|
importScript("User:Ohconfucius/test/Sources_subscript2.js"); //Correctly casing titles and apply or rem italicisation
importScript("User:Ohconfucius/test/Sources_subscript3.js"); //link-fixing, dabbing etc
//importScript("User:Ohconfucius/script/foreigndates.js"); //link-fixing, dabbing etc
function Ohc_add_ref_tags() {
var txt=document.editform.wpTextbox1;
regex(/([^>\*\s])\s?(\[https?:\/\/[^\s\[\]]*\])(?![ ]*[<\-]+)/gi, '$1<ref>$2</ref>');
}
var txt=document.editform.wpTextbox1;
//test
regex(/\s?(<ref>(?:[^<>]*\|\s*url\s*=|\[?)https?:\/\/((?:\w+\.)*\w+(?:\.(?:com?|org|net|gov|ac|)(?:\.[a-z]{2}|)))\/[^<>{}]+\|publisher=)(?=}}<\/ref>)/gi, "$1$2"); //capture ___domain name to add to publisher
regex(/(\|\s*(?:publisher|website)\s*\=\s*)w{3}\.(\w+\.(?:com?|org|net|gov|ac|)(?:\.[a-z]{2}|))(?=\s*[|}])/gi, '$1$2');
regex(/(\|\s*publisher=)\s?\|\s?via\s*\=\s*(\w+)(?=\s*[|}])/gi, '$1$2');
regex(/\s?[-–]\s?(?:The |)(\w+\.(?:com?|org|net|gov|ac|)(?:\.[a-z]{2}|))\s?(\|\s*publisher\s*\=\s*)\1(?=}})/gi, '$2$1');
regex(/\s?[-–]\s?([^|]+)\s?(\|\s*publisher\s*\=\s*)(The )\1(?=}})/gi, '$2$3$1');
regex(/\|\s?first\s*\=[^|]*\|\s?last\s*\=(?:Editor|Group|Staff|Reporter|Writer)\s*(?=\|)/gi, '');
regex(/({{Navbox deaths}})(\n)/gi, '==References==$2{{Reflist}}$2$1$2');
regex(/(==References==\n{{Reflist}}\n)\n?\1/gi, '$1');
}
// warning-tagging template:Primary source inline
regex(/(<ref[^<>]*>[^<>]*\|[ ]*url ?= ?https?:\/\/(?:(?:www\.|mobile\.|)(?:blogger|blogspot|facebook|sites\.google|instagram|tiktok|twitter|wordpress|x)\.com|www\.formspring\.me)\/[^<>{]*<\/ref>)(?:\{\{Primary source inline\}\}|)/gi, '$1{{Primary source inline}}');
regex(/(<ref[^<>]*>[^<>]*\|[ ]*url ?= ?https?:\/\/(?:(?:www\.|)(?:myspace|findagrave)\.com)\/[^<>{]*<\/ref>)(?:\{\{Primary source inline\}\}|)/gi, '$1{{Primary source inline}}');
regex(/(<ref>\s*https?:\/\/(?:(?:www\.|)(?:blogger|blogspot|facebook|sites\.google|findagrave|instagram|myspace|tiktok|twitter|wordpress|x)\.com)\/[^\s\]<]*<\/ref>)(?:\{\{Primary source inline\}\}|)/gi, '$1{{Primary source inline}}');
regex(/(<ref>\s*\[https?:\/\/(?:(?:www\.|)(?:blogger|blogspot|facebook|sites\.google|findagrave|instagram|myspace|tiktok|twitter|wordpress|x)\.com)\/[^\s\]]*[ ]+[\w\d][^\]]*\]<\/ref>)(?:\{\{Primary source inline\}\}|)/gi, '$1{{Primary source inline}}');
// removing http links within publisher/journal/work fields
//
regex(/(\|\s*title\s*\=)\s*https?:\/{2}(?:w{3}\.|)\w+\.com(?=\s?(?:[=|{]|\}\}))/gi, '$1 ');
regex(/(\|\s*title\s*\=)\s*https?:\/{2}[^|\s]+(?=\s?(?:[=|{]|\}\}))/gi, '$1 ');
regex(/\s?<!--ACTUAL ARTICLE TITLE BELONGS HERE!(?: original text:|)[^>]*-->/gi, ' '); //rem error introduced by earlier version of this script; entirely strip title field
regex(/(\|\s*(?:author(?:link\d?|)|chapter|journal|magazine|newspaper|publisher|title|work|via)\s*\=\s*)https?:\/{2}(?:w{3}\.|)(?=\w)/gi, '$1'); //removes http:// and optionally www.
regex(/(\|\s*(?:author(?:link\d?|)|chapter|journal|magazine|newspaper|publisher|title|work|via)\s*\=\s*)(?:w{3}\.)(?=\w)/gi, '$1'); //removes www.
regex(/(\|\s*(?:author(?:link\d?|)|chapter|journal|magazine|newspaper|publisher|title|work|via)\s*\=\s*)(\w+(?:\.(?:com?|net|org|gov|\w{2}))(?:\.\w{2}|))(?:\/[^|}]*|)(?=\s*[\]|}])/gi, '$1$2'); //returns ___domain name
regex(/(>{{cit[^}]+\|\s?website\s*\=\s*)https?:\/{2}(?:w{3}\.|)(?=\w)/gi, '$1'); //leave only ___domain name
regex(/(>{{cit[^}]+\|\s?website\s*\=\s*)(?:w{3}\.)(?=\w)/gi, '$1'); //leave only ___domain name
// removing hyperlinks within publisher/journal/website/work fields
regex(/(\|\s*(?:chapter|journal|magazine|newspaper|publisher|title|work|via)\s*\=\s*)\[https?:\/\/[^\s\]]*\s([\w][^\]]*)\]/gi, '$1$2'); //leave only linked text
regex(/({{cit[^}]+\|\s?website\s*\=\s*)\[https?:\/\/[^\s\]]*\s([\w][^\]]*)\]/gi, '$1$2'); //citation templates: rem url whilst leaving only linked text within |website=
regex(/(\|\s*title\s*=\s*)(?:\w+(?:\.(?:com?|net|org|gov|\w{2}))(?:\.\w{2}|))(?:\/[^|}]+)(?:\/[^|}]+)(?:\/[^|}]+)(?:\/[^|}]+)\/([^|}]+)\/?(?=\s*[\]|}])/gi, '$1$2'); //returns terminal part of url
regex(/(\|\s*title\s*=\s*)(?:\w+(?:\.(?:com?|net|org|gov|\w{2}))(?:\.\w{2}|))(?:\/[^|}]+)(?:\/[^|}]+)(?:\/[^|}]+)\/([^|}]+)\/?(?=\s*[\]|}])/gi, '$1$2'); //returns terminal part of url
regex(/(\|\s*title\s*=\s*)(?:\w+(?:\.(?:com?|net|org|gov|\w{2}))(?:\.\w{2}|))(?:\/[^|}]+)(?:\/[^|}]+)\/([^|}]+)\/?(?=\s*[\]|}])/gi, '$1$2'); //returns terminal part of url
regex(/(\|\s*title\s*=\s*)(?:\w+(?:\.(?:com?|net|org|gov|\w{2}))(?:\.\w{2}|))(?:\/[^|}]+)\/([^|}]+)\/?(?=\s*[\]|}])/gi, '$1$2'); //returns terminal part of url
regex(/(\|\s*title\s*=\s*)(?:\w+(?:\.(?:com?|net|org|gov|\w{2}))(?:\.\w{2}|))\/([^|}]+)\/?(?=\s*[\]|}])/gi, '$1$2'); //returns terminal part of url
regex(/(\|\s*author(?:link\d?|)\s*\=\s*)\[https?:\/\/[^\s\]]*\s([\w][^\]]*)\]/gi, '$1$2');
regex(/(\|\s*author(?:link\d?|)\s*\=\s*)(?:https?:\/\/|)www\.[\w][^|}]*(?=[|}])/gi, '$1'); //rem outright (not a WL)
// removing references to other WP articles and 'external' WP links
regex(/<ref[^<>]*>[^<>]*\|[ ]*url ?= ?https?:\/\/\w{2}\.wikipedia\.org\/w[^<>]*<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP-->');
regex(/<ref>\s*https?:\/\/\w{2}\.wikipedia\.org\/wiki\/[^\s\]<]*<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP-->');
regex(/<ref>\s*\[https?:\/\/\w{2}\.wikipedia\.org\/w[^\s\]]*[ ]+[\w\d][^\]]*\]<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP-->');
regex(/<ref(?: name=[^<>]|)>[^<>]*\|\s*url[ ]*=[ ]*https?:\/\/\w{2}\.wikipedia\.org\/w[^\s\|\{\}<]*[^<>]*<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP-->');
regex(/\[https?:\/\/\w{2}\.wikipedia\.org\/w[^\s\]]*[ ]+([\w][^\]]*)\]/gi, ' [[$1]]');
//deprecated sources
regex(/<ref[^<>]*>[^<>]*\|[ ]*url ?= ?https?:\/\/(?:(?:\w+\.|)((?:the|)epochtimes|ntdtv)\.com)\/[^<>{]*<\/ref>/gi, '<!--rem deprecated source \($1\)-->');
regex(/<ref[^<>]*>[^<>]*\|[ ]*url ?= ?https?:\/\/(?:(?:\w+\.|)(thesun|dailymail)\.co\.uk)\/[^<>{]*<\/ref>/gi, '<!--rem deprecated source \($1\)-->');
regex(/(\|\s*url\s*\=\s*|\[)(https?:[^|{}#\s]+)(?:#[A-Za-z0-9\.]{12,13}|\?CMP=fb_gu)(?=[\s\[\]|{}<>])/gi, '$1$2'); //rem link tracking
regex(/(\|\s*url\s*\=\s*)(https?:[^|{}#\s]+\.html?)\?[^|}]{1,5}(?=[\s\[\]|{}<>])/gi, '$1$2'); //rem link tracking
regex(/(\|\s*url\s*\=\s*|\[)(https?:\/\/books\.google\.[^\/]+\/books\?id=\w{12}&pg=PA\d{1,3})&dq[^\s|}]+(?=\s?[|}])/gi, '$1$2'); //rem browser optimisation
}
// removing artefacts within fields
regex(/(\|\s*author\s*\=\s*)(?:by |)(?:[^|]+staff|(?:staff |)(?:reporter|writer)s?|)[\s\n]*(?=[|}])/gi, '');
regex(/(\|\s*author\s*\=\s*)([A-Z][a-z]*(?: [A-Z][a-z]*)*) (?:(?:wire |)staff|(?:staff |)(?:reporter|writer)s?)[\s\n]*(?=[|}])/gi, '$1$2');
regex(/\|[ ]*last=(Reporter|staff)[ ]*\|[ ]*first=[^|\{\}]*(?=[\|{}])/gi, '');
regex(/\|[ ]*(?:first|last)=(?:staff |)(?:reporter|writer)[ ]*(?=[\|{}])/gi, '');
regex(/\|[ ]*first= ?staff ?\|[ ]*last=(?:reporter|writer)[ ]*(?=[\|{}])/gi, '');
regex(/\|[ ]*first= ?The ?\|[ ]*last=[^\|{}]*(?=[\|{}])/gi, '');
regex(/(\|\s*access-?date\s*\=\s*)(?:accessed|retrieved)(?: by| on|):?[ ]*(\d)/gi, '$1$2');
regex(/(\|\s*access-?date\s*\=\s*\d{4}\s?)(?=[|}])/gi, '');
regex(/(\|\s*work\s*\=\s*)(?:article|interview|review) ?(?=[|}])/gi, '$1');
regex(/(\|\s*volume\s*\=\s*)vol(?:ume|\.?)[ ]*(\d)/gi, '$1$2');
regex(/(\|\s*pages?\s*\=\s*)(?:pages?|p[gp]?\.?)[ ]*(\d)/gi, '$1$2');
regex(/ [-–] (?:每日明報 daily news|東方日報)/gi, '');
regex(/(\.\.\. |)\{\{!\}\} 立場(報道|新聞)/gi, '');
regex(/(\|\s*title\s*\=\s*)Login ?(?=[|}])/gi, '$1'); //creating deliberate error (blank title) per Trappist
regex(/(\|\s*)(?:publisher|website|work)=(Newspapers\.com|Twitter|Vimeo|Youtube)(?:\.com|)(?=\s*[|}])/gi, '$1via=$2');
regex(/(\|\s*)(?:publisher|website|work)=(Amazon)(?:\.com|)(?:\.\w{2}|)(?=\s*[|}])/gi, '$1via=$2');
regex(/(\|\s*)(?:publisher|website|work)=(\[\[Twitter\|𝕏\]\])(?: *\(Formerly (?:Twitter|\[\[Twitter\]\]\)) *|)(?=\s*[|}])/gi, '$1via=$2');
regex(/(\|\s*publisher=)\|\s?via\s*\=\s*(\w+)(?=\s*[|}])/gi, '$1$2');
regex(/(?:-[ ]*Google Books[ ]*(?:\|[^}]*|)|)\|\s?publisher\s*\=\s*(Google Books)(?=[\s\.]*[|}])/g, '|via=$1');
//Remove COinS corrupting templates from CS1 citations
regex(/(\|\s*(?:authors?|first\d?|last\d?|publisher|work)\s*\=\s*(?:[^{}|]*|)){{(?:Sm|Aut|SC|Small[- ]caps|Sm?caps)\|([^{}|]*)}}(?=(?:[^{}|]*|)[|}])/gi, '$1');
regex(/(\|\s*)\w+\=(url\s*\=\s*https?:\/\/)(?=[|}])/gi, '$1$2'); //common cs1 error
regex(/(\|\s*url\s*\=)(www\.)(?=[|}])/gi, '$1http//$2'); //common cs1 error
regex(/(\|\s*date\s*=\s*)(?:not? |non-|un)date[ds]?\s*(?=[|}])/gi, '$1n.d.'); //common cs1 error
regex(/(\|\s*dead-?url=no?)(?=\s*[|}])/gi, '|url-status=dead'); //common cs1 error (deprecated parameter)
regex(/(\*[ ]*|)\[\[n:[^\]\|]*\]\][\r\n]*/gi, '');
//citation template fixes
// rem copyright assertion
regex(/(\|\s*publisher\s*\=\s*)(?:\[\[copyright(?:\|©|)\]\])\s?/gi, '$1');
regex(/(\|\s*publisher\s*\=\s*)(?:©|copyright)\s?/gi, '$1');
regex(/(\|\s*title\s*\=\s*[^|}]+?)[-‒–—―]\s+([^|}]+?)(\|\s*(?:publisher|work)\s*\=\s*\2)/gi, '$1$3');
regex(/(\|\s*title\s*\=\s*([^|}]+?))[-‒–—―]\s+([^|}]+?\|\s?(?:publisher|work)\s*\=\s*\2)/gi, '$1$3');
// misused 'date' parameter
regex(/(\{\{\s?cit[ae][^}]+)\|\s?date(\s?=\s?[12]\d{3}\s?[|}])/gi, '$1|year$2');
// rem toggles and redundant quote marks
regex(/(\|\s*(?:agency|author|newspaper|work|journal|publisher|title)\s*\=\s*)\'\'([^|}]+)\'\'(?=\s*[\}\|])/gi, '$1$2'); //without link
regex(/(\|\s*(?:agency|author|newspaper|work|journal|publisher|title)\s*\=\s*)\'\'(\[\[(?:[^\|]+\||)[^\|\]]+\]\])\'\'(?=\s*[\}\|])/gi, '$1$2'); //with link
regex(/(\|\s*title\s*\=\s*)\''([^\|\{\}]+)\''/gi, '$1$2'); //rem ' in titles
regex(/(\|\s*publisher\s*\=\s*)\(([^\|\{\}]+)\)/gi, '$1$2'); //rem parenthetical publishers
regex(/(\|\s*publisher\s*\=\s*)\"([^\|\{\}]+)\"/gi, '$1$2'); //rem quote marks around publishers
// reordering 'work' and 'publisher' (first run - see second run in cleanup function)
// remove redundant parentheses and templates from dm and md dates (equivalents also exists in Mosnum script)
regex(/(=[ ]*)\(([^()|{}])\)/gi, '$1$2');
// rem corporate designation
//rem redundant top-level domains (.com, .net, .org), strip "www"
regex(/(\|\s*(?:journal|newspaper|periodical|publisher|work)\s*\=\s*)(\[\[[^\[\]\}]*\]\])\.(?:biz|com|net|org|co\.uk|(?:com\.|)[a-z]{2})(?=\s*[|}])/gi, '$1$2');
//rem duplicated publishers in separate fields (pre)
// eliminating time of day
regex(/(\|[ ]*author[ ]*=[ ]*)(?:posted|published)(?: by| on|)[\s:](?=\s*\w)/gi, "$1");
regex(/(\|[ ]*(?:date|archive-?date|access-?date|author|first|last)[ ]*=[ ]*)[0-2]?\d:[0-5]\d(?:[ ]| )(?:[ap]m ?|[ap]\.m\. |[A-Z]{1,2}T|UTC)[\.,]?[ ]?/gi, "$1");
// eliminating days of the week
regex(/(\|[ ]*(?:date|archive-?date|access-?date|author)[ ]*=[ ]*)(?:(?:Mon|Tues?|Wed|Thur?|Fri|Sat|Sun)(?:[\.,]|day)?)\s/gi, "$1");
//'Accessed'/'Obtained' -> 'Retrieved'
// regex(/(\[\[)(?:foo|bar)(\|)/gi, '$1foo bar \(dab\)$2');
regex(/(\[\[)(?:(?:British|English|London) Sun|Sun on Sunday|The Scottish Sun|(?:The |)Sun (?:\((?:British |)newspaper\)|\(tabloid\)|\(UK newspaper\)|\(UK\)|Newspaper|on Sunday|Online)|Thesun\.co\.uk)(?=\|)/gi, '$1The Sun (United Kingdom)');
regex(/(\[\[)Daily Star \((?:British|UK)\)(?=\|)/gi, '$1Daily Star (United Kingdom)');
regex(/(\[\[Metro)(?: \(Associated Metro Limited\)| \(Associated Newspapers\)| \(London newspaper\)| \(free London newspaper\)| UK| newspaper London| newspaper UK)(?=\|)/gi, '$1 (British newspaper)');
regex(/(?:\|\s?(newspaper|work|publisher)\s*\=\s*(ACP Magazines|The Herald and Weekly Times|John Fairfax (and Sons Ltd\.?|Holdings)|Fairfax(?: Media(?: Limited|)| Digital| newspapers|)))(?=[\s\.]*[|}])/gi, '');
regex(/(?:\|\s?(newspaper|work|publisher)\s*\=\s*\[\[(ACP Magazines|The Herald and Weekly Times|John Fairfax (and Sons Ltd\.?|Holdings)|Fairfax(?: Media(?: Limited|)| Digital| newspapers))\]\])(?=[\s\.]*[|}])/gi, '');
regex(/\| ?publisher ?= ?(?:Fandango Media|\[\[Fandango Media\]\]) ?/gi, '');
regex(/(?:\|\s?publisher\s*\=\s*(Alexander Lebedev|American Media|Associated Newspapers|Bauer (?:Consumer Media|Media Group)|Cond[eé] Nast(?: Publications|)|Daily Mail and General Trust|Devin Laz[ae]rine|Dow Jones & Company|Future plc|(Guardian|Telegraph) Media Group|(?:Guardian|Independent) News (?:and|&) Media(?: Limited| Ltd\.|)|Hachette Filipacchi Médias|Hearst (?:Corporation|Magazines(?: UK|))|Herald Media|IGN Entertainment|Imdb Inc\.?|InterMedia Partners|IDG|IPC Media|Lee Enterprises|Media ?News Group|Mediacorp|Mortimer Zuckerman|MTV Networks|News (?:Corporation|International|Limited)|Postmedia Network Inc\.?|Prometheus Global Media|Reed Business Information|Rovi Corporation|Trinity Mirror|Times Newspapers|Nielsen (?: Media Research|Business Media)|Viacom|Time(?: Warner ?|)))(,? Inc| LL[CP]| Ltd|Limited|)[\s\.]*(?=[|}])/gi, '');
regex(/\|\s?publisher\s*\=\s*(?:The |)(?:Deseret News Publishing|Dispatch Printing|E\. W\. Scripps|Evening Post Publishing|Forbes(?: Publishing|, Inc\.)|Gannett?|Independent News & Media|Irish Times Trust|(?:Jann Wenner|Wenner Media)|Johnson Publishing|Journal Communications|Mac Publishing|Media24|McClatchy|Nash holdings LLC|New York Times|Seattle Times|Star Tribune|Thomp?son(?:[- ]?Reuters)?(?: Corporation| Plc.?|)|Singapore Press Holdings|Torstar|Time Inc\.|Times (?:Group|Publishing)|Tribune|Vox Media|Washington Post|World Publishing|Ziff Davis Media)(?: Co(?:mpany|\.)?)?(?=[\s\.]*[|}])/g, '');
regex(/\|\s?publisher\s*\=\s*(?:Cox|Halifax|North Jersey|Sun-Times|Tampa|Herald|Stephens|WEHCO) Media(?: Group(?:,? Inc\.)?| Berhad)?(?=[\s\.]*[|}])/g, '');
// removing other artefacts
regex(/(UEFA\]\])\.(?:co(?:m|m?\.\w{2})|\.\w{2})(?= ?[\|{}])/gi, '$1');
regex(/\bthe ((?:'''?|)the )/gi, '$1');
//dynamic columns for reflists; remove scroll bar
// disambiguating duplicated ref names
//strips down duplicated refs with doubled-up citation templates
regex(/(<ref name=[^/>"]*)>(\{\{[^\}]*\}\})([\s\S]*)\1>\2<\/ref>([\s\S]*)\1>\2<\/ref>([\s\S]*)\1>\2<\/ref>/gi, '$1>$2$3$1/>$4$1/>$5$1/>');
regex(/(<ref name=[^/>"]*)>(\{\{[^\}]*\}\})([\s\S]*)\1>\2<\/ref>([\s\S]*)\1>\2<\/ref>/gi, '$1>$2$3$1/>$4$1/>');
regex(/(<ref name=[^/>"]*)>(\{\{[^\}]*\}\})([\s\S]*)\1>\2<\/ref>/gi, '$1>$2$3$1/>');
regex(/(<ref name=[^/>"]*)><\/ref>/gi, '$1/>');
regex(/(<ref name=[^/>"]*)>([\s\S]*)\1>([^\{\}]*)\1>([^\{\}]*)/gi, '$1A>$2$1B>$3$1C>$4');
}
var linkmap=[];
function ohc_protect_urlsOhc_protect_urls()
{
// protects only urls
// protect the rest (after purging urls inserted in ('website' or )'work' parameters)
regex(/((?:[\[=]\s*)(?:https?:|ftp:))([^\]\|\}]*)(\s*[\]|}])/gi, protect_function);
regex(/((?:Category|Image|File):)([^|\]]*)([|\]])/gi, protect_function); //protect file names from being changed
regex(/(\{\{(?:FAA-airport|harv\w*|sfn\w*|cite ?book|listen)\s?\|)([^\}]+)(\}\})/gi, protect_function);
regex(/(\|\s*(?:contribution|quote|title)\s*=)([^|}]+)([\|\}])/gi, protect_function);
//whitelisting -against changes made by generic regex in Ohc_sourcepub (e.g. Fast Company)
regex(/(\|\s*(?:journal|newspaper|periodical|website|work)\s*=\s*Fast )(Company\s*)([\|\}])/gi, protect_function);
}
{
//removes protection put in place by function ohc_protect_fmt (all cats, templates etc.)
regex(/⍌([0-9]+)⍍/g, function(x, n) {
var res = linkmap[n];
res = res.replace(/⍌([0-9]+)⍍/g, function(x, n) {
var txt=document.editform.wpTextbox1;
Ohc_remove_urls();
Ohc_duplicatedcite();
Ohc_protect_urls();
ohc_protect_urls();
Ohc_sources_prep();
// ohc_foreign_dates();
Ohc_unpipe();
Ohc_dab_news_sources();
Ohc_sourcename();
Ohc_sourcework();
Ohc_sourcepub();
Ohc_sourceagency();
Ohc_redo_pipe();
Ohc_publishers();
Ohc_sources_cleanup();
Ohc_unprotect_urls();
ohc_unprotect_urls();
Ohc_Source_edit_summary();
}
// removing references to other WP articles and 'external' WP links
regex(/<ref[^<>]*>[^<>]*\|[ ]*url ?= ?https?:\/\/(?:\w{2}\.wikipedia\.org\/wiki|(?:www\.|)(?:blogger|blogspot|facebook|findagrave|instagram|mailonline|myspace|twitter|x)\.com)\/[^<>]*<\/ref>/gi, '');
regex(/<ref>https?:\/\/(?:en\.wikipedia\.org\/wiki|(?:www\.|)(?:blogger|blogspot|facebook|findagrave|instagram|mailonline|myspace|twitter|x)\.com)\/[^\s\]<]*<\/ref>/gi, '');
regex(/<ref>\[https?:\/\/(?:en\.wikipedia\.org\/wiki|(?:www\.|)(?:blogger|blogspot|facebook|findagrave|instagram|mailonline|myspace|twitter|x)\.com)\/[^\s\]]*[ ]+[\w\d][^\]]*\]<\/ref>/gi, '');
regex(/\|[ ]*url[ ]*=[ ]*https?:\/\/(?:\w{2}\.wikipedia\.org\/wiki|(?:www\.|)(?:blogger|blogspot|facebook|findagrave|instagram|mailonline|myspace|twitter|x)\.com)[^\s\|\{\}<]*(?=[ ]*[|}])/gi, '');
regex(/[ ]\[https?:\/\/en\.wikipedia\.org\/wiki\/[^\s\]]*[ ]+([\w][^\]]*)\]/gi, ' [[$1]]');
}
//Note that this function may have unresolved bugs, particularly where the citation contains a numerical string with a '$' sign
regex(/<ref>((?:[\w,\s\.&]+\"?\[)https?:\/\/(?:[^|</]+\.)*(\w+)\.(?:(?:com?|org|net|gov|ac)(?:\.[a-z]{2}|))\/(?:[^<>|{}]*\D|)(\d{6,12})[^<>]*)(?=<\/ref>)/gi, "<ref name=$2_$3>$1"); //urls with non-date serial numbers
regex(/<ref>((?:[^<>]*\|\s*url\s*=|[\[\s]?)https?:\/\/(?:[^|</]+\.)*(\w+)\.(?:(?:com?|org|net|gov|ac)(?:\.[a-z]{2}|))\/(?:[^<>|{}]*\D|)(\d{6,12})[^<>]*)(?=<\/ref>)/gi, "<ref name=$2_$3>$1"); //urls with non-date serial numbers
regex(/<ref>((?:[^<>]*\|\s*url\s*=|[\[\s]?)https?:\/\/(?:[^|</]+\.)*([-\w]+)(?:\.[a-z]{2})\/[^<>|{}\d]*(\d{6,12})[^<>]*)(?=<\/ref>)/gi, "<ref name=$2_$3>$1"); //urls with non-date serial numbers
regex(/<ref>((?:[^<>]*\|\s*url\s*=|[\[\s]?)https?:\/\/(?:[^|</]+\.)*(reuters)\.com\/[^<>|{}\d]*(id\w{11})[^<>]*)(?=<\/ref>)/gi, "<ref name=$2_$3>$1"); //reuters urls with non-date serial numbers
regex(/<ref>((?:[^<>]*\|\s*url\s*=|[\[\s]?)https?:\/\/(?:[^|</]+\.)*([-\w]+)(?:\.[a-z]{2,3})\/[^<>|{}\d]*((?:19|20)\d\d)[-\/]((?:[0-1])\d|\w+)[-\/]((?:[0-3])\d)\/(\w+)[^<>]*)(?=<\/ref>)/gi, "<ref name=$2_$3$4$5_$6>$1"); //urls with non-date serial numbers
ohc_regex(/<ref>([^<>]*\|\s*url\s*=https?:\/\/(?:[^|</]+\.)*(\w+)\.(?:(?:com?|org|net|gov|ac|)(?:\.[a-z]{2}|))\/[^<>]*\|\s*date\s*=\s*@Day @Month @YYYY\s*[|}][^<>]*)(?=<\/ref>)/gi, "<ref name=$2_@Year@ZM@ZD>$1");
ohc_regex(/<ref>([^<>]*\|\s*url\s*=https?:\/\/(?:[^|</]+\.)*(\w+)\.(?:(?:com?|org|net|gov|ac|)(?:\.[a-z]{2}|))\/[^<>]*\|\s*date\s*=\s*@Month @Day, @YYYY\s*[|}][^<>]*)(?=<\/ref>)/gi, "<ref name=$2_@Year@ZM@ZD>$1"); //this line may cause unwarranted substitution of "$5" by a comma (e.g. in 2019–20 Hong Kong protests)
ohc_regex(/<ref>([^<>]*\|\s*url\s*=https?:\/\/(?:[^|</]+\.)*(\w+)\.(?:(?:com?|org|net|gov|ac|)(?:\.[a-z]{2}|))\/[^<>]*\|\s*date\s*=\s*=\s*((?:19|20)\d\d)[-\/]((?:[0-1])\d)[-\/]((?:[0-3])\d)\s*[|}][^<>]*)(?=<\/ref>)/gi, "<ref name=$2_$3$4$5>$1");
ohc_regex(/<ref>((?:[^<>]*\|\s*url\s*=|\[?)https?:\/\/(?:[^|<]+\.)*(\w+)\.(?:(?:com?|org|net|gov|ac|[a-z]{2})(?:\.[a-z]{2}|))\/[^<>|{}]+@YYYY[\/-]?@Month[\/-]?@Day[^<>]*)(?=<\/ref>)/gi, "<ref name=$2_@Year@ZM@ZD>$1"); //urls with embedded dates
}
| 