Jump to content

User:Ohconfucius/script/Sources.js

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Ohconfucius (talk | contribs) at 00:03, 30 November 2012 (new code). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.
(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)
Note: After saving, you have to bypass your browser's cache to see the changes. Google Chrome, Firefox, Microsoft Edge and Safari: Hold down the ⇧ Shift key and click the Reload toolbar button. For details and instructions about other browsers, see Wikipedia:Bypass your cache.
// *********************************************************************************************

//This is a test (non-production) script, and may have untested errors. Please exercise due care should you decide to use it.

// *********************************************************************************************

/*************
*** Regex menu framework
*** by [[m:user:Pathoschild]] <http://meta.wikimedia.org/wiki/User:Pathoschild/Scripts/Regex_menu_framework>
***	- adds a sidebar menu of user-defined scripts.
*************/
importScriptURI('http://meta.wikimedia.org/w/index.php?title=User:Pathoschild/Scripts/Regex_menu_framework.js&action=raw&ctype=text/javascript');
importScript("User:Ohconfucius/test/Sources_subscript1.js");
importScript("User:Ohconfucius/test/Sources_subscript2.js");
importScript("User:Ohconfucius/test/Sources_subscript3.js");
 
function Ohc_linkspam() {
 var txt=document.editform.wpTextbox1;
 
	txt.value=txt.value.replace(/([^>\*][ ]?)\[https?:\/\/[^\s\]]*[ ]([\w\d][^\]]*)\](?![ ]*[\n\-]+)/gi, '$1$2');
}




function Ohc_sources_prep() {
 var txt=document.editform.wpTextbox1;

// removing references to other WP articles
	txt.value=txt.value.replace(/<ref>https?:\/\/en\.wikipedia\.org\/wiki\/[^\s\]<]*<\/ref>/gi, '');
	txt.value=txt.value.replace(/<ref>\[https?:\/\/en\.wikipedia\.org\/wiki\/[^\s\]]*[ ][\w\d][^\]]*\]<\/ref>/gi, '');

// removing external links within publisher/journal/work fields
	txt.value=txt.value.replace(/(\|\s?(?:newspaper|work|journal|publisher)\s*\=\s*)\[https?:\/\/[^\s\]]*\s([\w\d][^\]]*)\]/gi, '$1$2');
	txt.value=txt.value.replace(/(\|\s?author(?:link\d?|)\s*\=\s*)\[https?:\/\/[^\s\]]*\s([\w\d][^\]]*)\]/gi, '$1$2');
	txt.value=txt.value.replace(/(\|\s?(?:newspaper|work|journal|publisher|author)\s*\=\s*)www\.([\w\d][^\|\}]*)(?=[\|\}])/gi, '$1$2');
	txt.value=txt.value.replace(/(\|\s?author(?:link\d?|)\s*\=\s*)www\.([\w\d][^\|\}]*)(?=[\|\}])/gi, '$1$2');

	txt.value=txt.value.replace(/(\|\s?author\s*\=\s*)(?:wire staff|staff reporters?|)[ ]*(?=[\|\}])/gi, '');
	txt.value=txt.value.replace(/(\|\s?author\s*\=\s*)([A-Z][a-z]*(?: [A-Z][a-z]*)*) (?:wire staff|(?:staff |)reporters?)[ ]*(?=[\|\}])/gi, '$1$2');
//		txt.value=txt.value.replace(/\{\{[ ]*cite /g, '{{Cite ');

	txt.value=txt.value.replace(/\{\{wikinews(|2|cat|has|portal|table|-inline)(\|[^\}]+|)\}\}\s*/gi, '');
	txt.value=txt.value.replace(/\*[ ]*\{\{Find a Grave\|\d{4}(\|[^\}]+|)\}\}\s*/gi, '');

//citation template fixes
    // rem copyright assertion
	txt.value=txt.value.replace(/(\|\s?publisher\s*\=\s*)(?:\[\[copyright(?:\|©|)\]\])\s?/gi, '$1');
	txt.value=txt.value.replace(/(\|\s?publisher\s*\=\s*)(?:©|copyright)\s?/gi, '$1');

	txt.value=txt.value.replace(/(?:\|\s?publisher(\s*\=\s*)\'\'\[\[([^\]]{1,40})\]\]\'\')/gi, '|work$1[[$2]]');
	txt.value=txt.value.replace(/(?:\|\s?publisher(\s*\=\s*)\'\'([^\|\}]{1,40})\'\')(?=\s*[\}\|])/gi, '|work$1$2');
	txt.value=txt.value.replace(/(?:\|\s?(?:newspaper|work)(\s*\=\s*)\'\'\[\[([^\]]{1,40})\]\]\'\')/gi, '|publisher$1[[$2]]');
	txt.value=txt.value.replace(/(?:\|\s?(?:newspaper|work)(\s*\=\s*)\'\'([^\|\}]{1,40})\'\')/gi, '|publisher$1$2');

    // rem corporate designation
	txt.value=txt.value.replace(/(\|\s?publisher\s*\=\s*[^\[\|\}]{1,40}), (?:Inc|LL[CP]|Ltd|PLC|SA)\.?(?=[ ]*\|\})/gi, '$1');
	txt.value=txt.value.replace(/(\|\s?publisher\s*\=\s*[^\[\|\}]{1,40}) (?:Inc|LL[CP]|Ltd|PLC|SA)\.?(?=[ ]*\|\})/gi, '$1');

    // rem unnecessary quote marks
	txt.value=txt.value.replace(/(\|\s?title\s*\=\s*)["“]([^\|]+)["”](?=\s?[\|\}])/gi, '$1$2');
	txt.value=txt.value.replace(/(\|\s?title\s*\=\s*)['‘]([^\|]+)['’](?=\s?[\|\}])/gi, '$1$2');
    // repl double 'in-title' quote marks with single quotes
	txt.value=txt.value.replace(/(\|\s?title\s*\=\s*[\w ]* )["“]((?:\w[\w]* )+(?:\w[\w]*))["”]([^\|]+|)(?=\s?[\|\}])/gi, '$1\'$2\'$3');

    // removing blank parameters
         regex(/(?:\|[ ]*(?:first\d?|agency|(?:co|)authors?\d?|archive(?:url|date)|journal|publisher|newspaper|work|(?:access|)date|doi|month|year|location|format|language|last\d?|publisher|authorlink\d?|volume|issue|pages?|firstn|lastn|authorn-link|editor|editorn|editorn-last|editorn-first|editor-link|editorn-link|others|nopp|chapter|trans_chapter|chapterurl|quote|ref|laysummary|laydate|separator|postscript|lastauthoramp|issn|oclc|pmid|pmd|bibcode|id)[ ]*=[\s]*)(?=[\}\|])/gi, '');

    //rem underlining within certain fields
	txt.value=txt.value.replace(/(\|\s?(?:journal|newspaper|periodical|publisher|work)\s*\=\s*)<u>([^\|\}]*)<\/u>/gi, '$1');

    //rem linking within locations field
         regex(/(\|[ ]*?location=[ ]*?)\[\[([^\|\]]+?)\]\](?:(,? )\[\[([^\|\]]+?)\]\]|)([ ]{0,1})/gi, '$1$2$3$4$5');
         regex(/(\|[ ]*?location=[ ]*?)\[\[(?:[^\|\]]+?\|)([\w\s\,]+?)\]\](?:(,? )\[\[([^\|\]]+?)\]\]|)([ ]{0,1})/gi, '$1$2$3$4$5');
         regex(/\[\[(New York)\]\]/gi, '$1');

    // eliminating time of day
    ohc_regex(/(\|[ ]*author[ ]*=[ ]*)(?:posted|published)(?: by| on|)[\s:](?=\w)/gi, "$1");
    regex(/(\|[ ]*(?:date|archivedate|accessdate|author)[ ]*=[ ]*)[0-2]?\d:[0-5]\d(?:[ ]|&nbsp;)(?:[ap]m |[ap]\.m\. |)([A-Z]{1,2}T|UTC)[\.,]?[ ]?/gi, "$1");

    // eliminating days of the week
    regex(/(\|[ ]*(?:date|archivedate|accessdate|author)[ ]*=[ ]*)(?:(?:Mon|Tues|Wednes|Thurs|Fri|Satur|Sun)day,?)\s/gi, "$1");
    regex(/(\|[ ]*(?:date|archivedate|accessdate|author)[ ]*=[ ]*)(?:(?:Mon|Tues?|Wed|Thur?|Fri|Sat|Sun)[\.,]?)\s/gi, "$1");

}

function Ohc_dab_news_sources() {
 var txt=document.editform.wpTextbox1;

//pre-dab of piped sources
//         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 \(United Kingdom\)$2');
         regex(/(\[\[)Daily Star \((?:British|UK)\)(\|)/gi, '$1Daily Star \(United Kingdom\)$2');
         regex(/(\[\[)(?:Calcutta Telegraph|The Telegraph \((?:kolkatt?a|India)\)|(?:The |)Telegraph India|Telegraphindia\.com)(\|)/gi, '$1The Telegraph \(Calcutta\)$2');
         regex(/(\[\[)Dawn(?:, Karachi| newspaper|\.com| \((?:Newspaper|Pakistan)\))(\|)/gi, '$1Dawn \(newspaper\)$2');
         regex(/(\[\[The Pioneer)(?:, Karachi| newspaper| \((?:indian newspaper)\))(\|)/gi, '$1 \(Indian newspaper\)$2');
         regex(/(\[\[)dailypioneer.com(\|)/gi, '$1The Pioneer \(Indian newspaper\)$2');

//unlinking of piped sources to source and location
         regex(/(?:author|agency|publisher)(\s?=\s?\[\[(Evening Standard))\|[\w,]*(\]\])/gi, 'work$1$2$3|location=London');

         regex(/((?:journal|newspaper|periodical|work)\s?=\s?\[\[(Daily News) \(New York\)\|)(?:[\w, ]*)(\]\])/gi, '$1$2$3 |location=New York');
         regex(/(?:author|agency|publisher)(\s?=\s?\[\[(Daily News) \(New York\)\|)(?:[\w, ]*)(\]\])/gi, 'work$1$2$3 |location=New York');
         regex(/((?:journal|newspaper|periodical|work)\s?=\s?\[\[(The Sun|Daily Star) \((United Kingdom)\)\|)(?:[\w, ]*)(\]\])/gi, '$1$2$4 |location=$3');
         regex(/(?:author|agency|publisher)(\s?=\s?\[\[(The Sun|Daily Star) \((United Kingdom)\)\|)(?:[\w, ]*)(\]\])/gi, 'work$1$2$4 |location=$3');
         regex(/((?:journal|newspaper|periodical|work)\s?=\s?\[\[(The Telegraph) \(Calcutta\)\|)(?:[\w, ]*)(\]\])/gi, '$1$2$4 |location=$3');
         regex(/((?:author|agency|publisher)\s*\=\s*\[\[(The Telegraph) \(Calcutta\)\|)(?:[\w, ]*)(\]\])/gi, 'work$1$2$4 |location=$3');
         regex(/(=[ ]*\[\[)(?:[BE]SPN ?(?:USA|HD|Network|the ocho|\(United States\))|E.S.P.N.|(?:The |)Entertainment (?:and |)Sports Programming Network)(?:\|[\w, ]*)(\]\])/gi, '$1ESPN$2');

         regex(/((?:journal|newspaper|periodical|work)\s?=\s?\[\[(Evening Standard)\|)(?:[\w, ]*)(\]\])/gi, '$1$2$3 |location=London');
         regex(/(?:author|agency|publisher)(\s?=\s?\[\[(Evening Standard))\|[\w, ]*(\]\])/gi, 'work$1$2$3|location=London');

//         regex(/(?:\|\s?(?:work|publisher)\s*\=\s*)(?:\[\[The Pioneer \(Indian newspaper\)\|(The Pioneer)\]\])(?=[\s\.]*[\|\}])/gi, '|work=$1 |location=India');   //


}

function Ohc_publishers() {
 var txt=document.editform.wpTextbox1;

//linked publishing houses
	txt.value=txt.value.replace(/(?:\|\s?(newspaper|work|publisher)\s*\=\s*\[?\[?Hachette Filipacchi Médias\|(Hachette Filipacchi) \(UK\) Ltd\]?\]?)(?=[\s\.]*[\|\}])/gi, '');
	txt.value=txt.value.replace(/(?:\|\s?(newspaper|work|publisher)\s*\=\s*\[?\[?(John Fairfax (and Sons Ltd\.?|Holdings)|Fairfax(?: Media( Limited)| Digital| newspapers))\]?\]?)(?=[\s\.]*[\|\}])/gi, '');
	txt.value=txt.value.replace(/(?:\|\s?publisher\s*\=\s*(\[\[|)(Associated Newspapers|Condé Nast Publications|Fairfax Media|Gannett Company|(Guardian|Telegraph) Media Group|(?:Guardian|Independent) News (?:and|&) Media|Imdb Inc\.?|IDG|IPC Media|MTV Networks|(The |)(?:Washington Post|(?:New York|Seattle) Times) Company|News (?:Corporation|International|Limited)|Prometheus Global Media|Tribune Company|Trinity Mirror|Times Newspapers (?:Limited|Ltd.?)|Nielsen (?: Media Research|Business Media(, Inc\.?|))|Rovi Corporation|Viacom|Time (?:Warner ?|)Inc\.?)(\]\]|))(?=[\s\.]*[\|\}])/gi, '');

}

function Ohc_sources_cleanup() {
 var txt=document.editform.wpTextbox1;

// relocating 'location' parameter outside citation templates
         //sources without dab but with inserted locator
         regex(/(''Daily News) \|location=(New York)('')/gi, '$1$3 \($2\)');
         regex(/(''\[\[Daily News\]\]) \|location=(New York)('')/gi, '$1$3 \($2\)');
         regex(/(\[\[|\|)(Daily News) \|location=(New York)(\]\])/gi, '$1$2$4$3');
         regex(/(''Evening Standard) \|location=(London)('')/gi, '$1$3 \($2\)');
         regex(/(''\[\[Evening Standard\]\]) \|location=(London) ?('')/gi, '$1$3 \($2\)');
         regex(/(\[\[|\|)(Evening Standard)( \|location=London)(\]\])/gi, '$1$2$4$3');

// displacing location-dab (in parentheses)
         regex(/( \|location=(?:New York|UK))(\]\])/gi, '$2$1');

         // The following regexes for dab-links are in sets of four. If changing, please ensure all sets are changed
         regex(/(=[ ]*(?:The ?|)[A-Z]\w*(?: [A-Z]\w*|)) \((South Africa)(?:n newspaper|)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''(?:The ?|)[A-Z]\w*(?: [A-Z]\w*|)) \((South Africa)(?:n newspaper|)\)(''[\.,;])/g, '$1$3$2');
         regex(/(\[\[((?:The ?|)[A-Z]\w*(?: [A-Z]\w*|)))( \(South Africa(?:n newspaper|)\))(\]\][\.,;]?)/g, '$1$3|$2$4');
         regex(/(\|)((?:The ?|)[A-Z]\w*(?: [A-Z]\w*|))(?: \((South Africa)(?:n newspaper|)\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*Daily Record) \((Scotland)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''Daily Record) \((Scotland)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(Daily Record)( \(Scotland\))(\]\][\.,;]?)/g, '$1$2$3|$2$4');
         regex(/(\|)(Daily Record)(?: \(Scotland\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*Dawn) \((newspaper)\)([ ]*[\|\}])/g, '$1|location=Pakistan$3');
         regex(/(''Dawn) \((newspaper)\)('')/g, '$1$3 \(Pakistan\)');
         regex(/(\[\[)(Dawn)( \(newspaper\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(Dawn)(?: \(newspaper\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*(?:Daily Star)) \((United Kingdom)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''(?:Daily Star)) \((United Kingdom)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(Daily Star)( \(United Kingdom\))(\]\][\.,;]?)/g, '$1$2$3|$2$4');
         regex(/(\|)(Daily Star)(?: \(United Kingdom\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*El Mundo) \((Columbia|Spain)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''El Mundo) \((Columbia|Spain)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(El Mundo)( \(Columbia|Spain\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(El Mundo)(?: \((?:Columbia|Spain)\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Daily Star) \((Lebanon)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''The Daily Star) \((Lebanon)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(The Daily Star)( \(Lebanon\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Daily Star)(?: \(Lebanon\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Gazette) \((Montreal)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''The Gazette) \((Montreal)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(The Gazette)( \(Montreal\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Gazette)(?: \(Montreal\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Herald) \((Glasgow)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''The Herald) \((Glasgow)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(The Herald)( \(Glasgow\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Herald)(?: \(Glasgow\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Nation) \((Malawi|Nigeria|Thailand)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''The Nation) \((Malawi|Nigeria|Pakistan|Thailand)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(The Nation)( \((?:Malawi|Nigeria|Pakistan|Thailand)\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Nation)(?: \((?:Malawi|Nigeria|Pakistan|Thailand)\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*La Presse) \((Canadian newspaper)\)([ ]*[\|\}])/g, '$1|location=Canada$3');
         regex(/(''La Presse) \((Canadian newspaper)\)('')/g, '$1$3 \(Canada\)');
         regex(/(\[\[)(La Presse)( \(Canadian newspaper\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(La Presse)(?: \(Canadian newspaper\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*Les Échos) \((France)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''Les Échos) \((France)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(Les Échos)( \(France\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(Les Échos)(?: \(France\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*Panorama) \((Gibraltar)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''Panorama) \((Gibraltar)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(Panorama)( \(Gibraltar\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(Panorama)(?: \(Gibraltar\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Pioneer) \((Indian newspaper)\)([ ]*[\|\}])/g, '$1|location=India$3');
         regex(/(''The Pioneer) \((Indian newspaper)\)('')/g, '$1$3 \(India\)');
         regex(/(\[\[)(The Pioneer)( \(Indian newspaper\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Pioneer)(?: \(Indian newspaper\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Sun) \((Hong Kong|Malaysia|Nigeria|United Kingdom)\)([ ]*[\|\}])/g, '$1|location=$2$3');
         regex(/(''The Sun) \((Hong Kong|Malaysia|Nigeria|United Kingdom)\)('')/g, '$1$3 \($2\)');
         regex(/(\[\[)(The Sun)( \((?:Hong Kong|Malaysia|Nigeria|United Kingdom)\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Sun)(?: \((?:Hong Kong|Malaysia|Nigeria|United Kingdom)\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*The Telegraph) \((Calcutta)\)([ ]*[\|\}])/g, '$1|location=Calcutta$3');
         regex(/(''The Telegraph) \((Calcutta)\)('')/g, '$1$3 \(Calcutta\)');
         regex(/(\[\[)(The Telegraph)( \(Calcutta\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(The Telegraph)(?: \(Calcutta\))(\]\])/g, '$1$2$3');
         regex(/(=[ ]*Vogue) \((British magazine)\)([ ]*[\|\}])/g, '$1|location=UK$3');
         regex(/(''Vogue) \((British magazine)\)('')/g, '$1$3 \(UK\)');
         regex(/(\[\[)(Vogue)( \(British magazine\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(Vogue)(?: \(British magazine\))(\]\])/g, '$1$2$3');

         regex(/(=(?:ABC|Sport)) \((newspaper)\)([ ]*[\|\}])/g, '$1|location=Spain$3');
         regex(/(''(?:ABC|Sport)) \((newspaper)\)('')/g, '$1$3 \(Spain\)');
         regex(/(\[\[)(ABC|Sport)( \(newspaper\))(\]\])/g, '$1$2$3|$2$4');
         regex(/(\|)(ABC|Sport)(?: \(newspaper\))(\]\])/g, '$1$2$3');

//         regex(/(=(?:Business Day|City Press|Daily News|Daily Voice|Independent Online|New Age|Post|Table Talk|The Citizen|The Mercury|The New Age|The Star|The Sunday Independent|The Sunday Times|The Times|The Witness|The World)) \((South Africa)(?:n newspaper|)\)([ ]*[\|\}])/g, '$1|location=$2$3');
//         regex(/(''(?:Business Day|City Press|Daily News|Daily Voice|Independent Online|New Age|Post|Table Talk|The Citizen|The Mercury|The New Age|The Star|The Sunday Independent|The Sunday Times|The Times|The Witness|The World)) \((South Africa)(?:n newspaper|)\)('')/g, '$1$3 \($2\)');
//         regex(/(\[\[)(Business Day|City Press|Daily News|Daily Voice|Independent Online|New Age|Post|Table Talk|The Citizen|The Mercury|The New Age|The Star|The Sunday Independent|The Sunday Times|The Times|The Witness|The World)( \(South Africa(?:n newspaper|)\))(\]\])/g, '$1$2$3|$2$4');
//         regex(/(\|)(Business Day|City Press|Daily News|Daily Voice|Independent Online|New Age|Post|Table Talk|The Citizen|The Mercury|The New Age|The Star|The Sunday Independent|The Sunday Times|The Times|The Witness|The World)(?: \(South Africa(?:n newspaper|)\))(\]\])/g, '$1$2$3');

         regex(/(''\[\[)(Nature|Science)(\]\]'')/g, '$1$2 \(journal\)|$2$3');
         regex(/(''\[\[)(Salon)(\]\]'')/g, '$1$2 \(website\)|$2$3');

// removing redundancies
         regex(/\|[ ]?language[ ]?\=[ ]?English[ ]*?(?=[\|\}])/gi, '');  //note: adjusted for false positive in infoboxes books
         regex(/- [\w]*\.com[ ]*\|/gi, '|');
         regex(/(.) – Google [^ \]]*(\][\.,;]) Books\.google\.\w{2,3}(\.| )/gi, '$1$2Google Books$3');
         regex(/(.) at Discogs(\][\.,;]) Discogs\.com(\.| )/gi, '$1$2Discogs$3');
         regex(/\|\s?author\s?\=(?:posted|publishe[dr]|written)\s?(?:by|on)\s/gi, '|author=');
         regex(/\|\s?(?:work|publisher)(\s?\=MTV)\|\s?publisher\s*\=\s*(?:MTV Networks|Viacom)/gi, '|publisher$1=');

         regex(/\|\s?(?:publisher|work)\s*\=\s*(?:BBC|BBC News(?: Online|))\s*(\|[^}<>]*|)\|\s?publisher\s*\=\s*(?:BBC|BBC News(?: Online|)|British Broadcasting Corporation)(?=[\s\.]*[\|\}])/g, '|publisher=BBC News $1');
         regex(/\|\s?(?:publisher|work)\s*\=\s*(BBC Sports?)\s*(\|[^}<>]*|)\|\s?publisher\s*\=\s*(?:BBC|BBC News(?: Online|)|British Broadcasting Corporation)(?=[\s\.]*[\|\}])/g, '|publisher=$1$2');

// removing publishers less well-known than their titles
         regex(/(\|\s?work\s*\=\s*(?:Time|People)\s*(?:\|[^}<>]*|))\|\s?publisher\s*\=\s*Time (?:Warner ?|)Inc.?(?=[\s\.]*[\|\}])/g, '$1');
         regex(/(\|\s?work\s*\=\s*(?:\[\[|)The New York Times(?:\]\]|)\s*)(\|[^}<>]*|)\|\s?publisher\s*\=\s*The New York Times Company(?=[\s\.]*[\|\}])/g, '$1');
         regex(/(\|\s?work\s*\=\s*(?:\[\[|)The (?:Daily Telegraph|Guardian)(?:\]\]|)\s*(?:\|[^}<>]*|))\|\s?publisher\s*\=\s*(?:\[\[|)(?:Telegraph|Guardian) Media Group(?:\]\]|)(?=[\s\.]*[\|\}])/g, '$1');
         regex(/(\|\s?publisher\s?\=MTV\|\s?)publisher\s*\=\s*(?:MTV Networks|Viacom)/gi, '$1=');

         regex(/(?:\|publisher=Turner Sports Interactive, Inc)\.? ?\|publisher=(NBA)(?= ?\|)/gi, '$1');
         regex(/(\|publisher=NBA) ?\|publisher=(?:Turner Sports Interactive, Inc)\.?(?= ?\|)/gi, '$1');

//per [[Help:Citation Style 1#Elements not included]]
         regex(/(?:-[ ]*Google Books[ ]*(\|[^}]*|)|)\|\s?publisher\s*\=\s*Google Books(?=[\s\.]*[\|\}])/g, '');
         regex(/\|\s?publisher\s*\=\s*(?:Project Gutenberg|Scribd)(?=[\s\.]*[\|\}])/g, '');

// removing identical/similar entries in 'work' and 'publisher'
         regex(/\|\s?work\s*\=\s*([^\|\}<>]*)(\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\1(?:\.com|)(?=[\s\.]*[\|\}])/g, '|work=$1$2');
         regex(/\|\s?work\s*\=\s*([^\|\}<>]*)(?:\.com|)(\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\1(?=[\s\.]*[\|\}])/g, '|work=$1$2');
         regex(/\|\s?work\s*\=\s*\[\[([^\|\}<>]*)\]\](\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\1(?:\.com|)(?=[\s\.]*[\|\}])/g, '|work=[[$1]]$2');
         regex(/\|\s?work\s*\=\s*([^\|\}<>]*)(?:\.com|)(\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\[\[\1\]\](?=[\s\.]*[\|\}])/g, '|work=$1$2');

         regex(/\|\s?publisher\s*\=\s*([^\|\}<>]*)(\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\1(?:\.com|)(?=[\s\.]*[\|\}])/g, '|publisher=$1$2');
         regex(/\|\s?publisher\s*\=\s*([^\|\}<>]*)(?:\.com|)(\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\1(?=[\s\.]*[\|\}])/g, '|publisher=$1$2');
         regex(/\|\s?publisher\s*\=\s*\[\[([^\|\}<>]*)\]\](\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\1(?:\.com|)(?=[\s\.]*[\|\}])/g, '|publisher=[[$1]]$2');
         regex(/\|\s?publisher\s*\=\s*([^\|\}<>]*)(?:\.com|)(\s?\|[^}<>]*|)\|\s?(?:publisher|work)\s*\=\s*\[\[\1\]\](?=[\s\.]*[\|\}])/g, '|publisher=$1$2');

         regex(/\|\s?location\s*\=\s*New York(?: City|)\s*(\|[^}<>]*|)\|\s?location\s*\=\s*(New York(?: City|)|USA)(?=[\s\.]*[\|\}])/g, '|location=New York $1');

         regex(/(?:\|[ ]*?location=[^\[\]\|]*)(\|[ ]*?location=[^\[\]\|\}]*)(?=[\|\}])+/gi, '$1');
         regex(/(\|[ ]*?publisher=[^\[\]\|]*)(?:\|[ ]*?publisher=[^\[\]\|\}]*)(?=[\|\}])+/gi, '$1');
         regex(/(\|[ ]*?work=[^\[\]\|]*)(?:\|[ ]*?work=[^\[\]\|\}]*)(?=[\|\}])+/gi, '$1');

         regex(/(\|[ ]*?author=)(?:(?:Mon|Tues|Wednes|Thurs|Fri|Satur|Sun)day,? ?)(?=[^\]\|\}]*\|)/gi, '$1');

         regex(/( &#124; [\w, ]*?)(?=[ ]&#124)/gi, '');
//         regex(/( \| [^=\|\{\}\]]*?)(?=[ ]\|)/gi, ''); //disabled 3 October 2012 - false positive removal of elements in wikitable
         regex(/( &#124; News)(?=[ ]?[&\|])/gi, '');
         regex(/( &#124; (?:Football|Latest)(?: News|))(?=[ ]?[&\|])/gi, '');
         regex(/\|\s?title\s*\=\s*BBC (?:News|Sport)\s?(?:–|&#124; )\s?/gi, '|title=');

         regex(/(DOC|PDF)\) \./gi, '$1).');

// removing artefacts (outside of citation templates)
         regex(/([\w]+\'\')\.(?:co(?:m|m?\.\w{2})|\.\w{2})[ ]/gi, '$1. ');

//dynamic columns for reflists; remove scroll bar
	regex(/(={2,4}[\n\r])[\r\n\s]*(?:<div class="\w*" [^>]*)>([\S\s]*)<\/div>/g, '$1$2'); 	
	regex(/(?:\{\{[Rr]eflist\}\}|<[Rr]eferences ?\/>)/g, '{{reflist|colwidth=30em}}');

}

function Ohc_sourceunlink() {
 var txt=document.editform.wpTextbox1;

//removal of all links from sources
//rem linking within citation template parameters
         regex(/(\|[ ]*?(?:author|agency|publisher|journal|newspaper|periodical|work)=[ ]*?)\[\[([^\|\]]+?)\]\](?:(,? )\[\[([^\|\]]+?)\]\]|)([ ]{0,1})/gi, '$1$2$3$4$5');
         regex(/(\|[ ]*?(?:author|agency|publisher|journal|newspaper|periodical|work)=[ ]*?)\[\[(?:[^\|\]]+?\|)([\w\s\,]+?)\]\](?:(,? )\[\[([^\|\]]+?)\]\]|)([ ]{0,1})/gi, '$1$2$3$4$5');

//rem other linking within refs tags
         regex(/(<ref[^>]*>[^<]+?[\]\.,;]\s+)\[\[(?:[^\|\]<]*\||)([^\|\]<]*)(?: online|)\]\]([^<]*?<\/ref>)\) \./gi, '$1$2$3).');
         regex(/(<ref[^>]*>[^<]+?[\]\.,;]\s+\'\')\[\[(?:[^\|\]<]*\||)([^\|\]<]*)(?: online|)\]\](\'\'[^<]*?<\/ref>)\) \./gi, '$1$2$3).');
}

/** ------------------------------------------------------------------------ **/
/// PROTECTION BY STRING SUBSTITUTION

var linkmap=[];
function ohc_protect_linkspam()
{
    // protects everything within reference tags 
    // the sensitive part is stored and replaced with a unique identifier,
    // which is later replaced with the stored part.
 
    var protect_function = function(s, begin, replace, end) {
        linkmap.push(replace);
        return begin + "⍌"+(linkmap.length-1)+"⍍" + end;
    };

    regex(/(<ref[^>]*?>)(.*?)(<\/ref>)/gi, protect_function);
    regex(/(\*[ ]?\[(?:https?:|ftp:))([^\]]*)(\])/gi, protect_function);

}


function ohc_unprotect_linkspam()
{

    //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 res = linkmap[n];
            res = res.replace(/⍌([0-9]+)⍍/g, function(x, n) {
                var res = linkmap[n];
                res = res.replace(/⍌([0-9]+)⍍/g, function(x, n) {
                    return linkmap[n];
                });
                return res;
            });
            return res;
        });
        return res;
    });
}

var linkmap=[];
function ohc_protect_urls()
{
    // protects only urls 
    // the sensitive part is stored and replaced with a unique identifier,
    // which is later replaced with the stored part.
 
    var protect_function = function(s, begin, replace, end) {
        linkmap.push(replace);
        return begin + "⍌"+(linkmap.length-1)+"⍍" + end;
    };

    regex(/(https?:|ftp:)([^\]\|]*)([\]\|])/gi, protect_function);
    regex(/(\{\{cite ?book\s?\|)([^\}]+)(\})/gi, protect_function);

}


function ohc_unprotect_urls()
{

    //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 res = linkmap[n];
            res = res.replace(/⍌([0-9]+)⍍/g, function(x, n) {
                var res = linkmap[n];
                res = res.replace(/⍌([0-9]+)⍍/g, function(x, n) {
                    return linkmap[n];
                });
                return res;
            });
            return res;
        });
        return res;
    });
}

/** ------------------------------------------------------------------------ **/
function Ohc_Source_edit_summary(){
	//Add a tag to the summary box
	setoptions(minor='true'); 		
	setreason('per [[Help:Citation Style 1]] by [[User:Ohconfucius/script|script]]', 'append');
	doaction('diff');

}

function Ohc_linkspam_driver() {
 var txt=document.editform.wpTextbox1;

	ohc_protect_linkspam();
	Ohc_linkspam();
	ohc_unprotect_linkspam();
	setreason('rem [[WP:Linkspam|linkspam]]', 'append');
}

function Ohc_ref_format_new() {
 var txt=document.editform.wpTextbox1;

      ohc_protect_urls();
      Ohc_sources_prep();
      Ohc_unpipe();
      Ohc_dab_news_sources();
      Ohc_sourcename();
      Ohc_sourcework();
      Ohc_sourcepub();
      Ohc_sourceagency();
      Ohc_redo_pipe();
      Ohc_sources_cleanup();
      ohc_unprotect_urls();


      Ohc_Source_edit_summary();
}

function Ohc_ref_format_driver() {
 var txt=document.editform.wpTextbox1;

	Ohc_ref_format();
	Ohc_Source_edit_summary();
}

addOnloadHook(function () {
 if(document.forms.editform) {
//  addPortletLink('p-tb', 'javascript:function_name()', 'Button name', 't-dmy', 'Hover text', '', '');

  addPortletLink('p-tb', 'javascript:Ohc_linkspam_driver()', 'Linkspam', 'rm-linkspam', 'removes linkspam in running text', '', '');
  addPortletLink('p-tb', 'javascript:Ohc_ref_format_driver()', 'Fix news sources', 't-citefix', 'format citations', '', '');
  addPortletLink('p-tb', 'javascript:Ohc_publishers()', 'Rem publishers', 't-citefix', 'Removing certain publishers fields', '', '');
//  addPortletLink('p-tb', 'javascript:Ohc_sourcename()', 'Align source name', 't-citefix', 'Corrects source name – subscript1', '', '');
//  addPortletLink('p-tb', 'javascript:Ohc_sourcework()', 'Cleanup WORK', 't-citefix', 'Cleanup and reclassifies as WORK – subscript2', '', '');
//  addPortletLink('p-tb', 'javascript:Ohc_sourcepub()', 'Cleanup publisher', 't-citefix', 'Cleanup and reclassifies as PUBLISHER – subscript2', '', '');
//  addPortletLink('p-tb', 'javascript:Ohc_sources_cleanup()', 'Final cleanup', 't-citefix', 'Cleanup after script actions', '', '');
//  addPortletLink('p-tb', 'javascript:Ohc_sourceunlink()', 'Unlink source name', 't-citefix', 'Unlinks source', '', '');
  addPortletLink('p-tb', 'javascript:Ohc_ref_format_new()', 'Fix sources', 't-citefix', 'Run entire new module', '', '');
  }
});