<?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
*/
/**
* @return string
*/
function retrieveMetaData() {
- global $wgDjvuToXML, $wgDjvuDump;
+ global $wgDjvuToXML, $wgDjvuDump, $wgDjvuTxt;
+ wfProfileIn( __METHOD__ );
+
if ( isset( $wgDjvuDump ) ) {
# djvudump is faster as of version 3.5
# http://sourceforge.net/tracker/index.php?func=detail&aid=1704049&group_id=32953&atid=406583
} else {
$xml = null;
}
+ # Text layer
+ if ( isset( $wgDjvuTxt ) ) {
+ wfProfileIn( 'djvutxt' );
+ $cmd = wfEscapeShellArg( $wgDjvuTxt ) . ' --detail=page ' . wfEscapeShellArg( $this->mFilename ) ;
+ wfDebug( __METHOD__.": $cmd\n" );
+ $retval = '';
+ $txt = wfShellExec( $cmd, $retval );
+ wfProfileOut( 'djvutxt' );
+ if( $retval == 0) {
+ # Strip some control characters
+ $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>' ;
+ }
+ }
+ wfProfileOut( __METHOD__ );
return $xml;
}
+ function pageTextCallback( $matches ) {
+ # Get rid of invalid UTF-8, strip control characters
+ return '<PAGE value="' . htmlspecialchars( UtfNormal::cleanUp( $matches[1] ) ) . '" />';
+ }
+
/**
* Hack to temporarily work around djvutoxml bug
*/