed scheme (ex: + * 'http://www.google.com'), a prefixed 'www' (ex: 'www.google.com'), or + * was matched by a known top-level domain (ex: 'google.com'). + */ + + /** + * @cfg {Boolean} protocolUrlMatch (required) + * + * `true` if the URL is a match which already has a protocol (i.e. + * 'http://'), `false` if the match was from a 'www' or known TLD match. + */ + + /** + * @cfg {Boolean} protocolRelativeMatch (required) + * + * `true` if the URL is a protocol-relative match. A protocol-relative match + * is a URL that starts with '//', and will be either http:// or https:// + * based on the protocol that the site is loaded under. + */ + + /** + * @cfg {Object} stripPrefix (required) + * + * The Object form of {@link Autolinker#cfg-stripPrefix}. + */ + + /** + * @cfg {Boolean} stripTrailingSlash (required) + * @inheritdoc Autolinker#cfg-stripTrailingSlash + */ + + + /** + * @constructor + * @param {Object} cfg The configuration properties for the Match + * instance, specified in an Object (map). + */ + constructor : function( cfg ) { + Autolinker.match.Match.prototype.constructor.call( this, cfg ); + + if( cfg.urlMatchType !== 'scheme' && cfg.urlMatchType !== 'www' && cfg.urlMatchType !== 'tld' ) throw new Error( '`urlMatchType` cfg must be one of: "scheme", "www", or "tld"' ); + if( !cfg.url ) throw new Error( '`url` cfg required' ); + if( cfg.protocolUrlMatch == null ) throw new Error( '`protocolUrlMatch` cfg required' ); + if( cfg.protocolRelativeMatch == null ) throw new Error( '`protocolRelativeMatch` cfg required' ); + if( cfg.stripPrefix == null ) throw new Error( '`stripPrefix` cfg required' ); + if( cfg.stripTrailingSlash == null ) throw new Error( '`stripTrailingSlash` cfg required' ); + + this.urlMatchType = cfg.urlMatchType; + this.url = cfg.url; + this.protocolUrlMatch = cfg.protocolUrlMatch; + this.protocolRelativeMatch = cfg.protocolRelativeMatch; + this.stripPrefix = cfg.stripPrefix; + this.stripTrailingSlash = cfg.stripTrailingSlash; + }, + + + /** + * @private + * @property {RegExp} schemePrefixRegex + * + * A regular expression used to remove the 'http://' or 'https://' from + * URLs. + */ + schemePrefixRegex: /^(https?:\/\/)?/i, + + /** + * @private + * @property {RegExp} wwwPrefixRegex + * + * A regular expression used to remove the 'www.' from URLs. + */ + wwwPrefixRegex: /^(https?:\/\/)?(www\.)?/i, + + /** ... etc. - the rest is truncated _______________________________________________ Libreoffice-commits mailing list libreoffice-comm...@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/libreoffice-commits