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

Revision as of 08:07, 1 April 2015

Revision as of 00:19, 4 April 2015

Line 19:

importScript("User:Ohconfucius/test/Sources_subscript3.js"); //link-fixing, dabbing etc

importScript("User:Ohconfucius/script/foreigndates.js");

function Ohc_add_ref_tagsOhc_linkspam() {

var txt=document.editform.wpTextbox1;

txt.value=txt.value.replace(/([^>\*][ ]?)(\[https?:\/\/[^\s\[\]]*[ ]([\'\w\d][^\[\]]*)\](?![ ]*[<\n\-]+)/gi, '$1<ref>$2</ref>');

Line 41:

// removing references to other WP articles and 'external' WP links

regex(/<ref[^<>]*>[^<>]*\|[ ]*url ?=https?:\/\/(?:\w{2}\.wikipedia\.org\/wiki|(?:www\.|)(?:facebook|myspace|twitter)\.com)\/[^<>]*<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP:SPS (Twitter, FB, WP)-->');

regex(/<ref>\s*https?:\/\/(?:\w{2}\.wikipedia\.org\/wiki|(?:www\.|)(?:facebook|myspace)\.com)\/[^\s\]<]*<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP:SPS (Twitter, FB, WP)-->');

regex(/<ref>\s*\[https?:\/\/(?:\w{2}\.wikipedia\.org\/wiki|(?:www\.|)(?:facebook|myspace)\.com)\/[^\s\]]*[ ]+[\w\d][^\]]*\]<\/ref>/gi, '{{cn}}<!-- WP:RS needed; removed link to WP:SPS (Twitter, FB, WP)-->');

regex(/\|\s[ ]*url[ ]*=[ ]*https?:\/\/(?:\w{2}\.wikipedia\.org\/wiki|(?:www\.|)(?:facebook|myspace)\.com)[^\s\|\{\}<]*(?=[ ]*[|}])/gi, '');

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

Line 57:

// removing artefacts within fields

regex(/(\|\s?author\s*\=\s*)(?:by |)(?:[^|]+staff|(?:staff |)reporters?|)[ ]*(?=[|}\n])/gi, '');

regex(/(\|\s?author\s*\=\s*)([A-Z][a-z]*(?: [A-Z][a-z]*)*) (?:(?:wire |)staff|(?:staff |)reporters?)[ ]*(?=[|}\n])/gi, '$1$2');

regex(/\|[ ]*last=(Reporter|staff)[ ]*\|[ ]*first=[^|\{\}]*(?=[\|{}])=/gi, '');

regex(/(\|\s?accessdate\s*\=\s*)(?:accessed|retrieved)(?: by| on|):?[ ]*(\d)/gi, '$1$2');

regex(/(\|\s?work\s*\=\s*)(?:article|interview|review) ?(?=[|}\n])/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');

Line 71 ⟶ 70:

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

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

regex(/(\*[ ]*|)\[\[n:[^\]]*\]\][^\r\n]*[\r\n]/gi, '');

regex(/\*[ ]*\{\{(?:Facebook|Find a Grave|Myspace)\|([^}]*)\}\}[\n\r\s]*/gi, '');

Line 128 ⟶ 127:

// removing blank or redundant parameters

regex(/(?:\|[ ]*(?:accessdate|agency|archive(?:date|url)|arxiv|asin|at|author(-?link|-mask|-name-separator|-separator|\d|\d-link|link\d?|)|bibcode|chapter|chapter-url|coauthors?|contribution(?:-url|)|date|deadurl|display-authors|doi|doi-inactive|doibroken|edition|editor(?:-first|-last|-link|\d|\d-first|\d-last|\d-link)|(?:first|last)\d?|format|id|is[bs]n|issue|jfm|journal|jstor|language|lay(?:date|source|summary)|lccn|___location|magazine|day|month|mr|newspaper|nopp|oclc|ol|origyear|osti|others|pages?|periodical|place|pm[cd]|pmid|postscript|publication(?:-date|-place)|publisher|quote|ref|rfc|separator|series|ssrn|trans_title|type|url|volume|work|year|zbl)[ ]*=[\s]*)(?=[\}\|])/gi, '');

// regex(/\|[ ]*deadurl[ ]*=[ ]*yes[ ]*/gi, ''); //disabling per request although default

//rem underlining within certain fields

Line 162 ⟶ 161:

regex(/(\|[ ]*(?:date|archivedate|accessdate|author)[ ]*=[ ]*)(?:(?:Mon|Tues?|Wed|Thur?|Fri|Sat|Sun)[\.,]?)\s/gi, "$1");

//'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 fordue to 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');

ohc_regex(/(\w|\])[\.,;]?[ ]\((Retrieved (?:@Month\s@DD,\s@YYYY|@DD\s@Month\s@YYYY|@yyyy-@mm-@dd))\)/gi, '$1. $2');

Line 217 ⟶ 216:

regex(/\|\s?publisher\s*\=\s*\[\[(?:The |)(?:Deseret News Publishing|Dispatch Printing|E. W. Scripps|Evening Post Publishing|Forbes(?: Publishing|, Inc\.)|Gannett?|Irish Times Trust|(?:Jann Wenner|Wenner Media)|Johnson Publishing|Journal Communications|Mac Publishing|McClatchy|Nash holdings LLC|New York Times|Seattle Times|Star Tribune|Thomp?son(?:[- ]?Reuters)?(?: Corporation| Plc.?|)|Torstar|Time Inc\.|Times Publishing|Tribune|Vox Media|Washington Post|World Publishing|Ziff Davis Media)(?: Co(?:mpany|\.)?)?\]\](?=[\s\.]*[|}])/g, '');

regex(/\|\s?publisher\s*\=\s*\[\[(?:Cox|Halifax|North Jersey|Sun-Times|Tampa|Herald|Stephens|WEHCO|\w+) Media(?: Group(?:,? Inc\.)?| Berhad)?\]\](?=[\s\.]*[|}])/g, '');

// regex(/\|\s?publisher\s*\=\s*\[\[(?:\w+ )+(?:Media|Publishing|Publications)(?: Group(?:,? Inc\.)?| Berhad)\]\](?=[\s\.]*[|}])/g, ''); //disabling - false positives for book citations

regex(/\| ?publisher ?= ?Star Publications \(Malaysia\)|\[\[Star Publications \(Malaysia\)\]\] ?/gi, '');

regex(/\| ?publisher ?= ?(?:New Straits Times Press|\[\[New Straits Times Press\]\]) ?/gi, '');

regex(/(\|\s?publisher\s?\=\s?MTV\s?)\|\s*\=\s*\(\w+\)/gi, '$1='); //palliative - correction for unsuppoeted parameters

}

Line 248 ⟶ 247:

regex(/(\|)(Daily Record|Sunday Mail)(?: \((Scotland)\))(\]\])/g, '$1$2$4|___location=$3');

regex(/(\[\[)(Daily Record|Sunday Mail)( \((Scotland)\))(\]\])/g, '$1$2$3|$2$5|___location=$4');

regex(/(=[ ]*(?:Daily Times)) \((Pakistan)\)(\s*[|}])/g, '$1|___location=$2$3');

regex(/(''(?:Daily Times)) \((Pakistan)\)('')/g, '$1$3 ($2)');

regex(/(\|)(Daily Times)(?: \(Pakistan\))(\]\])/g, '$1$2$3');

regex(/(=[ ]*Dawn) \((newspaper)\)(\s*[|}])/g, '$1|___location=Pakistan$3');

regex(/(''Dawn) \((newspaper)\)('')/g, '$1$3 (Pakistan)');

Line 399 ⟶ 395:

// removing artefacts (outside of citation templates)

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

regex(/\bthe ((?:'''?|)the )/gi, '$1');

// removing other artefacts

regex(/(UEFA\]\])\.(?:co(?:m|m?\.\w{2})|\.\w{2})(?= ?[\|{}])/gi, '$1');

regex(/\bthe ((?:'''?|)the )/gi, '$1');

// expanding/dating tags

regex(/{{(?:cn|fact)}}/gi, '{{citation needed|date={{subst:CURRENTMONTHNAME}} {{subst:CURRENTYEAR}}}}');

//dynamic columns for reflists; remove scroll bar

regex(/((?:[Rr]eferences|[Nn]otes)[ ]?={2,4}[\n\r])[\r\n\s]*<div (?:style|class)=[^>]*>([\S\s]*)<\/div>/g, '$1$2');

Line 428 ⟶ 424:

/** ------------------------------------------------------------------------ **/

/// 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[\[=^>]\s*)(?:https?:|ftp:)>)([^\]\|\}].*?)(<\s*[\]|}]/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=[];

Line 435 ⟶ 470:

// 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);

Line 441 ⟶ 476:

};

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

// protect the rest (after purging urls inserted in ('website' or )'work' parameters)

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

regex(/(\{\{(?:harv\w*|sfn\w*|cite ?book|listen)\s?\|)([^\}]+)(\})/gi, protect_function);

regex(/(\|\s*contribution\s*=)([^|}]+)(\|\})/gi, protect_function);

Line 448 ⟶ 482:

}

function ohc_unprotect_urls()

{

Line 473 ⟶ 507:

function Ohc_Source_edit_summary(){

//Add a tag to the summary box

setoptions(minor='true');

setreason('Sources per [[Help:Citation Style 1|CS1]], [[Template:Citation]] and [[MOS:ITALICS]] 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');

}