*
* A set of replace-on-edit rules for automatically converting
* HTML to PmWiki markup
*
* Developed and tested using the PmWiki 2.2.0-beta series.
*
* To install, add the following line to your configuration file :
include_once("$FarmD/cookbook/convert-html.php");
*
* For more information, please see the online documentation at
* http://www.pmwiki.org/wiki/Cookbook/ConvertHTML
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License,
* Version 2, as published by the Free Software Foundation.
* http://www.gnu.org/copyleft/gpl.html
*/
$RecipeInfo['ConvertHTML']['Version'] = '2008-10-07';
SDVA( $ROEPatterns, array(
'#\s*(.*?)\*s\n*#is' => "(: title $1:)\n",
'#\n*#i' => "(:$2 $4:)\n",
'##' => "%comment% $1 %%",
'#<(ul|ol|dl)\s+([^>]+)>\s*(<(li|dt)\b[^>]*>)#i' => '<$1>$3%apply=list $2% ',
'#<(li|dt)\s+([^>]+)>#i' => "<$1>%apply=item $2% ",
'#\s*(<(ul|ol)\s*>\s*)\n?#ise' => 'ConvertHtmlList(stripmagic("$1"))',
'#\s*(.*?)(?:)?\s*\s*(.*?)(?:)?\n#is' => "\n:$1:$2\n",
'#\s*#i' => '',
'#\s*]*)?>(.*?)\s*#is' => "\n(:table$1:)$2\n(:tableend:)",
'#\s*]*)?>(.*?)#is' => "\n(:cell$1:)$2",
'#\s*]*)?>\s*\(:cell\b(.*?)#is' => "\n(:cellnr$1$2",
'#<(p|h\d)\s+([^>]+)>#i' => "<$1>%block $2% ",
'#\s*(.*?)\n*#ise' => "\"\n\n\".str_repeat('!','$1').' '.stripmagic('$2').\"\n\"",
'#\s*\s*(.*?)\n?#is' => "\n\n$1\n",
'#\s*\s*#is' => "\n\n",
'#\s*]*)?>\s*(.*?)\n?\n*#is' => "\n(:div$1:)\n$2\n(:divend:)\n",
'#]*)>(.*?)#ise' => '"%".ConvertHtmlSpan(stripmagic("$1"))."% $2 %%"',
'#\s*\s*(.*?)
\n*#is' => "\n->$1\n",
'#\n*#i' => "[[<<]]\n",
'#
\n*#i' => "\\\\\\\n",
'#\s*
\n*#i' => "\n----\n",
'##i' => "''",
'##i' => "'''",
'##i' => "@@",
'#(.*?)
#is' => "[@$1@]",
'#(.*?)#is' => "'+$1+'",
'#(.*?)#is' => "'-$1-'",
'#(.*?)#is' => "'^$1^'",
'#(.*?)#is' => "'_$1_'",
'#(.*?)#is' => "{+$1+}",
'#(.*?)#is' => "{-$1-}",
'#(<(?:a|img)\b[^>]+\b(href|src)=)([\'"])([./][^\'"]*?)\3#i' => "$1$3Path:$4$3",
'#(<(?:a|img)\b[^>]+\b(href|src)=)([\'"])([^/:\'"]+?)\3#i' => "$1$3Attach:$4$3",
'#]*\bname=([\'"])([^\'"]*?)\1[^>]*>(.*?)#ise' => '"[[#".preg_replace("/\s+/","_",PSS("$2")).\']] $3\'',
'#]*\bhref=([\'"])([^\'"]*?)\1[^>]*>(.*?)#is' => "[[$2|$3]]",
'#]*)\bsrc=([\'"])([^\'"]*?)\2\s([^>]*?)\s*(?:/?|>\n?#i' => "%apply=img $1$4%$3%%\n",
'#(.*%apply=img\b[^%]+)\balign=([\'"]?)(l|r)(?:eft|ight)\2([^%]*%[^%]+)%%#i' => '%$3float% $1$4%%',
'#(%apply=img\b[^%]+)\b(?:alt|title)=([\'"])([^\'"]+?)\2([^%]*%[^%]+)%%#i' => '$1$4"$3"%%',
'#%apply=img\b(?:\s+(?:alt|title)=([\'"])\s*\1)*\s*%([^%]+)%%#' => '$2',
));
function ConvertHtmlSpan($param) {
return preg_replace(
array( '/%/', '/(?:class|style)=([\'"])(.*?)\1/' ),
array( 'pct', '$2' ),
$param );
}
function ConvertHtmlList($html) {
$out = '';
$lit = array();
$strip = FALSE;
$html = preg_replace('#(]+)>#i','$1>',$html);
$lia = preg_split( '#\s*()\s*#i', $html, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE );
foreach( $lia as $n ) switch($n) {
case '': case '':
$lit[] = "\n".str_repeat( '*', count($lit)+1 ).' ';
break;
case '': case '':
$lit[] = "\n".str_repeat( '#', count($lit)+1 ).' ';
break;
case '
': case '
':
case '': case '':
array_pop($lit);
$strip = FALSE;
break;
case '': case '':
if($lit) $out .= end($lit);
$strip = TRUE;
break;
case '': case '':
$strip = FALSE;
break;
default:
if ($strip) {
$out .= preg_replace('/\s+/',' ',$n);
$strip = FALSE;
} else $out .= $n;
}
return $out;
}