<?php
-
/**
+ * DjVu image handler
*
- * Copyright (C) 2006 Brion Vibber <brion@pobox.com>
+ * Copyright © 2006 Brion Vibber <brion@pobox.com>
* http://www.mediawiki.org/
*
* This program is free software; you can redistribute it and/or modify
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
+ * @file
*/
/**
wfProfileIn( 'djvutxt' );
$cmd = wfEscapeShellArg( $wgDjvuTxt ) . ' --detail=page ' . wfEscapeShellArg( $this->mFilename ) ;
wfDebug( __METHOD__.": $cmd\n" );
+ $retval = '';
$txt = wfShellExec( $cmd, $retval );
wfProfileOut( 'djvutxt' );
if( $retval == 0) {
- $txt = utf8_encode($txt);
- $txt = htmlspecialchars($txt);
- $txt = preg_replace( "/\((page\s[\d-]*\s[\d-]*\s[\d-]*\s[\d-]*\s*\"([^<]*?)\"\s*|)\)/s", "<PAGE value=\"$2\" />", $txt );
+ # Get rid of invalid UTF-8, strip control characters
+ $txt = UtfNormal::cleanUp( $txt );
+ $txt = preg_replace( "/[\013\035\037]/", "", $txt );
+ $reg = <<<EOR
+ /\(page\s[\d-]*\s[\d-]*\s[\d-]*\s[\d-]*\s*"
+ ((?> # Text to match is composed of atoms of either:
+ \\\\. # - any escaped character
+ | # - any character different from " and \
+ [^"\\\\]+
+ )*?)
+ "\s*\)
+ | # Or page can be empty ; in this case, djvutxt dumps ()
+ \(\s*()\)/sx
+EOR;
+ $txt = preg_replace_callback( $reg, array( $this, 'pageTextCallback' ), $txt );
$txt = "<DjVuTxt>\n<HEAD></HEAD>\n<BODY>\n" . $txt . "</BODY>\n</DjVuTxt>\n";
$xml = preg_replace( "/<DjVuXML>/", "<mw-djvu><DjVuXML>", $xml );
$xml = $xml . $txt. '</mw-djvu>' ;
return $xml;
}
+ function pageTextCallback( $matches ) {
+ return '<PAGE value="' . htmlspecialchars( $matches[1] ) . '" />';
+ }
+
/**
* Hack to temporarily work around djvutoxml bug
*/