// This script converts between multiple variations of English spellings
// PLEASE READ THE DOCUMENTATION at [[User:Ohconfucius/EngvarB]] (click on the link above) before using.
// Feedback and constructive criticism are welcome.
// As I am a scripting newbie, any technical advice on the 'hows and the wherefores' are especially welcome.
/*************
*** Regex menu framework
*** by [[m:User:Pathoschild]] <https://meta.wikimedia.org/wiki/User:Pathoschild/Scripts/Regex_menu_framework>
*** - adds a sidebar menu of user-defined scripts.
*************/
mw.loader.load('//en.wikisource.org/w/index.php?title=User:Pathoschild/standardise.js&action=raw&ctype=text/javascript');
/* menu links */
// In the function below, add more lines like "regexTool('link text','function_name()')" to add
// links to the sidebar menu. The function name is the function defined in rfmscripts() below.
function rmflinks() {
//regexTool('Custom regex', 'custom()'); // a default tool which performs regex input in a dynamic form
//regexTool('Edit my regexes ↗', 'function opennew(url) { window.open(url); }; opennew(wgServer + wgScript + "?title=User:" + wgUserName + "/EngvarB.js&action=edit");');
//regexTool('• Protect words', 'ohc_ENGVAR_protect()');
regexTool('• Flip imperial units', 'ohc_imperial_units()');
regexTool('• Flip international units', 'ohc_international_units()');
regexTool('• AMERICAN', 'ohc_ENGVAR_set_variation("U")');
regexTool('• AUSTRALIAN', 'ohc_ENGVAR_set_variation("A")');
regexTool('• BRITISH', 'ohc_ENGVAR_set_variation("B")');
regexTool('• BRITISH (Oxford)', 'ohc_ENGVAR_set_variation("Ox")');
regexTool('• CANADIAN', 'ohc_ENGVAR_set_variation("C")');
regexTool('• INDIAN', 'ohc_ENGVAR_set_variation("I")');
}
/* scripts */
// Below, define the functions linked to from rmflinks() above. These functions can use any JavaScript,
// but there is a set of simplified tools documented at
// https://meta.wikimedia.org/wiki/User:Pathoschild/Scripts/Regex_menu_framework
/** ------------------------------------------------------------------------ **/
// PROTECTION FROM STRING SUBSTITUTION
var linkmap = [];
function ohc_ENGVAR_protect() {
//protects categories, templates, link pipings, quotes, etc
//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(/(pre)(string)(post)/gi, protect_function); //template
regex(/(<blockquote>)(.*?)(<\/blockquote>)/gi, protect_function);
regex(/({\| class= ?\"wikitable ?\")([\S\s]*?)(\|})/gi, protect_function);
regex(/(<table[^<>]*?>)([^<>]*)(<\/table>)/gi, protect_function);
regex(/(<timeline[^<>]*?>)([^<>]*)(<\/timeline>)/gi, protect_function);
regex(/(\|\s*style\s*=[^|]*)(color|center)([^|]*\|)/gi, protect_function);
regex(/(<\/?[ ]*)(center)([ ]*>)/gi, protect_function); //<center> tags
regex(/(align\/?[ ]*=\/?[ ]*[ "'][ ]*)(center)([ ]*[ "'])/gi, protect_function); //align="center" in tables
regex(/(\\|\/?[ ]*)(center)([ ]*\\|)/gi, protect_function); //|center| in files
regex(/(<ref[^<>]*?>)([^<>]*)(<\/ref>)/gi, protect_function);
regex(/(<ref name=)([^<>]*)(\/>)/gi, protect_function);
regex(/(\{[\w ]{0,12}(?:quot[^\|]{1,7}\s?|sic|(?:not a |)typo|as written)\|)([^\}]+)(\})/gi, protect_function);
regex(/([\s\(]["“])([^"“”\n]*)(["”])/gi, protect_function); //double quotes
regex(/((?:Category|Image):)([^|\]]*)([\|\]])/gi, protect_function); //cats, images
regex(/((?:image\d?|image_skyline|image[ _]location\d?|image[ _](?:map|name)|img|pic)\s*=)([^\|\}]*)([\|\}])/gi, protect_function); //images within templates infoboxes etc
regex(/(.)(cite encyclopedia\s*\|)(.)/gi, protect_function);
regex(/(\|)(\s*colors(?:_label|)\s*)(=)/gi, protect_function);
regex(/(\|)(\s*analog\s*)(=)/gi, protect_function);
regex(/((?:url)\s*=)([^\|\}]*)([\|\}])/gi, protect_function); //urls within templates infoboxes etc
regex(/(\[(?:https?:|ftp:))([^\]]*)(\])/gi, protect_function);
regex(/(\[(?:https?:|ftp:))([^\s\]]*)([\s\]])/gi, protect_function);
regex(/(\[\[)([^\|\]]*)(\|)/gi, protect_function); //pipings
regex(/(.)(Back in the U.S.S.R.)(.)/gi, protect_function); //title of work
regex(/(.)(Born in the U.S.A.)(.)/gi, protect_function); //title of work
regex(/(\{(?:See ?also|Main))(\|[^\}]*)(\})/gi, protect_function); //see also and main templates
regex(/(\{\{(?:external|wide )image\s?\|)([^\}]+)(\})/gi, protect_function);
regex(/(\{\{(?:harvnb|wikisource)\|)([^\}]+)(\})/gi, protect_function);
regex(/(\{\{)((?:NYT|WSJ)topic\|[^\}]*)(\}\})/gi, protect_function);
regex(/(\{\{\w*)([^\|=\[\]]*)(\}\})/gi, protect_function); //templates
regex(/(\{Infobox )((?:[\w ]*)organization)(\s+)/gi, protect_function);
regex(/(\|\s*)(cleanup|color|coordinates\w*)([ ]*=)/gi, protect_function); //parameters within infoboxes
regex(/(\|(?:[^=\|\{\}]*))(cleanup|encyclopa?edia|enroll?ment|honors|lockup\w{1,4}|organi[sz]ation|catalog\snumber)(\s*=)/g, protect_function);
regex(/(\|\s*)(encyclopedia|\w*colors)(\s?=)/gi, protect_function);
regex(/(\|\s*)(local[ _]authority)(\s?=)/gi, protect_function);
regex(/(\|\s*)([Ss]hip[ _](?:armou?r|honou?rs))([ ]*?\=)/g, protect_function);
regex(/(\|\s*title\s?=)([^|\]]*)(\|)/gi, protect_function);
regex(/(.)(solid gray)(.)/gi, protect_function);
//protect from hyphenation
regex(/(.)(\breed(?:|s)[^aeiou]|[Rr]eegan)(.)/g, protect_function);
//protect from function ohc_ENGVAR_restore_z
regex(/(.)((?:enterpri|promi|surpri|treati)(?:se[drs]?|ing))(.)/gi, protect_function);
regex(/(.)((?: ant)(?:ic|idote|imon|ipath|iq))(.)/g, protect_function);
regex(/(.)((?:(?:mercury|nobel)pri|imagesi|picsi)(?:ze))(.)/g, protect_function);
}
function ohc_ENGVAR_unprotect() {
//removes protection put in place by function ohc_protect_fmt (all cats, templates etc.)
regex(/[♫]/g, '');
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_ENGVAR_plain() {
//per https://www.gov.uk/guidance/style-guide/a-to-z-of-gov-uk-style
//redundancies
regex(/B\.B\.C\./g, 'BBC');
regex(/U\.S\.A\./g, 'U.S.');
regex(/U\.S\.S\.R\./g, 'USSR');
regex(/U\.K\./g, 'UK');
regex(/E\.U\./g, 'EU');
regex(/(fill )out/gi, '$1in');
// regex(/in order (to )/g, '$1'); // disabling per discussion on my talk (archive 35)
regex(/In order t(o )/g, 'T$1');
//hyphenation
regex(/(co)(o(?:per|rdin)at(e\b|ing|ion))/g, '$1-$2');
regex(/\b(re)(e\w[aeiou]\w{4,})/gi, '$1-$2');
regex(/\b(over|under)(r\w{4,})/gi, '$1-$2');
regex(/\b(vice) (president|chairman|chancellor|minister)/gi, '$1-$2');
//capitalisation
//rem geographical regions - too many false positives
regex(/(local )authority/g, '$1council');
regex(/w(estern European Union)/g, 'W$1');
regex(/(New )s(outh Wales)/g, '$1S$2');
}
function ohc_ENGVAR_simple_b() {
var table = {
'aging': '$1ageing',
'aluminum': '$1aluminium',
'adrenalin(\\b)': '$1adrenaline$2',
'annex(\\b)': '$1annexe$2',
'artifact': '$1artefact',
'(ana|breatha|cata|hydro|para)lyz(e|ing)': '$1$2lys$3',
'bestsell': '$1best-sell',
'diarrhea': '$1diarrhoea',
'(de|of)fense': '$1$2fence',
'license': '$1licence',
'(licen)c(ing|ed)': '$1$2s$3',
'(practi)c(ing|ed)': '$1$2s$3',
'furor(\\b)': '$1furore$2',
'(light-|dark-|\\b)gray': '$1$2grey',
'guerilla': '$1guerrilla',
'jewelry': '$1jewellery',
'maneuver(ab|ed|ing)': '$1manoeuvr$2',
'maneuver': '$1manoeuvre',
'louve(red|ring)': '$1louv$2',
'louver': '$1louvre',
'ped(iatric|ophil)': '$1paed$2',
'encyclopedi(a|c)': '$1encyclopaedi$2',
'skeptic': '$1sceptic',
'mollusk': '$1mollusc',
'vapor(s?\\b)': '$1vapour$2',
'licorice': '$1liquorice',
//composite words
'(break|drop|clean|line|lock|pick)(out|up)': '$1$2-$3',
//oe/ae words
'gyneco': '$1gynaeco',
'hemo(globin|ly|phil|rr)': '$1haemo$2',
'orthopedic': '$1orthopaedic',
'archeo': '$1archaeo',
'paleonto': '$1palaeonto',
'enology': '$1oenology',
'esophag': '$1oesophag',
'estrogen': '$1oestrogen',
'(an|)esthe(sia|tic|tist)': '$1$2aesthe$3',
'anesthesiologist': '$1anaesthetist',
'homeopath': '$1homoeopath',
// 'medieval(\\b)': '$1mediaeval$2',
'omelet(\\b)': '$1omelette$2',
'rigor(\\b)': '$1rigour$2',
'(an|leuk|septic|tox)emi(a|c)': '$1$2aemi$3',
//'f' words
'(S|s)ulfur': '$1$2ulphur',
'anymore': '$1any more',
'specialty': '$1speciality',
// non-redundant e
'(lik|liv|rat|sal|siz|shak)(able)': '$1$2e$3',
//'~our' words
'(arm|clam|glam|harb|neighb|rum|savi?)or(ed|ful|ing|less|ly|s|\\b)': '$1$2our$3',
'(arm|sav)or(ies|y|s|\\b)': '$1$2our$3',
'(cand|od)or((?:ful|less)(?:ly|)|\\b)': '$1$2our$3',
'neighborhood': '$1neighbourhood',
'behavior(al|s|\\b)': '$1behaviour$2',
'favor(abl[ey]|ed|i[\\w]*|s|\\b)': '$1favour$2',
'honor(abl[ey]|ed|ing|s|\\b)': '$1honour$2',
'(endeav|lab)or(e[dr]|ing|s|\\W)': '$1$2our$3',
'mol(d|t)(ed|ing|s|\\W)': '$1moul$2$3',
//'~re~' words
'(calib|fib|goit|lust|mit|nit|och|reconnoit|sab|saltpet|spect|theat|tit)er(s?\\W)': '$1$2re$3',
'(centi|kilo|micro|milli|nano|-|\\d\\s)meter': '$1$2metre',
'(centi|milli|deci|pico|hecto|\\b)liter(s?\\b)': '$1$2litre$3',
'(dema|peda|mono|syna)gog(s?\\W)': '$1$2gogue$3',
// '(\\W[a-zA-Z]{3,12}[^s\\b])iz(e[drs]?|ation(s|al|)|ing)': '$1$2is$3',
//'~l' words where the 'l' doubles as past and present participle
'((?:\\w{3,9}[-–—]|)(?:fu|pan))el(e[dr]|ist|ing)': '$1$2ell$3',
'(bev|jew|lev|mod|rev|trav)el(e[dr]|ing)': '$1$2ell$3',
'([a-zA-Z]{2,8}[^eglstz ])el(e[dr]|est|ing)(\\b)': '$1$2ell$3$4', //added 'z' to avoid changing of "embezzled"
'(app|di|enthr|equ|initi|journ|riv|sign|tot)al(e[dr]|ing)': '$1$2all$3'
};
for (var word in table) {
try {
regex(new RegExp('([ \\|\\[\\*])' + word, 'g'), table[word]);
}
catch (err) {
var text = 'There was an error on function ohc_ENGVAR_simple_b(), when changing "' + word + '" => "' + table[word] + '".\n\n';
text += 'Error: ' + err.message + '\n\n';
text += 'Click OK to continue.\n\n';
alert(text);
}
}
var table = {
//'~our' words
'([ \\|\\[\\*])(col|flav|hum)or(ed|ful|fully|ings?|less|lessly|s\\W)': '$1$2our$3',
'( [\\w\\D]*\\-)(col|flav|hum)ored': '$1$2oured',
'([^\\w\\d\\-\\/=:])(col)or(\\W)': '$1$2our$3',
//'~re~' words
'([^\\w\\d\\-\\/=])(calib|fib|goit|lust|mit|nit|reconnoit|sab|saltpet|spect|theat|tit)er(ed|ing)': '$1$2re$3',
'([^\\w\\d\\-\\/=:])(cent|epicent|recent)er(ed|ing)': '$1$2re$3',
'([^\\w\\d\\-\\/=:])(cent|epicent|recent)er(s?\\b)': '$1$2re$3',
//'~logu~' words
'([^\\w\\d\\-\\/])(ana|cata|dia|epi|homo|mono|pro)log(ed|ing)': '$1$2logu$3',
'([^\\w\\d\\-\\/])(ana|cata|dia|epi|homo|mono|pro)log(s?\\b)': '$1$2logue$3',
//'~l' words where the 'l' doubles as past and present participle
'([ \\|\\[])(counc[ie])l(e[dr]|ing|ors?)(\\b)': '$1$2ll$3$4',
'\\b([a-zA-Z]*)ll(ful|ment)': '$1l$2',
'(movie theat(er|re))': 'cinema',
'([ \\|\\[\\*])airplane': '$1aeroplane',
'([ \\|\\[\\*])\\b[Mm](um|om(my|))\\b': '$1mother'
};
for (var word in table) {
try {
regex(new RegExp(word, 'g'), table[word]);
}
catch (err) {
var text = 'There was an error on function ohc_ENGVAR_simple_b(), when changing "' + word + '" => "' + table[word] + '".\n\n';
text += 'Error: ' + err.message + '\n\n';
text += 'Click OK to continue.\n\n';
alert(text);
}
}
//remove US spelling from {{convert}} template output
regex(/(\{\{convert\|[^\}]*)\|(?:sp|spell)[ ]*=[ ]*us/gi, '$1');
regex(/(\{\{(?:in|ft|yd|[mck]?m)[23]?[ ]+to[ ]+[^\}]*)\|(?:sp|spell)[ ]*=[ ]*(?:American|us)/gi, '$1');
regex(/(\{\{(?:pd|pop[ ]+density[ ])+(?:km|mi)2[^\}]*)\|(?:sp|spell)[ ]*=[ ]*(?:American|us)/gi, '$1');
//remove ambiguous pound sign; rem incidental intervening space
regex(/₤ ?(\d)/g, '£$1');
regex(/rigour mortis/g, 'rigor mortis');
//reconvert special cases
}
function ohc_ENGVAR_simple_c() {
var table = {
'ageing': '$1aging',
'aluminium': '$1aluminum',
'adrenalin(\\b)': '$1adrenaline$2',
'annex(\\b)': '$1annexe$2',
'(ana|breatha|cata|hydro|para)lyz(e|ing)': '$1$2lys$3',
'(de|of)fense': '$1$2fence',
'license': '$1licence',
'(licen)c(ing|ed)': '$1$2s$3',
'(practi)s(ing|ed)': '$1$2c$3',
'furor(\\b)': '$1furore$2',
'(light-|dark-|\\b)gray': '$1$2grey',
'guerilla': '$1guerrilla',
'maneuver(ab|ed|ing)': '$1manoeuvr$2',
'maneuver': '$1manoeuvre',
'louve(red|ring)': '$1louv$2',
'louver': '$1louvre',
'encyclopaedi(a|c)': '$1encyclopedi$2',
'skeptic': '$1sceptic',
'mollusk': '$1mollusc',
'vapor(s?\\b)': '$1vapour$2',
'liquorice': '$1licorice',
//composite words
// 'onstage': '$1on-stage',
'(break|drop|clean|line|lock|pick)(out|up)': '$1$2-$3',
//oe/ae words
'anaesthesiologist': '$1anesthetist',
'(an|)aesthe(sia|tic|tist)': '$1$2esthe$3',
'archaeo': '$1archeo',
'diarrhoea': '$1diarrhea',
'foetus': '$1fetus',
'gyneco': '$1gynaeco',
'haemo(globin|ly|phil|rr)': '$1hemo$2',
'orthopaedic': '$1orthopedic',
'oenology': '$1enology',
'oesophag': '$1esophag',
'oestrogen': '$1estrogen',
'homoeopath': '$1homeopath',
'omelet(\\b)': '$1omelette$2',
'paed(iatric|ophil)': '$1ped$2',
'palaeonto': '$1paleonto',
'rigor(\\b)': '$1rigour$2',
'(an|leuk|septic|tox)aemi(a|c)': '$1$2emi$3',
//'f' words
'(S|s)ulfur': '$1$2ulphur',
'anymore': '$1any more',
'speciality': '$1specialty',
// non-redundant e
'(lik|liv|rat|sal|siz|shak)(able)': '$1$2e$3',
//'~our' words
'(arm|clam|glam|harb|neighb|rum|savi?)or(ed|ful|ing|less|ly|s|\\b)': '$1$2our$3',
'(arm|sav)or(ies|y|s|\\b)': '$1$2our$3',
'(cand|od)or((?:ful|less)(?:ly|)|\\b)': '$1$2our$3',
'neighborhood': '$1neighbourhood',
'behavior(al|s|\\b)': '$1behaviour$2',
'favor(abl[ey]|ed|i[\\w]*|s|\\b)': '$1favour$2',
'honor(abl[ey]|ed|ing|s|\\b)': '$1honour$2',
'(endeav|lab)or(e[dr]|ing|s|\\W)': '$1$2our$3',
'mol(d|t)(ed|ing|s|\\W)': '$1moul$2$3',
//'~re~' words
'(calib|fib|goit|lust|mit|nit|och|reconnoit|sab|saltpet|spect|theat|tit)er(s?\\W)': '$1$2re$3',
'(centi|kilo|micro|milli|nano|-|\\d\\s)meter': '$1$2metre',
'(centi|milli|deci|pico|hecto|\\b)liter(s?\\b)': '$1$2litre$3',
'(dema|peda|mono|syna)gog(s?\\W)': '$1$2gogue$3',
//'~l' words where the 'l' doubles as past and present participle
'((?:\\w{3,9}[-–—]|)(?:fu|pan))el(e[dr]|ist|ing)': '$1$2ell$3',
'(bev|jew|lev|mod|rev|trav)el(e[dr]|ing)': '$1$2ell$3',
'([a-zA-Z]{2,8}[^eglstz ])el(e[dr]|est|ing)(\\b)': '$1$2ell$3$4', //added 'z' to avoid changing of "embezzled"
'(app|di|enthr|equ|initi|journ|riv|sign|tot)al(e[dr]|ing)': '$1$2all$3'
};
for (var word in table) {
try {
regex(new RegExp('([ \\|\\[\\*])' + word, 'g'), table[word]);
}
catch (err) {
var text = 'There was an error on function ohc_ENGVAR_simple_c(), when changing "' + word + '" => "' + table[word] + '".\n\n';
text += 'Error: ' + err.message + '\n\n';
text += 'Click OK to continue.\n\n';
alert(text);
}
}
var table = {
//'~our' words
'([ \\|\\[\\*])(col|flav|hum)or(ed|ful|fully|ings?|less|lessly|s\\W)': '$1$2our$3',
'( [\\w\\D]*\\-)(col|flav|hum)ored': '$1$2oured',
'([^\\w\\d\\-\\/=:])(col)or(\\W)': '$1$2our$3',
//'~re~' words
'([^\\w\\d\\-\\/=])(calib|fib|goit|lust|mit|nit|reconnoit|sab|saltpet|spect|theat|tit)er(ed|ing)': '$1$2r$3',
'([^\\w\\d\\-\\/=:])(cent|epicent|recent)er(ed|ing)': '$1$2r$3',
'([^\\w\\d\\-\\/=:])(cent|epicent|recent)er(s?\\b)': '$1$2re$3',
//'~logu~' words
'([^\\w\\d\\-\\/])(ana|cata|dia|epi|homo|mono|pro)log(ed|ing)': '$1$2logu$3',
'([^\\w\\d\\-\\/])(ana|cata|dia|epi|homo|mono|pro)log(s?\\b)': '$1$2logue$3',
//'~l' words where the 'l' doubles as past and present participle
'([ \\|\\[])(counc[ie])l(e[dr]|ing|ors?)(\\b)': '$1$2ll$3$4',
'\\b([a-zA-Z]*)ll(ful|ment)': '$1l$2',
'(movie theat(er|re))': 'cinema',
'([ \\|\\[\\*])airplane': '$1aeroplane',
'([ \\|\\[\\*])\\b[Mm](um|om(my|))\\b': '$1mother'
};
for (var word in table) {
try {
regex(new RegExp(word, 'g'), table[word]);
}
catch (err) {
var text = 'There was an error on function ohc_ENGVAR_simple_c(), when changing "' + word + '" => "' + table[word] + '".\n\n';
text += 'Error: ' + err.message + '\n\n';
text += 'Click OK to continue.\n\n';
alert(text);
}
}
//remove US spelling from {{convert}} template output
regex(/(\{\{convert\|[^\}]*)\|(?:sp|spell)[ ]*=[ ]*us/gi, '$1');
regex(/(\{\{(?:in|ft|yd|[mck]?m)[23]?[ ]+to[ ]+[^\}]*)\|(?:sp|spell)[ ]*=[ ]*(?:American|us)/gi, '$1');
regex(/(\{\{(?:pd|pop[ ]+density[ ])+(?:km|mi)2[^\}]*)\|(?:sp|spell)[ ]*=[ ]*(?:American|us)/gi, '$1');
//remove ambiguous dollar sign; rem incidental intervening space
regex(/$ ?(\d)/g, '$$1');
regex(/rigour mortis/g, 'rigor mortis');
//reconvert special cases
}
function ohc_ENGVAR_simple_a() {
var table = {
'ageing': '$1aging',
'aluminium': '$1aluminum',
'adrenaline(\\b)': '$1adrenalin$2',
'annexe(\\b)': '$1annex$2',
'artefact': '$1artifact',
'(ana|breatha|cata|hydro|para)lys(e|ing)': '$1$2lyz$3',
'best-sell': '$1bestsell',
'diarrhoea': '$1diarrhea',
'(de|of)fence': '$1$2fense',
'licence': '$1license',
'(licen)c(ing|ed)': '$1$2s$3',
'(practi)s(ing|ed)': '$1$2c$3',
'furore(\\b)': '$1furor$2',
'(light-|dark-|\\b)grey': '$1$2gray',
'guerilla': '$1guerrilla',
'jewellery': '$1jewelry',
'manoeuvr(ab|ed|ing)': '$1maneuver$2',
'manoeuvre': '$1maneuver',
'louv(red|ring)': '$1louve$2',
'louvre': '$1louver',
'paed(iatric|ophil)': '$1ped$2',
'encyclopaedi(a|c)': '$1encyclopedi$2',
'sceptic': '$1skeptic',
'mollusc': '$1mollusk',
'vapour(s?\\b)': '$1vapor$2',
'liquorice': '$1licorice',
//composite words
'(break|drop|clean|line|lock|pick)-(out|up)': '$1$2$3',
//oe/ae words
'gynaeco': '$1gyneco',
'haemo(globin|ly|phil|rr)': '$1hemo$2',
'orthopaedic': '$1orthopedic',
'archaeo': '$1archeo',
'palaeonto': '$1paleonto',
'oenology': '$1enology',
'oesophag': '$1esophag',
'oestrogen': '$1estrogen',
'(an|)aesthe(sia|tic|tist)': '$1$2esthe$3',
'anaesthetist': '$1anesthesiologist',
'homoeopath': '$1homeopath',
// 'mediaeval(\\b)': '$1medieval$2',
'omelette(\\b)': '$1omelet$2',
'rigour(\\b)': '$1rigor$2',
'(an|leuk|septic|tox)aemi(a|c)': '$1$2emi$3',
//'f' words
'(S|s)ulfur': '$1$2ulphur',
'any more': '$1anymore',
'speciality': '$1specialty',
// non-redundant e
'(lik|liv|rat|sal|siz|shak)e(able)': '$1$2$3',
//'~our' words
'(arm|clam|glam|harb|neighb|rum|savi?)our(ed|ful|ing|less|ly|s|\\b)': '$1$2or$3',
'(arm|sav)our(ies|y|s|\\b)': '$1$2or$3',
'(cand|od)oru((?:ful|less)(?:ly|)|\\b)': '$1$2or$3',
'neighbourhood': '$1neighborhood',
'behaviour(al|s|\\b)': '$1behavior$2',
'favour(abl[ey]|ed|i[\\w]*|s|\\b)': '$1favor$2',
'honour(abl[ey]|ed|ing|s|\\b)': '$1honor$2',
'(endeav|lab)our(e[dr]|ing|s|\\W)': '$1$2or$3',
'moul(d|t)(ed|ing|s|\\W)': '$1mol$2$3',
//'~re~' words
'(calib|fib|goit|lust|mit|nit|och|reconnoit|sab|saltpet|spect|theat|tit)re(s?\\W)': '$1$2er$3',
'(centi|kilo|micro|milli|nano|-|\\d\\s)metre': '$1$2meter',
'(centi|milli|deci|pico|hecto|\\b)litre(s?\\b)': '$1$2liter$3',
'(dema|peda|mono|syna)gogue(s?\\W)': '$1$2gog$3',
// '(\\W[a-zA-Z]{3,12}[^s\\b])iz(e[drs]?|ation(s|al|)|ing)': '$1$2is$3',
//'~l' words where the 'l' doubles as past and present participle
'((?:\\w{3,9}[-–—]|)(?:fu|pan))ell(e[dr]|ist|ing)': '$1$2el$3',
'(bev|jew|lev|mod|rev|trav)ell(e[dr]|ing)': '$1$2el$3',
'([a-zA-Z]{2,8}[^eglstz ])ell(e[dr]|est|ing)(\\b)': '$1$2el$3$4', //added 'z' to avoid changing of "embezzled"
'(app|di|enthr|equ|initi|journ|riv|sign|tot)all(e[dr]|ing)': '$1$2al$3'
};
for (var word in table) {
try {
regex(new RegExp('([ \\|\\[\\*])' + word, 'g'), table[word]);
}
catch (err) {
var text = 'There was an error on function ohc_ENGVAR_simple_a(), when changing "' + word + '" => "' + table[word] + '".\n\n';
text += 'Error: ' + err.message + '\n\n';
text += 'Click OK to continue.\n\n';
alert(text);
}
}
var table = {
//'~our' words
'([ \\|\\[\\*])(col|flav|hum)our(ed|ful|fully|ings?|less|lessly|s\\W)': '$1$2or$3',
'( [\\w\\D]*\\-)(col|flav|hum)oured': '$1$2ored',
'([^\\w\\d\\-\\/=:])(col)our(\\W)': '$1$2or$3',
//'~re~' words
'([^\\w\\d\\-\\/=])(calib|fib|goit|lust|mit|nit|reconnoit|sab|saltpet|spect|theat|tit)re(ed|ing)': '$1$2er$3',
'([^\\w\\d\\-\\/=:])(cent|epicent|recent)re(ed|ing)': '$1$2er$3',
'([^\\w\\d\\-\\/=:])(cent|epicent|recent)re(s?\\b)': '$1$2er$3',
//'~logu~' words
'([^\\w\\d\\-\\/])(ana|cata|dia|epi|homo|mono|pro)logu(ed|ing)': '$1$2log$3',
'([^\\w\\d\\-\\/])(ana|cata|dia|epi|homo|mono|pro)logue(s?\\b)': '$1$2log$3',
//'~l' words where the 'l' doubles as past and present participle
'([ \\|\\[])(counc[ie])ll(e[dr]|ing|ors?)(\\b)': '$1$2l$3$4',
'\\b([a-zA-Z]*)([^l])l(ful|ment)': '$1$2ll$3',
'(movie theat(er|re))': 'cinema',
'([ \\|\\[\\*])aeroplane': '$1airplane',
'([ \\|\\[\\*])\\b[Mm](um|om(my|))\\b': '$1mother'
};
for (var word in table) {
try {
regex(new RegExp(word, 'g'), table[word]);
}
catch (err) {
var text = 'There was an error on function ohc_ENGVAR_simple_a(), when changing "' + word + '" => "' + table[word] + '".\n\n';
text += 'Error: ' + err.message + '\n\n';
text += 'Click OK to continue.\n\n';
alert(text);
}
}
//remove US spelling from {{convert}} template output
regex(/(\{\{convert\|[^\}]*)\|(?:sp|spell)[ ]*=[ ]*us/gi, '$1');
regex(/(\{\{(?:in|ft|yd|[mck]?m)[23]?[ ]+to[ ]+[^\}]*)\|(?:sp|spell)[ ]*=[ ]*(?:American|us)/gi, '$1');
regex(/(\{\{(?:pd|pop[ ]+density[ ])+(?:km|mi)2[^\}]*)\|(?:sp|spell)[ ]*=[ ]*(?:American|us)/gi, '$1');
//remove ambiguous dollar sign; rem incidental intervening space
regex(/$ ?(\d)/g, '$$1');
regex(/rigour mortis/g, 'rigor mortis');
//reconvert special cases
}
function ohc_ENGVAR_set_variation(v) {
ohc_ENGVAR_protect();
switch (v) {
case 'A':
case 'B':
case 'I':
ohc_ENGVAR_simple_b();
ohc_ENGVAR_remove_z();
break;
case 'Ox':
case 'C':
ohc_ENGVAR_simple_c();
ohc_ENGVAR_restore_z();
break;
case 'U':
ohc_ENGVAR_simple_a();
ohc_ENGVAR_restore_z();
break;
}
ohc_ENGVAR_plain();
ohc_ENGVAR_unprotect();
ohc_retask_pipes();
ohc_ENGVAR_insert_template(v);
ohc_ENGVAR_edit_summary(v);
doaction('diff');
}
/** ------------------------------------------------------------------------ **/
function ohc_retask_pipes() {
regex(/([^\w\-\.]\[\[)(?:(?:[a-zA-Z]+? |)[a-zA-Z]+?[^s ]i[sz]ation)\|((?:[a-zA-Z]+? |)[a-zA-Z]{3,12}[^s ]i[sz](?:e[drs]?|ations?|abl[ey]|ing))/g, '$1$2');
// regex(/(empha|synthe)siz(e|ing)/g, '$1sis$2');
}
function ohc_ENGVAR_remove_z() {
regex(/([^\w\-\.][a-zA-Z]{3,12}[^s ])iz(e[drs]?|ations?|abl[ey]|ing)(\W)/g, '$1is$2$3');
regex(/(empha)siz(e|ing)/g, '$1sis$2');
regex(/(synthe)siz(e[ds]|ing)/g, '$1sis$2');
}
function ohc_ENGVAR_restore_z() {
//converts 's-words' into 'z-words'
regex(/([^\w\-\.\/])(ar|de[mv]|improv|parad|(?:com|)pr[eo][cm]|(?:un|)rev|surm|telev)is(e|ing)/g, '$1$2♫is$3');
regex(/([\w])remise/g, '$1rem♫ise'); // Premise et al.
regex(/([\w])radise/g, '$1rad♫ise'); // Paradise et al.
regex(/([^\w\-\.\/][a-zA-Z]{5,12})is(ations?)(\W)/g, '$1iz$2$3');
regex(/([^\w\-\.\/][a-zA-Z]{0,12}(?:[aeiou][^aeiosuw]|ph|rd|thes))is(e[drs]?|ing)(\W)/g, '$1iz$2$3');
}
function ohc_imperial_units() {
//measurements and perception
// regex(/\[\[(foobar)(s|)\]\]/gi, '$1$2');
//Template:{{convert}}
// regex(/(\{\{convert)(\s*\|)/gi, '$1/flip$2'); //rem linking within convert template (area) //needs resolving
regex(/(\{\{convert\|[\d\.,]+?\|(?:(?:sq|cu|)(?:[mck]?m)(?:2|3|))(?:\|(?:sq|cu|)(?:in|ft|yd|mi)(?:2|3|))?(\|\d)?(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //rem linking within convert template (area)
regex(/(\{\{convert\|[\d\.,]+?\|tonnes?(?:\|tons?)?(\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //rem linking within convert template
regex(/(\{\{convert\|[\d\.,]+?\|(?:(?:sq|)(?:k?m)(?:2|3|)|hectare))(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*?(?=\})/gi, '$1$2|disp=flip'); //putting metres and hectares behind
regex(/(\{\{convert\|[\d\.,]+?\|(?:hectares?|ha)(?:\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //flip hectares
regex(/(\{\{convert\|[\d\.,]+?\|(?:kmh|km\/h)(?:\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //flip kmh
regex(/(\{\{convert\|[\d\.,]+?\|(?:to|by|x)(?:\|[\d\.,]+?\|(?:[mck]?m))(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //rem linking within convert template (input ranges only)
regex(/(\{\{convert\|[\d\.,]+?\|nmi)(2|)(\|mi\2 km\2|\|km\2 mi\2|)(?=[|}])/gi, '$1$2|mi$2 km$2'); //putting miles first in nautical mile conversion
regex(/(\{\{convert\|[\d\.,]+?\|(?:kg|°?F))(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]+?)*(?=\})/gi, '$1$2|disp=flip'); //putting pounds and °C first
// regex(/(\{\{(?:in|ft|mi|[mck]?m)[23]?\sto\s(?:in|ft|mi|[mck]?m)[23]?[^\}]*?)\|wiki=(?:yes|no)/gi, '$1');
//manipulating "|disp=flip" parameter where already "flipped"
regex(/(\{\{convert\|[\d\.,]+?\|\w{1,4}(?:\|\w{1,4}|)?(?:\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(\|disp=flip)(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)+(?=\})/gi, '$1$3$2'); //reordering flipping parameter within convert template (last parameter)
regex(/(\{\{convert\|[\d\.,]+?\|(?:(?:sq|cu|)(?:in|ft|yd|mi|acre)(?:2|3|))(?:\|(?:sq|cu|)(?:[mck]?m|ha)(?:2|3|))?(\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)\|disp=flip(?=\})/gi, '$1$2'); //rem flipping within convert template (Imperial, sq and cubed)
regex(/(\{\{convert\|[\d\.,]+?\|(?:mi|miles?|mph)(?:\|kph|km\/h|)?(\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)\|disp=flip(?=\})/gi, '$1$2'); //rem flipping within convert template (Imperial, sq and cubed)
}
function ohc_international_units() {
//measurements and perception
// regex(/\[\[(foobar)(s|)\]\]/gi, '$1$2');
//Template:{{convert}}
// regex(/(\{\{convert)(\s*\|)/gi, '$1/flip$2'); //rem linking within convert template (area) //needs resolving
regex(/(\{\{convert\|[\d\.,]+?\|(?:(?:sq|cu|)(?:in|ft|yd|mi)(?:2|3|))(?:\|(?:sq|cu|)(?:[mck]?m)(?:2|3|))?(\|\d)?(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //rem linking within convert template (area)
regex(/(\{\{convert\|[\d\.,]+?\|tonnes?(?:\|tons?)?(\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //rem linking within convert template
regex(/(\{\{convert\|[\d\.,]+?\|(?:(?:sq|)mi(?:2|3|)|acre))(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*?(?=\})/gi, '$1$2|disp=flip'); //putting metres and hectares behind
// regex(/(\{\{convert\|[\d\.,]+?\|(?:hectares?|ha)(?:\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //flip hectares
// regex(/(\{\{convert\|[\d\.,]+?\|mp[gh](?:\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //flip kmh
regex(/(\{\{convert\|[\d\.,]+?\|(?:to|by|x)(?:\|[\d\.,]+?\|(?:yd|f(?:oo|)t|in))(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(?=\})/gi, '$1|disp=flip'); //rem linking within convert template (input ranges only)
regex(/(\{\{convert\|[\d\.,]+?\|nmi)(2|)(\|mi\2 km\2|\|km\2 mi\2|)(?=[|}])/gi, '$1$2|km$2 mi$2'); //putting miles first in nautical mile conversion
regex(/(\{\{convert\|[\d\.,]+?\|(?:lb|oz|°?F))(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]+?)*(?=\})/gi, '$1$2|disp=flip'); //putting pounds and °C first
// regex(/(\{\{(?:in|ft|mi|[mck]?m)[23]?\sto\s(?:in|ft|mi|[mck]?m)[23]?[^\}]*?)\|wiki=(?:yes|no)/gi, '$1');
//manipulating "|disp=flip" parameter where already "flipped"
regex(/(\{\{convert\|[\d\.,]+?\|\w{1,4}(?:\|\w{1,4}|)?(?:\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)(\|disp=flip)(\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)+(?=\})/gi, '$1$3$2'); //reordering flipping parameter within convert template (last parameter)
regex(/(\{\{convert\|[\d\.,]+?\|(?:(?:sq|cu|)(?:[mck]?m|ha)(?:2|3|))(?:\|(?:sq|cu|)(?:in|ft|yd|mi|acre)(?:2|3|))?(\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)\|disp=flip(?=\})/gi, '$1$2'); //rem flipping within convert template (Imperial, sq and cubed)
regex(/(\{\{convert\|[\d\.,]+?(?:\|kph|km\/h|)(?:\|mi|miles?|mph)?(\|\d)?(?:\|(?:sp|adj|abbr|lk|sigfig|sortable)=[^\|\}]*)*)\|disp=flip(?=\})/gi, '$1$2'); //rem flipping within convert template (Imperial, sq and cubed)
}
function ohc_ENGVAR_insert_template(v) {
// Add a template to the article identifying English variant
var box = document.editform.wpTextbox1;
var article = box.value;
// Build a string with "Month YYYY"
var dateobj = new Date();
var month = ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October', 'November', 'December'];
var datestr = month[dateobj.getMonth()] + ' ' + dateobj.getFullYear();
// Matches "Use Australian English" or "EngvarA"
var reA = new RegExp('{{[_ ]*(?:[Uu]se[_ ]+Australian[_ ]+English|[Ee]ngvarA)[_ ]*(?:|\\|[ ]*date[ ]*=[^{}\\|]*)[ ]*}}', 'gi');
// Matches "Use British English" or "EngvarB"
var reB = new RegExp('{{[_ ]*(?:[Uu]se[_ ]+British[_ ]+English|[Ee]ngvarB)[_ ]*(?:|\\|[ ]*date[ ]*=[^{}\\|]*)[ ]*}}', 'gi');
// Matches "Use British (Oxford) English", "Use British English Oxford spelling" or "EngvarOx"
var reOx = new RegExp('{{[_ ]*(?:[Uu]se[_ ]+British[_ ]+\\(Oxford\\)[_ ]+English|[Uu]se[_ ]+British[_ ]+English[_ ]+Oxford[_ ]+[Ss]pelling|[Ee]ngvarOx)[_ ]*(?:|\\|[ ]*date[ ]*=[^{}\\|]*)[ ]*}}', 'gi');
// Matches "Use Canadian English" or "EngvarC"
var reC = new RegExp('{{[_ ]*(?:[Uu]se[_ ]+Canadian[_ ]+English|[Ee]ngvarC)[_ ]*(?:|\\|[ ]*date[ ]*=[^{}\\|]*)[ ]*}}', 'gi');
// Matches "Use American English"
var reU = new RegExp('{{[_ ]*(?:[Uu]se[_ ]+American[_ ]+English)[_ ]*(?:|\\|[ ]*date[ ]*=[^{}\\|]*)[ ]*}}', 'gi');
// Matches "Use Indian English"
var reI = new RegExp('{{[_ ]*(?:[Uu]se[_ ]+Indian[_ ]+English)[_ ]*(?:|\\|[ ]*date[ ]*=[^{}\\|]*)[ ]*}}', 'gi');
var reg;
var template;
switch (v) {
case 'A':
template = '{{Use Australian English|date=' + datestr + '}}';
reg = reA;
break;
case 'B':
template = '{{Use British English|date=' + datestr + '}}';
reg = reB;
break;
case 'Ox':
template = '{{Use British English Oxford spelling|date=' + datestr + '}}';
reg = reOx;
break;
case 'C':
template = '{{Use Canadian English|date=' + datestr + '}}';
reg = reC;
break;
case 'U':
template = '{{Use American English|date=' + datestr + '}}';
reg = reU;
break;
case 'I':
template = '{{Use Indian English|date=' + datestr + '}}';
reg = reI;
break;
}
// Replace with existing variants
article = article.replace(reA, template);
article = article.replace(reB, template);
article = article.replace(reOx, template);
article = article.replace(reC, template);
article = article.replace(reU, template);
article = article.replace(reI, template);
// Prepend template if not already tagged
if (article.search(reg) === -1) {
article = template + '\r\n' + article;
}
box.value = article;
}
function ohc_ENGVAR_edit_summary(v) {
//Add a tag to the summary box
setoptions(minor = 'true');
//removed ",watch='false'" in response to user notification 13 Nov. 2010
var variation = 'English';
switch (v) {
case 'A':
variation = 'Australian English';
break;
case 'B':
variation = 'British English';
break;
case 'Ox':
variation = 'British English Oxford';
break;
case 'C':
variation = 'Canadian English';
break;
case 'U':
variation = 'American English';
break;
case 'I':
variation = 'Indian English';
break;
}
setreason(variation + ' spelling per [[WP:ENGVAR]] by [[User:Ohconfucius/EngvarB|script]]', 'append');
}
