/**
* @class Autolinker
* @extends Object
*
* Utility class used to process a given string of text, and wrap the URLs, email addresses, and Twitter handles 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/Twitter handle match that is encountered.
*
* For example:
*
* var input = "..."; // string with URLs, Email Addresses, and Twitter Handles
*
* var linkedText = Autolinker.link( input, {
* replaceFn : function( autolinker, 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 = autolinker.getTagBuilder().build( match ); // 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 'twitter' :
* var twitterHandle = match.getTwitterHandle();
* console.log( twitterHandle );
*
* return '<a href="http://newplace.to.link.twitter.handles.to/">' + twitterHandle + '</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} [config] The configuration options for the Autolinker instance, specified in an Object (map).
*/
var Autolinker = function( cfg ) {
Autolinker.Util.assign( this, cfg ); // assign the properties of `cfg` onto the Autolinker instance. Prototype properties will be used for missing configs.
this.matchValidator = new Autolinker.MatchValidator();
};
Autolinker.prototype = {
constructor : Autolinker, // fix constructor property
/**
* @cfg {Boolean} urls
*
* `true` if miscellaneous URLs should be automatically linked, `false` if they should not be.
*/
urls : true,
/**
* @cfg {Boolean} email
*
* `true` if email addresses should be automatically linked, `false` if they should not be.
*/
email : true,
* @cfg {Boolean} twitter
*
* `true` if Twitter handles ("@example") should be automatically linked, `false` if they should not be.
*/
twitter : true,
/**
* @cfg {Boolean} newWindow
*
* `true` if the links should open in a new window, `false` otherwise.
*/
newWindow : true,
/**
* @cfg {Boolean} stripPrefix
*
* `true` if 'http://' or 'https://' and/or the 'www.' should be stripped from the beginning of URL links' text,
* `false` otherwise.
*/
stripPrefix : true,
/**
* @cfg {Number} truncate
*
* A number for how many characters long URLs/emails/twitter handles should be truncated to inside the text of
* a link. If the URL/email/twitter 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..'
*/
/**
* @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 url/email/twitter suffixes for styling url/email/twitter 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
* - Twitter links will have the CSS classes: "myLink myLink-twitter"
*/
className : "",
/**
* @cfg {Function} replaceFn
*
* A function to individually process each URL/Email/Twitter match found in the input string.
*
* See the class's description for usage.
*
* This function is called with the following parameters:
*
* @cfg {Autolinker} replaceFn.autolinker The Autolinker instance, which may be used to retrieve child objects from (such
* as the instance's {@link #getTagBuilder tag builder}).
* @cfg {Autolinker.match.Match} replaceFn.match The Match instance which can be used to retrieve information about the
* {@link Autolinker.match.Url URL}/{@link Autolinker.match.Email email}/{@link Autolinker.match.Twitter Twitter}
* match that the `replaceFn` is currently processing.
*/
/**
* @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,
/**
* @private
* @property {RegExp} matcherRegex
*
* The regular expression that matches URLs, email addresses, and Twitter handles.
*
* This regular expression has the following capturing groups:
*
* 1. Group that is used to determine if there is a Twitter handle match (i.e. \@someTwitterUser). Simply check for its
* existence to determine if there is a Twitter handle match. The next couple of capturing groups give information
* about the Twitter handle match.
* 2. The whitespace character before the \@sign in a Twitter handle. This is needed because there are no lookbehinds in
* JS regular expressions, and can be used to reconstruct the original string in a replace().
* 3. The Twitter handle itself in a Twitter match. If the match is '@someTwitterUser', the handle is 'someTwitterUser'.
* 4. Group that matches an email address. Used to determine if the match is an email address, as well as holding the full
* address. Ex: 'me@my.com'
* 5. Group that matches a URL in the input text. Ex: 'http://google.com', 'www.google.com', or just 'google.com'.
* This also includes a path, url parameters, or hash anchors. Ex: google.com/path/to/file?q1=1&q2=2#myAnchor
* 6. Group that matches a protocol URL (i.e. 'http://google.com'). This is used to match protocol URLs with just a single
* word, like 'http://localhost', where we won't double check that the domain name has at least one '.' in it.
* 7. A protocol-relative ('//') match for the case of a 'www.' prefixed URL. Will be an empty string if it is not a
* protocol-relative match. We need to know the character before the '//' in order to determine if it is a valid match
* or the // was in a string we don't want to auto-link.
* 8. A protocol-relative ('//') match for the case of a known TLD prefixed URL. Will be an empty string if it is not a
* protocol-relative match. See #6 for more info.
*/
matcherRegex : (function() {
var twitterRegex = /(^|[^\w])@(\w{1,15})/, // For matching a twitter handle. Ex: @gregory_jacobs
emailRegex = /(?:[\-;:&=\+\$,\w\.]+@)/, // something@ for email addresses (a.k.a. local-part)
protocolRegex = /(?:[A-Za-z]{3,9}:(?![A-Za-z]{3,9}:\/\/)(?:\/\/)?)/, // match protocol, allow in format "http://" or "mailto:". However, do not match the first part of something like 'link:http://www.google.com' (i.e. don't match "link:")
wwwRegex = /(?:www\.)/, // starting with 'www.'
domainNameRegex = /[A-Za-z0-9\.\-]*[A-Za-z0-9\-]/, // anything looking at all like a domain, non-unicode domains, not ending in a period
tldRegex = /\.(?:international|construction|contractors|enterprises|photography|productions|foundation|immobilien|industries|management|properties|technology|christmas|community|directory|education|equipment|institute|marketing|solutions|vacations|bargains|boutique|builders|catering|cleaning|clothing|computer|democrat|diamonds|graphics|holdings|lighting|partners|plumbing|supplies|training|ventures|academy|careers|company|cruises|domains|exposed|flights|florist|gallery|guitars|holiday|kitchen|neustar|okinawa|recipes|rentals|reviews|shiksha|singles|support|systems|agency|berlin|camera|center|coffee|condos|dating|estate|events|expert|futbol|kaufen|luxury|maison|monash|museum|nagoya|photos|repair|report|social|supply|tattoo|tienda|travel|viajes|villas|vision|voting|voyage|actor|build|cards|cheap|codes|dance|email|glass|house|mango|ninja|parts|photo|shoes|solar|today|tokyo|tools|watch|works|aero|arpa|asia|best|bike|blue|buzz|camp|club|cool|coop|farm|fish|gift|guru|info|jobs|kiwi|kred|land|limo|link|menu|mobi|moda|name|pics|pink|post|qpon|rich|ruhr|sexy|tips|vote|voto|wang|wien|wiki|zone|bar|bid|biz|cab|cat|ceo|com|edu|gov|int|kim|mil|net|onl|org|pro|pub|red|tel|uno|wed|xxx|xyz|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)\b/, // match our known top level domains (TLDs)
// Allow optional path, query string, and hash anchor, not ending in the following characters: "!:,.;"
// http://blog.codinghorror.com/the-problem-with-urls/
urlSuffixRegex = /(?:[\-A-Za-z0-9+&@#\/%?=~_()|!:,.;'\$\*]*[\-A-Za-z0-9+&@#\/%=~_()|'\$\*])?/; // note: optional part of the full regex
return new RegExp( [
'(', // *** Capturing group $1, which can be used to check for a twitter handle match. Use group $3 for the actual twitter handle though. $2 may be used to reconstruct the original string in a replace()
// *** Capturing group $2, which matches the whitespace character before the '@' sign (needed because of no lookbehinds), and
// *** Capturing group $3, which matches the actual twitter handle
twitterRegex.source,
')',
'|',
'(', // *** Capturing group $4, which is used to determine an email match
emailRegex.source,
domainNameRegex.source,
tldRegex.source,
')',
'|',
'(', // *** Capturing group $5, which is used to match a URL
'(?:', // parens to cover match for protocol (optional), and domain
'(', // *** Capturing group $6, for a protocol-prefixed url (ex: http://google.com)
protocolRegex.source,
domainNameRegex.source,
')',
'|',
'(?:', // non-capturing paren for a 'www.' prefixed url (ex: www.google.com)
'(.?//)?', // *** Capturing group $7 for an optional protocol-relative URL. Must be at the beginning of the string or start with a non-word character
wwwRegex.source,
domainNameRegex.source,
')',
'|',
'(?:', // non-capturing paren for known a TLD url (ex: google.com)
'(.?//)?', // *** Capturing group $8 for an optional protocol-relative URL. Must be at the beginning of the string or start with a non-word character
domainNameRegex.source,
tldRegex.source,
')',
')',
urlSuffixRegex.source, // match for path, query string, and/or hash anchor
')'
].join( "" ), 'gi' );
} )(),
/**
* @private
* @property {RegExp} charBeforeProtocolRelMatchRegex
*
* The regular expression used to retrieve the character before a protocol-relative URL match.
*
* This is used in conjunction with the {@link #matcherRegex}, which needs to grab the character before a protocol-relative
* '//' due to the lack of a negative look-behind in JavaScript regular expressions. The character before the match is stripped
* from the URL.
*/
charBeforeProtocolRelMatchRegex : /^(.)?\/\//,
/**
* @private
* @property {Autolinker.MatchValidator} matchValidator
*
* The MatchValidator object, used to filter out any false positives from the {@link #matcherRegex}. See
* {@link Autolinker.MatchValidator} for details.
*/
/**
* @private
* @property {Autolinker.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.AnchorTagBuilder} tagBuilder
*
* The AnchorTagBuilder instance used to build the URL/email/Twitter replacement anchor tags. This is lazily instantiated
* in the {@link #getTagBuilder} method.
*/
/**
* Automatically links URLs, email addresses, and Twitter handles 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 link URLs, email addresses, and Twitter handles within (depending on if
* the {@link #urls}, {@link #email}, and {@link #twitter} options are enabled).
* @return {String} The HTML, with URLs/emails/Twitter handles automatically linked.
*/
link : function( textOrHtml ) {
var me = this, // for closure
htmlParser = this.getHtmlParser(),
htmlCharacterEntitiesRegex = this.htmlCharacterEntitiesRegex,
anchorTagStackCount = 0, // used to only process text around anchor tags, and any inner text/html they may have
resultHtml = [];
htmlParser.parse( textOrHtml, {
// Process HTML nodes in the input `textOrHtml`
processHtmlNode : function( tagText, tagName, isClosingTag ) {
if( tagName === 'a' ) {
if( !isClosingTag ) { // 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
}
}
resultHtml.push( tagText ); // now add the text of the tag itself verbatim
},
// Process text nodes in the input `textOrHtml`
processTextNode : function( text ) {
if( anchorTagStackCount === 0 ) {
// If we're not within an <a> tag, process the text node
var unescapedText = Autolinker.Util.splitAndCapture( text, htmlCharacterEntitiesRegex ); // split at HTML entities, but include the HTML entities in the results array
for ( var i = 0, len = unescapedText.length; i < len; i++ ) {
var textToProcess = unescapedText[ i ],
processedTextNode = me.processTextNode( textToProcess );
resultHtml.push( processedTextNode );
}
} else {
// `text` is within an <a> tag, simply append the text - we do not want to autolink anything
// already within an <a>...</a> tag
resultHtml.push( text );
}
}
} );
return resultHtml.join( "" );
},
/**
* Lazily instantiates and returns the {@link #htmlParser} instance for this Autolinker instance.
*
* @protected
* @return {Autolinker.HtmlParser}
*/
getHtmlParser : function() {
var htmlParser = this.htmlParser;
if( !htmlParser ) {
htmlParser = this.htmlParser = new Autolinker.HtmlParser();
}
return htmlParser;
},
/**
* 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( autolinker, match ) {
* var tag = autolinker.getTagBuilder().build( match ); // 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;
},
/**
* Process the text that lies inbetween HTML tags. This method does the actual wrapping of URLs with
* anchor tags.
*
* @private
* @param {String} text The text to auto-link.
* @return {String} The text with anchor tags auto-filled.
*/
processTextNode : function( text ) {
var me = this; // for closure
return text.replace( this.matcherRegex, function( matchStr, $1, $2, $3, $4, $5, $6, $7, $8 ) {
var matchDescObj = me.processCandidateMatch( matchStr, $1, $2, $3, $4, $5, $6, $7, $8 ); // match description object
// Return out with no changes for match types that are disabled (url, email, twitter), or for matches that are
// invalid (false positives from the matcherRegex, which can't use look-behinds since they are unavailable in JS).
if( !matchDescObj ) {
return matchStr;
} else {
// Generate the replacement text for the match
var matchReturnVal = me.createMatchReturnVal( matchDescObj.match, matchDescObj.matchStr );
return matchDescObj.prefixStr + matchReturnVal + matchDescObj.suffixStr;
}
} );
},
/**
* Processes a candidate match from the {@link #matcherRegex}.
*
* Not all matches found by the regex are actual URL/email/Twitter matches, as determined by the {@link #matchValidator}. In
* this case, the method returns `null`. Otherwise, a valid Object with `prefixStr`, `match`, and `suffixStr` is returned.
*
* @private
* @param {String} matchStr The full match that was found by the {@link #matcherRegex}.
* @param {String} twitterMatch The matched text of a Twitter handle, if the match is a Twitter match.
* @param {String} twitterHandlePrefixWhitespaceChar The whitespace char before the @ sign in a Twitter handle match. This
* is needed because of no lookbehinds in JS regexes, and is need to re-include the character for the anchor tag replacement.
* @param {String} twitterHandle The actual Twitter user (i.e the word after the @ sign in a Twitter match).
* @param {String} emailAddressMatch The matched email address for an email address match.
* @param {String} urlMatch The matched URL string for a URL match.
* @param {String} protocolUrlMatch The match URL string for a protocol match. Ex: 'http://yahoo.com'. This is used to match
* something like 'http://localhost', where we won't double check that the domain name has at least one '.' in it.
* @param {String} wwwProtocolRelativeMatch The '//' for a protocol-relative match from a 'www' url, with the character that
* comes before the '//'.
* @param {String} tldProtocolRelativeMatch The '//' for a protocol-relative match from a TLD (top level domain) match, with
* the character that comes before the '//'.
*
* @return {Object} A "match description object". This will be `null` if the match was invalid, or if a match type is disabled.
* Otherwise, this will be an Object (map) with the following properties:
* @return {String} return.prefixStr The char(s) that should be prepended to the replacement string. These are char(s) that
* were needed to be included from the regex match that were ignored by processing code, and should be re-inserted into
* the replacement stream.
* @return {String} return.suffixStr The char(s) that should be appended to the replacement string. These are char(s) that
* were needed to be included from the regex match that were ignored by processing code, and should be re-inserted into
* the replacement stream.
* @return {String} return.matchStr The `matchStr`, fixed up to remove characters that are no longer needed (which have been
* added to `prefixStr` and `suffixStr`).
* @return {Autolinker.match.Match} return.match The Match object that represents the match that was found.
*/
processCandidateMatch : function(
matchStr, twitterMatch, twitterHandlePrefixWhitespaceChar, twitterHandle,
emailAddressMatch, urlMatch, protocolUrlMatch, wwwProtocolRelativeMatch, tldProtocolRelativeMatch
) {
var protocolRelativeMatch = wwwProtocolRelativeMatch || tldProtocolRelativeMatch,
match, // Will be an Autolinker.match.Match object
prefixStr = "", // A string to use to prefix the anchor tag that is created. This is needed for the Twitter handle match
suffixStr = ""; // A string to suffix the anchor tag that is created. This is used if there is a trailing parenthesis that should not be auto-linked.
// Return out with `null` for match types that are disabled (url, email, twitter), or for matches that are
// invalid (false positives from the matcherRegex, which can't use look-behinds since they are unavailable in JS).
if(
( twitterMatch && !this.twitter ) || ( emailAddressMatch && !this.email ) || ( urlMatch && !this.urls ) ||
!this.matchValidator.isValidMatch( urlMatch, protocolUrlMatch, protocolRelativeMatch )
) {
return null;
}
// Handle a closing parenthesis at the end of the match, and exclude it if there is not a matching open parenthesis
// in the match itself.
if( this.matchHasUnbalancedClosingParen( matchStr ) ) {
matchStr = matchStr.substr( 0, matchStr.length - 1 ); // remove the trailing ")"
suffixStr = ")"; // this will be added after the generated <a> tag
}
if( emailAddressMatch ) {
match = new Autolinker.match.Email( { matchedText: matchStr, email: emailAddressMatch } );
} else if( twitterMatch ) {
// fix up the `matchStr` if there was a preceding whitespace char, which was needed to determine the match
// itself (since there are no look-behinds in JS regexes)
if( twitterHandlePrefixWhitespaceChar ) {
prefixStr = twitterHandlePrefixWhitespaceChar;
matchStr = matchStr.slice( 1 ); // remove the prefixed whitespace char from the match
}
match = new Autolinker.match.Twitter( { matchedText: matchStr, twitterHandle: twitterHandle } );
} else { // url match
// If it's a protocol-relative '//' match, remove the character before the '//' (which the matcherRegex needed
// to match due to the lack of a negative look-behind in JavaScript regular expressions)
if( protocolRelativeMatch ) {
var charBeforeMatch = protocolRelativeMatch.match( this.charBeforeProtocolRelMatchRegex )[ 1 ] || "";
if( charBeforeMatch ) { // fix up the `matchStr` if there was a preceding char before a protocol-relative match, which was needed to determine the match itself (since there are no look-behinds in JS regexes)
prefixStr = charBeforeMatch;
matchStr = matchStr.slice( 1 ); // remove the prefixed char from the match
}
}
match = new Autolinker.match.Url( {
matchedText : matchStr,
url : matchStr,
protocolRelativeMatch : protocolRelativeMatch,
stripPrefix : this.stripPrefix
} );
}
return {
prefixStr : prefixStr,
suffixStr : suffixStr,
matchStr : matchStr,
match : match
};
},
/**
* Determines if a match found has an unmatched closing parenthesis. If so, this parenthesis will be removed
* from the match itself, and appended after the generated anchor tag in {@link #processTextNode}.
*
* A match may have an extra closing parenthesis at the end of the match because the regular expression must include parenthesis
* for URLs such as "wikipedia.com/something_(disambiguation)", which should be auto-linked.
*
* However, an extra parenthesis *will* be included when the URL itself is wrapped in parenthesis, such as in the case of
* "(wikipedia.com/something_(disambiguation))". In this case, the last closing parenthesis should *not* be part of the URL
* itself, and this method will return `true`.
*
* @private
* @param {String} matchStr The full match string from the {@link #matcherRegex}.
* @return {Boolean} `true` if there is an unbalanced closing parenthesis at the end of the `matchStr`, `false` otherwise.
*/
matchHasUnbalancedClosingParen : function( matchStr ) {
var lastChar = matchStr.charAt( matchStr.length - 1 );
if( lastChar === ')' ) {
var openParensMatch = matchStr.match( /\(/g ),
closeParensMatch = matchStr.match( /\)/g ),
numOpenParens = ( openParensMatch && openParensMatch.length ) || 0,
numCloseParens = ( closeParensMatch && closeParensMatch.length ) || 0;
if( numOpenParens < numCloseParens ) {
return true;
}
}
return false;
},
/**
* Creates the return string value for a given match in the input string, for the {@link #processTextNode} method.
*
* This method handles the {@link #replaceFn}, if one was provided.
*
* @private
* @param {Autolinker.match.Match} match The Match object that represents the match.
* @param {String} matchStr The original match string, after having been preprocessed to fix match edge cases (see
* the `prefixStr` and `suffixStr` vars in {@link #processTextNode}.
* @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, matchStr ) {
// Handle a custom `replaceFn` being provided
var replaceFnResult;
if( this.replaceFn ) {
replaceFnResult = this.replaceFn.call( this, this, match ); // Autolinker instance is the context, and the first arg
}
if( typeof replaceFnResult === 'string' ) {
return replaceFnResult; // `replaceFn` returned a string, use that
} else if( replaceFnResult === false ) {
return matchStr; // no replacement for the match
} else if( replaceFnResult instanceof Autolinker.HtmlTag ) {
return replaceFnResult.toString();
} else { // replaceFnResult === true, or no/unknown return value from function
// Perform Autolinker's default anchor tag generation
var tagBuilder = this.getTagBuilder(),
anchorTag = tagBuilder.build( match ); // returns an Autolinker.HtmlTag instance
return anchorTag.toString();
}
}
};
/**
* Automatically links URLs, email addresses, and Twitter handles 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 URLs, email addresses, and Twitter handles within (depending on if
* the {@link #urls}, {@link #email}, and {@link #twitter} 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 URLs automatically linked
*/
Autolinker.link = function( textOrHtml, options ) {
var autolinker = new Autolinker( options );
return autolinker.link( textOrHtml );
};
// Namespace for `match` classes
Autolinker.match = {};