User:Pilaf/InstaView/Devel
From Wikipedia, the free encyclopedia
< User:Pilaf | InstaView
/*
This version is not functional. Cacycle 01:48, 1 April 2007 (UTC)
InstaView - a Mediawiki to HTML converter in JavaScript Version 0.6.2 Last update: 11:11, 24 July 2006 (UTC) by Shtriter Andrew, http://meta.wikimedia.org/wiki/User:Shtriter Copyright (C) Pedro Fayolle 2005-2006 http://en.wikipedia.org/wiki/User:Pilaf Distributed under the BSD license
Contents |
[edit] Changelog:
[edit] 0.6.4
- MD5 code is moved to md5.js
- Multiple changes to parse_inline_wiki(str) function:
- Changed categories handling: categories are displayed as catlinks now, not just deleted...
- Added title attribute for all internal links
- Apostrophes (') in a tags changed to double quotes (")
- Fixed 2 bugs with trails of internal links (watch the Known bugs).
- Fixed misrendering of short external links ([1] -> [1]): [#] in label changed with the ordered number.
- Multiple changes to make_image(..) function
- Fixed undefined width bug: if width wasn't defined it doesn't added to output (the word undefined was earlier).
- Apostrophes (') in tags changed to double quotes (")
- Added longdesc attribute
- onError attribute moved from the beggining to the end of the img tag
- Removed px suffix from the width attribute
[edit] 0.6.3
- Multiple changes to IV's output. There are (almost) no diffs between MW and IV for:
- paragraphs
- tables
- < pre > tags
- limple lists (not heavily tested yet)
- Lot's of unnecessary linebreaks deleted.
[edit] 0.6.2
- The linebreaks are preserved now (customisable, can be used to output endline's tokens)
- Added closing tags - almost XHTML compatible
- Fix misrendering of the folowing elements:
- Full support for < nowiki >
- Content between < pre > tags
- Tables on the lines that start with space (if there's no sp_lines before - 2do)
[edit] 0.6.1
- Fixed problem caused by \r characters
- Improved inline formatting parser
[edit] 0.6
- Changed name to InstaView
- Some major code reorganizations and factored out some common functions
- Handled conversion of relative links (i.e. /foo)
- Fixed misrendering of adjacent definition list items !!! Not fully
- Fixed bug in table headings handling
- Changed date format in signatures to reflect Mediawiki's output
- Fixed handling of Image: ...
- Updated MD5 function (hopefully it will work with UTF-8)
- Fixed bug in handling of links inside images
[edit] To do:
- Add standart namespaces handling in addition to the local ns (i.e. '..' + InstaView.conf.locale.image + '|Image')
- The reason is that Image, Category and other standart ns work in non-english wikis too.
- Urlencode the article name in href attribute
- Improve html-tags handling (i.e. don't parse block elements and < html > tag)
- Improve transcluding (through AJAX)
- Handle < noinclude > and < includeonly > tags depending on the URL (the page is transcluded or not)...
- Substitute MagicWords (store the list in iw.conf?) and template's arguments
- Fix misrendering of the folowing elements:
- Nested definition lists
- Validate the XHTML of output
- Support for coloured links (AJAX)
- Better support for < math > (Ajax).
- Parser-based (as opposed to RegExp-based) inline wikicode handling (make it one-pass and bullet-proof)
[edit] Known bugs - for discussion
- Non-english words are ignored due to \w
- Solved for cyrilic: \w -> [\wа-яё]
- Use \0n sintax for other?
- Upcase chars should be ignored, they dont
- Solved: \w - > [a-z]
- Compare with MW's regexp
//
// Script to embed InstaView in MediaWiki's edit page
addOnloadHook(function(){
if (document.getElementById('editpage-copywarn')) {
var oldPreview = document.getElementById('wpPreview');
var newPreview = document.createElement('input');
newPreview.setAttribute('type', 'button');
newPreview.setAttribute('style', 'font-style: italic');
newPreview.setAttribute('value', 'InstaView');
newPreview.setAttribute('onclick', "InstaView.dump('wpTextbox1', 'InstaViewDump')");
oldPreview.parentNode.insertBefore(newPreview, oldPreview);
oldPreview.parentNode.innerHTML += '<div style="margin: 5px 0 5px 0; padding: 5px; border: 2px solid orange;" id="InstaViewDump"></div>';
oldPreview.value = 'Classic Preview';
}
});
document.write('<script type="text/javascript" src="md5.js"> </script>\n');
*/
var InstaView = {}
// options
InstaView.conf =
{
user: {},
wiki: {
lang: 'en',
interwiki: 'ab|aa|af|ak|sq|als|am|ang|ar|an|arc|hy|roa-rup|as|ast|av|ay|az|bm|ba|eu|be|bn|bh|bi|bs|br|bg|my|ca|ch|ce|chr|chy|ny|zh|zh-tw|zh-cn|cho|cv|kw|co|cr|hr|cs|da|dv|nl|dz|en|eo|et|ee|fo|fj|fi|fr|fy|ff|gl|ka|de|got|el|kl|gn|gu|ht|ha|haw|he|hz|hi|ho|hu|is|io|ig|id|ia|ie|iu|ik|ga|it|ja|jv|kn|kr|csb|ks|kk|km|ki|rw|rn|tlh|kv|kg|ko|kj|ku|ky|lo|la|lv|li|ln|lt|jbo|nds|lg|lb|mk|mg|ms|ml|mt|gv|mi|minnan|mr|mh|zh-min-nan|mo|mn|mus|nah|na|nv|ne|se|no|nn|oc|or|om|pi|fa|pl|pt|pa|ps|qu|ro|rm|ru|sm|sg|sa|sc|gd|sr|sh|st|tn|sn|scn|simple|sd|si|sk|sl|so|st|es|su|sw|ss|sv|tl|ty|tg|ta|tt|te|th|bo|ti|tpi|to|tokipona|ts|tum|tr|tk|tw|uk|ur|ug|uz|ve|vi|vo|wa|cy|wo|xh|ii|yi|yo|za|zu',
default_thumb_width: 180
},
paths: {
articles: '/wiki/',
math: '/math/',
images: '',
images_fallback: 'http://upload.wikimedia.org/wikipedia/commons/',
magnify_icon: 'skins/common/images/magnify-clip.png'
},
locale: {
user: 'User',
image: 'Image',
category: 'Category',
months: ['Jan','Feb','Mar','Apr','May','Jun','Jul','Aug','Sep','Oct','Nov','Dec']
}
}
// options with default values or backreferences
with (InstaView.conf) {
user.name = user.name || 'Wikipedian'
user.signature = '[['+locale.user+':'+user.name+'|'+user.name+']]'
paths.images = 'http://upload.wikimedia.org/wikipedia/' + wiki.lang + '/'
}
//reset internal counters
// pregormated text token
InstaView.inPre = false;
// the level of nowiki nesting
InstaView.nestlev = 0;
// define constants
// Maximum number of includes
/**///InstaView.IncNum = 0;
// new line token
// One of the folowing strings (or combinaton):
// '\n' | '<br style="display:none;"/>' | '<br class="hidden"/>' | ''
InstaView.br = '\n';
//Regular Expression for wiki images processing
InstaView.BLOCK_IMAGE = new RegExp('^\\[\\['+InstaView.conf.locale.image+':.*?\\|.*?(?:frame|thumbnail|thumb|none|right|left|center)', 'i');
InstaView.el = function(aID)
{
return (typeof(aID) != 'string') ? aID : (document.getElementById) ? document.getElementById(aID)
: (document.layers) ? document.layers[aID] : document.all[aID];
}
InstaView.dump = function(from, to)
{
this.el(to).innerHTML = this.convert( this.el(from).value )
}
InstaView.convert = function(wiki)
{
var ll = (typeof wiki == 'string')? wiki.replace(/\r/g,'').split(/\n/): wiki, // lines of wikicode
o='', // output
p=0, // para flag
$r // result of passing a regexp to $()
// some shorthands
function remain() { return ll.length }
function sh() { return ll.shift() } // shift
function ps(s) { o+=s } // push
function f() // similar to C's printf, uses ? as placeholders, ?? to escape question marks
{
var i=1,a=arguments,f=a[0],o='',c,p
for (;i<a.length; i++) if ((p=f.indexOf('?'))+1) {
// allow character escaping
i -= c=f.charAt(p+1)=='?'?1:0
o += f.substring(0,p)+(c?'?':a[i])
f=f.substr(p+1+c)
} else break;
return o+f
}
function html_entities(s) { return s.replace(/&/g,"&").replace(/</g,"<").replace(/>/g,">") }
function max(a,b) { return (a>b)?a:b }
function min(a,b) { return (a<b)?a:b }
// return the first non matching character position between two strings
function str_imatch(a, b)
{
for (var i=0, l=min(a.length, b.length); i<l; i++) if (a.charAt(i)!=b.charAt(i)) break
return i
}
// compare current line against a string or regexp
// if passed a string it will compare only the first string.length characters
// if passed a regexp the result is stored in $r
function $(c) { return (typeof c == 'string') ? (ll[0].substr(0,c.length)==c) : ($r = ll[0].match(c)) }
function $$(c) { return ll[0]==c } // compare current line against a string
function _(p) { return ll[0].charAt(p) } // return char at pos p
//function endl(s) { ps(s); sh() }
/**/function endl(s) { ps(s+InstaView.br); sh() }
/**/function endP() { /*alert(o);*/ if (p) { p=0; ps('</p>') } return !p; }
/**/function trim(s) { return s.replace(/^\s*(.*)\s*$/, '$1') ; }
/**/function ltrim() {
var str = ll[0];
//alert('str = "' + str + '"');
ll[0] = str.replace(/^\s*(.*)$/, '$1') ;
//alert('ll[0] = "' + ll[0] + '"');
str = str.replace(/^(\s*)(.*)$/, '$1') ;
ps (str);
//alert('str = "' + str + '"');
}
// Delete 1-st empty line. (like MW does - propose to delete ALL empty lines - while not if)
/**/ while ($$('')) sh();
function parse_nowiki ()
{
var start=0, open=0, close=0;
while ( InstaView.nestlev || ( remain() && /<nowiki>/i . test( ll[0].substring( start ) ) ) ) {
open = ll[0] . toLowerCase(). indexOf( '<nowiki>' , start);
close = ll[0]. toLowerCase(). indexOf( '</'+'nowiki>', start);
// if < nowiki > tag is opened and < / nowiki > closing tag stands before the next < nowiki > (if it exists...)
if (InstaView.nestlev && (close < open || ( open == -1 && close >= 0 ) ) ) {
// extract the substring from the current line
// (the text between the starting point and closing tag),
// replace '<', '>' and '&' with their html entities
// and push the result to output
ps( html_entities( ll[0] . substring(start, close) ) );
// close opened span indicating the borders of each nowiki container
ps( '</span class="nowiki_' + InstaView.nestlev-- + '">' );
// and shift the starting point to 9 simbols after closing tag position
start = close + 9;
// if < nowiki > was found on the line
} else if (open >= 0) {
// select text before the opening nowiki tag
var before = ll[0] . substring( start, open );
// if inside the multiline nowiki replace special html symbols (<, >, &)
// before the opening tag with their html entities otherwise paste the text as it is
// and push the result to output
ps( (InstaView.nestlev) ? html_entities(before) : before );
// anyway - create new span indicating the borders of each nowiki container
ps( '<span class="nowiki_' + ++InstaView.nestlev + '">' );
// if there are no closing < / nowiki > tags...
if (close == -1) {
// extract the substring from the current line (the text after the opening tag),
// replace special html symbols after the opening tag with their html entities
// and push the result to output
endl( html_entities( ll[0] . substring(open + 8) ) );
// reset the starting point
start=0;
// if closing tag stands after the opening ( .. < nowiki > .. < / nowiki > .. )
} else if ( close > open) {
// replace special html symbols between the nowiki tags with their html entities
ps( html_entities( ll[0] . substring(open + 8, close) ) );
// close opened span indicating the borders of each nowiki container
ps( '</span class="nowiki_' + InstaView.nestlev-- + '">' );
// and shift the starting point to 9 simbols after closing tag position
start = close + 9;
}
}
//alert('Current line:\n' + ll[0] +
// '\n InstaView.nestlev = ' + InstaView.nestlev + '\n open = ' + open + '\n close = ' + close );
var after = ll[0] . substring( start );
// if the line doesn't contain's nowiki tags...
if ( !/<\/?nowiki>/i . test( after ) ) {
// if inside the multiline nowiki replace special html symbols (<, >, &)
// before the opening tag with their html entities otherwise paste the text as it is;
// then push the result to output and shift the array of lines
endl( (InstaView.nestlev) ? html_entities(after) : after );
}
}
//alert('nowiki ended:\n' + o);
}
function parse_pre ()
{
function doInPre( $0, $1, $2, $3)
{
if ($2 == '<pre>') return $1 + $2 + html_entities($3);
return html_entities($1) + $2 + $3;
}
if ( !remain() ) return;
if ( ll[0].match('<pre>') && !InstaView.inPre ) {
InstaView.inPre = true;
endl( ll[0].replace(/(.*?)(<pre>)(.*)/i, doInPre) );
}
while ( InstaView.inPre ) {
parse_nowiki();
if ( !remain() ) return;
if ( !ll[0].match('</'+'pre>') ) endl( html_entities(ll[0]) );
else {
InstaView.inPre = false;
endl( ll[0].replace(/(.*?)(<\/pre>)(.*)/i, doInPre) );
}
}
//alert('preformatted line passed:\n' + o);
}
/*
function dont_parse()
{
var openmatch = '(<html|<table|<blockquote|<h1|<h2|<h3|<h4|<h5|<h6|<pre|<p|<ul|<ol|<li' +
//.'|<\\/center|<tr|<\\/tr|<\\/td|<\\/th'+
')';
var closematch = '(<\\/html|<\\/table|<\\/blockquote|<\\/h1|<\\/h2|<\\/h3|<\\/h4|<\\/h5|<\\/h6|' +
//.'<td|<th|<div|<\\/div|<hr|<\\/pre|<center|' +
'<\\/p|<\\/li|<\\/ul|<\\/ol);
var patterns = [openmatch, closematch]
if (!remain()) return true;
//alert(' Open Match: ' + openmatch.test(ll[0]) + '\n Close Match: ' + closematch.test(ll[0]) )
op_part = RegExp( '^\\s*' + openmatch + '.*$', 'i' );
cl_pat = RegExp( '^.*' + closematch + '\\s*$', 'i' );
if ( $(op_pat) ) {
//if (InstaView.BlockEl) ps('</'+'pre>');
ps('<pre>');
InstaView.BlockEl = true;
ltrim();
//alert('Trimed line with html tag(s):\n' + ll[0])
endl(ll[0]);
return true;
}
if ( $(cl_pat) ) {
if (InstaView.BlockEl) ps('</'+'pre>');
InstaView.BlockEl = false;
ltrim();
//alert('Trimed line with html tag(s):\n' + ll[0])
endl(ll[0]);
return true;
}
if ( $(/^\s*\{\|/) ) {
if (this.inPre) ps('</'+'pre>');
InstaView.BlockEl = false;
parse_table();
return true;
}
return false;
}
*/
function parse_list()
{
var prev='';
var DtOpen = false;
function next(char)
{
switch (char) {
case '*': case '#':
ps('</li><li>');
//alert('Countinue "ol" or "ul"')
break;
case ';':
ps( (DtOpen)?'</dt>':'</dd>' + '<dt>' );
//alert('Countinue "dl" - dt')
break
case ':':
ps( (DtOpen)?'</dt>':'</dd>' + '<dd>' );
//alert('Countinue "dl" - dd')
DtOpen = false;
}
}
function close(pi)
{
if (pi=='*') {
ps('</li></ul>');
//alert('Close "ul"')
}
else if (pi=='#') {
ps('</li></ol>');
//alert('Close "ol"')
}
// close a dl only if the new item is not a dl item (:, ; or empty)
else switch (l_match[1].charAt(i)) {
case'':case'*':case'#':
ps( (DtOpen)?'</dt>':'</dd>' + '</dl>' );
//alert('Close "dl"');
DtOpen = false;
} //switch
// print the line-break after each list's closing tag (if the line isn't last)
//if (remain()>1)
//alert('Close list at: '+ll[0]);
ps(InstaView.br);
return t;
}
function open(li)
{
if (li=='*') {
ps('<ul><li>');
//alert('Start "ul"')
}
else if (li=='#') {
ps('<ol><li>');
//alert('Start "ol"')
}
// do wee need the coparison at all? it don't work... (imho)
else switch(prev.charAt(i)) {
case'':case'*':case'#':
// open a new dl only if it is needed for nesting:
// don't add <dl> if the previous and the current
// char are equal to ';' at the same time
if ( (l_match[1].charAt(i-1) != ';') || (l_match[1].charAt(i) != ';') ) {
ps('<dl>');
//alert('Start "dl"')
if (li==':') ps('<dd>');
else {
ps('<dt>');
DtOpen = true;
} //else
} // if
} //else
}
while (remain() && $(/^([*#:;]+)(.*)$/)) {
var l_match = $r
sh()
var ipos = str_imatch(prev, l_match[1])
// continue opened lists
//if ( prev == l_match[1] ) next(l_match[1].charAt(l_match[1].length-1))
//else if ( l_match[1].length || prev.length ) {
// close uncontinued lists
for (var i=prev.length-1; i >= ipos; i--) ps( close(prev.charAt(i)) );
// open new lists
for (var i=ipos; i<l_match[1].length; i++) open(l_match[1].charAt(i));
// continue unclosed lists %)
if ( l_match[1].length <= ipos && ipos > 0 ) {
//alert('Continue list: '+ l_match[1][ipos-1] +
// ',\n cause the current prefix is shorter then previous')
next( l_match[1][ipos-1] );
}
// process the remaining wikitext
prev=l_match[1]
// Nested DL's solution - see bug #6569 [http://bugzilla.wikimedia.org/show_bug.cgi?id=6569]
// ps( l_match[1].replace(/^.*?[;:]([;:]*)$/g, '$1') )
var dt_match
var pr_char = prev.charAt(prev.length-1)
// handle ;dt :dd format
if ( (pr_char == ';') && (dt_match = l_match[2].match(/(.*?) (:.*?)$/) ) ) {
ps(parse_inline_wiki(dt_match[1]))
//alert(dt_match[1])
ll.unshift(dt_match[2])
} else {
ps(parse_inline_wiki(l_match[2]));
//alert(l_match[2])
}
// print the line-break
ps(InstaView.br);
//} // else if
} // while
//alert(prev+', '+ipos)
for (var i=prev.length-1; i >= ipos-1; i--) ps( close(prev.charAt(i)) );
} //function
function parse_table()
{
ltrim();
//alert('ll[0] = "' + ll[0] + '"');
/**/endl(f('<table?>', $(/^\s*\{\|( .*)$/)? $r[1] : '' ));
//ps(f('<table?>', $(/^\{\|( .*)$/)? $r[1]: ''));
//sh();
while (remain()) {
ltrim();
//alert('ll[0] = "' + ll[0] + '"');
if ($('|')) switch (_(1)) {
// close table and parse inline wiki after it
case '}': endl('</table>' + parse_inline_wiki(ll[0].substr(ll[0].indexOf('}')+1))); return
case '-': endl(f('<tr ?>', $(/\|-*(.*)/)[1])); break
default: parse_table_data()
} else if ($('!')) parse_table_data()
//else sh();
// add new line token and shift the array of lines
/**/else endl('')
}
}
function parse_table_data()
{
var td_line, match_i
// 1: "|+", '|' or '!'
// 2: Full string:
// all the chars before the "|" and "[" but not "||" if such pattern exists in the string ; and any way - the rest of the line
// (?: .. ) and (?! .. ) doesn't save the matches. So they aren't counted.
// The first matches for pattern agter the colon but not saves it.
// The second matches ig the pattern given after ! doesn't match the string.
// So:
// (?: .. )?(.*)$ - if the line before the '|' exists (see #3) return "substring"+"the_rest_of_the_line" ; otherwise return "the rest of the line" only
// (?!\|) - not a "|"
// 3: attribute - any minimal (maybe even 0-length) number of occurances of neither "[" nor "|" characters
// 4: The rest of the line - can be less that #2 - any chars till the end of the line
var td_match = sh().match(/^\s*(\|\+|\||!)((?:([^[|]*?)\|(?!\|))?(.*))$/)
ltrim();
//alert('td_match =\n' + td_match);
if (td_match[1] == '|+') ps('<caption');
else ps('<t' + ((td_match[1]=='|')?'d':'h'))
// the was some attribute
if (typeof td_match[3] != 'undefined') {
ps(' ' + td_match[3])
match_i = 4
} else match_i = 2
/**/ps('>')
//ps('>' + InstaView.br)
if (td_match[1] != '|+') {
// use || or !! as a cell separator depending on context
// NOTE: when split() is passed a regexp make sure to use non-capturing brackets
td_line = td_match[match_i].split((td_match[1] == '|')? '||': /(?:\|\||!!)/)
ps(parse_inline_wiki(td_line.shift()))
while (td_line.length) ll.unshift(td_match[1] + td_line.pop())
} else ps(td_match[match_i])
var tc = 0, td = []
while (remain()) {
if ($('|')) {
if (!tc) break // we're at the outer-most level (no nested tables), skip to td parse
else if (_(1)=='}') tc--
}
else if (!tc && $('!')) break
else if ($('{|')) tc++
td.push(sh());
ltrim();
}
if (td.length) ps(InstaView.convert(td))
//add closing <td> or <th> and new line token
/**/ps('</t' + ((td_match[1]=='|')?'d':'h')+'>' + InstaView.br);
}
function parse_sp_lines()
{
//close paragraph if it was opened
/**/endP();//p=0
ps('<pre>');
while (_(0)==' ' && remain()) {
/*if ( !remain() || dont_parse() ) break;
this.inPre = true;
*/
endl(parse_inline_wiki(ll[0].substring(1)));
}
if (this.inPre) ps('</'+'pre>');
}
function parse_block_image()
{
//ps(parse_image(sh()))
//add new line token
/**/ps(parse_image(sh()) + InstaView.br)
}
function parse_image(str)
{
// get what's in between "[[Image:" and "]]"
var tag = str.substring(InstaView.conf.locale.image.length + 3, str.length - 2);
var width;
var attr = [], filename, caption = '';
var thumb=0, frame=0, center=0;
var align='';
if (tag.match(/\|/)) {
// manage nested links
var nesting = 0;
var last_attr;
for (var i = tag.length-1; i > 0; i--) {
if (tag.charAt(i) == '|' && !nesting) {
last_attr = tag.substr(i+1);
tag = tag.substring(0, i);
break;
} else switch (tag.substr(i-1, 2)) {
case ']]':
nesting++;
i--;
break;
case '[[':
nesting--;
i--;
}
}
attr = tag.split(/\s*\|\s*/);
attr.push(last_attr);
filename = attr.shift();
var w_match;
for (;attr.length; attr.shift())
if (w_match = attr[0].match(/^(\d*)px$/)) width = w_match[1]
else switch(attr[0]) {
case 'thumb':
case 'thumbnail':
thumb=true;
case 'frame':
frame=true;
break;
case 'none':
case 'right':
case 'left':
center=false;
align=attr[0];
break;
case 'center':
center=true;
align='none';
break;
default:
if (attr.length == 1) caption = attr[0];
}
} else filename = tag;
var o='';
if (frame) {
if (align=='') align = 'right';
o += f('<div class="thumb t?">', align);
if (thumb) {
if (!width) width = InstaView.conf.wiki.default_thumb_width;
o += f('<div style="width:?px;">?', 2+width*1, make_image(filename, caption, width)) +
f('<div class="thumbcaption"><div class="magnify" style="float:right"><a href="?" class="internal" title="Enlarge"><img src="?"></a></div>?</div>',
InstaView.conf.paths.articles + InstaView.conf.locale.image + ':' + filename,
InstaView.conf.paths.magnify_icon,
parse_inline_wiki(caption)
)
} else {
o += '<div>' + make_image(filename, caption) + f('<div class="thumbcaption">?</div>', parse_inline_wiki(caption))
}
o += '</div></div>';
} else if (align != '') {
o += f('<div class="float?"><span>?</span></div>', align, make_image(filename, caption, width));
} else {
return make_image(filename, caption, width);
}
//alert(width);
return center? f('<div class="center">?</div>', o): o;
}
function make_image(filename, caption, width)
{
// uppercase first letter in file name
filename = filename.charAt(0).toUpperCase() + filename.substr(1);
// replace spaces with underscores
filename = filename.replace(/ /g, '_');
caption = strip_inline_wiki(caption);
var md5 = hex_md5(filename);
var source = md5.charAt(0) + '/' + md5.substr(0,2) + '/' + filename;
width = (width) ? 'width="' + width + '"' : '';
var img = f('<img src="?" ? longdesc="?" ? onerror="this.onerror=null;this.src=\'?\'">', InstaView.conf.paths.images + source, (caption!='')? 'alt="' + caption + '"' : '', InstaView.conf.paths.articles + InstaView.conf.locale.image + ':' + filename, width, InstaView.conf.paths.images_fallback + source);
return f('<a href="?" class="image" ?>?</a>', InstaView.conf.paths.articles + InstaView.conf.locale.image + ':' + filename, (caption!='')? 'title="' + caption + '"' : '', img);
}
function parse_inline_images(str)
{
var start, substart=0, nestlev=0;
var loop, close, open, wiki, html;
while (-1 != (start=str.indexOf('[[', substart))) {
if(str.substr(start+2).match(RegExp('^' + InstaView.conf.locale.image + ':','i'))) {
loop=true;
substart=start;
do {
substart+=2;
close=str.indexOf(']]',substart);
open=str.indexOf('[[',substart);
if (close<=open||open==-1) {
if (close==-1) return str;
substart=close;
if (nestlev) {
nestlev--;
} else {
wiki=str.substring(start,close+2);
html=parse_image(wiki);
str=str.replace(wiki,html);
substart=start+html.length;
loop=false;
}
} else {
substart=open;
nestlev++;
}
} while (loop)
} else break;
}
return str;
}
// the output of this function doesn't respect the FILO structure of HTML
// but since most browsers can handle it I'll save myself the hassle
function parse_inline_formatting(str)
{
var em,st,i,li,o='';
while ((i=str.indexOf("''",li))+1) {
o += str.substring(li,i);
li=i+2;
if (str.charAt(i+2)=="'") {
li++;
st=!st;
//o+=st?'<strong>':'</strong>';
//MW uses <b> and <i>
/**/o+=st?'<b>':'</b>';
} else {
em=!em;
//o+=em?'<em>':'</em>';
/**/o+=em?'<i>':'</i>';
}
}
return o+str.substr(li);
}
function parse_inline_wiki(str)
{
var aux_match;
str = parse_inline_images(str);
str = parse_inline_formatting(str);
// math
while (aux_match = str.match(/<(?:)math>(.*?)<\/math>/i)) {
var math_md5 = hex_md5(aux_match[1]);
str = str.replace(aux_match[0], f('<img src="?.png">', InstaView.conf.paths.math+math_md5));
}
// Build a Mediawiki-formatted date string
var date = new Date;
var minutes = date.getUTCMinutes();
if (minutes < 10) minutes = '0' + minutes;
var date = f("?:?, ? ? ? (UTC)", date.getUTCHours(), minutes, date.getUTCDate(), InstaView.conf.locale.months[date.getUTCMonth()], date.getUTCFullYear());
//alert('Строка' + urlencode('Строка') );
// text formatting
return str.
// signatures
replace(/~{5}(?!~)/g, date).
replace(/~{4}(?!~)/g, InstaView.conf.user.name+' '+date).
replace(/~{3}(?!~)/g, InstaView.conf.user.name).
/*
//**********************************
// {{{ Variables }}} and {{{ Replaced | Variables }}}
replace(/\{\{\{(.*?)(?:\|(.*?))?\}\}\}/g, this.replaceArguments).
// {{ (Striped:)? Templates (| with_args )? }}
replace(/\{\{([^\]]*?:)?(.*?)(?:\|(.*?))?\}\}/g, this.replaceTemplates).
//**********************************
*/
// 2Do: Urlencode the article name in ''href'' attribute
// [[:Category:...]], [[:Image:...]], etc...
replace(RegExp('\\[\\[:((?:'+InstaView.conf.locale.category+'|'+InstaView.conf.locale.image+'|'+InstaView.conf.wiki.interwiki+'):.*?)\\]\\]','gi'), '<a href="'+InstaView.conf.paths.articles+'$1" title="$1">$1</a>').
replace(RegExp('\\[\\[('+InstaView.conf.locale.category+'|'+InstaView.conf.wiki.interwiki+'):(.*?)\\]\\]','gi'), '<span dir="ltr" style="display:none"><a href="'+InstaView.conf.paths.articles+'$1:$2" title="$1:$2">$2</a></span>').
// [[/Relative links]]
replace(/\[\[(\/[^|]*?)\]\]/g, f('<a href="?$1" title="$1">$1</a>', location)).
// [[/Replaced|Relative links]]
replace(/\[\[(\/.*?)\|(.+?)\]\]/g, f('<a href="?$1" title="$1">$2</a>', location)).
// Bug: Non-english words are ignored due to \w
// Solved for cyrilic: \w -> [\wа-яё]
// Bug: Upcase chars should be ignored, they dont
// Solved: \w - > [a-z]
// [[Common links]]with_trail
replace(/\[\[([^|]*?)\]\]([a-zа-яё]*)/g, f('<a href="?$1" title="$1">$1$2</a>', InstaView.conf.paths.articles)).
// [[Replaced|Links]]with_trail
replace(/\[\[(.*?)\|([^\]]+?)\]\]([a-zа-яё]*)/g, f('<a href="?$1" title="$1">$2$3</a>', InstaView.conf.paths.articles)).
// [[Stripped:Namespace|]]
replace(/\[\[([^\]]*?:)?(.*?)( *\(.*?\))?\|\]\]/g, f('<a href="?$1$2$3" title="$1$2$3">$2</a>', InstaView.conf.paths.articles)).
// External links
replace(/\[(https?|news|ftp|mailto|gopher|irc):(\/*)([^\]]*?) (.*?)\]/g, '<a href="$1:$2$3">$4</a>').
replace(/\[http:\/\/(.*?)\]/g, '<a href="http://$1">[#]</a>').
replace(/\[(news|ftp|mailto|gopher|irc):(\/*)(.*?)\]/g, '<a href="$1:$2$3">$1:$2$3</a>').
replace(/(^| )(https?|news|ftp|mailto|gopher|irc):(\/*)([^ $]*)/g, '$1<a href="$2:$3$4">$2:$3$4</a>').
replace('__NOTOC__','').
replace('__NOEDITSECTION__','');
}
function strip_inline_wiki(str)
{
return str
.replace(/\[\[[^\]]*\|(.*?)\]\]/g,'$1')
.replace(/\[\[(.*?)\]\]/g,'$1')
.replace(/''(.*?)''/g,'$1');
}
// begin parsing
do {
parse_nowiki();
parse_pre();
//dont_parse();
if (!remain()) break;
//parse headings
if ($(/^(={1,6})(.*)\1(.*)$/)) {
//close paragraph if it was opened
/**/endP();//p=0
endl(f('<h?>?</h?>?', $r[1].length, parse_inline_wiki($r[2]), $r[1].length, $r[3]))
//alert('headings processed:\n' + o)
//parse lists
} else if ($(/^[*#:;]/)) {
//close paragraph if it was opened
/**/endP();//p=0
/**/ps(InstaView.br);
parse_list()
//alert('lists processed:\n' + o)
//parse tables
} else if ($(/^(?:\s*)\{\|/)) {
//alert('ll[0] = "' + ll[0] + '"')
//close paragraph if it was opened
/**/endP();//p=0
parse_table()
//alert('tables processed:\n' + o)
//parse lines that start with space
} else if ( _(0) == ' ') {
parse_sp_lines()
//alert('spaced lines processed:\n' + o)
//do the <hr>
} else if ($(/^----+$/)) {
//close paragraph if it was opened
/**/endP();//p=0
endl('<hr>')
//alert('horizontal lines processed:\n' + o)
//parse images
} else if ($(InstaView.BLOCK_IMAGE)) {
//close paragraph if it was opened
/**/endP();//p=0
parse_block_image()
//alert('images processed:\n' + o)
} else {
//escape < /pre > tag cause there's no opening tag and it should be treaten as text
ll[0] = ll[0].replace( '</'+'pre>', '</pre>')
// handle paragraphs
if (trim(ll[0]) == '') { //blank line
//if (p = (remain()>1 && ll[1]==(''))) endl('<p><br>')
//if para was opened - close it
//if 2 empty strings - add hard line break
if ( endP() )
if ( remain()>1 ){
ps('<p>');
p=1;
/**/ if (trim(ll[1])==('') )
/**/ {sh(); ps('<br>'); p=1}
} else break;
} else {
if(!p) {
ps('<p>')
p=1
}
if (remain()<2) {
//alert('The last line:' + ll[0]);
ps(parse_inline_wiki(ll[0]));
endP();
break;
} else ps(parse_inline_wiki(ll[0]));
//add new line token
//ps(parse_inline_wiki(ll[0]) + InstaView.br)
//alert('Add inblockElem - in order to disable the creation of new paragraph' +
//'for such elements as:\n tables, headings, lists and so on.' );
}
//alert('paragraphs processed:\n' + o)
//sh();
//add new line token and shift the array of lines
/**/endl('');
}
} while (remain())
//add closing </tr>
/**/o = o.replace(/(<\/t[dh]>\s*)(<tr (.*)>|<\/table>)/gim, '$1</tr>'+ InstaView.br +'$2')
/**/.replace(/<tr >/gim, '<tr>')
//escape closing < / nowiki > tags
/**/.replace(/<\/nowiki>/i, '</nowiki>');
CatLinks = o.match(/<span dir="ltr" style="display:none">(.*?)<\/span>/gim);
if (CatLinks)
{
o += '<div id="catlinks"><p class="catlinks">';
for (i in CatLinks)
{
alert(CatLinks[i]);
o += CatLinks[i].replace(' style="display:none"', '');
if ( i != CatLinks.length-1 ) { alert(i); alert(CatLinks.length-1); o += ' | ';}
}
o += '</p></div>';
}
/*// - maybe faster, but don't work :(((.
ShortExtLinks = o.match('[#]');
for (i in ShortExtLinks)
{
alert(ShortExtLinks[i] + ' ' + i);
o.replace(/\[#\]/m, '[' + i + ']');
}
*/
i=0;
while ( /\[#\]/m.test(o) ) o=o.replace(/\[#\]/m, '[' + ++i + ']');
//alert('"'+o+'"');
return o
}
//
