مدیاویکی:Gadget-Extra-Editbuttons-persiantools.js: تفاوت میان نسخهها
ظاهر
imported>Ebrahim بدون خلاصۀ ویرایش |
imported>Ebrahim بیاستفاده |
||
| خط ۱: | خط ۱: | ||
/* | var EE_faChrs = "ءاآأإئؤبپتثجچحخدذرزژسشصضطظعغفقکگلمنوهیةيک" + "ًٌٍَُِّْ"; | ||
// < | var EE_faNums = "۰۱۲۳۴۵۶۷۸۹"; | ||
/** | var EE_arNums = "٠١٢٣٤٥٦٧٨٩"; | ||
* | //here we will list none farsi chars like ە ە which is Kurdish char instead of ه ه (Farsi) | ||
var NoneFarsi={//حروف کردی به فارسی | |||
'ہ':'ه',//Urdu ہ > ه ه (Farsi) | |||
'ى':'ی',//Urdu ى > ی | |||
'ې':'ی',//Uyghur ې >ی | |||
'ە':'ه',//Kurdish ە > ه ه (Farsi) | |||
'ھ':'ه', | |||
} | |||
var tupN = []; | |||
var tupO = []; | |||
//Also it uses variables of [[مدیاویکی:Gadget-Extra-Editbuttons-Dictionary.js]] | |||
/* | |||
* Javascript Diff Algorithm | |||
* http://ejohn.org/projects/javascript-diff-algorithm/ | |||
*/ | |||
function links_underline(str, rev_type) { | |||
//this function is used to have better results for Diff Algorithm in wikilinks | |||
var falinks = str.match(/\[\[.*?\]\]/g); | |||
if (falinks) { | |||
if (rev_type == 'Start') { | |||
for (var i = 0; i < falinks.length; i++) { | |||
var item_s = falinks[i]; | |||
var intem_u = falinks[i].replace(/\s/g, '_'); | |||
str = str.replace(item_s, intem_u); | |||
} | |||
} else { | |||
for (var i = 0; i < falinks.length; i++) { | |||
var item_s = falinks[i].replace(/\_/g, ' '); | |||
var intem_u = falinks[i]; | |||
str = str.replace(intem_u, item_s); | |||
} | |||
} | |||
}; | |||
return str; | |||
} | |||
function escape(s) { | |||
//Diff Algorithm's functions | |||
var n = s; | |||
n = n.replace(/&/g, "&"); | |||
n = n.replace(/</g, "<"); | |||
n = n.replace(/>/g, ">"); | |||
n = n.replace(/"/g, """); | |||
return n; | |||
} | |||
function di_escape(s) { | |||
//Diff Algorithm's functions | |||
var n = s; | |||
n = n.replace(/&/g, "&"); | |||
n = n.replace(/</g, "<"); | |||
n = n.replace(/>/g, ">"); | |||
n = n.replace(/"/g, '"'); | |||
return n; | |||
} | |||
function diffString(o, n) { | |||
//Diff Algorithm's functions | |||
tupN = []; | |||
tupO = []; | |||
o = o.replace(/\s+$/, ''); | |||
n = n.replace(/\s+$/, ''); | |||
var out = diff(o == "" ? [] : o.split(/\s+/), n == "" ? [] : n.split(/\s+/)); | |||
var oSpace = o.match(/\s+/g); | |||
if (oSpace == null) { | |||
oSpace = ["\n"]; | |||
} else { | |||
oSpace.push("\n"); | |||
} | |||
var nSpace = n.match(/\s+/g); | |||
if (nSpace == null) { | |||
nSpace = ["\n"]; | |||
} else { | |||
nSpace.push("\n"); | |||
} | |||
if (out.n.length == 0) { | |||
for (var i = 0; i < out.o.length; i++) { | |||
tupO.push(escape(out.o[i])) | |||
} | |||
} else { | |||
if (out.n[0].text == null) { | |||
for (n = 0; n < out.o.length && out.o[n].text == null; n++) { | |||
tupO.push(escape(out.o[n])); | |||
} | |||
} | |||
for (var i = 0; i < out.n.length; i++) { | |||
if (out.n[i].text == null) { | |||
tupN.push(escape(out.n[i])); | |||
} else { | |||
for (n = out.n[i].row + 1; n < out.o.length && out.o[n].text == null; n++) { | |||
tupO.push(escape(out.o[n])); | |||
} | |||
} | |||
} | |||
} | |||
o = ''; | |||
n = ''; | |||
} | |||
function diff(o, n) { | |||
//Diff Algorithm's functions | |||
var ns = {}; | |||
var os = {}; | |||
for (var i = 0; i < n.length; i++) { | |||
if (ns[n[i]] == null) ns[n[i]] = { | |||
rows: [], | |||
o: null | |||
}; | |||
ns[n[i]].rows.push(i); | |||
} | |||
for (var i = 0; i < o.length; i++) { | |||
if (os[o[i]] == null) os[o[i]] = { | |||
rows: [], | |||
n: null | |||
}; | |||
os[o[i]].rows.push(i); | |||
} | |||
for (var i in ns) { | |||
if (ns[i].rows.length == 1 && typeof (os[i]) != "undefined" && os[i].rows.length == 1) { | |||
n[ns[i].rows[0]] = { | |||
text: n[ns[i].rows[0]], | |||
row: os[i].rows[0] | |||
}; | |||
o[os[i].rows[0]] = { | |||
text: o[os[i].rows[0]], | |||
row: ns[i].rows[0] | |||
}; | |||
} | |||
} | |||
for (var i = 0; i < n.length - 1; i++) { | |||
if (n[i].text != null && n[i + 1].text == null && n[i].row + 1 < o.length && o[n[i].row + 1].text == null && n[i + 1] == o[n[i].row + 1]) { | |||
n[i + 1] = { | |||
text: n[i + 1], | |||
row: n[i].row + 1 | |||
}; | |||
o[n[i].row + 1] = { | |||
text: o[n[i].row + 1], | |||
row: i + 1 | |||
}; | |||
} | |||
} | |||
for (var i = n.length - 1; i > 0; i--) { | |||
if (n[i].text != null && n[i - 1].text == null && n[i].row > 0 && o[n[i].row - 1].text == null && n[i - 1] == o[n[i].row - 1]) { | |||
n[i - 1] = { | |||
text: n[i - 1], | |||
row: n[i].row - 1 | |||
}; | |||
o[n[i].row - 1] = { | |||
text: o[n[i].row - 1], | |||
row: i - 1 | |||
}; | |||
} | |||
} | |||
return { | |||
o: o, | |||
n: n | |||
}; | |||
} | |||
function RevertBug(diffO, diffN, str) { | |||
//Diff Algorithm's functions + Reverting Bug's functions | |||
for (var i = 0; i < diffN.length; i++) { | |||
//Checking Interwikis' Links | |||
var diffN_di = di_escape(diffN[i]) | |||
var diffO_di = di_escape(diffO[i]) | |||
var item = diffN_di | |||
var regex = /\[\[([a-z]{2,3}|[a-z]{2,3}\-[a-z\-]{2,}|simple)(\s|_|)\:(.*?)(\s|_|\:.*|)\]\]/g | |||
var interwikis = item.match(regex); | |||
if (interwikis != null) { | |||
str = str.replace(diffN_di, diffO_di); | |||
}; | |||
//Checking Files' Links | |||
if (item.replace(/\|/g, "") != item) { | |||
var regex = /\[\[ *(?:پرونده|تصویر|[Ff]ile|[Ii]mage)(\s|_|)\:(\s|_|)(.*?)\|/g | |||
} else { | |||
var regex = /\[\[ *(?:پرونده|تصویر|[Ff]ile|[Ii]mage)(\s|_|)\:(\s|_|)(.*?)\]\]/g | |||
}; | |||
var filelinkN = diffN_di.match(regex); | |||
var filelinkO = diffO_di.match(regex); | |||
if (filelinkN != null) { | |||
str = str.replace(filelinkN, filelinkO); | |||
}; | |||
//Checking User's Sign Link | |||
var regex = /\[\[(\s|_|)([Uu]ser|کاربر|بحث کاربر|بحث_کاربر|ویژه)(\s|_|)\:/g | |||
var UserSign = item.match(regex); | |||
if (UserSign != null) { | |||
str = str.replace(diffN_di, diffO_di); | |||
}; | |||
//Checking URLs | |||
var regex = /(\[\/\/[\w\-]+?\.wiki|https?\:\/\/)(\S+)/g | |||
var URLlinkN = diffN_di.match(regex); | |||
var URLlinkO = diffO_di.match(regex); | |||
if (URLlinkN != null) { | |||
str = str.replace(URLlinkN, URLlinkO); | |||
}; | |||
}; | |||
diffO = ''; | |||
diffN = ''; | |||
return str; | |||
} | |||
/** fromEntityToUtf8 | |||
* | |||
* Description: Takes an HTML entitiy like v and returns the | |||
* Unicode equivalent of it (in this example, letter "v"). | |||
* | |||
* This is needed because older browsers sometimes turned in HTML | |||
* entities instead of Unicode characters. | |||
* | * | ||
*/ | */ | ||
function fromEntityToUtf8(str) { | |||
return str.replace(/&#([0-9]+);/g, function (s, n, ofs, all) { | |||
return String.fromCharCode(n); | |||
}); | |||
} | |||
/** fromUtf8ToEntity | |||
* | |||
* Description: Takes a Unicode character like the letter "v" and | |||
* returns the equivalent HTML entity (in this example, v). | |||
* | |||
* This is not in use anymore and is only kept for historical | |||
* purposes. | |||
* | |||
*/ | |||
function fromUtf8ToEntity(str) { | |||
return str.replace(/([^\x00-\x7f])/g, function (s, c, ofs, all) { | |||
c = String(c); | |||
return "&#" + c.charCodeAt(0) + ";"; | |||
}); | |||
} | |||
function digits(str) { | |||
//These two lines are for reverting link's bugs! | |||
str = links_underline(str, 'Start') | |||
var old_text = str; | |||
// end | |||
str = fromEntityToUtf8(str, true); | |||
var old = str; | |||
/* // فارسی به انگلیسی | |||
while (1 == 1) { | |||
for (var i = 0; i < 10; i++) { | |||
var reFaToEn = new RegExp("([A-Za-z0-9][^" + EE_faChrs + EE_faNums + "\\n\\{\\}\\|=]*)" + EE_faNums[i] + "([^" + EE_faNums + "\\n\\{\\}\\|=]*?[A-Za-z0-9])", "g"); | |||
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2"); | |||
old = old.replace(/¬!¬/g, ""); | |||
var reFaToEn = new RegExp("(^|[\\n=>])([^" + EE_faChrs + EE_faNums + "\\n\\{\\}\\|=]*)" + EE_faNums[i] + "([^" + EE_faNums + "\\n\\{\\}\\|=]*?[A-Za-z0-9])", "g"); | |||
old = old.replace(reFaToEn, "$1$2¬!¬" + i + "$3"); | |||
old = old.replace(/¬!¬/g, ""); | |||
var reFaToEn = new RegExp("([A-Za-z0-9][^" + EE_faChrs + EE_faNums + "\\n\\{\\}\\|=]*)" + EE_faNums[i] + "([^" + EE_faNums + "\\n\\{\\}\\|=]*?[\\n\\{\\}\\|<$])", "g"); | |||
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2"); | |||
old = old.replace(/¬!¬/g, ""); | |||
} | |||
if (old == str) break; | |||
str = old; | |||
} | |||
*/ | |||
// انگلیسی به فارسی | |||
while (1 == 1) { | |||
for (var i = 0; i < 10; i++) { | |||
var reEnToFa = new RegExp("([" + EE_faChrs + ">][^A-Za-z0-9\\n\\{\\}\\|=]*)" + i + "([^A-Za-z\\n\\{\\}\\|=]*?[<" + EE_faChrs + EE_faNums + "])", "g"); | |||
old = old.replace(reEnToFa, "$1" + EE_faNums[i] + "$2"); | |||
var reEnToFa = new RegExp("(^|[=\\n\\{\\}\\|>])([^A-Za-z0-9\\n\\{\\}\\|=]*)" + i + "([^A-Za-z\\n\\{\\}\\|=]*?[\\n\\{\\}\\|<$])", "g"); | |||
old = old.replace(reEnToFa, "$1$2" + EE_faNums[i] + "$3"); | |||
} | |||
if (old == str) break; | |||
str = old; | |||
} | |||
// فارسی به انگلیسی (آنهایی که صددرصد باید انگلیسی شوند) | |||
while (1 == 1) { | |||
for (var i = 0; i < 10; i++) { | |||
var reFaToEn = new RegExp('(style|colspan|rowspan|cellspacing|width|size|border|thumbtime)( *= *[^\\|\\n]*?)' + EE_faNums[i] + '(.*?\\|)', 'g'); | |||
old = old.replace(reFaToEn, "$1$2¬!¬" + i + "$3"); | |||
old = old.replace(/¬!¬/g, ""); | |||
var reFaToEn = new RegExp('(<math.*?>[^<]*?)' + EE_faNums[i] + '([^<]*<\\/math>)', 'g'); | |||
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2"); | |||
old = old.replace(/¬!¬/g, ""); | |||
var reFaToEn = new RegExp('(<source.*?>[^<]*?)' + EE_faNums[i] + '([^<]*<\\/source>)', 'g'); | |||
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2"); | |||
old = old.replace(/¬!¬/g, ""); | |||
var reFaToEn = new RegExp('(https?://[^\\s\\r\\n\\|\\}]*?)' + EE_faNums[i], 'g'); | |||
old = old.replace(reFaToEn, "$1¬!¬" + i); | |||
old = old.replace(/¬!¬/g, ""); | |||
var reFaToEn = new RegExp('(' + EE_faNums[i] + ')پیکسل', 'g'); | |||
old = old.replace(reFaToEn, "$1¬!¬پیکسل" + i); | |||
old = old.replace(/¬!¬/g, ""); | |||
} | |||
if (old == str) break; | |||
str = old; | |||
} | |||
// عربی به فارسی | |||
for (var i = 0; i < 10; i++) { | |||
str = str.replace(new RegExp(EE_arNums[i], 'g'), EE_faNums[i]); | |||
} | } | ||
//These three lines are for reverting link's bugs! | |||
diffString(old_text, str); | |||
str = RevertBug(tupO, tupN, str); | |||
str = links_underline(str, 'End') | |||
//end | |||
// Decimal point, and thousands' separator | |||
str = str.replace(/([۱۲۳۴۵۶۷۸۹۰])\.([۱۲۳۴۵۶۷۸۹۰])/g, '$1٫$2'); | |||
str = str.replace(/([۱۲۳۴۵۶۷۸۹۰]),([۱۲۳۴۵۶۷۸۹۰])/g, '$1٬$2'); | |||
return str; | |||
} | |||
function Punctuation(str) { | |||
str = str.replace(/ *(\<\/? ?br ?\/?\>|\{\{بر\}\}) */g, "{{سخ}}"); | |||
str = str.replace(/([،\.])([^\s\.\(\)«»\"\[\]\<\>\d\w\{\}\|۰-۹])/g, "$1 $2"); | |||
str = str.replace(/([\(«])\s/g, '$1'); | |||
str = str.replace(/\s([\)»])/g, '$1'); | |||
str = str.replace(/٬\s/g, "، "); | |||
str = str.replace(/(\<\/ref\>)\s+(\<ref)/g, "$1$2"); | |||
// Format headings level 2 and above | |||
str = str.replace(/(\={2,})\s*([^\=]*?)\s*(\={2,})/g, "$1 $2 $3"); | |||
// TODO: remove extra lines AFTER this part | |||
// تغییرات جزئی که برای رباتها تعریف شده بود | |||
str = str.replace(/[\r\n]{3,}/g, "\n\n"); | |||
str = str.replace(/[\r\n]\s{1,}[\r\n]/g, "\n\n"); | |||
str = str.replace(/([^=])[\r\n]+(\=.*?\=[\r\n]+)/g, "$1\n\n$2"); | |||
str = str.replace(/[\s\r\n]+\<ref/g, "<ref"); | |||
str = str.replace(/([\r\n]?)[\s\r\n]+?\<\/ref\>/g, "$1</ref>"); | |||
// Add a space after the # or * for lists | |||
str = str.replace(/^([*#]+)([^*#:\s])/mg, "$1 $2"); | |||
// Remove extra newlines between two list lines | |||
old = ""; | |||
while (str != old) { | |||
old = str; | |||
str = str.replace(/(^|\n)(#+[^\n]*)\n\n+([#])/mg, "$1$2\n$3"); | |||
str = str.replace(/(^|\n)(\*+[^\n]*)\n\n+([\*])/mg, "$1$2\n$3"); | |||
} | } | ||
//برداشتن حروف نالازم در ابتدا و انتهای عنوان زیر بخشهای سطح ۲ به بالا | |||
var notneededs = ":,;'<>»«&^#@•→←↔↑↓—–…~٫،؛ٔ" | |||
for (var i = 0; i < 27; i++) { | |||
str = str.replace(new RegExp('((\=+){2,}) ' + notneededs[i], 'g'), "== "); | |||
str = str.replace(new RegExp(notneededs[i] + ' ((\=+){2,})', 'g'), " $1"); | |||
} | |||
// Redirect pages must start with #تغییرمسیر with no extra spaces | |||
// before or inside the تغییرمسیر part, and one space after it but | |||
// before the link | |||
str = str.replace(/^#\s*(REDIRECT|تغییر[ _]?مسیر)/ig, '#تغییرمسیر'); | |||
str = str.replace(/^#تغییرمسیر(\S)/g, '#تغییرمسیر $1'); | |||
// Remove extra newline between two lines both starting with a * | |||
str = str.replace(/(\n\*.*?)\n+(?=\n\*)/g, '$1'); | |||
// فاصله را از آخر خط پاک میکند | |||
str = str.replace(/([^=]) *$/mg, "$1"); | |||
// اصلاح {{•}} | |||
str = str.replace(/[\n\s]*\{\{[•·ن](w?)\}\}\s*/g, "{{•$1}} "); | |||
// برای گذاشتن گیومه برای خاصیتهای برچسب طبق اکسامال | |||
// اشکال مشخصی که دارد این است که همهٔ نویسههای قابل قبول برای اکسامال را نمیپذیرد، چه نویسههایی لازم است؟ | |||
var old = ""; | |||
while (old != str) { | |||
old = str; | |||
str = str.replace(/(\<\w*(?:\s\w*=['"\w\d]+)*\s+\w*=)([\w\d_]+)((?:\s\w*=['"\w\d]+)*\s?\/?\>)/g, "$1\"$2\"$3") | |||
// first version: .replace(/\<(\w*\s+\w*=)(\w+[\w\d]*)\>/, "<$1\"$2\">"); | |||
} | |||
// Remove spaces preceding the }} closing tag for templates | |||
str = str.replace(/\s+\}\}/g, '}}'); | |||
// Remove space after ( and before ) if there are Persian characters | |||
// on both sides; also, add a space before ( and after ) in the same | |||
// situation | |||
re = new RegExp("([" + EE_faChrs + "]+)\\s*\\(\\s*([" + EE_faChrs + "]+)", "g"); | |||
str = str.replace(re, "$1 ($2"); | |||
re = new RegExp("([" + EE_faChrs + "]+)\\s*\\)\\s*([" + EE_faChrs + "]+)", "g"); | |||
str = str.replace(re, "$1) $2"); | |||
// Full stop and comma should be before citation. | |||
old = ""; | |||
while (old != str) { | |||
old = str; | |||
str = str.replace(/\.? ?(<ref>.*?<\/ref>) ?\./g, '.$1'); | |||
str = str.replace(/\،? ?(<ref>.*?<\/ref>) ?\،/g, '،$1'); | |||
} | } | ||
old = ""; | |||
while (old != str) { | |||
old = str; | |||
// Convert , to ، if there are Persian characters on both sides of it | |||
// and also remove any spaces between the words on each side and the | |||
// Persian comma itself. | |||
// NOTE: we will add a space after the comma later on | |||
var re = new RegExp("([ " + EE_faChrs + "]+),([ " + EE_faChrs + "]+)", "g"); | |||
str = str.replace(re, "$1،$2"); | |||
// Remove space preceding puncations | |||
str = str.replace(/ ([؟،:؛!\.])/g, "$1"); | |||
// Add space after punctuations | |||
// NOTE: Adds a space after :, which affects internal links (categories, images, etc) | |||
re = new RegExp("([" + EE_faChrs + "]+)([؟،؛!\.])([" + EE_faChrs + "]+)", "g"); | |||
str = str.replace(re, "$1$2 $3"); | |||
} | } | ||
// Remove unnecessary space caused by last line in category links (it had bug for پرونده:) | |||
re = new RegExp("\\[\\[(رده|الگو|ویکی\u200cپدیا)\\:\\s+", "g"); | |||
str = str.replace(re, "[[$1\:"); | |||
// str = str.trim(); //Removing \n and \r from first and end of pages | |||
); | return str; | ||
return | } | ||
/** Dictation Tool | |||
* | |||
* Description: Correcting ZWNJ and diction mistakes | |||
* it uses [[مدیاویکی:Gadget-Extra-Editbuttons-Dictionary.js]] as dictionary. | |||
* | |||
*/ | |||
function Regex_Replace(W1, W2, Extensions, str) { | |||
var regex = new RegExp("(^|[^" + EE_faChrs + "])(\\s|\u200c|\_|)(" + W1 + ")(\\s|\_)(" + W2 + ")(\\s|\u200c|\_|)(" + Extensions + ")($|[^" + EE_faChrs + "])", "g"); | |||
str = str.replace(regex, "$1$2$3\u200c$5$6$7$8"); | |||
return str; | |||
} | |||
function ZWNJ_Dictation(str) { | |||
//These two lines are for reverting link's bugs! | |||
str = links_underline(str, 'Start') | |||
var old_text = str; | |||
// end | |||
//for Complexes | |||
for (var word in Complexes) { | |||
var W1 = word; | |||
var W2 = Complexes[word]; | |||
var Extensions = "ی|ها|های|هایی|هایم|هایت|هایش|هایمان|هایتان|هایشان|"; | |||
str = Regex_Replace(W1, W2, Extensions, str) | |||
} | |||
//for last name | |||
var W1 = Person_Name; | |||
var W2 = "ی|زاده|نیا|پور|گان|فر|نژاد|یان|یها|یها"; | |||
var Extensions = "ی|"; | |||
str = Regex_Replace(W1, W2, Extensions, str) | |||
//for Abad | |||
var W1 = Person_Name + "|" + Add2Abad; | |||
var W2 = "آباد"; | |||
var Extensions = "زاده|نیا|پور|گان|فر|نژاد|ی|یان|ها|های|هایی|یها|یها|"; | |||
str = Regex_Replace(W1, W2, Extensions, str) | |||
//for First name | |||
for (var word in FirstNameComplex) { | |||
var W1 = word; | |||
var W2 = FirstNameComplex[word]; | |||
var regex = new RegExp("(^|[^" + EE_faChrs + "]|\\s|\_)(" + W1 + ")(\\s|\_)(" + W2 + ")(\\s|\_)($|[^" + EE_faChrs + "]|[^+ EE_faChrs +])", "g"); | |||
str = str.replace(regex, "$1$2\u200c$4$5$6"); | |||
} | |||
//for colors | |||
var W1 = Color_Name; | |||
var W2 = "فام|گون"; | |||
var Extensions = "زاده|نیا|پور|گان|فر|نژاد|ی|ها|های|هایی|یها|یها|هایم|هایت|هایش|هایمان|هایتان|هایشان|"; | |||
str = Regex_Replace(W1, W2, Extensions, str) | |||
//for Numbers | |||
var W1 = Farsi_Numbers; | |||
var W2 = "گانه|ماهه"; | |||
var Extensions = "زاده|نیا|پور|گان|فر|نژاد|ی|ها|های|هایی|هایم|هایت|هایش|هایمان|هایتان|هایشان|"; | |||
str = Regex_Replace(W1, W2, Extensions, str) | |||
//wrong dictation | |||
for (var word in ForReplace) { | |||
var W1 = word; | |||
var W2 = ForReplace[word]; | |||
var regex = new RegExp("(^|[^" + EE_faChrs + "])(\\s|\u200c|_|)(" + W1 + ")(\\s|\u200c|_|)($|[^" + EE_faChrs + "])", "g"); | |||
str = str.replace(regex, "$1$2" + W2 + "$4$5"); | |||
} | |||
//Function for removing incorrect ZWNJs | |||
str=persianTools.cleanUselessZwnj(str) | |||
//حذف فاصلهٔ مجازی قبل و بعد از سجاوندی | |||
str = str.replace(/\u200c([\n\s\.،«»\:\(\)\؛\؟\?\;\$\!\@\-\=\+\\])/g, '$1'); | |||
str = str.replace(/([\n\s\.،«»\:\(\)\؛\؟\?\;\$\!\@\-\=\+\\])\u200c/g, '$1'); | |||
//These three lines are for reverting link's bugs! | |||
diffString(old_text, str); | |||
str = RevertBug(tupO, tupN, str); | |||
str = links_underline(str, 'End') | |||
//end | |||
return str; | |||
} | } | ||
نسخهٔ ۱۶ ژوئن ۲۰۱۳، ساعت ۱۵:۰۱
var EE_faChrs = "ءاآأإئؤبپتثجچحخدذرزژسشصضطظعغفقکگلمنوهیةيک" + "ًٌٍَُِّْ";
var EE_faNums = "۰۱۲۳۴۵۶۷۸۹";
var EE_arNums = "٠١٢٣٤٥٦٧٨٩";
//here we will list none farsi chars like ە ە which is Kurdish char instead of ه ه (Farsi)
var NoneFarsi={//حروف کردی به فارسی
'ہ':'ه',//Urdu ہ > ه ه (Farsi)
'ى':'ی',//Urdu ى > ی
'ې':'ی',//Uyghur ې >ی
'ە':'ه',//Kurdish ە > ه ه (Farsi)
'ھ':'ه',
}
var tupN = [];
var tupO = [];
//Also it uses variables of [[مدیاویکی:Gadget-Extra-Editbuttons-Dictionary.js]]
/*
* Javascript Diff Algorithm
* http://ejohn.org/projects/javascript-diff-algorithm/
*/
function links_underline(str, rev_type) {
//this function is used to have better results for Diff Algorithm in wikilinks
var falinks = str.match(/\[\[.*?\]\]/g);
if (falinks) {
if (rev_type == 'Start') {
for (var i = 0; i < falinks.length; i++) {
var item_s = falinks[i];
var intem_u = falinks[i].replace(/\s/g, '_');
str = str.replace(item_s, intem_u);
}
} else {
for (var i = 0; i < falinks.length; i++) {
var item_s = falinks[i].replace(/\_/g, ' ');
var intem_u = falinks[i];
str = str.replace(intem_u, item_s);
}
}
};
return str;
}
function escape(s) {
//Diff Algorithm's functions
var n = s;
n = n.replace(/&/g, "&");
n = n.replace(/</g, "<");
n = n.replace(/>/g, ">");
n = n.replace(/"/g, """);
return n;
}
function di_escape(s) {
//Diff Algorithm's functions
var n = s;
n = n.replace(/&/g, "&");
n = n.replace(/</g, "<");
n = n.replace(/>/g, ">");
n = n.replace(/"/g, '"');
return n;
}
function diffString(o, n) {
//Diff Algorithm's functions
tupN = [];
tupO = [];
o = o.replace(/\s+$/, '');
n = n.replace(/\s+$/, '');
var out = diff(o == "" ? [] : o.split(/\s+/), n == "" ? [] : n.split(/\s+/));
var oSpace = o.match(/\s+/g);
if (oSpace == null) {
oSpace = ["\n"];
} else {
oSpace.push("\n");
}
var nSpace = n.match(/\s+/g);
if (nSpace == null) {
nSpace = ["\n"];
} else {
nSpace.push("\n");
}
if (out.n.length == 0) {
for (var i = 0; i < out.o.length; i++) {
tupO.push(escape(out.o[i]))
}
} else {
if (out.n[0].text == null) {
for (n = 0; n < out.o.length && out.o[n].text == null; n++) {
tupO.push(escape(out.o[n]));
}
}
for (var i = 0; i < out.n.length; i++) {
if (out.n[i].text == null) {
tupN.push(escape(out.n[i]));
} else {
for (n = out.n[i].row + 1; n < out.o.length && out.o[n].text == null; n++) {
tupO.push(escape(out.o[n]));
}
}
}
}
o = '';
n = '';
}
function diff(o, n) {
//Diff Algorithm's functions
var ns = {};
var os = {};
for (var i = 0; i < n.length; i++) {
if (ns[n[i]] == null) ns[n[i]] = {
rows: [],
o: null
};
ns[n[i]].rows.push(i);
}
for (var i = 0; i < o.length; i++) {
if (os[o[i]] == null) os[o[i]] = {
rows: [],
n: null
};
os[o[i]].rows.push(i);
}
for (var i in ns) {
if (ns[i].rows.length == 1 && typeof (os[i]) != "undefined" && os[i].rows.length == 1) {
n[ns[i].rows[0]] = {
text: n[ns[i].rows[0]],
row: os[i].rows[0]
};
o[os[i].rows[0]] = {
text: o[os[i].rows[0]],
row: ns[i].rows[0]
};
}
}
for (var i = 0; i < n.length - 1; i++) {
if (n[i].text != null && n[i + 1].text == null && n[i].row + 1 < o.length && o[n[i].row + 1].text == null && n[i + 1] == o[n[i].row + 1]) {
n[i + 1] = {
text: n[i + 1],
row: n[i].row + 1
};
o[n[i].row + 1] = {
text: o[n[i].row + 1],
row: i + 1
};
}
}
for (var i = n.length - 1; i > 0; i--) {
if (n[i].text != null && n[i - 1].text == null && n[i].row > 0 && o[n[i].row - 1].text == null && n[i - 1] == o[n[i].row - 1]) {
n[i - 1] = {
text: n[i - 1],
row: n[i].row - 1
};
o[n[i].row - 1] = {
text: o[n[i].row - 1],
row: i - 1
};
}
}
return {
o: o,
n: n
};
}
function RevertBug(diffO, diffN, str) {
//Diff Algorithm's functions + Reverting Bug's functions
for (var i = 0; i < diffN.length; i++) {
//Checking Interwikis' Links
var diffN_di = di_escape(diffN[i])
var diffO_di = di_escape(diffO[i])
var item = diffN_di
var regex = /\[\[([a-z]{2,3}|[a-z]{2,3}\-[a-z\-]{2,}|simple)(\s|_|)\:(.*?)(\s|_|\:.*|)\]\]/g
var interwikis = item.match(regex);
if (interwikis != null) {
str = str.replace(diffN_di, diffO_di);
};
//Checking Files' Links
if (item.replace(/\|/g, "") != item) {
var regex = /\[\[ *(?:پرونده|تصویر|[Ff]ile|[Ii]mage)(\s|_|)\:(\s|_|)(.*?)\|/g
} else {
var regex = /\[\[ *(?:پرونده|تصویر|[Ff]ile|[Ii]mage)(\s|_|)\:(\s|_|)(.*?)\]\]/g
};
var filelinkN = diffN_di.match(regex);
var filelinkO = diffO_di.match(regex);
if (filelinkN != null) {
str = str.replace(filelinkN, filelinkO);
};
//Checking User's Sign Link
var regex = /\[\[(\s|_|)([Uu]ser|کاربر|بحث کاربر|بحث_کاربر|ویژه)(\s|_|)\:/g
var UserSign = item.match(regex);
if (UserSign != null) {
str = str.replace(diffN_di, diffO_di);
};
//Checking URLs
var regex = /(\[\/\/[\w\-]+?\.wiki|https?\:\/\/)(\S+)/g
var URLlinkN = diffN_di.match(regex);
var URLlinkO = diffO_di.match(regex);
if (URLlinkN != null) {
str = str.replace(URLlinkN, URLlinkO);
};
};
diffO = '';
diffN = '';
return str;
}
/** fromEntityToUtf8
*
* Description: Takes an HTML entitiy like v and returns the
* Unicode equivalent of it (in this example, letter "v").
*
* This is needed because older browsers sometimes turned in HTML
* entities instead of Unicode characters.
*
*/
function fromEntityToUtf8(str) {
return str.replace(/&#([0-9]+);/g, function (s, n, ofs, all) {
return String.fromCharCode(n);
});
}
/** fromUtf8ToEntity
*
* Description: Takes a Unicode character like the letter "v" and
* returns the equivalent HTML entity (in this example, v).
*
* This is not in use anymore and is only kept for historical
* purposes.
*
*/
function fromUtf8ToEntity(str) {
return str.replace(/([^\x00-\x7f])/g, function (s, c, ofs, all) {
c = String(c);
return "&#" + c.charCodeAt(0) + ";";
});
}
function digits(str) {
//These two lines are for reverting link's bugs!
str = links_underline(str, 'Start')
var old_text = str;
// end
str = fromEntityToUtf8(str, true);
var old = str;
/* // فارسی به انگلیسی
while (1 == 1) {
for (var i = 0; i < 10; i++) {
var reFaToEn = new RegExp("([A-Za-z0-9][^" + EE_faChrs + EE_faNums + "\\n\\{\\}\\|=]*)" + EE_faNums[i] + "([^" + EE_faNums + "\\n\\{\\}\\|=]*?[A-Za-z0-9])", "g");
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2");
old = old.replace(/¬!¬/g, "");
var reFaToEn = new RegExp("(^|[\\n=>])([^" + EE_faChrs + EE_faNums + "\\n\\{\\}\\|=]*)" + EE_faNums[i] + "([^" + EE_faNums + "\\n\\{\\}\\|=]*?[A-Za-z0-9])", "g");
old = old.replace(reFaToEn, "$1$2¬!¬" + i + "$3");
old = old.replace(/¬!¬/g, "");
var reFaToEn = new RegExp("([A-Za-z0-9][^" + EE_faChrs + EE_faNums + "\\n\\{\\}\\|=]*)" + EE_faNums[i] + "([^" + EE_faNums + "\\n\\{\\}\\|=]*?[\\n\\{\\}\\|<$])", "g");
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2");
old = old.replace(/¬!¬/g, "");
}
if (old == str) break;
str = old;
}
*/
// انگلیسی به فارسی
while (1 == 1) {
for (var i = 0; i < 10; i++) {
var reEnToFa = new RegExp("([" + EE_faChrs + ">][^A-Za-z0-9\\n\\{\\}\\|=]*)" + i + "([^A-Za-z\\n\\{\\}\\|=]*?[<" + EE_faChrs + EE_faNums + "])", "g");
old = old.replace(reEnToFa, "$1" + EE_faNums[i] + "$2");
var reEnToFa = new RegExp("(^|[=\\n\\{\\}\\|>])([^A-Za-z0-9\\n\\{\\}\\|=]*)" + i + "([^A-Za-z\\n\\{\\}\\|=]*?[\\n\\{\\}\\|<$])", "g");
old = old.replace(reEnToFa, "$1$2" + EE_faNums[i] + "$3");
}
if (old == str) break;
str = old;
}
// فارسی به انگلیسی (آنهایی که صددرصد باید انگلیسی شوند)
while (1 == 1) {
for (var i = 0; i < 10; i++) {
var reFaToEn = new RegExp('(style|colspan|rowspan|cellspacing|width|size|border|thumbtime)( *= *[^\\|\\n]*?)' + EE_faNums[i] + '(.*?\\|)', 'g');
old = old.replace(reFaToEn, "$1$2¬!¬" + i + "$3");
old = old.replace(/¬!¬/g, "");
var reFaToEn = new RegExp('(<math.*?>[^<]*?)' + EE_faNums[i] + '([^<]*<\\/math>)', 'g');
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2");
old = old.replace(/¬!¬/g, "");
var reFaToEn = new RegExp('(<source.*?>[^<]*?)' + EE_faNums[i] + '([^<]*<\\/source>)', 'g');
old = old.replace(reFaToEn, "$1¬!¬" + i + "$2");
old = old.replace(/¬!¬/g, "");
var reFaToEn = new RegExp('(https?://[^\\s\\r\\n\\|\\}]*?)' + EE_faNums[i], 'g');
old = old.replace(reFaToEn, "$1¬!¬" + i);
old = old.replace(/¬!¬/g, "");
var reFaToEn = new RegExp('(' + EE_faNums[i] + ')پیکسل', 'g');
old = old.replace(reFaToEn, "$1¬!¬پیکسل" + i);
old = old.replace(/¬!¬/g, "");
}
if (old == str) break;
str = old;
}
// عربی به فارسی
for (var i = 0; i < 10; i++) {
str = str.replace(new RegExp(EE_arNums[i], 'g'), EE_faNums[i]);
}
//These three lines are for reverting link's bugs!
diffString(old_text, str);
str = RevertBug(tupO, tupN, str);
str = links_underline(str, 'End')
//end
// Decimal point, and thousands' separator
str = str.replace(/([۱۲۳۴۵۶۷۸۹۰])\.([۱۲۳۴۵۶۷۸۹۰])/g, '$1٫$2');
str = str.replace(/([۱۲۳۴۵۶۷۸۹۰]),([۱۲۳۴۵۶۷۸۹۰])/g, '$1٬$2');
return str;
}
function Punctuation(str) {
str = str.replace(/ *(\<\/? ?br ?\/?\>|\{\{بر\}\}) */g, "{{سخ}}");
str = str.replace(/([،\.])([^\s\.\(\)«»\"\[\]\<\>\d\w\{\}\|۰-۹])/g, "$1 $2");
str = str.replace(/([\(«])\s/g, '$1');
str = str.replace(/\s([\)»])/g, '$1');
str = str.replace(/٬\s/g, "، ");
str = str.replace(/(\<\/ref\>)\s+(\<ref)/g, "$1$2");
// Format headings level 2 and above
str = str.replace(/(\={2,})\s*([^\=]*?)\s*(\={2,})/g, "$1 $2 $3");
// TODO: remove extra lines AFTER this part
// تغییرات جزئی که برای رباتها تعریف شده بود
str = str.replace(/[\r\n]{3,}/g, "\n\n");
str = str.replace(/[\r\n]\s{1,}[\r\n]/g, "\n\n");
str = str.replace(/([^=])[\r\n]+(\=.*?\=[\r\n]+)/g, "$1\n\n$2");
str = str.replace(/[\s\r\n]+\<ref/g, "<ref");
str = str.replace(/([\r\n]?)[\s\r\n]+?\<\/ref\>/g, "$1</ref>");
// Add a space after the # or * for lists
str = str.replace(/^([*#]+)([^*#:\s])/mg, "$1 $2");
// Remove extra newlines between two list lines
old = "";
while (str != old) {
old = str;
str = str.replace(/(^|\n)(#+[^\n]*)\n\n+([#])/mg, "$1$2\n$3");
str = str.replace(/(^|\n)(\*+[^\n]*)\n\n+([\*])/mg, "$1$2\n$3");
}
//برداشتن حروف نالازم در ابتدا و انتهای عنوان زیر بخشهای سطح ۲ به بالا
var notneededs = ":,;'<>»«&^#@•→←↔↑↓—–…~٫،؛ٔ"
for (var i = 0; i < 27; i++) {
str = str.replace(new RegExp('((\=+){2,}) ' + notneededs[i], 'g'), "== ");
str = str.replace(new RegExp(notneededs[i] + ' ((\=+){2,})', 'g'), " $1");
}
// Redirect pages must start with #تغییرمسیر with no extra spaces
// before or inside the تغییرمسیر part, and one space after it but
// before the link
str = str.replace(/^#\s*(REDIRECT|تغییر[ _]?مسیر)/ig, '#تغییرمسیر');
str = str.replace(/^#تغییرمسیر(\S)/g, '#تغییرمسیر $1');
// Remove extra newline between two lines both starting with a *
str = str.replace(/(\n\*.*?)\n+(?=\n\*)/g, '$1');
// فاصله را از آخر خط پاک میکند
str = str.replace(/([^=]) *$/mg, "$1");
// اصلاح {{•}}
str = str.replace(/[\n\s]*\{\{[•·ن](w?)\}\}\s*/g, "{{•$1}} ");
// برای گذاشتن گیومه برای خاصیتهای برچسب طبق اکسامال
// اشکال مشخصی که دارد این است که همهٔ نویسههای قابل قبول برای اکسامال را نمیپذیرد، چه نویسههایی لازم است؟
var old = "";
while (old != str) {
old = str;
str = str.replace(/(\<\w*(?:\s\w*=['"\w\d]+)*\s+\w*=)([\w\d_]+)((?:\s\w*=['"\w\d]+)*\s?\/?\>)/g, "$1\"$2\"$3")
// first version: .replace(/\<(\w*\s+\w*=)(\w+[\w\d]*)\>/, "<$1\"$2\">");
}
// Remove spaces preceding the }} closing tag for templates
str = str.replace(/\s+\}\}/g, '}}');
// Remove space after ( and before ) if there are Persian characters
// on both sides; also, add a space before ( and after ) in the same
// situation
re = new RegExp("([" + EE_faChrs + "]+)\\s*\\(\\s*([" + EE_faChrs + "]+)", "g");
str = str.replace(re, "$1 ($2");
re = new RegExp("([" + EE_faChrs + "]+)\\s*\\)\\s*([" + EE_faChrs + "]+)", "g");
str = str.replace(re, "$1) $2");
// Full stop and comma should be before citation.
old = "";
while (old != str) {
old = str;
str = str.replace(/\.? ?(<ref>.*?<\/ref>) ?\./g, '.$1');
str = str.replace(/\،? ?(<ref>.*?<\/ref>) ?\،/g, '،$1');
}
old = "";
while (old != str) {
old = str;
// Convert , to ، if there are Persian characters on both sides of it
// and also remove any spaces between the words on each side and the
// Persian comma itself.
// NOTE: we will add a space after the comma later on
var re = new RegExp("([ " + EE_faChrs + "]+),([ " + EE_faChrs + "]+)", "g");
str = str.replace(re, "$1،$2");
// Remove space preceding puncations
str = str.replace(/ ([؟،:؛!\.])/g, "$1");
// Add space after punctuations
// NOTE: Adds a space after :, which affects internal links (categories, images, etc)
re = new RegExp("([" + EE_faChrs + "]+)([؟،؛!\.])([" + EE_faChrs + "]+)", "g");
str = str.replace(re, "$1$2 $3");
}
// Remove unnecessary space caused by last line in category links (it had bug for پرونده:)
re = new RegExp("\\[\\[(رده|الگو|ویکی\u200cپدیا)\\:\\s+", "g");
str = str.replace(re, "[[$1\:");
// str = str.trim(); //Removing \n and \r from first and end of pages
return str;
}
/** Dictation Tool
*
* Description: Correcting ZWNJ and diction mistakes
* it uses [[مدیاویکی:Gadget-Extra-Editbuttons-Dictionary.js]] as dictionary.
*
*/
function Regex_Replace(W1, W2, Extensions, str) {
var regex = new RegExp("(^|[^" + EE_faChrs + "])(\\s|\u200c|\_|)(" + W1 + ")(\\s|\_)(" + W2 + ")(\\s|\u200c|\_|)(" + Extensions + ")($|[^" + EE_faChrs + "])", "g");
str = str.replace(regex, "$1$2$3\u200c$5$6$7$8");
return str;
}
function ZWNJ_Dictation(str) {
//These two lines are for reverting link's bugs!
str = links_underline(str, 'Start')
var old_text = str;
// end
//for Complexes
for (var word in Complexes) {
var W1 = word;
var W2 = Complexes[word];
var Extensions = "ی|ها|های|هایی|هایم|هایت|هایش|هایمان|هایتان|هایشان|";
str = Regex_Replace(W1, W2, Extensions, str)
}
//for last name
var W1 = Person_Name;
var W2 = "ی|زاده|نیا|پور|گان|فر|نژاد|یان|یها|یها";
var Extensions = "ی|";
str = Regex_Replace(W1, W2, Extensions, str)
//for Abad
var W1 = Person_Name + "|" + Add2Abad;
var W2 = "آباد";
var Extensions = "زاده|نیا|پور|گان|فر|نژاد|ی|یان|ها|های|هایی|یها|یها|";
str = Regex_Replace(W1, W2, Extensions, str)
//for First name
for (var word in FirstNameComplex) {
var W1 = word;
var W2 = FirstNameComplex[word];
var regex = new RegExp("(^|[^" + EE_faChrs + "]|\\s|\_)(" + W1 + ")(\\s|\_)(" + W2 + ")(\\s|\_)($|[^" + EE_faChrs + "]|[^+ EE_faChrs +])", "g");
str = str.replace(regex, "$1$2\u200c$4$5$6");
}
//for colors
var W1 = Color_Name;
var W2 = "فام|گون";
var Extensions = "زاده|نیا|پور|گان|فر|نژاد|ی|ها|های|هایی|یها|یها|هایم|هایت|هایش|هایمان|هایتان|هایشان|";
str = Regex_Replace(W1, W2, Extensions, str)
//for Numbers
var W1 = Farsi_Numbers;
var W2 = "گانه|ماهه";
var Extensions = "زاده|نیا|پور|گان|فر|نژاد|ی|ها|های|هایی|هایم|هایت|هایش|هایمان|هایتان|هایشان|";
str = Regex_Replace(W1, W2, Extensions, str)
//wrong dictation
for (var word in ForReplace) {
var W1 = word;
var W2 = ForReplace[word];
var regex = new RegExp("(^|[^" + EE_faChrs + "])(\\s|\u200c|_|)(" + W1 + ")(\\s|\u200c|_|)($|[^" + EE_faChrs + "])", "g");
str = str.replace(regex, "$1$2" + W2 + "$4$5");
}
//Function for removing incorrect ZWNJs
str=persianTools.cleanUselessZwnj(str)
//حذف فاصلهٔ مجازی قبل و بعد از سجاوندی
str = str.replace(/\u200c([\n\s\.،«»\:\(\)\؛\؟\?\;\$\!\@\-\=\+\\])/g, '$1');
str = str.replace(/([\n\s\.،«»\:\(\)\؛\؟\?\;\$\!\@\-\=\+\\])\u200c/g, '$1');
//These three lines are for reverting link's bugs!
diffString(old_text, str);
str = RevertBug(tupO, tupN, str);
str = links_underline(str, 'End')
//end
return str;
}