<?php
-
/**
* Import data from a UseModWiki into a MediaWiki wiki
* 2003-02-09 Brion VIBBER <brion@pobox.com>
* schema changes.
* 2005-03-14
*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
* @todo document
- * @addtogroup Maintenance
+ * @file
+ * @ingroup Maintenance
*/
-if( php_sapi_name() != 'cli' ) {
+if ( php_sapi_name() != 'cli' ) {
echo "Please customize the settings and run me from the command line.";
die( -1 );
}
/* globals */
$wgFieldSeparator = "\xb3"; # Some wikis may use different char
$FS = $wgFieldSeparator ;
- $FS1 = $FS."1" ;
- $FS2 = $FS."2" ;
- $FS3 = $FS."3" ;
+ $FS1 = $FS . "1" ;
+ $FS2 = $FS . "2" ;
+ $FS3 = $FS . "3" ;
# Unicode sanitization tools
require_once( dirname( dirname( __FILE__ ) ) . '/includes/normal/UtfNormal.php' );
global $wgRootDirectory;
$gt = '>';
- echo <<<END
-<?xml version="1.0" encoding="UTF-8" ?$gt
+ echo <<<XML
+<?xml version="1.0" encoding="UTF-8" ?>
<mediawiki xmlns="http://www.mediawiki.org/xml/export-0.1/"
- xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
- xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.1/
- http://www.mediawiki.org/xml/export-0.1.xsd"
- version="0.1"
- xml:lang="en">
+ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+ xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.1/
+ http://www.mediawiki.org/xml/export-0.1.xsd"
+ version="0.1"
+ xml:lang="en">
<!-- generated by importUseModWiki.php -->
-END;
+XML;
$letters = array(
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I',
'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R',
'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'other' );
- foreach( $letters as $letter ) {
+ foreach ( $letters as $letter ) {
$dir = "$wgRootDirectory/page/$letter";
- if( is_dir( $dir ) )
+ if ( is_dir( $dir ) )
importPageDirectory( $dir );
}
- echo <<<END
+ echo <<<XML
</mediawiki>
-END;
+XML;
}
function importPageDirectory( $dir, $prefix = "" )
{
echo "\n<!-- Checking page directory " . xmlCommentSafe( $dir ) . " -->\n";
$mydir = opendir( $dir );
- while( $entry = readdir( $mydir ) ) {
+ while ( $entry = readdir( $mydir ) ) {
$m = array();
- if( preg_match( '/^(.+)\.db$/', $entry, $m ) ) {
+ if ( preg_match( '/^(.+)\.db$/', $entry, $m ) ) {
echo importPage( $prefix . $m[1] );
} else {
- if( is_dir( "$dir/$entry" ) ) {
- if( $entry != '.' && $entry != '..' ) {
+ if ( is_dir( "$dir/$entry" ) ) {
+ if ( $entry != '.' && $entry != '..' ) {
importPageDirectory( "$dir/$entry", "$entry/" );
}
} else {
function useModFilename( $title ) {
$c = substr( $title, 0, 1 );
- if(preg_match( '/[A-Z]/i', $c ) ) {
+ if ( preg_match( '/[A-Z]/i', $c ) ) {
return strtoupper( $c ) . "/$title";
}
return "other/$title";
function fetchPage( $title )
{
- global $FS1,$FS2,$FS3, $wgRootDirectory;
+ global $FS1, $FS2, $FS3, $wgRootDirectory;
$fname = $wgRootDirectory . "/page/" . useModFilename( $title ) . ".db";
- if( !file_exists( $fname ) ) {
+ if ( !file_exists( $fname ) ) {
echo "Couldn't open file '$fname' for page '$title'.\n";
die( -1 );
}
function fetchKeptPages( $title )
{
- global $FS1,$FS2,$FS3, $wgRootDirectory;
+ global $FS1, $FS2, $FS3, $wgRootDirectory;
$fname = $wgRootDirectory . "/keep/" . useModFilename( $title ) . ".kp";
- if( !file_exists( $fname ) ) return array();
+ if ( !file_exists( $fname ) ) return array();
$keptlist = explode( $FS1, file_get_contents( $fname ) );
array_shift( $keptlist ); # Drop the junk at beginning of file
$revisions = array();
- foreach( $keptlist as $rev ) {
+ foreach ( $keptlist as $rev ) {
$section = splitHash( $FS2, $rev );
$text = splitHash( $FS3, $section["data"] );
- if ( $text["text"] && $text["minor"] != "" && ( $section["ts"]*1 > 0 ) ) {
+ if ( $text["text"] && $text["minor"] != "" && ( $section["ts"] * 1 > 0 ) ) {
array_push( $revisions, array2object( array ( "text" => $text["text"] , "summary" => $text["summary"] ,
"minor" => $text["minor"] , "ts" => $section["ts"] ,
"username" => $section["username"] , "host" => $section["host"] ) ) );
function splitHash ( $sep , $str ) {
$temp = explode ( $sep , $str ) ;
$ret = array () ;
- for ( $i = 0; $i+1 < count ( $temp ) ; $i++ ) {
+ for ( $i = 0; $i + 1 < count ( $temp ) ; $i++ ) {
$ret[$temp[$i]] = $temp[++$i] ;
}
return $ret ;
{
global $usercache;
- if( $name ) {
- if( in_array( $name, $usercache ) ) {
+ if ( $name ) {
+ if ( in_array( $name, $usercache ) ) {
$userid = $usercache[$name];
} else {
# If we haven't imported user accounts
function importPage( $title )
{
- global $usercache;
-
echo "\n<!-- Importing page " . xmlCommentSafe( $title ) . " -->\n";
$page = fetchPage( $title );
$newtitle = xmlsafe( str_replace( '_', ' ', recodeText( $title ) ) );
$munged = mungeFormat( $page->text );
- if( $munged != $page->text ) {
+ if ( $munged != $page->text ) {
/**
* Save a *new* revision with the conversion, and put the
* previous last version into the history.
*/
$revisions = array( $page );
}
- $xml = <<<END
+ $xml = <<<XML
<page>
<title>$newtitle</title>
-END;
+XML;
# History
$revisions = array_merge( $revisions, fetchKeptPages( $title ) );
- if(count( $revisions ) == 0 ) {
+ if ( count( $revisions ) == 0 ) {
return NULL; // Was "$sql", which does not appear to be defined.
}
- foreach( $revisions as $rev ) {
+ foreach ( $revisions as $rev ) {
$text = xmlsafe( recodeText( $rev->text ) );
- $minor = ($rev->minor ? '<minor/>' : '');
+ $minor = ( $rev->minor ? '<minor/>' : '' );
list( /* $userid */ , $username ) = checkUserCache( $rev->username, $rev->host );
$username = xmlsafe( recodeText( $username ) );
$timestamp = xmlsafe( timestamp2ISO8601( $rev->ts ) );
$comment = xmlsafe( recodeText( $rev->summary ) );
- $xml .= <<<END
+ $xml .= <<<XML
<revision>
<timestamp>$timestamp</timestamp>
<contributor><username>$username</username></contributor>
<text>$text</text>
</revision>
-END;
+XML;
}
$xml .= "</page>\n\n";
return $xml;
return $string;
}
-function wfUtf8Sequence($codepoint) {
- if($codepoint < 0x80) return chr($codepoint);
- if($codepoint < 0x800) return chr($codepoint >> 6 & 0x3f | 0xc0) .
- chr($codepoint & 0x3f | 0x80);
- if($codepoint < 0x10000) return chr($codepoint >> 12 & 0x0f | 0xe0) .
- chr($codepoint >> 6 & 0x3f | 0x80) .
- chr($codepoint & 0x3f | 0x80);
- if($codepoint < 0x100000) return chr($codepoint >> 18 & 0x07 | 0xf0) . # Double-check this
- chr($codepoint >> 12 & 0x3f | 0x80) .
- chr($codepoint >> 6 & 0x3f | 0x80) .
- chr($codepoint & 0x3f | 0x80);
+function wfUtf8Sequence( $codepoint ) {
+ if ( $codepoint < 0x80 ) return chr( $codepoint );
+ if ( $codepoint < 0x800 ) return chr( $codepoint >> 6 & 0x3f | 0xc0 ) .
+ chr( $codepoint & 0x3f | 0x80 );
+ if ( $codepoint < 0x10000 ) return chr( $codepoint >> 12 & 0x0f | 0xe0 ) .
+ chr( $codepoint >> 6 & 0x3f | 0x80 ) .
+ chr( $codepoint & 0x3f | 0x80 );
+ if ( $codepoint < 0x100000 ) return chr( $codepoint >> 18 & 0x07 | 0xf0 ) . # Double-check this
+ chr( $codepoint >> 12 & 0x3f | 0x80 ) .
+ chr( $codepoint >> 6 & 0x3f | 0x80 ) .
+ chr( $codepoint & 0x3f | 0x80 );
# Doesn't yet handle outside the BMP
return "&#$codepoint;";
}
-function wfMungeToUtf8($string) {
+function wfMungeToUtf8( $string ) {
$string = preg_replace ( '/&#([0-9]+);/e', 'wfUtf8Sequence($1)', $string );
$string = preg_replace ( '/&#x([0-9a-f]+);/ie', 'wfUtf8Sequence(0x$1)', $string );
# Should also do named entities here
}
function timestamp2ISO8601( $ts ) {
- #2003-08-05T18:30:02Z
+ # 2003-08-05T18:30:02Z
return gmdate( 'Y-m-d', $ts ) . 'T' . gmdate( 'H:i:s', $ts ) . 'Z';
}
function array2object( $arr ) {
$o = (object)0;
- foreach( $arr as $x => $y ) {
+ foreach ( $arr as $x => $y ) {
$o->$x = $y;
}
return $o;
return placeholder();
}
-?>
+