//<nowiki>
// Script for cleanup of file description pages. Script does NOT work with Internet Explorer 8 or lower. Currently known to work with Google Chrome (best functionality), Firefox (usually just as well, but having occasional bugs), Opera, Internet Explorer 9, and probably Safari.
// To use, add this line to your common.js file: importScript('User:Magog the Ogre/cleanup.js');
// mto_cleanup tagger (initially developed by Patstuart/Magog the Ogre)
/**********************
* Function which removes <nowiki> and <!--...--> from the text, and replaces them with a set of
* temporary strings. This is necessary, because functions which change text will may to leave the
* nowikis/comments intact. The temporary strings function as "markers", so that
* rebuild_comments_nowikis() can later be called and the nowikis/comments will return to the correct
* position, untouched.
* Returns: An array, whose 0th element contains the altered string, and whose 1st element contains
* another array which will focus as a set "tokens", which should be kept unaltered and passed to
* rebuild_comments_nowikis() later.
**********************/
function parse_comments_nowikis (text)
{
//constants
nw_regex = /<nowiki>((?:.|\n)*?)<\/nowiki>/;
c_regex = /<!\-\-((?:.|\n)*?)\-\->/;
cs_regex = /<\!\-\-(\s*categories\s*by\s*commonsense\s*)\-\->/i; /* special one for CommonSense.... causing grouping headaches */
//variables
var comments = new Array(0);
var nowikis = new Array(0);
var comments_cs = new Array(0);
var nw_com_order = new Array();
while (1)
{
next_nw = text.search(nw_regex);
next_c = text.search(c_regex );
next_cs = text.search(cs_regex);
if (next_nw == -1 && next_c == -1) break; /* cs_regex will be -1 if c_regex is -1 */
if (next_nw == -1 || (next_c !=-1 && next_c<next_nw))
{
if (next_cs === next_c)
{
var index = comments_cs.length;
comments_cs.push(cs_regex.exec(text)[1]);
text = text.replace(c_regex, "%%%MTOCSCOMMENT"+index+"%%%");
nw_com_order.push('s');
}
else
{
var index = comments.length;
comments.push(c_regex.exec(text)[1]);
text = text.replace(c_regex, "%%%MTOCOMMENT"+index+"%%%");
nw_com_order.push('c');
}
}
else
{
var index = nowikis.length;
nowikis.push(nw_regex.exec(text)[1]);
text = text.replace(nw_regex, "%%%MTONOWIKI"+index+"%%%");
nw_com_order.push('n');
}
}
return [text, [comments, nowikis, comments_cs, nw_com_order]];
}
/**********************
* See function immediately above for explanation
* remove_whitespace: when rebuilding nowikis, remove unnecessary whitespace (not shown in final version anyway)
* Returns: Rebuilt text.
**********************/
function rebuild_comments_nowikis(text, tokens, remove_whitespace)
{
comments = tokens[0];
nowikis = tokens[1];
comments_cs = tokens[2];
nw_com_order = tokens[3];
while (nw_com_order.length>0)
{
var next = nw_com_order.pop();
if (next=='s')
{text = text.replace("%%%MTOCSCOMMENT"+(comments_cs.length-1)+"%%%", "<!--"+comments_cs.pop()+"-->");}
else if (next=='c')
{text = text.replace("%%%MTOCOMMENT"+(comments.length-1)+"%%%", "<!--"+comments.pop()+"-->");}
else /* i.e., nw_com_order.pop was 'n'; also, mediawiki registers all whitespace inside nw's as just one space */
{
text_tmp = nowikis.pop();
if (remove_whitespace) {text_tmp = text_tmp.replace(/\s+/g, ' ');}
text = text.replace("%%%MTONOWIKI"+(nowikis.length)+"%%%", "<nowiki>"+text_tmp+"</"+"nowiki>");
}
}
return text;
}
/**********************
* Function which iterates over 'text' and replaces each instance of 'code' with 'replacement' until
* running the iteration no longer results in a change of the text.
* Parameter code: Should be a string or regular expression (both are allowed by the
* replace() function in Javascript).
* Parameter replacement: Should be a string or a functor (both are allowed by the replace() function
* in Javascript).
* Parameter text: The text that will be altered.
* Returns: The altered text.
**********************/
function iterative_replace(code, replacement, text)
{
while(1) //only headers that aren't already inside a template will suffice, per what seems right to me
{
temptext = text.replace(code, replacement);
if (temptext==text) break;
text=temptext;
}
return text;
}
function mto_parse_date(input_string, month_name_re /* case insensitive*/, month_number /* 1-12 */)
{
regexp1 = new RegExp("(^\\s*\\|\\s*[Dd]ate\\s*\\=\\s*)"+month_name_re+"[\\\\\\/\\-\\.\\s\\,]+(\\d{1,2})(?:st|nd|rd|th)?[\\\\\\/\\-\\.\\s\\,]+(\\d{4})(?!\\d)", "mi");
regexp2 = new RegExp("(^\\s*\\|\\s*[Dd]ate\\s*\\=\\s*)(\\d{1,2})(?:st|nd|rd|th)?[\\\\\\/\\-\\.\\s\\,]+"+month_name_re+"[\\\\\\/\\-\\.\\s\\,]+(\\d{4})(?!\\d)", "mi");
regexp3 = new RegExp("(^\\s*\\|\\s*[Dd]ate\\s*\\=\\s*)(\\d{4})[\\\\\\/\\-\\.\\s\\,]+"+month_name_re+"[\\\\\\/\\-\\.\\s\\,]+(\\d{1,2})(?:st|nd|rd|th)?(?!\\d)", "mi");
regexp4 = new RegExp("(^\\s*\\|\\s*[Dd]ate\\s*\\=\\s*)(\\d{4})[\\\\\\/\\-\\.\\s\\,]+(\\d{1,2})(?:st|nd|rd|th)?[\\\\\\/\\-\\.\\s\\,]+"+month_name_re, "mi");
regexp5 = new RegExp("(^\\s*\\|\\s*[Dd]ate\\s*\\=\\s*)(\\d{4})[\\\\\\/\\-\\.\\s\\,]+"+month_name_re, "mi");
regexp6 = new RegExp("(^\\s*\\|\\s*[Dd]ate\\s*\\=\\s*)"+month_name_re+"[\\\\\\/\\-\\.\\s\\,]+(\\d{4})(?!(?:[\\\\\\/\\-\\.\\s\\,]+\\d{1,2}|\\d))", "mi");
input_string = input_string.replace(regexp1, '$1{{Date|$3|'+month_number+'|$2}}');
input_string = input_string.replace(regexp2, '$1{{Date|$3|'+month_number+'|$2}}');
input_string = input_string.replace(regexp3, '$1{{Date|$2|'+month_number+'|$3}}');
input_string = input_string.replace(regexp4, '$1{{Date|$2|'+month_number+'|$3}}');
input_string = input_string.replace(regexp5, '$1{{Date|$2|'+month_number+'}}');
input_string = input_string.replace(regexp6, '$1{{Date|$2|'+month_number+'}}');
return input_string;
}
/* returns author information, as found. Returns in vector form, as {(Entire author string), (author project code), (author username)}. If unable to parse project code or username, then they will be null */
function mto_parse_author_info(text)
{
var return_array = new Array(3);
var authorstart = text.search(/^\s*\|\s*[Aa]uthor\s*\=\s*(.+?)\.?\s*$/m);
return_array[0] = text.substring(authorstart, text.indexOf('\n', authorstart)).replace(/^\s*\|\s*[Aa]uthor\s*\=\s*(.+?)\s*\.?(?:\s*<\s*[Bb][Rr]\s*\/?>\s*)?\s*?$/, '$1');
var username_array = /^.*\[\[(?:\s*\:?\s*([a-z]{1,2}))\s*\:[A-Za-z]?[a-z]+:(.*?)[\|\]](?:.\n*)*$/.exec(return_array[0]);
if (username_array) //successful username extraction match
{
return_array[1]= username_array[1];
return_array[2]= username_array[2];
}
return return_array;
}
function mto_uploader_is_author(text)
{
return text.replace(/(\|\s*[Aa]uthor\s*\=\s*.*?)\s*\.{0,2}(?:\s*<\s*[Bb][Rr]\s*\/?>)?\s*\n\s*([^\s\|\}].*\n\s*[\|\}])/, '$1 / $2');
}
function mto_uploader_isnt_author(text)
{
//original upload date is useless
text = text.replace(/(\|[Dd]ate\s*\=.*?)\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\*?\s*\{\{\s*[Oo]riginal +upload +date\s*\|\s*[\d\-]+\s*\}\}(?:; *\{\{[Dd]ate[\d\|\s]+\}\} *\(last +version\)*)?/, '$1');
//original author info is useless
text = text.replace(/(\|\s*[Aa]uthor\s*\=\s*?.*?)\.?(?:\s*<\s*[Bb][Rr]\s*\/?>)?\s*(?:[Uu]ploaded\s+by\s+)?\[\[\s*\:?\s*([a-z]{1,2})\s*\:(?:[A-Za-z]?[a-z]+)\:(?:.+?)\s*(?:\|(?:.*?))\]\] at (?:\[http:\/\/)?\2\.w[\w\. ]+\]?.*\n/, '$1\n');
return text.replace(/(\|\s*[Aa]uthor\s*\=\s*?.*?)\.?(?:\s*<\s*[Bb][Rr]\s*\/?>)?\s*Later +version\(s\) +were +uploaded +by\s*?\n?/, '$1\n');
}
//must process source cleanup in order to continue
function own_replace_pre(text)
{
text = text.replace(/Transferred from \[(http:\/\/[\w\. ]+)\]; transferr?ed to Commons/im, 'Transferred from [$1] to Commons');
text = text.replace(/Transferred from \[(http:\/\/[\w\. ]+)\]; Transfer was stated to be made by \[\[(.+?)\]\]/im, 'Transferred from [$1] to Commons by [[$2]]');
text = text.replace(/\|(\s*source\s*=\s*)transferred from \[(http:\/\/[\w\. ]+)\]((?: to commons by \[\[.+?\]\]\.?)?)\s*?(?:<\s*br\s*\/?>)?((?:\susing .+?)?)\s*\.?(?:\s*<\s*br\s*\/?\s*>)?\n+\s*\(original\stext\s*\:\s*('')?([\S\s]*?)\5\)(\s*(?:\|\s*(?:description|date|author|permission|other[ _]+versions|other[ _]+fields)\s*\=|\}\}))/im, '|$1$6<br/>\nTransferred from [$2]$3$4.$7');
return text;
}
/* internal function only */
function own_replace(text, username, projcode, force)
{
//define functions
function own_replace_1(text, internal_re, replace_text)
{
var re = new RegExp("(\\|\\s*source\\s*\\=[^\\S\\n]*(?!\\|))("+internal_re+".*?)(?:\\s*?<\\s*[Bb][Rr]\\s*\\/?>)?\\s*?(\\n?(?:transferr?ed +from +\\[http|\\(?Original(?:ly)? +uploaded +on +[a-z\\-]{2,}\\.wik).+)?\\n", "i");
var re_parsed = re.exec(text);
if (re_parsed!==null)
{
//just prepend under circumstances
if (re_parsed[2].search(/(?:\s*transferr?ed +from +\[http|\(?Original(?:ly)? +uploaded +on + [a-z\-]{2,}\.wik)/i)===0)
{return text.replace(re, "$1"+replace_text+"<br/>$2\n");}
//prepend plus original text
else if (re_parsed[2].search(/\s*(?:\*\s*)?\{\{\s*(?:[Oo]wn|[Ss]elf(?:\-| +)photographed)\s*\}\}/)!==0 )
{return text.replace(re, "$1"+replace_text+" ({{original caption|1=$2|nobold=1}})<br/>$3\n");}
}
//we've decided not to parse for whatever reason
return text;
}
function own_replace_2(text, internal_re, replace_text)
{
var re = new RegExp("(\\|\\s*source\\s*\\=[^\\S\\n]*)(?!\\|)("+internal_re+".*?)(?:\\s*?<\\s*[Bb][Rr]\\s*\\/?>)?\\n", "i");
var re_parsed = re.exec(text);
if (re_parsed!==null)
{
if (re_parsed[2].search(/\s*(?:\*\s*)?\{\{\s*(?:[Oo]wn|[Ss]elf\-photographed)\s*\}\}/)!==0 &&
re_parsed[2].search(/(?:\s*transferr?ed +from +\[http|\(?Original(?:ly)? +uploaded +on + [a-z\-]{2,}\.wik)/i)!==0)
{return text.replace(re, "$1"+replace_text+" ({{original caption|1=$2|nobold=1}})\n");}
//just prepend under circumstances
else if (re_parsed[2].search(/\|\s*source\s*\=\s*\*?\s*\{\{\s*(?:[Oo]wn|[Ss]elf(?:\-| +)photographed)\s*\}\}/)===0)
{return text.replace(re, "$1"+replace_text+"<br/>$2\n");}
}
return text;
}
text = own_replace_pre(text);
var username_test_re = (projcode && username)?"|\\[\\[\\s*:\\s*"+(projcode?projcode.replace("-", "\\\\-"):/*dummy*/"")+"\\s*:\\s*[^\\s\\d\\+\\:\\|\\[\\]]+?\\s*:\\s*"+username+"\\s*\\|\\s*(?:[^\\s\\d\\+\\:\\|\\[\\]]+?\\s*\\:\\s*)?"+username+"\\s*\\]\\].*?":"";
var sp_re_const = force=="selfphoto"?".+?":"(?:selb(?:st|er)[\\s\\-]*(?:(?:ph|f)oto(?:gra(?:f|ph)ie(?:rt)?)?|aufgenommen|geknipst)|self[\\-\\s+]taken|i[^a-z]took[^a-z]this[^a-z](?:photo(?:graph)?|picture))\\.?";
var own_re_const = force?".+?":"(?:I\,? .*created this (?:work|image) entirely by myself\\.?|self[\\-\\s+]made|own(?:\\s+work)?|(?:selb(?:st|er)|eigen(?:e|es)?)(?:\\s*(?:werk|(?:ph|f)oto(?:gra(?:f|ph)ie(?:rt)?)?|archiv|gezeichnet|erstellt|aufnahme|bild(?:er)?|arbeit))?|opera propria"+username_test_re+")\\.?";
text_bak = own_replace_1(text, sp_re_const, "{{self-photographed}}");
if (text_bak===text)
{
text_bak = own_replace_2(text, sp_re_const, "{{self-photographed}}");
if (text_bak===text)
{
text_bak = own_replace_1(text, own_re_const, "{{own}}");
if (text_bak===text)
{
text_bak = own_replace_2(text, own_re_const, "{{own}}");
if (text_bak===text && force)
{
text_bak = text=text.replace(/(\|\s*source\s*\=(?!\s*\{\{\s*(?:[Oo]wn|[Ss]elf(?:\-| +)photographed)\s*\}\}))/i, force=="selfphoto"?"$1{{self-photographed}}":"$1{{own}}");
}
}
}
}
text = text_bak.replace(/\|(\s*[Ss]ource\s*\=\s*{{(?:[Oo]wn|[Ss]elf\-photographed)}}(?:\s*\(?\s*\{\{\s*[Oo]riginal +caption\s*\|.+?\|\s*nobold\s*\=\s*1\s*\}\}\s*\)?)?)(?:\s*<\s*[Bb][Rr]\s*\/?>){2,}\s*/, '|$1<br/>\n');
text = text.replace(/\|(\s*[Ss]ource\s*\=\s*{{(?:[Oo]wn|[Ss]elf\-photographed)}}(?:\s*\(?\s*\{\{\s*[Oo]riginal +caption\s*\|.+?\|\s*nobold\s*\=\s*1\s*\}\}\s*\)?)?)\s*<\s*[Bb][Rr]\s*\/?>(\s*(?:\|\s*(?:description|date|author|permission|other[ _]+versions|other[ _]+fields)\s*\=|\}\}|\*))/, '|$1$2');
return text;
}
function mto_self_photographed_wrapper(autosave_ignored)
{
cleanup = document.editform.wpTextbox1.value;
//parse comments/nowikis
cnwt = parse_comments_nowikis(cleanup);
cleanup = cnwt[0];
tokens = cnwt[1];
cleanup = mto_own(cleanup, true);
//rebuild comments/nowikis
cleanup = rebuild_comments_nowikis(cleanup, tokens, false);
document.editform.wpTextbox1.value=cleanup;
}
function mto_own_wrapper(autosave_ignored)
{
cleanup = document.editform.wpTextbox1.value;
//parse comments/nowikis
cnwt = parse_comments_nowikis(cleanup);
cleanup = cnwt[0];
tokens = cnwt[1];
cleanup = mto_own(cleanup, false);
//rebuild comments/nowikis
cleanup = rebuild_comments_nowikis(cleanup, tokens, false);
document.editform.wpTextbox1.value=cleanup;
}
function mto_own(text, selfphoto)
{
var tokens=null;
//author cleanup
text = mto_uploader_is_author(text);
var authorinfo = mto_parse_author_info(text);
var author = authorinfo[0];
var project = authorinfo[1];
var user = authorinfo[2];
text = own_replace(text, user, project, selfphoto?"selfphoto":"own");
//specific license cleanup
if (user)
{text = text.replace(/{{\s*pd\-release\s*}}/mi, "{{PD-user-w|"+project+"|wikipedia|"+user+"}}");}
//{{Self}} cleanup
text = text.replace(/{{\s*([Ss]elf2?|[Pp]ropio|[Сс]ебе|[Mm]ultilicense +replacing +placeholder(?: +new)?)\s*\|(?!.*\s*[Aa]uthor\s*\=[^\|]+\|\s*)(.*?)}}/m, "{{$1|author="+author+"|$2}}");
text = iterative_replace(/\|(\s*[Ss]ource\s*\=\s*{{(?:[Oo]wn|[Ss]elf\-photographed)}}<br\/>)\s*<\s*[Bb][Rr]\s*\/?>\s*/, '|$1\n', text);
return text;
}
// mto_cleanup tagger (initially developed by Patstuart/Magog the Ogre)
function mto_cleanup(autosave_ignored){
var cleanup = document.editform.wpTextbox1.value;
var originaltext = cleanup;
var de_wp_re = /{{Bild\-GFDL\-Neu}}\s*\r?\n{{(?:\s*self\s*\|\s*author\=.*\|)?Cc\-by\-sa\-3\.0}}\s*\r?\n{{Cc\-by\-sa\-3\.0\-de}}\s*\r?\n{{GFDL(?:\-user\-de(?:\|.*)?)?}}/i;
//store comments, nowikis as is to avoid changing them
cnwt = parse_comments_nowikis(cleanup);
cleanup = cnwt[0];
tokens = cnwt[1];
cleanup = cleanup.replace(/×/g, '×');
cleanup = cleanup.replace(/|/g, '|');
cleanup = cleanup.replace(/{{BotMoveToCommons.*}}\s*\n/, '');
cleanup = cleanup.replace('The tool and the bot are operated by [[User:Jan Luca]] and [[User:Magnus Manske]].', '');
cleanup = cleanup.replace('The upload bot is [[User:CommonsHelper2 Bot]] which is called by [http://toolserver.org/~commonshelper2/index.php CommonsHelper2].', '');
//because the new bot really is this dumb
cleanup = cleanup.replace(/(\|\s*[Dd]escription\s*\=\s*(.+)[\s\S]+)\=\=\s*[Ss]ummary\s*\=\=\n+\2/, '$1');
//Excessive wordage/markup in description
cleanup = cleanup.replace(/{{\s*([a-z]{2,4}(?:\-[a-z]{5})?)\s*\|\s*(1\s*\=)?\s*(?:this\s+is\s+)?(?:an?\s+|the\s+)?(?:photo(?:graph)?|picture|image)\s+(?:taken\s+)?(?:of|depicting)\s+(\S)/ig, "{{$1|$2$3");
cleanup = iterative_replace(/{{\s*([a-z]{2,4}(?:\-[a-z]{5})?)\s*\|\s*((?:.|\n?)+?)(?:\s*<\s*[Bb][Rr]\s*\/?>\n+)?(?:\s*\[\[\s*\:\s*\1\s*\:\s*(?:[Cc]ategor(?:y|ia)|[Cc]atégorie|[Kk]ategorie|[Кк]атегория)\s*\:[^\]]+\]\])+\s*}}/, "{{$1|$2}}", cleanup)
cleanup = cleanup.replace(/{{(\s*[a-z]{2,4}(?:\-[a-z]{5})?\s*\|\s*(.+?))\s*(?:<\s*[Bb][Rr]\s*\/?>)?(\s*\n+\=\=[^\=]+\=\=)*\s*}}/m, "{{$1}}");
cleanup = cleanup.replace(/{\{\s*[a-z]{2,4}(?:\-[a-z]{5})?\s*\|\s*(\=+).*?\1\s*\}\}/, "");
//capitalization of first letter of description
cleanup = cleanup.replace(/({{\s*(?:[Aa]a|[Aa]b|[Aa]ce|[Aa]f|[Aa]k|[Aa]ln|[Aa]ls|[Aa]m|[Aa]n|[Aa]ng|[Aa]r|[Aa]rc|[Aa]rn|[Aa]rz|[Aa]s|[Aa]st|[Aa]v|[Aa]vk|[Aa]y|[Aa]z|[Bb]a|[Bb]ar|[Ss]gs|[Bb]aybayin|[Bb]cc|[Bb]cl|[Bb]e|[Bb]e-tarask|[Bb]g|[Bb]h|[Bb]i|[Bb]jn|[Bb]m|[Bb]n|[Bb]o|[Bb]py|[Bb]r|[Bb]s|[Bb]ug|[Bb]xr|[Bb]yp|[Cc]a|[Cc]bk-zam|[Cc]do|[Cc]e|[Cc]eb|[Cc]g|[Cc]h|[Cc]ho|[Cc]hr|[Cc]hy|[Cc]o|[Cc]r|[Cc]rh|[Cc]rh-cyrl|[Cc]s|[Cc]sb|[Cc]u|[Cc]v|[Cc]y|[Dd]a|[Dd]e|[Dd]ia|[Dd]iq|[Dd]sb|[Dd]v|[Dd]z|[Ee]e|[Ee]l|[Ee]ml|[Ee]n|[Ee]o|[Ee]s|[Ee]t|[Ee]u|[Ee]xt|[Ff]a|[Ff]f|[Ff]i|[Ff]il|[Ff]iu-vro|[Ff]j|[Ff]o|[Ff]r|[Ff]rc|[Ff]rp|[Ff]rr|[Ff]ur|[Ff]y|[Gg]a|[Gg]ag|[Gg]an|[Gg]d|[Gg]l|[Gg]lk|[Gg]n|[Gg]ot|[Gg]sw|[Gg]u|[Gg]v|[Hh]a|[Hh]ak|[Hh]aw|[Hh]e|[Hh]i|[Hh]if|[Hh]mn|[Hh]o|[Hh]r|[Hh]sb|[Hh]t|[Hh]u|[Hh]y|[Hh]z|[Ii]a|[Ii]d|[Ii]e|[Ii]g|[Ii]i|[Ii]k|[Ii]ke-latn|[Ii]lo|[Ii]o|[Ii]s|[Ii]t|[Ii]u|[Jj]a|[Jj]a2|[Jj]bo|[Jj]v|[Kk]a|[Kk]aa|[Kk]ab|[Kk]g|[Kk]i|[Kk]j|[Kk]k|[Kk]l|[Kk]m|[Kk]n|[Kk]o|[Kk]r|[Kk]rc|[Kk]rj|[Kk]s|[Kk]sh|[Kk]u|[Kk]v|[Kk]y|[Ll]a|[Ll]ad|[Ll]b|[Ll]be|[Ll]fn|[Ll]g|[Ll]i|[Ll]ij|[Ll]mo|[Ll]n|[Ll]o|[Ll]oz|[Ll]t|[Ll]tg|[Ll]v|[Ll]zh|[Mm]ap-bms|[Mm]df|[Mm]g|[Mm]h|[Mm]hr|[Mm]i|[Mm]k|[Mm]l|[Mm]n|[Mm]o|[Mm]r|[Mm]rj|[Mm]s|[Mm]t|[Mm]us|[Mm]wl|[Mm]y|[Mm]yv|[Mm]zn|[Nn]a|[Nn]ah|[Nn]al|[Nn]ap|[Nn]b|[Nn]ds|[Nn]ds-nl|[Nn]e|[Nn]ew|[Nn]g|[Nn]l|[Nn]n|[Nn]o|[Nn]on|[Nn]ov|[Nn]rm|[Nn]so|[Nn]v|[Nn]y|[Oo]c|[Oo]m|[Oo]r|[Oo]s|[Pp]a|[Pp]ag|[Pp]am|[Pp]ap|[Pp]cd|[Pp]dc|[Pp]dt|[Pp]fl|[Pp]i|[Pp]ih|[Pp]l|[Pp]ms|[Pp]nb|[Pp]nt|[Pp]s|[Pp]t|[Pp]t-br|[Qq]u|[Rr]m|[Rr]my|[Rr]n|[Rr]o|[Rr]oa-rup|[Rr]oa-tara|[Rr]u|[Rr]ue|[Rr]w|[Ss]a|[Ss]ah|[Ss]c|[Ss]cn|[Ss]co|[Ss]d|[Ss]dc|[Ss]e|[Ss]ei|[Ss]es|[Ss]g|[Ss]h|[Ss]hi|[Ss]i|[Ss]k|[Ss]l|[Ss]li|[Ss]m|[Ss]ma|[Ss]n|[Ss]o|[Ss]q|[Ss]r|[Ss]r-ec|[Ss]r-el|[Ss]rn|[Ss]s|[Ss]t|[Ss]tq|[Ss]u|[Ss]v|[Ss]w|[Tt]a|[Tt]e|[Tt]et|[Tt]g|[Tt]gl|[Tt]h|[Tt]i|[Tt]im|[Tt]k|[Tt]n|[Tt]o|[Tt]okipona|[Tt]pi|[Tt]r|[Tt]s|[Tt]t|[Tt]um|[Tt]w|[Tt]y|[Tt]yv|[Uu]dm|[Uu]g|[Uu]k|[Uu]nknown +language|[Uu]r|[Uu]z|[Vv]e|[Vv]ec|[Vv]ep|[Vv]i|[Vv]ls|[Vv]o|[Ww]a|[Ww]ar|[Ww]o|[Ww]uu|[Xx]al|[Xx]h|[Yy]ai|[Yy]dd|[Yy]i|[Yy]i-latn|[Yy]o|[Yy]ue|[Zz]a|[Zz]ea|[Zz]h|[Zz]h-hans|[Zz]h-hant|[Zz]h-hk|[Zz]h-min-nan|[Zz]h-sg|[Zz]u|[Zz]xx)\s*\|\s*(?:1\s*\=\s*)?)(\S)(\S*)/gm, function($0, $1, $2, $3) {return $1 + (($2+$3).match(/^(?:(?:https?|gopher|news|ftp|irc):\/\/|mailto:)/)?$2:$2.toUpperCase()) + $3;});
//pipe wikilinks in descriptions
cleanup = iterative_replace(/\|(\s*[Dd]escription\s*\=(?:.|\n?)*?){{\s*([a-z]{2,4}(?:\-[a-z]{5})?)\s*\|((?:.|\n?)*)\[\[\s*\:\s*\2\s*\:\s*([^\|\]]*?)\]\]((?:.|\n?)*}}(?:.|\n?)*?\|\s*(?:[Ss]ource|[Dd]ate)\s*)\=/, "|$1{{$2|$3[[:$2:$4|$4]]$5=", cleanup)
//Empty descriptions
cleanup = cleanup.replace(/(?:(\=)\s*)?{{\s*[a-z]{2,4}(?:\-[a-z]{5})?\s*\|\s*(?:1\s*\=\s*)?(?:\'\'no original description\'\'\s*)?\s*}}\s*$/mg, "$1");
//internationalization
cleanup = cleanup.replace(/\s*original upload date\s*(?!(?:}}|\|))/im, '{{original upload date}}');
cleanup = cleanup.replace(/^(\=+) *li[cz]en(?:s(?:e|ing)|za(?: +d\'uso)?|z) *\:? *\1\s*$/mig, '$1 {{int:license-header}} $1')
cleanup = cleanup.replace(/^(\=+) *{{\s*(?:[Ii][Nn][Tt]|[Mm][Ee][Dd][Ii][Aa][Ww][Ii][Kk][Ii])\s*\:\s*[Ll]icense\s*}} *\:? *\1\s*?$/mg, '$1 {{int:license-header}} $1');
cleanup = cleanup.replace(/^(\=+) *original upload (?:log|history) *\:? *\1\s*$/mig, '$1 {{Original upload log}} $1')
cleanup = cleanup.replace(/^(\=+) *(?:summary|dettagli|beschreibung|beschreibung\W+quelle) *\:? *\1\s*$/mig, '$1 {{int:filedesc}} $1')
//Magnus bot bug where it's transferring over a second and incorrect license
cleanup = cleanup.replace(/((\=+) *\{\{int:licens[e|ing](?:\-header)?\}\} *\2[\s\S]+?)((\=+) *\{\{int:licens[e|ing](?:\-header)?\}\} *\4)(?:\s*\{\{.+?\}\})+\s*$/, "$1");
//because the new bot by Jan Luca and Magnus Manske spams itself like crazy and thus creates two headrs
cleanup = iterative_replace(/^(\=+) {{int:filedesc}} (?:\1(?:\s*\n)+)\1 {{int:filedesc}} \1\s*\n/mig, '$1 {{int:filedesc}} $1\n', cleanup);
//rm various useless permission messages
cleanup = cleanup.replace(/(\|\s*[Pp]ermission\s*\=[^\|\n]*?)(?:\s*?<\s*[Bb][Rr]\s*\/?>)?\n\(Original +text *: *(?:\'\')?(?:[Pp]ublic\s+[Dd]omain|GNU\s*\-?\s*FDL|[Yy][Ee][Ss]|[Jj][Aa]|[Ss][Ee][Ee]\s+[Bb][Ee][Ll][Oo][Ww]|[Bb]ild\-frei|[Ss]ee +license +section|(?:[Cc][Cc]\-(?:[Bb][Yy](?:\-[Ss][Aa])?(?:\-\d\.\d)?|zero)\,?\s*)+)\.?\s*(?:\'\')?\)\s*?\n(\s*?\|)/, "$1\n$2");
cleanup = iterative_replace(/(\|\s*[Pp]ermission\s*\=)(?:(.+?);)?\s*(?:PD[A-Z0-9\-\| ]*\d*|CC\-(?:ZERO|BY(?:[\w\-\,\.]*)?)|GFDL[A-Z\-\|]*|ATTRIBUTION|NORIGHTSRESERVED|BSD|[Tt]his image is in the (?:\[\[)?public domain(?:\]\])?(?: due to its age| because it is ineligible for copyright)?|[Rr]eleased under the \[\[GNU Free Documentation License\]\]|[Rr]eleased into the public domain \(?by the author\)?|[Ll]icensed under the \[\[GFDL\]\] \(?by the author\)?|\-+)\s*(\;.*?)?\.?(?:<\s*[Bb][Rr]\s*\/?>)?\s*?(?:\s*\([Oo]riginal +text\s*\:\s*(\'\')([\S\s]*?)\4\)|\s*(\{\{\s*(?:[Pp]ermission *OTRS|[Oo]TRSPermission|[Cc]rediti|[Рр]азрешение +OTRS)\s*\|[\s\S]*?\}\})\s*)?(\n\s*\|(?:description|date|author|permission|other[ _]+(?:versions|fields)))/, '$1$2$3; $5$6$7', cleanup); //\| included due to early buggy bot moves
cleanup = cleanup.replace(/(\|\s*[Pp]ermission\s*\=)\s*(\'\')?(?:see +license +section|see +below)\.?\s*\2\s*\n/i, '$1\n');
cleanup = cleanup.replace(/(\|\s*[Pp]ermission\s*\=\s*);+\s*([^\s\|])/, '$1$2');
cleanup = cleanup.replace(/(\|\s*[Pp]ermission\s*\=.*);+(?:\s*(\.))?(\s*\|(?:description|date|author|permission|other[ _]+(?:versions|fields)))/i, '$1$2$3');
//wordage changes
cleanup = cleanup.replace(/\|(\s*source\s*\=.*\s*(?:\(?\s*)Original uploaded on [a-z]+\.wiki[a-z]+)(?:\s*\)?)((?:\s*\|\s*date\s*\=\s*.*)?)\s*\|\s*(\s*author\s*=\s*.+)\s*\(transferr?ed\s*by\s*(.+?)\)/im, '|$1 (transferred to commons by $4)$2\n|$3');
cleanup = cleanup.replace(/\|(\s*source\s*\=.+\s*(?:\(\s*)Original(?:ly)? uploaded on [a-z]+\.wiki[a-z]+(?:\s*\)))((?:.|\n)+?)\/Original(?:ly)?\s+uploaded\s+by\s+.+?(\){0,1}\s*$)/im, '|$1 - $2$3');
//author cleanup
cleanup = cleanup.replace(/(?:Original upload(?:er was|ed by)|Uploaded by) (.+)/m, "$1");
cleanup = cleanup.replace(/^(\|\s*[Aa]uthor\s*\=\s*)(.+?)\.?\s*(?:<\s*br\s*\/?>\s*)?\n+\s*\[\[\s*\:\s*([a-z]{2,4}(?:\-[a-z]{5})?\s*\:\s*.+?\s*\:\s*\2(?:\s*\|.*))\s*\]\]/mi, "$1[[:$3]]");
cleanup = cleanup.replace(/^(\|\s*[Aa]uthor\s*\=\s*)\[\[\s*\:\s*([a-z]{2,4}(?:\-[a-z]{5})?)\s*\:\s*.+?\s*\:\s*(.+?)(?:\s*\|.*)?\s*\]\](.*?)\s*\)?\s*\.?\s*(?:<\s*br\s*\/?>\s*)?\n+\s*(\[\[\s*\:\s*\2\s*\:\s*.+?\s*\:\s*\3(?:\s*\|.*)\s*\]\] .*)$/mi, "$1$5$4");
cleanup = cleanup.replace(/^(\|\s*[Aa]uthor\s*\=.*) 0?\d{1,2}:\d{2}\, \d{1,2}\.? (?:[A-Za-z]{3}\.|[A-Za-z]{3,}) \d{4} \((?:UTC|CES?T)\)?/m, "$1");
//check if original uploader appears not to be the author
var uploader_status = 0;
var UNKNOWN = 1;
var AUTHOR = 2;
var NOTAUTHOR = 4;
var PD_UNKNOWN = "release|text(?: *logo)?|ineligible|trivial|uegnet|markenrecht|shape|simple|geometry|link|chem|author|because|reason|porque|reden";
var PD_AUTHOR = "self|users?|utente|own";
var GFDL_AUTHOR= "users?|self";
if (cleanup.match(new RegExp("\\{\\{\\s*(?:pd\\-(?:"+PD_UNKNOWN+")|cc|gfdl(?!\\-)|gfdl\\-(?!"+GFDL_AUTHOR+")|bild\\-pd\\-(?:frei|auteur))", "i")))
uploader_status |= UNKNOWN;
if (cleanup.match(new RegExp("\\{\\{\\s*(?:pd\\-(?:"+PD_AUTHOR+")|Јв\\-ја|مالکیت عمومی-خود |گنو-خود |Pd\\=self|self|gfdl\\-(?:"+GFDL_AUTHOR+"))", "i")) || de_wp_re.test(cleanup))
uploader_status |= AUTHOR;
if (cleanup.match(new RegExp("\\{\\{\\s*(?:pd\\-(?!"+PD_UNKNOWN+"|review|"+PD_AUTHOR+").+|larsencopyright)\s*(?:\\}\\}|\\|)", "i")))
uploader_status |= NOTAUTHOR;
if (uploader_status === AUTHOR)
cleanup = mto_uploader_is_author(cleanup);
if (uploader_status === NOTAUTHOR)
cleanup = mto_uploader_isnt_author(cleanup);
var project_code; var username;
var authorinfo = mto_parse_author_info(cleanup);
if (authorinfo)
{
//var author = authorinfo[0]; ---- unneeded for now ----
project_code = authorinfo?authorinfo[1]:null;
username = authorinfo?authorinfo[2]:null;
}
//own template (internationalization/standardization). I am perfectly aware that some code is run twice, but whatever
cleanup = own_replace_pre(cleanup);
cleanup2 = own_replace(cleanup, username, project_code, false);
if (cleanup!==cleanup2)
{
cleanup=mto_own(cleanup2);
//own_replace may have altered the text; worth a retry
if (!username)
{
authorinfo = mto_parse_author_info(cleanup);
if (authorinfo)
{
//var author = authorinfo[0]; ---- unneeded for now ----
project_code = authorinfo?authorinfo[1]:null;
username = authorinfo?authorinfo[2]:null;
}
}
}
//LOC-image automatic detection
cleanup = cleanup.replace(/(?:\s*?<\s*[Bb][Rr]\s*\/?>)*\s*(?:http:\/\/)?[\w\-]+\.loc\.gov\/loc.pnp\/([\w\.]+\w*\d)\.?(?:\s*?<\s*[Bb][Rr]\s*\/?>)*\s*/, "{{LOC-image|id=$1}}");
cleanup = cleanup.replace(/([\s\S]+)(\{\{\s*[Ll]OC\-image\s*\|\s*(?:(?:1|id)\=)?[\w\.]+\w\}\})([\s\S]+)(\|\s*[Ss]ource\s*\=)([\s\S]+)/, "$1$3$4$2$5");
cleanup = cleanup.replace(/([\s\S]+)(\|\s*[Ss]ource\s*\=)([\s\S]+)(\{\{\s*[Ll]OC\-image\s*\|\s*(?:(?:1|id)\=)?[\w\.]+\w\}\})([\s\S]+)/, "$1$2$4$3$5");
//date fixup (rm needless text)
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)\d\d:\d\d\, (\d\d?) ([A-Z][a-z]+) (\d{4}) \(UTC\)(?:\s*<\s*[Bb][Rr]\s*\/?>)?\s*[\s\n]\s*\(?({{\s*[Dd]ate\s*\|\s*\4\s*\|\s*\d\d\s*\|\s*0?\2\s*}})\s*\(\s*{{\s*[Oo]riginal +upload +date\s*}}\s*\)\s*\)?/, '$1$5 ({{original upload date}})');
cleanup = cleanup.replace(/\|(\s*date\s*=\s*.*?\s*?)(?:\(Uploaded on Commons at )?[\d\- \:]+\(UTC\)\s*[\(\/]original(?:ly)? uploaded at (\d{4})\-(\d{2})\-(\d{2})[\s\d\:]+\)?/i, '|$1 {{Date|$2|$3|$4}} ({{original upload date}})');
//circa/or/before/early/late/between date (also remove upload date if this is provided)
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)[Cc](?:(?:[Ii][Rr][Cc])?[Aa])?\.?\s*(\d{4}(?:\s*\-\s*\d{1,2}(?:\s*\-\s*\d{1,2})?)?)(\W)/, '$1{{circa|$2}}$3');
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)(\d{4})(?:\s*(\-)\s*(\d{1,2}))?(?:\s*(\-)\s*(\d{1,2}))?\s*[Oo][Rr]\s*(\d{4})(?:\s*(\-)\s*(\d{1,2}))?(?:\s*(\-)\s*(\d{1,2}))?\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\s*(?:\(?{{\s*[Dd]ate\s*\|\s*\d{4}s*\|\s*\d{1,2}s*\|\s*?\d{1,2}\s*}}\s*\(\s*{{\s*[Oo]riginal +upload +date\s*}}\s*\)\s*\)?)?\s*/, "$1{{other date|or|$2$3$4$5$6|$7$8$9$10$11}}\n");
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*\{\{circa\|.+\}\})\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\s*\(?\{\{\s*[Dd]ate[\|\s\d]+\}\}\s*\(\s*(?:{{\s*[Oo]riginal +upload +date\s*}}|first +version)\s*?\)(?:\s*\;?\s*{\{\s*[Dd]ate[\|\s\d]+\}\}\s*\(\s*last\s+version\))?\s*?\)?/, '$1');
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)(?:[Bb][Ee][Ff][Oo][Rr][Ee]\s+|[Pp][Rr][Ee]\s*\-)(\d{4}(?:\s*\-\s*\d{1,2}(?:\s*\-\s*\d{1,2})?)?)\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\n\s*\(?{{\s*[Dd]ate\s*\|\s*\d{4}s*\|\s*\d{1,2}s*\|\s*?\d{1,2}\s*}}\s*\(\s*{{\s*[Oo]riginal +upload +date\s*}}\s*\)\s*\)?/, '$1{{other date|before|$2}}');
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)(?:[Ll][Aa][Tt][Ee]\s+|[Pp][Rr][Ee]\s*\-)(\d{4}(?:\s*\-\s*\d{1,2}(?:\s*\-\s*\d{1,2})?)?)\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\n\s*\(?{{\s*[Dd]ate\s*\|\s*\d{4}s*\|\s*\d{1,2}s*\|\s*?\d{1,2}\s*}}\s*\(\s*{{\s*[Oo]riginal +upload +date\s*}}\s*\)\s*\)?/, '$1{{other date|late|$2}}');
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)(?:[Ee][Aa][Rr][Ll][Yy]\s+|[Pp][Rr][Ee]\s*\-)(\d{4}(?:\s*\-\s*\d{1,2}(?:\s*\-\s*\d{1,2})?)?)\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\n\s*\(?{{\s*[Dd]ate\s*\|\s*\d{4}s*\|\s*\d{1,2}s*\|\s*?\d{1,2}\s*}}\s*\(\s*{{\s*[Oo]riginal +upload +date\s*}}\s*\)\s*\)?/, '$1{{other date|early|$2}}');
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)(?:[Bb][Ee][Tt][Ww][Ee]{2}[Nn])\s*(\d{4})(?:\s*(\-)\s*(\d{1,2}))?(?:\s*(\-)\s*(\d{1,2}))?\s*(?:[Aa][Nn][Dd]|\W)\s*(\d{4})(?:\s*(\-)\s*(\d{1,2}))?(?:\s*(\-)\s*(\d{1,2}))?\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?\s*(?:\(?{{\s*[Dd]ate\s*\|\s*\d{4}s*\|\s*\d{1,2}s*\|\s*?\d{1,2}\s*}}\s*\(\s*{{\s*[Oo]riginal +upload +date\s*}}\s*\)\s*\)?)?\s*/, "$1{{other date|between|$2$3$4$5$6|$7$8$9$10$11}}\n");
cleanup = mto_parse_date(cleanup, "(?:jan(?:uary?|\\.)?|gennaio)", "01")
cleanup = mto_parse_date(cleanup, "(?:feb(?:ruary?|\\.)?|febbraio)", "02")
cleanup = mto_parse_date(cleanup, "(?:(?:mar(?:ch|\\.)?)|mär[z\\.]?|marzo)", "03")
cleanup = mto_parse_date(cleanup, "(?:apr(?:il|\\.)?|aprile)", "04")
cleanup = mto_parse_date(cleanup, "(?:ma[iy]|maggio)", "05")
cleanup = mto_parse_date(cleanup, "(?:jun[ie\\.]?|giugno)", "06")
cleanup = mto_parse_date(cleanup, "(?:jul[iy\\.]?|luglio)", "07")
cleanup = mto_parse_date(cleanup, "(?:aug(?:ust|\\.)?|agosto)", "08")
cleanup = mto_parse_date(cleanup, "(?:sept?(?:ember|\\.)?|settembre)", "09")
cleanup = mto_parse_date(cleanup, "(?:o[ck]t(?:ober|\\.)?|ottobre)", "10")
cleanup = mto_parse_date(cleanup, "(?:nov(?:ember|\\.)?|novembre)", "11")
cleanup = mto_parse_date(cleanup, "(?:de[cz](?:ember|\\.)?|dicembre)", "12")
//{{date}} for single year dates
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*)(\d{4})(\s*\.?\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)?)$/m, "$1{{Date|$2}}$3");
//fix single digit dates (first run)
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*{{\s*[Dd]ate\s*\|\d{4}\s*\|)(\d)(?!\d)/, "$10$2");
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*{{\s*[Dd]ate\s*\|\d{4}\s*\|\s*\d{2}\s*\|\s*)(\d)(?!\d)/, "$10$2");
//rm parens around entirely original upload date
cleanup = cleanup.replace(/\(({{[Dd]ate[^}]+}}\s*\({{original upload date}}\))\)/, "$1");
for (i=0; i<2; i++) //run twice to get both possible instances of date (the regex can conflict with itself); avoid changing format when undesired
{
/* A date written in format \d\d.\d\d.\d\d\d\d or \d\d.\d\d.\d\d is very common in Germany, apparently */
if (project_code=="de")
{
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(0?\d|[1-2][0-9]|3[0-1])\.(0?\d|1[0-2]|\d)\.(\d{4})(?!\d)/, '|$1{{Date|$4|$3|$2}}');
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(0?\d|[1-2][0-9]|3[0-1])\.(0?\d|1[0-2]|\d)\.([01]\d)(?!\d)/, '|$1{{Date|20$4|$3|$2}}'); /* FIXME: change this in the year 2020!! */
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(0?\d|[1-2][0-9]|3[0-1])\.(0?\d|1[0-2]|\d)\.([2-9]\d)(?!\d)/, '|$1{{Date|19$4|$3|$2}}');
}
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(1[3-9]|2\d|3[01])[\\\/\-\.\s\,]+(0?\d|1[0-2]|\d)[\\\/\-\.\s\,]+(\d{4})(?!\d)/mg, '|$1{{Date|$4|$3|$2}}');
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(0?\d|1[0-2]|\d)[\\\/\-\.\s\,]+(1[3-9]|2\d|3[01])[\\\/\-\.\s\,]+(\d{4})(?!\d)/mg, '|$1{{Date|$4|$2|$3}}');
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(0?\d|1[0-2]|\d)[\\\/\-\.\s\,]+\2[\\\/\-\.\s\,]+(\d{4})(?!\d)/mg, '|$1{{Date|$3|$2|$2}}');
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=.*\s*)(\d{4})\s*([\\\\\\/\.\s])\s*(\d{1,2})\s*\3\s*(\d{2})(?!\d)/mg, '|$1{{Date|$2|$4|$5}}')
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=.*\s*)(\d{4})\s*\-\s*(\d)\s*\-\s*(\d{2})(?!\d)/mg, '|$1$2-0$3-$4')
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=.*\s*)(\d{4})\s*\-\s*(\d{2})\s*\-\s*(\d{2})(?!\d)(?!\s*\n)(?![\|}])/mg, '|$1{{Date|$2|$3|$4}}')
}
for (i=0; i<2; i++) //run twice to get both possible instances of date (the regex can conflict with itself); avoid changing format when undesired
{
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(\d|1[0-2]|\d(?!\d))[\\\/\-\.\s\,]+(\d{4})(?!(?:[\\\/\-\.\s\,]+\d{1,2}|\d))/mg, '|$1{{Date|$3|$2}}');
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*(?:.*\n)?)(\d{4})[\\\/\-\.\s\,]+(0\d|1[0-2]|\d(?!\d))(?!(?:[\\\/\-\.\s\,]+\d{1,2}|\d))/mg, '|$1{{Date|$2|$3}}');
}
//don't need to have upload date if a date is already provided
cleanup = cleanup.replace(/(\|\s*[Dd]ate\s*\=\s*\{\{\s*[Dd]ate[\|\s\d]+\}\})\s*\.?(?:\s*\;?\s*<\s*[Bb][Rr]\s*\/?>)?\s*\(?(?:\{\{\s*[Dd]ate[\|\s\d]+\}\}\s*\(\s*(?:{{\s*[Oo]riginal +upload +date\s*}}|first +version)\s*?\)|\{\{\s*[Oo]riginal +upload +date\s*\|[\d\-\s]+\}\})(?:\s*\;?\s*{\{\s*[Dd]ate[\|\s\d]+\}\}\s*\(\s*last\s+version\))?\s*?\)?/, '$1');
//fix single digit dates, which confuses the parser below
cleanup = cleanup.replace(/{{\s*[Dd]ate\s*\|\s*(\d+)\s*\|\s*(\d)\s*((?:\|\s*\d+\s*)?)}}/g, "{{Date|$1|0$2$3}}");
cleanup = cleanup.replace(/{{\s*[Dd]ate\s*\|\s*(\d+)\s*\|\s*(\d{2})\s*\|\s*(\d)\s*}}/g, "{{Date|$1|$2|0$3}}");
cleanup = cleanup.replace(/{{\s*[Dd]ate\s*\|\s*(\d{4})\s*\|(\d{1,2})\s*\|(\d{1,2})\s*}}\s*\(first version\)\s*;?\s*{{\s*[Dd]ate\s*\|\s*\1\s*\|\2\s*\|\3\s*}}\s*\(last version\)/, "{{Date|$1|$2|$3}} ({{original upload date}})");
cleanup = cleanup.replace(/{{\s*[Dd]ate\s*\|\s*(\d{4})\s*\|(\d{1,2})\s*\|(\d{1,2})\s*}}\s*\(first version\)\s*/m, "{{Date|$1|$2|$3}} ({{original upload date}})");
cleanup = cleanup.replace(/\|(\s*[Dd]ate\s*\=\s*({{[Dd]ate\|.+}}))\s*(?:<\s*br\s*\/?>)?\s*\n*\s*\(?\2\s*\(\s*{{\s*[Oo]riginal upload date\s*}}\s*\)?\)?/, "|$1");
cleanup = cleanup.replace(/(?:\(\s*)?{{\s*[Dd]ate\s*\|\s*(\d{4})\s*\|(\d{1,2})\s*\|(\d{1,2})\s*}}\s+\(?{{\s*[Oo]riginal upload date\s*}}\)?(?:\s*\))?/mg, "{{original upload date|$1-$2-$3}}")
cleanup = cleanup.replace(/\d{2}:\d{2}\, +\d{1,2} +[A-Z][a-z]+ +\d{4} +\([A-Z]{3,4}\)(?:<\s*br\s*\/?>)?\s*\n*\s*(?:\(\s*)?({{\s*[Oo]riginal +upload +date\s*\|\s*[\d\-]+\s*}})(?:\s*\))?/mg, "$1") //~~~~~ for date is ignored if upload date present
//{{date}} format -> xxxx-yy-zz format where possible
cleanup = cleanup.replace(/\=(\s*){{\s*[Dd]ate\s*\|\s*(\d{4})\s*\|(\d{2})\s*\|(\d{2})\s*}}(\s*\|)/mg, "=$1$2-$3-$4$5")
cleanup = cleanup.replace(/\=(\s*){{\s*[Dd]ate\s*\|\s*(\d{4})\s*\|(\d{1,2})\s*}}(\s*\|)/mg, "=$1$2-$3$4")
cleanup = cleanup.replace(/\=(\s*){{\s*[Dd]ate\s*\|\s*(\d{4})\s*}}(\s*\|)/mg, "=$1$2$3")
//rm unnecessary comments, templates that upload bot needlessly transports over; __NOTOC__
cleanup = cleanup.replace(/^\s*{{\s*(?:[Tt]emplate +other|[Tt]ls?x?p?|FULLROOTPAGENAME|[Nn]s\s+has\s+subpages|\!\)|\(\!|\!\!?|[a-zA-Z]?[Mm]box|[Jj]ULIANDAY|[Ll]an|[Rr]ed|[Ee]n)\s*\|?\s*}}\s*$/gm, '');
if (!cleanup.match(/\{\{\s*[Cc]heck\s+categories/))
cleanup = cleanup.replace(/^__NOTOC__\s*?\n/gm, '');
cleanup = cleanup.replace(/{{P[Dd]\-user\-w\s*\|\s*(als|ar|az|bg|ca|cs|da|de|en|es||fa|fi|fr|he|hi|hr|hu|it|ja|lt|ml|nl|nn|no|pl|pt|ro|ru|sk|sl|th|uk|vls|zh)\s*\|\s*wikipedia\s*\|\s*([^\|}]+)\s*}}/m, '{{PD-user-$1|$2}}');
cleanup = cleanup.replace(/{{P[Dd]\-user\s*\|\s*([^\|}]+)\s*\|\s*(als|ar|az|bg|ca|cs|da|de|en|es||fa|fi|fr|he|hi|hr|hu|it|ja|lt|ml|nl|nn|no|pl|pt|ro|ru|sk|sl|th|uk|vls|zh)\s*}}/m, '{{PD-user-$2|$1}}');
//specific silliness reserved for de.wp transfers
var self_author_text;
if (username && project_code)
self_author_text = "[[:"+project_code+":"+username+"|"+username+"]] at [http://"+project_code+".wikipedia.org "+project_code+".wikipedia]";
else
self_author_text = "The original uploader";
cleanup = cleanup.replace(de_wp_re, "{{self|author="+self_author_text+"|cc-by-sa-3.0|cc-by-sa-3.0-de|GFDL|migration=redundant}}");
//GFDL cleanup: multiple GFDLs
if (username && cleanup.match(/{{\s*(?:Bild\-)?GFDL\s*[\-\|}]/im))
{
var migration;
if (cleanup.match(/{{\s*(?:Bild\-)?GFDL.*\|\s*migration\s*\=\s*opt\-out/im))
migration = "opt-out";
else if (cleanup.match(/{{\s*GFDL.*\|\s*migration\s*\=\s*not\-eligible/im))
migration = "not-eligible";
else if (cleanup.match(/{{\s*GFDL.*\|\s*migration\s*\=\s*relicense/im))
migration = "relicense";
else if (cleanup.match(/{{\s*GFDL.*\|\s*migration\s*\=\s*needs\-review/im))
migration = "needs-review";
else if (cleanup.match(/{{\s*GFDL.*\|\s*migration\s*\=\s*redundant/im))
migration = "redundant";
else if (cleanup.match(/{{\s*[Cc]c\-by\-sa\-3.0\-migrated[\-\.\,\w]*\s*}}/m))
migration = "relicense";
else if (cleanup.match(/{{\s*[Ll]icense +migration +not +eligible\s*}}/m))
migration = "not-eligible";
else if (cleanup.match(/{{\s*[Cc]c\-by\-sa\-(?:all|3.0[\-\.\,\w]*)\s*}}/m))
migration = "redundant";
else if (project_code=="de") //User:Leyo informs me this is always relicense
migration = "relicense";
else
{
//not stated; do intelligent search based on most recent upload date
var upload_date = /^\s*\=+\s*{{Original upload log}}\s*\=+\n+(?!\*).+?\n+\s*\*\s*(\d{4})\-(\d{2})\-\d{2}/im.exec(cleanup);
if (upload_date===null)
upload_date = /^\s*\=+\s*{{Original upload log}}\s*\=+\n+(?!\*)[\s\S]+comment\s*\n+\s*\*\s*(\d{4})\-(\d{2})\-\d{2}/im.exec(cleanup);
//uploaded before November 1, 2008
if (upload_date!==null && (upload_date[1]<=2007 || (upload_date[1]==2008 && upload_date[2]<11)))
migration="relicense";
//couldn't parse or later upload date
else
migration="needs-review";
}
var en_disclaimers=false;
if (cleanup.match(/{{\s*GFDL[^}\|]*(?:en|\-with\-disclaimers)\s*[\|}]/m))
en_disclaimers = true;
var MTO_REPLACE_TMP = "%%%MTOTEMPTEXT%%%";
cleanup = cleanup.replace(/{{\s*(?:Bild\-)?GFDL.*}}\s*\n?/im, MTO_REPLACE_TMP) //locate first instance
cleanup = cleanup.replace(/{{\s*(?:Bild\-)?GFDL.*}}\s*\n?/gim, ""); //empty all others
cleanup = cleanup.replace(MTO_REPLACE_TMP, "{{GFDL-user-"+project_code+
(en_disclaimers?"-with-disclaimers":(project_code=="en"?"-no-disclaimers":""))+"|"+username+"|migration="+migration+"}}\n");
}
//unknown template
cleanup = cleanup.replace(/(\|\s*date\s*\=\s*)(?:unknown(?: +date)?|not known|desconocido|unbekannt)\s*\.?\s*(?:(?:<\s*br\/?>)?\n?|\n)(?:(?!\|).+\n)?(\s*(?:\||\}\}))/i, "$1{{unknown|date}}\n$2");
cleanup = cleanup.replace(/(\|\s*author\s*\=\s*)(?:unknown(?: +author)?|not known|desconocido|unbekannt)\s*\.?\s*(?:(?:<\s*br\/?>)?\n?|\n)(?:(?!\|).+\n)?(\s*(?:\||\}\}))/i, "$1{{unknown|author}}\n$2");
//useless other_versions messages
cleanup = cleanup.replace(/(\|\s*other[_ ]versions\s*\=\s*)(?:no|none(?:\s+known)?|nein|yes|keine|\-+)\s*\.?\s*\n(\s*(?:\||\}\}))/i, "$1\n$2");
//duplicate templates
cleanup = cleanup.replace(/{{\s*(?:[Cc]c\-by\-sa\-3.0\-migrated|[Ll]icense +migration +not +eligible)\s*}}\s*?\n?/, '');
cleanup = iterative_replace(/\{\{\s*(?:[Tt]rademark(?:ed)?|[Tt][Mm]|[Ss]VG\-Logo|®)\s*}}([\s\S]*)\{\{\s*(?:[Tt]rademark(?:ed)?|[Tt][Mm]|[Ss]VG\-Logo|®)\s*}}/, "{{Trademarked}}$1", cleanup);
cleanup = iterative_replace(/\{\{\s*(?:[Mm]oney\-US|[Pp]D\-USGov\-money)\s*\}\}([\s\S]*)\{\{\s*(?:[Mm]oney\-US|[Pp]D\-USGov\-money)\s*\}\}/, "{{PD-USGov-money}}$1", cleanup);
cleanup = iterative_replace(/(\{\{\s*(?:[Cc]c\-by\-sa\-3\.0\,2\.5\,2\.0,1\.0|[Cc]c\-by\-sa\-all)\s*}}\s*?){2,}/, "{{Cc-by-sa-3.0,2.5,2.0,1.0}}", cleanup);
cleanup = iterative_replace(/\{\{\s*(?:[Pp]D\-China|[Pp]D\-cn|[Cc]hina\-PD)}}([\s\S]*?)\{\{\s*(?:[Pp]D\-China|[Pp]D\-cn|[Cc]hina\-PD)\s*}}/, "{{PD-China}}$1", cleanup);
cleanup = iterative_replace(/\{\{\s*(?:PD\-USGov(\-[A-Za-z]+)(\-[A-Za-z\-]+?))\s*\}\}([\s\S]*?)\{\{\s*PD\-USGov\1?\2\s*\}\}/, "{{PD-USGov$2}}$3", cleanup);
cleanup = iterative_replace(/\{\{\s*bad *jpe?g\s*}}([\s\S]*)\{\{\s*bad *jpe?g\s*}}/i, "{{badjpeg}}$1", cleanup);
cleanup = iterative_replace(/\{\{\s*(?:(?:convert *to|to|should *be)? *svg|vectorize)\s*}}([\s\S]*)\{\{\s*(?:(?:convert *to|to|should *be)? *svg|vectorize)\s*}}/i, "{{Convert to SVG}}$1", cleanup);
if (cleanup.search(/\{\{\s*(?:[Pp]D\-text(?: *|\-)logo|[Pp]d\-textlogo|[Tt]extlogo|[Pp]D-\Markenrecht)\s*(?:\|[\s\S]*?)?\}\}/) !==-1 && cleanup.search(/\{\{\s*(?:[Tt]rademark(?:ed)?|[Tt][Mm]|[Ss]VG\-Logo|®)\s*(?:\|[\s\S]*?)?\}\}/) !==-1)
{cleanup = iterative_replace(/\{\{\s*Bild\-LogoSH\s*(?:\|[\s\S]*?)?\}\}\s*?\n?/, "", cleanup);}
//templates which are unneeded immediately after license header
cleanup = iterative_replace(/((\=\=)\s*.+\s*\2\s*\n)\s*\{\{\s*(?:description +missing|date)\s*\}\}\s*?\n?/i, "$1", cleanup);
cleanup = iterative_replace(/((\=\=)\s*.+\s*\2\s*\n(?:\s*\{\{.+\}\}\s*\n)*)\s*\{\{\s*hidden\s*\}\}\s*?\n?/i, "$1", cleanup);
//redundant pd-old
cleanup = cleanup.replace(/{{\s*[Pp]D\-old\s*}}\s*?\n?\s*{{\s*[Pp]D\-old\-100\s*}}/, '{{PD-old-100}}');
//pd-art cleanup
cleanup = cleanup.replace(/{{\s*([Pp][Dd]\-[Aa]rte?|[Bb]ild\-PD\-Kunst|[Pp]D\-kunst)\s*}}\s*?\n?\s*{{\s*([Pp]D\-[^\|]+)\s*}}/, '{{$1|$2}}');
cleanup = cleanup.replace(/{{\s*(?:[Pp][Dd]\-[Aa]rte?|[Bb]ild\-PD\-Kunst|[Pp]D\-kunst)\s*\|\s*[Pp][Dd]\-old\-(70|100)\s*}}/, '{{PD-art-$1}}');
cleanup = cleanup.replace(/{{\s*(?:[Pp][Dd]\-[Aa]rte?|[Bb]ild\-PD\-Kunst|[Pp]D\-kunst)\s*\|\s*[Pp][Dd]\-old\s*}}/, '{{PD-art-70}}');
cleanup = cleanup.replace(/{{\s*[Pp][Dd]\-US\s*\}\}\s*\{\{\s*([Pp][Dd]\-[Aa]rte?|[Bb]ild\-PD\-Kunst|[Pp]D\-kunst)\s*}}/, '{{$1|PD-US}}');
//insert header, but only above an {{information}} template and if there is at least one other header
// on the page already, for asthetic purposes (request by Leyo)
headercheck = cleanup.replace(/([^{]|\s){(?!{)/, "$1MTOWASHERE"); //removing markings which will confuse parser
headercheck = cleanup.replace(/((?:{{)+){(?!{)/, "$1MTOWASHERE");
headercheck = cleanup.replace(/([^}]|\s)}(?!})/, "$1MTOWASHERE");
headercheck = cleanup.replace(/((?:}})+)}(?!})/, "$1MTOWASHERE");
headercheck = iterative_replace(/{{(?:[^{]|\n)+?}}/g, "MTOTEMPLATE", headercheck); //only headers that aren't already inside a template will suffice, per what seems right to me
if (headercheck.match(/\n(\=+).+\1\s*\n/))
cleanup = cleanup.replace(/^\s*({{[Ii]nformation\s*\|)/, '== {{int:filedesc}} ==\n$1');
/* uploader_status was set wayyyy above; this is a second run (lazy coding) */
if (uploader_status === NOTAUTHOR)
cleanup = mto_uploader_isnt_author(cleanup);
//further cleanup second upload type
cleanup = cleanup.replace(/(\|\s*[Ss]ource\s*\=\s*.*)(\n\s*\|(?:[\s\S]*\|)?\s*[Aa]uthor\s*\=\s*.*)\s*(\([Tt]ransferr?ed +by +\[\[.+\]\]\))/, '$1 $3$2');
cleanup = cleanup.replace(/(\(Originally uploaded on [a-z\-]{1,6}\.w[a-z]+)\)?\s*\-\s*\(?([Tt]ransferr?ed +by +\[\[.+\]\]\))/, '$1 - $2');
cleanup = cleanup.replace(/([Aa]uthor\s*\=.*?)\s*(?:\([Tt]ransferr?ed +by +\[\[.+\]\]\))/, "$1"); //sometimes leftover text from {{self}} template
//move category related stuff to bottom
var categories="";
cleanup = cleanup + "\n";
var re_cat = /^([\s\S]*)\[\[\s*category\s*\:\s*([^\[\]]?)([^\[\]]*?)\s*\]\](?:(\s*%%%MTOCOMMENT\d+%%%)?\s*?\n)?([\s\S]*?)$/i;
while(1)
{
nextcat = cleanup.replace(re_cat, function($0, $1, $2, $3, $4) {return "[[Category:"+$2.toUpperCase()+$3+"]]"+($4===undefined?"":$4)+"\n";});
if (nextcat==cleanup) break;
categories=nextcat+categories;
cleanup = cleanup.replace(re_cat, "$1$5");
}
var re_unc = /^([\s\S]*){{\s*([Uu]ncat(?:egorized)?(?:\s*\|(?:.|\n)*?)*?)\s*}}(?:(\s*%%%MTOCOMMENT\d+%%%)?\s*?\n)?([\s\S]*?)$/;
var unc = cleanup.replace(re_unc, "{{$2}}$3\n");
if (unc!=cleanup) //positive match: uncat present
{
//even if categories isn't empty, they might be hidden categories, so we don't want to remove {{uncat}}
categories = unc + categories;
cleanup = cleanup.replace(re_unc, "$1$4");
}
var re_ds = /^([\s\S]*)\{\{\s*DEFAULTSORT\s*\:([^\[\]\{]*?)\}\}(?:(\s*%%%MTOCOMMENT\d+%%%)?\s*?\n)?([\s\S]*?)$/;
var ds = cleanup.replace(re_ds, "{{DEFAULTSORT:$2}}$3\n")
if (ds!=cleanup) //positive match: DEFAULTSORT present
{
categories = ds + categories;
cleanup = cleanup.replace(re_ds, "$1$4");
}
var re_chc = /^([\s\S]*)(\{\{\s*[Cc]heck +categories[^}]+\}\})(\s*%%%MTOCOMMENT\d+%%%)?(\s*?\n[\s\S]*?)$/;
var chc = cleanup.replace(re_chc, "$2$3\n")
if (chc!=cleanup) //positive match: checkcategories present
{
categories = chc + categories;
cleanup = cleanup.replace(re_chc, "$1$4");
}
var re_cs_chc = /^([\s\S]*)(%%%MTOCSCOMMENT\d+%%%)(\s*?\n[\s\S]*?)$/;
var cs_chc = cleanup.replace(re_cs_chc, "$2\n")
if (cs_chc!=cleanup) //positive match: commonsense comment present
{
categories = cs_chc + categories;
cleanup = cleanup.replace(re_cs_chc, "$1$3");
}
cleanup = cleanup.replace(/\s*$/, "\n\n"); //we want exactly one trailing newline character
//remove duplicate categories
categories = iterative_replace(/\[\[Category:(.+?)(\s*\|[^\]]*)?\]\](.*?)\n((?:.+\n)*?)\[\[Category:\1(?:\s*\|[^\]]*)?\]\](.*?)\n/, "[[Category:$1$2]]$3$5\n$4", categories);
categories = iterative_replace(/^\s*%%%MTOCOMMENT\d+%%%s*$/m, "", categories);
cleanup += categories;
//add {{int:license-header}} where no license header exists, and it unambiguously would be appropriate
//first, search for end of {{Information}} template, if applicable
var infoend = cleanup.search(/{{\s*[Ii]nformation/);
for (var template_level=1; template_level>0 && infoend>-1;)
{
infoend+=2;
var opennext = cleanup.indexOf("{{", infoend);
var closenext = cleanup.indexOf("}}", infoend);
if (closenext==-1)
{infoend=-1; break;}
else if (opennext<closenext && opennext!==-1)
{infoend=opennext; template_level++;}
else
{infoend=closenext; template_level--;}
}
if (infoend==-1) {infoend=0;}
else {infoend+=2;}
var cleanup_pre = cleanup.substr(0, infoend);
var cleanup_post = cleanup.substr(infoend);
cleanup_post = cleanup_post.replace(/^((?:\s*?\{\{\s*(?:(?:should *be|(?:convert *)?to) *(?:svg|png)|svg|vectorize|artifacts|blurry|low quality[\w\-\.\, ]*|wrong +license|disputed[\w\-\.\, ]*|bad *(?:jpe?g|gif|svg)|crop|cleanup[\w\-\.\, ]*|ifc|(?:object +|globe +)?location[\w\-\.\, ]*)\s*(?:\|\s*[^}]+)?\}\})*)\s*(\{\{\s*(?:fop[\w\-\.\, ]*|freedom +of +panorama|cc(?:\-zero|\-by[\w\-\.\, ]*)?|gfdl[\w\-\.\, ]*|pd[\w\-\.\, ]*|trademark|(?:image|remove +)water +mark|self2?|Propio|[Сс]ебе|jac|multilicense[\w\-\.\, ]*|attribution[\w\-\.\, ]*|fal[\w\-\.\, ]*|GPL[\w\-\.\, ]*|wik(?:i[mp]edia|isource|iquote|iversity|tionary)-screenshot|wikiportrait|wikimedia +project +screenshot|flickrr?eview|license *review|ipernityreview|openphotoreview|panoramioreview|PD\-?review|Picasa(?:review|web)|GFDL[\w\-\.\, ]*)\s*(?:\|\s*[^}]+)?\}\})/i, "$1\n=={{int:license-header}}==\n$2");
cleanup = cleanup_pre + cleanup_post;
//remove {{ImageUpload|...}} (outside comments)
cleanup = cleanup.replace(/\{\{\s*[Ii]mageUpload\s*(?:\|.+?)?\}\}(?:(\n)\n*)?/, "$1");
//rebuild <nowiki>, <!-- --> tags
cleanup = rebuild_comments_nowikis(cleanup, tokens, true);
//remove {{ImageUpload|...}} (inside comments)
cleanup = cleanup.replace(/<\!\-\-\s*{\{\s*[Ii]mageUpload\s*(?:\|.+?)?\}\}\s*\-\->(?:(\n)\n*)?/, "$1");
//unnecessary transfer message for User:Boteas (per request from Leyo)
cleanup = cleanup.replace(/(\|\s*[Ss]ource\s*\=[\s\S]+?)\s*(?:<\s*[Bb][Rr]\s*\/?>\s*|\s+)[Tt]ransferr?ed +from +\[?[a-z\.\:\/ ]+\]? +to +[Cc]ommons +by +\[\[\s*[Uu]ser\s*\:\s*[Bb]oteas\]\] .+/i, "$1");
cleanup = cleanup.replace(/(\|\s*[Ss]ource\s*\=\s*[Tt]ransferr?ed +from +\[?[a-z\.\:\/ ]+\]? +to +[Cc]ommons) +by +\[\[\s*[Uu]ser\s*\:\s*[Bb]oteas\]\](?: +using +\[[^\]]+])?\.?\s*$/mi, "$1");
//remove transfer message if it doesn't communicate anything, and other text isn't present
cleanup = cleanup.replace(/(\|\s*[Ss]ource\s*\=[\s\S]{3,}?)\s*(?:<\s*[Bb][Rr]\s*\/?>\s*|\s+)[Tt]ransferr?ed +from +\[?[a-z\.\:\/ ]+\]?(?: +to +[Cc]ommons)?(?: +using +\[[^\]]+])?\.?\s*$/m, "$1");
cleanup = cleanup.replace(/(\|\s*[Ss]ource\s*\=.+?)\s*(?:<\s*[Bb][Rr]\s*\/?>\s*)(\|\s*(?:[Dd]ate|[Aa]uthor|[Pp]ermission|[Oo]ther[_ ]versions)\s*\=)/, "$1\n$2"); //rm extra <br>
//spacing 0
cleanup = iterative_replace(/((\=+)\s*\{\{\s*int\s*\:\s*license\-header\s*\}\}\s*\2*\n(?:\s*?\{\{.+\}\}\n\s*?)*(?:\s*?\{\{.+\}\}\n\s*?))\s*\n+/, "$1", cleanup);
//spacing 1
cleanup = cleanup.replace(/(dimensions\s*\|\s*comment)(\s*\n){2,}\*/i, '$1\n*') //inexplicably, this bothers me beyond measure
//completely empty nowikis... no reason for these
cleanup = cleanup.replace(/\s*(?:\'\'|<small>)\s*<nowiki>\s*<\/nowiki>\s*(?:\'\'|<\/small>)\s*?\n/gm, '\n'); /* completely empty... just get rid of whole clause */
cleanup = cleanup.replace(/\n<!\-\- Templates .+ do not appear to exist on commons. \-\->\s*\n/, '\n');
//spacing 2
cleanup = cleanup.replace(/^\s+((\=+)\s*{{\s*[Ii]nt\s*\:\s*[Ff]iledesc\s*}}\s*\2\s*\n)/, '$1');
cleanup = cleanup.replace(/\n+(\=+)(.+)\1\s*?\n+/g, '\n\n$1$2$1\n')
cleanup = cleanup.replace(/\s*(\[\[Category:.*?\]\]|\{\{\s*[Uu]ncat(?:egorized)?[\s\S]*?\s*\}\}|\{\{\s*DEFAULTSORT\s*\:([^\[\]\{]*?)\}\}|\{\{\s*[Cc]heck +categories[\s\S]*?\s*\}\}|<\!\-\-\s*[Cc][Aa][Tt][Ee][Gg][Oo][Rr][Ii][Ee][Ss]\s*[Bb][Yy]\s*[Cc][Oo][Mm][Mm][Oo][Nn][Ss][Ee][Nn][Ss][Ee]\s*\-\->)/, '\n\n$1')
var re_cs_chc = /^([\s\S]*)(%%%MTOCSCOMMENT\d+%%%)(\s*?\n[\s\S]*?)$/;
document.editform.wpTextbox1.value=cleanup;
if (originaltext!==cleanup)
{
if (document.editform.wpSummary.value.match(/^\s*$/))
document.editform.wpSummary.value += 'cleanup';
else if (!document.editform.wpSummary.value.match(/^.*cleanup\s*$/m))
document.editform.wpSummary.value = document.editform.wpSummary.value.replace(/(.*?)\s*/m, "$1") + ' +cleanup';
}
}
//stolen shamelessly and modified from the add {{information}} template text
function add_toolbox_button(text, _href)
{
var toolbox = document.getElementById ( "p-tb" ) ;
if ( !toolbox )
return ;
var ul = toolbox.getElementsByTagName ( "UL" ) [0] ;
var li = document.createElement ( "LI" ) ;
var a = document.createElement ( "A" ) ;
a.appendChild (document.createTextNode(text));
a.href = _href;
a.className = "external" ;
li.appendChild ( a ) ;
ul.appendChild ( li ) ;
}
//stolen shamelessly and modified from the add {{information}} template text
function add_topbar_button(text, _href)
{
mw.util.addPortletLink("p-cactions", _href, text, "");
}
function addFunction(functionNameString, buttonDisplayName, checkNameSpaceFlag, whereAdd)
{
checkNameSpaceFlag|= (wgPageName=="Commons:Sandbox");
if (!checkNameSpaceFlag)
return;
if (getParamValue('functionName')==functionNameString)
{
addOnloadHook
(
function ()
{
eval(functionNameString+"(true)")
}
);
}
var _href;
if (wgAction=="edit" || wgAction=="submit")
_href = "javascript:"+functionNameString+"(true)";
else
_href = wgScript + "?title="+encodeURIComponent(mw.config.get('wgPageName'))+ "&action=edit&functionName="+functionNameString;
if (whereAdd=="top")
addOnloadHook(function (){add_topbar_button(buttonDisplayName, _href);})
else if (whereAdd=="toolbox")
addOnloadHook(function (){add_toolbox_button(buttonDisplayName, _href);})
}
function addImageFunction(functionNameString, buttonDisplayName, buttonLocation)
{
addFunction(functionNameString, buttonDisplayName, wgNamespaceNumber == 6, buttonLocation);
}
addImageFunction("mto_cleanup", "cleanup", "toolbox");
if (wgAction=="edit" || wgAction=="submit")
addImageFunction("mto_own_wrapper", "{{own}}", "toolbox");
if (wgAction=="edit" || wgAction=="submit")
addImageFunction("mto_self_photographed_wrapper", "{{self-photographed}}", "toolbox");
//</nowiki>