User:Ohconfucius/script/Sources.js: Difference between revisions

Revision as of 20:19, 16 June 2018

Revision as of 19:30, 6 October 2019

Line 57:

regex(/\[https?:\/\/\w{2}\.wikipedia\.org\/w[^\s\]]*[ ]+([\w][^\]]*)\]/gi, ' [[$1]]');

regex(/(<ref[^<>]*>[^<>]*\|[ ]*url ?=https?:\/\/(?:(?:www\.|)(?:facebook|myspace|twitter|mailonline|findagrave)\.com|dailymail\.co\.uk)\/[^<>{]*)(<\/ref>)/gi, '$1{{Primary source inline}}$2');

regex(/(<ref[^<>]*>[^<>]*\|[ ]*url ?=https?:\/\/(?:(?:www\.|)(?:myspace|findagrave)\.com)\/[^<>{]*)(<\/ref>)/gi, '$1{{Primary source inline}}$2');

regex(/(<ref>\s*https?:\/\/(?:(?:www\.|)(?:facebook|myspace|twitter|mailonline|findagrave)\.com|dailymail\.co\.uk)\/[^\s\]<]*)(<\/ref>)/gi, '$1{{Primary source inline}}$2');

regex(/(<ref>\s*\[https?:\/\/(?:(?:www\.|)(?:facebook|myspace|twitter|mailonline|findagrave)\.com|dailymail\.co\.uk)\/[^\s\]]*[ ]+[\w\d][^\]]*\])(<\/ref>)/gi, '$1{{Primary source inline}}$2');

Line 97 ⟶ 98:

regex(/(\|\s?url\s*\=)(www\.)(?=[|}\n])/gi, '$1http//$2'); //common cs1 error

regex(/(\|\s*date\s*=\s*)(?:not? |non-|un)date[ds]?\s*(?=[|}\n])/gi, '$1n.d.'); //common cs1 error

regex(/(\|\s?dead-?url=no?)(?=\s*[|}])/gi, ''); //common cs1 error (deprecated parameter)

regex(/\{\{wikinews ?(|2|cat(?:egory)?|has|par2?|portal|table|-inline)(\|[^\}]+|)\}\}\s*/gi, '');

Line 114 ⟶ 116:

// 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*)\'&#39;([^\|\{\}]+)\'&#39;/gi, '$1$2'); //rem &#39; in titles

regex(/(\|\s?publisher\s*\=\s*)\(([^\|\{\}]+)\)/gi, '$1$2'); //rem parenthetical publishers

Line 136 ⟶ 138:

// rem corporate designation

regex(/(\|\s?(?:author|publisher|work)\s*\=\s*[^\[|}]{1,40}),? (?:Inc|LL[CP]|Ltd|Limited|PLC|SA|(?:Snd\. |)Berhad)\.?(?=[ ]*\|\})/gi, '$1');

// correcting yahoo! corporate designation

Line 180 ⟶ 182:

// removing english language parameters

regex(/[ ]?\{\{en[- ]icon\}\}/gi, "");

regex(/\|[ ]*?language[ ]*?=[ ]*?en(?:-\w{2}|glish|)(?=[\s*[}|]+)/gi, "");

regex(/(\|[ ]*?language[ ]*?=[ ]*?)\{\{(\w{2})(?:[- ](?:icon|UK|GB|US)|)\}\}/gi, ""); // removing icon template from within "|language=" parameter

Line 192 ⟶ 194:

//'Accessed'/'Obtained' -> 'Retrieved'

ohc_regex(/(?:[\.,;][ ]*(?:url |link |last |)(?:Retrieved|Accessed|Obtained))(?: on(?:line|)|):? (@month|@dd|@yyyy)(?=\D)/gi, '. Retrieved $1');

ohc_regex(/(\w|\])(?:[ ]*(?:url |link |last |)(?:Retrieved|Accessed|Obtained))(?: on(?:line|)|):? (@month|@dd|@yyyy)(?=\D)/gi, '$1. Retrieved $2');

// (disabling for persistent errors) ohc_regex(/(?:Retrieved|Accessed)(?: on(?:line|)|):? (@Month\s@DD,?\s@YYYY|@DD\s@Month\s@YYYY|@yyyy-@mm-@dd)(?=\D)/gi, 'Retrieved $1');

Line 387 ⟶ 389:

regex(/\|\s?(?:publisher|website|work)(\s?\=MTV)\|\s?publisher\s*\=\s*(?:MTV Networks|Viacom)/gi, '|publisher$1=');

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

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

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

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

Line 401 ⟶ 403:

// toggling domains within |website= parameter

// regex(/(\|\s?(?:work|website)\s*\=\s*)(\w+\.(?:com?|org|net|)(?:\.[a-z]{2}|))(?=\s*[|}])/gi, '$1\'\'$2\'\'');

// reordering 'work' and 'publisher'; reordering 'work' and 'website'