MediaWiki to DokuWiki Converter

Thanks to all of the great scripts on here I was able to do a bit more work towards making something a bit more automated. It's not perfect, but it converted over my 200 page site + files to Dokuwiki pretty well. I figured at this point any other little bugs I find I can change by hand. I didn't have time to perfect it - but hopefully someone else does.

Here's the download: http://www.passportparking.info/Download/mediawiki2dokuwiki2.tar.gz

As I said, it's got some bugs still. You need to run this on your actual mediawiki/dokuwiki server as it copies files between the two file locations.

4/16/2011 - Charlie Youakim (charlie.youakim@passportparking.com)

Bugfix! UPPER to lower convert charset, change getContent.sh:

#	lowertitle="$(echo $title | tr "[:upper:]" "[:lower:]").txt" 
	lowertitle="$(echo $title | awk '{print tolower(substr($0,0))}').txt" 

Hey, I was playing with AWK and Perl a little bit. I created a MediaWiki to DokuWiki Converter. A online converter is now hosted at http://johbuc6.coconia.net/mediawiki2dokuwiki.php.

• bash
• Perl

It is able to transform

• Links
• Bold/italic text
• Lists
• Talkings
• Code

• One Page at once

It is not able to transform

• tables
• CODE (that is, different lines of text starting with a space), should be surrounded by <code></code> in DokuWiki

• [text hello]

  is converted into a link

  [[text|hello]]

  but it should just stay like that

• '''''IMPORTANT!!!'''''

  is converted into

  **//IMPORTANT!!!**//

  but should be

  //**IMPORTANT!!!**//

  or

  **//IMPORTANT!!!//**

• //server/share

  is not converted, but since // opens italic font, this line should be translated to

  <nowiki>//</nowiki>server/share

File mediawiki2dokuwiki.sh:

#! /bin/sh
# Mediawiki2Dokuwiki Converter
# originally by Johannes Buchner <buchner.johannes [at] gmx.at>
# License: GPL (http://www.gnu.org/licenses/gpl.txt)
 
# Headings
cat mediawiki | \
   perl -pe 's/^[ ]*=([^=])/<h1> ${1}/g' | \
   perl -pe 's/([^=])=[ ]*$/${1} <\/h1>/g' | \
   perl -pe 's/^[ ]*==([^=])/<h2> ${1}/g' | \
   perl -pe 's/([^=])==[ ]*$/${1} <\/h2>/g' | \
   perl -pe 's/^[ ]*===([^=])/<h3> ${1}/g' | \
   perl -pe 's/([^=])===[ ]*$/${1} <\/h3>/g' | \
   perl -pe 's/^[ ]*====([^=])/<h4> ${1}/g' | \
   perl -pe 's/([^=])====[ ]*$/${1} <\/h4>/g' | \
   perl -pe 's/^[ ]*=====([^=])/<h5> ${1}/g' | \
   perl -pe 's/([^=])=====[ ]*$/${1} <\/h5>/g' | \
   perl -pe 's/^[ ]*======([^=])/<h6> ${1}/g' | \
   perl -pe 's/([^=])======[ ]*$/${1} <\/h6>/g' \
    > mediawiki1
 
cat mediawiki1 | \
   perl -pe 's/<\/?h1>/======/g' | \
   perl -pe 's/<\/?h2>/=====/g' | \
   perl -pe 's/<\/?h3>/====/g' | \
   perl -pe 's/<\/?h4>/===/g' | \
   perl -pe 's/<\/?h5>/==/g' | \
   perl -pe 's/<\/?h6>/=/g' | \
   cat > mediawiki2
 
# lists
cat mediawiki2 |
  perl -pe 's/^[\*#]{4}\*/          * /g'  | \
  perl -pe 's/^[\*#]{3}\*/        * /g'    | \
  perl -pe 's/^[\*#]{2}\*/      * /g'      | \
  perl -pe 's/^[\*#]{1}\*/    * /g'        | \
  perl -pe 's/^\*/  * /g'                  | \
  perl -pe 's/^[\*#]{4}#/          \- /g'  | \
  perl -pe 's/^[\*\#]{3}\#/      \- /g'    | \
  perl -pe 's/^[\*\#]{2}\#/    \- /g'      | \
  perl -pe 's/^[\*\#]{1}\#/  \- /g'        | \
  perl -pe 's/^\#/  - /g'                  | \
  cat > mediawiki3
 
#[link] => [[link]]
cat mediawiki3 |
  perl -pe 's/([^\[])\[([^\[])/${1}[[${2}/g' |
  perl -pe 's/^\[([^\[])/[[${1}/g' |
  perl -pe 's/([^\]])\]([^\]])/${1}]]${2}/g' |
  perl -pe 's/([^\]])\]$/${1}]]/g' \
  > mediawiki4
 
#[[url text]] => [[url|text]]
cat mediawiki4 |
  perl -pe 's/(\[\[[^| \]]*) ([^|\]]*\]\])/${1}|${2}/g' \
  > mediawiki5
 
# bold, italic
cat mediawiki5 |
  perl -pe "s/'''/**/g" |
  perl -pe "s/''/\/\//g" \
  > mediawiki6
 
# talks
cat mediawiki6 |
  perl -pe "s/^[ ]*:/>/g" |
  perl -pe "s/>:/>>/g" |
  perl -pe "s/>>:/>>>/g" |
  perl -pe "s/>>>:/>>>>/g" |
  perl -pe "s/>>>>:/>>>>>/g" |
  perl -pe "s/>>>>>:/>>>>>>/g" |
  perl -pe "s/>>>>>>:/>>>>>>>/g" \
  > mediawiki7
 
cat mediawiki7 |
  perl -pe "s/<pre>/<code>/g" |
  perl -pe "s/<\/pre>/<\/code>/g" \
  > mediawiki8
 
cat mediawiki8 > dokuwiki

1. Make sure you are under Linux/Unix
2. Save the code above in a file named mediawiki2dokuwiki.sh.
3. Save the MediaWiki page you want to transform to a file called mediawiki in the same directory.
4. In the shell go to the directory (using cd) and execute:

   chmod +x mediawiki2dokuwiki.sh #we want to be able to execute it
   ./mediawiki2dokuwiki.sh

5. Now you got some files called mediawiki+a number. These are debugging steps (ignore).
6. In the file 'dokuwiki' you'll find your DokuWiki-Syntax.

Remember, all the fame goes to me, cause I started this ! — Johannes Buchner 2006-01-26 19:27

• added Talkings — Johannes Buchner 2006-01-27 11:37

Would be great if someone wants to improve this! What is needed:

• See Limitations & Missing features
• A web-based service: now available: http://johbuc6.coconia.net/mediawiki2dokuwiki.php. (This is no longer active! ← wrong, it still is!)

• Yeah, i could remove leading whitespaces at all, but this might ruin the design. Johannes Buchner 2006-01-27 11:41
• I just began to implement tables with:

    perl -pe "s/^[ ]*\{\|[^\|]*$//g" |
    perl -pe "s/^[ ]*\|\}[ ]*$//g" |
    perl -pe "s/^[ ]*\|([^\|]+)\|[ ]*$/|${1}|/g" 
    # ...

  But tables in Wikimedia are crap. I suggest to use a html2wiki implementation for this need ('cause the needs will be very special) like http://diberri.dyndns.org/html2wiki.html Johannes Buchner 2006-01-27 12:00

• Feedback/Questions:
  • Feedback by Juergen Mueller: Is there an easy way to convert a bunch of MediaWiki articles to DokuWiki articles at once? Our MediaWiki wiki has some hundreds of articles and therefore it is not feasible to do it manually file by file.

Graham Macleod 30/1/08 1:50pm GMT - Hi there. Code mark up which displays such as

<?php echo 'THIS IS CODE'; ?>

in DokuWiki uses double spaces but your converter seems to keep the single space that MediaWiki uses. I'd also just like to take the time to give you massive props on this. It's been a life saver.

• I changed this script to use sed, and have made a few improvements (see bugs & missing features). Maybe this can be of use for someone.

  mw2dw-conv_sed.sh

  #! /bin/sh
  # Mediawiki2Dokuwiki Converter
  # originally by Johannes Buchner <buchner.johannes [at] gmx.at>
  # changes by Frederik Tilkin:		- uses sed instead of perl
  #				- resolved some bugs ('''''IMPORTANT!!!''''' becomes //**IMPORTANT!!!**//, // becomes <nowiki>//</nowiki> if it is not in a CODE block)
  # 				- added functionality (multiple lines starting with a space become CODE blocks)
  #
  # Licence: GPL (http://www.gnu.org/licenses/gpl.txt)
   
  # First escape things that are already DokuWiki but not MediaWiki syntax
  # //	=>	<nowiki>//</nowiki> 	(only when it is NOT in a PREFORMATTED line, and when it is NOT in a LINK [] !)
  # **	=>  <nowiki>**</nowiki		(only when it is NOT in a PREFORMATTED line, NOR on the beginning of a line)
  # surround preformatted blocks (lines starting with space) with <PRE> so that it's correctly converted to DokuWiki <CODE> blocks later on
   
  cat mediawiki \
  	| sed -r -n '
  		#starts with a SPACE, so it is part of a code block, just print and do nothing
  		/^[ ]/ { p; d }
  		#else: replace ALL **... strings (not at beginning of line)
  		s/([^^][^\*]*)(\*\*+)/\1<nowiki>\2<\/nowiki>/g
  		# 		also replace ALL //... strings 
  		s/([^\/]*)(\/\/+)/\1<nowiki>\2<\/nowiki>/g
  		#		change the ones that have been replaced in a link [] BACK to normal (do it twice in case [http://addres.com http://address.com] ) [quick and dirty]
  		s/([\[][^\[]*)(<nowiki>)(\/\/+)(<\/nowiki>)([^\]]*)/\1\3\5/g ; s/([\[][^\[]*)(<nowiki>)(\/\/+)(<\/nowiki>)([^\]]*)/\1\3\5/g
   
  		p
  	  ' \
  	| sed -r -n '
  		# See also: http://www.grymoire.com/Unix/Sed.html#uh-40
  		# 	http://en.wikipedia.org/wiki/Regular_expression
  		# This is pretty advanced sed syntax, so I ll try to explain as much as possible
  		################################################################################
   
  		# if line starts with a space, add it to the hold buffer
  		# we do this by 'branching' to :addtopre
  		/^ [ ]*[^ ][^ ]*/ b addtopre
  		# if line has only whitespace or is empty, the preformatted block is over, so we surround that with <pre>
  		# we do this by 'branching' to :outputpre
  		/^[ ]*$/ b outputpre
  		# if line starts with NO whitespace, the preformatted block is over, so we surround that with <pre>
  		/^[^ ].*$/ b outputpre
   
  		#else this is a normal line
  				#s/(.*)/NORMAL LINE: \1/g; p
  			# print the line
  			p
  			#delete the current pattern space (so new cycle is started -> jumps to top)
  			d
   
  		# this is a line that should be part of a CODE block
  		:addtopre
  			#add it to the hold buffer
  			H
  				#s/(.*)/ADDED LINE: \1/g; p
  			# if this is the last line of the file (end-of-file), empty this line and then output this last preformatted block
  			$ { s/.*//g
  				b outputpre
  			}
  			#delete the current pattern space (so new cycle is started -> jumps to top)
  			d
  		# this is where a paragraph is surrounded by <pre></pre>
  		:outputpre
  				#s/(.*)/END OF CODE LINE: \1/g; p
  			# HOLD buffer is exchanged with the pattern space
  			x
   
  			# IF not empty, surround with <PRE> and PRINT the pattern space
  			/(.+)/ {
  				# surround it with <pre>
  				s/(.+)/<pre>\1<\/pre>/g
  				p
  			}
  			# exchange pattern space and hold buffer again, pattern is now the current line (not part of the preformatted block) and PRINT this line
  			x
  			p
  			#delete the current pattern space			
  			s/.*//g
  			#and exchange this again with the hold buffer, so that the hold buffer is empty again			
  			x
  			#delete the current pattern space (so new cycle is started -> jumps to top)
  			d
  	' \
      > mediawiki0
   
  # Headings
  cat mediawiki0 \
     | sed -r 's/^[ ]*=([^=])/<h1> \1/g' \
     | sed -r 's/([^=])=[ ]*$/\1 <\/h1>/g' \
     | sed -r 's/^[ ]*==([^=])/<h2> \1/g' \
     | sed -r 's/([^=])==[ ]*$/\1 <\/h2>/g' \
     | sed -r 's/^[ ]*===([^=])/<h3> \1/g' \
     | sed -r 's/([^=])===[ ]*$/\1 <\/h3>/g' \
     | sed -r 's/^[ ]*====([^=])/<h4> \1/g' \
     | sed -r 's/([^=])====[ ]*$/\1 <\/h4>/g' \
     | sed -r 's/^[ ]*=====([^=])/<h5> \1/g' \
     | sed -r 's/([^=])=====[ ]*$/\1 <\/h5>/g' \
     | sed -r 's/^[ ]*======([^=])/<h6> \1/g' \
     | sed -r 's/([^=])======[ ]*$/\1 <\/h6>/g' \
     > mediawiki1
   
  cat mediawiki1 \
     | sed -r 's/<\/?h1>/======/g' \
     | sed -r 's/<\/?h2>/=====/g' \
     | sed -r 's/<\/?h3>/====/g' \
     | sed -r 's/<\/?h4>/===/g' \
     | sed -r 's/<\/?h5>/==/g' \
     | sed -r 's/<\/?h6>/=/g'  \
     > mediawiki2
   
  # lists
  cat mediawiki2 \
    | sed -r 's/^[*#][*#][*#][*#]\*/          * /g'  \
    | sed -r 's/^[*#][*#][*#]\*/        * /g'    \
    | sed -r 's/^[*#][*#]\*/      * /g'      \
    | sed -r 's/^[*#]\*/    * /g'        \
    | sed -r 's/^\*/  * /g'                  \
    | sed -r 's/^[*#][*#][*#][*#]#/          - /g'  \
    | sed -r 's/^[*#][*#][*#]#/        - /g'    \
    | sed -r 's/^[*#][*#]#/      - /g'      \
    | sed -r 's/^[*#]#/    - /g'        \
    | sed -r 's/^#/  - /g'                   \
    > mediawiki3
   
   
  #[url text] => [url|text]
  cat mediawiki3 \
    | sed -r 's/([^[]|^)(\[[^] ]*) ([^]]*\])([^]]|$)/\1\2|\3\4/g' \
    > mediawiki4
   
   
  #[link] => [[link]]
  cat mediawiki4 \
    | sed -r 's/([^[]|^)(\[[^]]*\])([^]]|$)/\1[\2]\3/g' \
    > mediawiki5
   
  # bold, italic
  cat mediawiki5 \
    | sed -r "s/'''''(.*)'''''/\/\/**\1**\/\//g" \
    | sed -r "s/'''/**/g" \
    | sed -r "s/''/\/\//g" \
    > mediawiki6
   
  # talks
  cat mediawiki6 \
    | sed -r "s/^[ ]*:/>/g" \
    | sed -r "s/>:/>>/g" \
    | sed -r "s/>>:/>>>/g" \
    | sed -r "s/>>>:/>>>>/g" \
    | sed -r "s/>>>>:/>>>>>/g" \
    | sed -r "s/>>>>>:/>>>>>>/g" \
    | sed -r "s/>>>>>>:/>>>>>>>/g" \
    > mediawiki7
   
  cat mediawiki7 \
     | sed -r "s/<code>/\'\'/g" \
     | sed -r "s/<\/code>/\'\'/g" \
    > mediawiki8
   
  cat mediawiki8 \
     | sed -r "s/<pre>/<code>/g" \
     | sed -r "s/<\/pre>/<\/code>/g" \
    > mediawiki9
   
  #100720-MSe: remove "<\code>\n \n<code>"
  cat mediawiki9 \
     | sed 'N;N;s/<\/code>\n[ \t]*\n<code>//;P;D;D;' \
    > mediawiki10
   
  cat mediawiki10 > dokuwiki

There is also one issue, when bold and italic texts are combined. I tested with the German UNIX Wikipedia article and there were 2 tags that made whole parts of the generated DokuWiki in bold. The following code fixes this behaviour:

$ diff mediawiki2dokuwiki.sh mediawiki2dokuwiki.sh.080925-1
7d6
< # changes by Reiner Rottmann: - fixed erroneous interpretation of combined bold and italic text.
165,169c164
<
< cat mediawiki9 \
<    | sed -r "s/\*\*\/\//\/\/\*\*/g"> mediawiki10
<
< cat mediawiki10 > dokuwiki
---
> cat mediawiki9 > dokuwiki

This script get the contents of your mediawiki (by database connection), and convert it to dokuwiki syntax. All, out of the box, you only need to configure user/password of database.

Example:

cd mediawiki2dokuwiki
./getContent.sh
mv old /var/www/dokuwiki/data/pages
chmod a+r /var/www/dokuwiki/data/pages/old -R

Here you can find the package: http://dabax.net/files/mediawiki2dokuwiki.tar.gz

This is the main script.

#!/bin/bash

#About your mediawiki
WIKIDB="DATABSE_NAME"
WIKIPASS="DATABASE_PASSWORD"

#The destination folder
DEST="old"

#Dont touch this
TITLES="titles"
PHARSER="./m2d.sh"

mysql --password=$WIKIPASS $WIKIDB -e 'select cur_title from cur;' | \
while read title; do

	newtitle="$(echo $title | tr "[:upper:]" "[:lower:]").txt" 
	echo "$newtitle"
	mysql --password=$WIKIPASS $WIKIDB -e "select cur_text from cur where cur_title='$title';" \
	| sed s/'\\n'/\\n/g | grep -v cur_text |  $PHARSER $DEST/$newtitle 

done

for f in $DEST/*; do 
	[ $(cat $f | wc -w) -lt 25 ] && \
	{ echo "Deleting $f, too short"; rm -f $f;}
done



echo ""
echo "Done. Put the contents of $DEST to Path_Of_dokuwiki/data/pages/"

m2d.sh is the “sed version” published in this page, with some modifications. Enjoy it!

Hi,

Using the above attached code, I'm having some problems:

ERROR 1146 (42S02) at line 1: Table 'pswiki.cur' doesn't exist
cat: old/*: No such file or directory
Deleting old/*, too short

Done. Put the contents of old to Path_Of_dokuwiki/data/pages/

(where pswiki is the database containing my MW data, which came from a Windows-based MySQL server via mysqldump.) The directory ./old is empty.

If I turn on MySQL statement logging:

SET GLOBAL general_log_file='/var/log/mysql/sql.log';
SET GLOBAL general_log='ON';

then I get the following only in that log file when I run ./getContent.sh:

110216  2:11:17    75 Connect   root@localhost on pswiki
                   75 Query     select @@version_comment limit 1
                   75 Query     select cur_title from cur
                   75 Quit

It looks to me as if what's intended to be a cursor is being interpreted as a literal table name, but I'm getting out of my depth there. I have tried back-ticking `cur` in getContent.sh to no avail.

Can anyone shed light?

Thanks!

— tomgreentomgreen

2011/02/16 03:06

EDIT: I've used the web-based service linked above, and apart from some table funnies it worked very well - a lifesaver. Thanks!

— tomgreentomgreen

2011/02/18 03:26

I have solved the “cur problem”. It is assumed, for my opinion, as a VIEW. Create this view, named “cur”, with the following SQL request :

CREATE VIEW cur AS SELECT mw_page.page_title AS cur_title, mw_text.old_text AS cur_text
FROM mw_page,mw_text WHERE mw_page.page_id=mw_text.old_id;

and re-run the shell.

Hope this helps!

— gtournat 2011/11/06 13:16

This script will automatically convert a MediaWiki install to DokuWiki. No configuration is required as all it needs is the path to LocalSettings.php. The above shell script did not work as expected as DokuWiki did not find the pages after they were injected manually. Instead, this script uses DokuWiki's own API to programmatically insert pages from MediaWiki. Script is not complete as it only converts the pages and not images but the framework is there.

Uses the mw2dw-conv_sed.sh script also found on this page to perform the MediaWiki syntax conversion.

Find on GitHub: https://github.com/tetsuo13/MediaWiki-to-DokuWiki-Importer

Having a webspace with no shell access I combined all of the above to have a single page which imports a mediawiki page via a DB connection.

mw2dw.php

<?php
/**
* MediaWiki2DokuWiki. Imports a MediaWiki install into DokuWiki.
*
* Copyright (C) 2011 Andrei Nicholson
*
* 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 3 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, see <http://www.gnu.org/licenses/>.
*
* @author Andrei Nicholson
* @since 2011-11-18
*/
 
ini_set('display_errors', '1');
error_reporting(E_ALL | E_STRICT);
 
// Path to root DokuWiki install. Required by include files.
define('DOKU_INC', dirname(__FILE__) . '/');
 
require_once DOKU_INC . 'inc/init.php';
require_once DOKU_INC . 'inc/common.php';
 
if (urldecode($_REQUEST['action']) == 'import') {
    print "<pre>\n";
    $mwikiSettingsPath = realpath($_SERVER['argv'][1]);
    $mwikiSettingsPath = urldecode($_REQUEST['localsetting']);
 
    if (!file_exists($mwikiSettingsPath)) {
        exit("Path to LocalSettings.php, $mwikiSettingsPath, is invalid");
    }
 
    $mwikiSettings = file($mwikiSettingsPath,
                          FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
 
    $mwikiDb = dbConnectionSettings($mwikiSettings);
    print_r($mwikiDb);
 
    if ( (int)count($mwikiDb) <= 8 ) {
        exit('Something went wrong with scraping LocalSettings.php for DB info');
    }
 
    $db = dbConnect($mwikiDb);
    convert($db, $mwikiDb);
    print "<pre>\n";
} else {
    print "<h1>path to LocalSettings.php</h1>\n";
    print "<form>\n";
    print "<input name='localsetting' value='../wiki/LocalSettings.php'><br>\n";
    print "<input type='submit' name='action' value='import'>\n";
    print "</form>\n";
}
 
/*******************************************************************************
* Convert pages from MediaWiki.
*
* @param PDO $db DB handle.
* @param array $mwikiDb DB attributes.
*/
function convert(PDO $db, array $mwikiDb) {
    $prefix = $mwikiDb['wgDBprefix'];
 
    $sql = "SELECT p.page_title, p.page_namespace, t.old_text
FROM {$prefix}page p
INNER JOIN {$prefix}revision r ON
p.page_latest = r.rev_id
INNER JOIN {$prefix}text t ON
r.rev_text_id = t.old_id
ORDER BY p.page_title";
 
    try {
        $statement = $db->prepare($sql);
 
        if (!$statement->execute()) {
            $error = $statement->errorInfo();
            exit('Could not fetch MediaWiki: ' . $error[2]);
        }
 
        while ($row = $statement->fetch(PDO::FETCH_ASSOC)) {
            echo 'Processing ' . $row['page_title'] . '... ';
            //if ($i++ > 10) {break;}
            switch ($row['page_namespace']) {
                case 0:
                    processPage($row);
                    break;
 
                case 6:
                    processImage($row);
                    break;
 
                default:
                    echo 'Unknown type. Skipping.';
            }
            echo PHP_EOL;
        }
    } catch (PDOException $e) {
        exit('Could not select all pages: ' . $e->getMessage());
    }
}
 
/**
* Inject new page into DokuWiki.
*
* @param array $record Info on page.
*/
function processPage(array $record) {
 
    $page = $record['old_text'];
    //print $page;
    $file = explode(PHP_EOL, $page);
 
    foreach ($file as $i=>$line) {
        //print "$i:$line\n";
 
        //Headings
        $line = preg_replace("/^[ ]*=([^=])/", "<h1> $1", $line);
        $line = preg_replace("/([^=])=[ ]*$/", "$1 </h1>", $line);
        $line = preg_replace("/^[ ]*==([^=])/", "<h2> $1", $line);
        $line = preg_replace("/([^=])==[ ]*$/", "$1 </h2>", $line);
        $line = preg_replace("/^[ ]*===([^=])/", "<h3> $1", $line);
        $line = preg_replace("/([^=])===[ ]*$/", "$1 </h3>", $line);
        $line = preg_replace("/^[ ]*====([^=])/", "<h4> $1", $line);
        $line = preg_replace("/([^=])====[ ]*$/", "$1 </h4>", $line);
        $line = preg_replace("/^[ ]*=====([^=])/", "<h5> $1", $line);
        $line = preg_replace("/([^=])=====[ ]*$/", "$1 </h5>", $line);
        $line = preg_replace("/^[ ]*======([^=])/", "<h6> $1", $line);
        $line = preg_replace("/([^=])======[ ]*$/", "$1 </h6>", $line);
 
        $line = preg_replace("/<\/?h1>/", "======", $line);
        $line = preg_replace("/<\/?h2>/", "=====", $line);
        $line = preg_replace("/<\/?h3>/", "====", $line);
        $line = preg_replace("/<\/?h4>/", "===", $line);
        $line = preg_replace("/<\/?h5>/", "==", $line);
        $line = preg_replace("/<\/?h6>/", "=", $line);
 
        //lists
        $line = preg_replace("/^[\*#]{4}\*/", "          * ", $line);
        $line = preg_replace("/^[\*#]{3}\*/", "        * ", $line);
        $line = preg_replace("/^[\*#]{2}\*/", "      * ", $line);
        $line = preg_replace("/^[\*#]{1}\*/", "    * ", $line);
        $line = preg_replace("/^\* /", "  * ", $line); // test
 
        $line = preg_replace("/^[\*#]{4}#/", "          \- ", $line);
        $line = preg_replace("/^[\*\#]{3}\#/", "      \- ", $line);
        $line = preg_replace("/^[\*\#]{2}\#/", "    \- ", $line);
        $line = preg_replace("/^[\*\#]{1}\#/", "  \- ", $line);
        $line = preg_replace("/^\#/", "  - ", $line);
 
        //[link] => [[link]]
        //$line = preg_replace("/(\[)([^\[\]]*)(\])/", "--$2--", $line);
 
        $line = preg_replace("/([^\[])\[([^\[])/", "$1[[$2", $line);
        $line = preg_replace("/^\[([^\[])/", "[[$1", $line);
        $line = preg_replace("/([^\]])\]([^\]])/", "$1]]$2", $line);
        $line = preg_replace("/([^\]])\]$/", "$1]]", $line);
 
        // [[url text]] => [[url|text]]
        $line = preg_replace("/(\[\[[http|ftp|file][^| \]]*) ([^|\]]*\]\])/", "$1|$2", $line);
 
        // bold, italic
        $line = preg_replace("/'''/","**", $line);
        $line = preg_replace("/''/","\/\/", $line);
 
        //talks
        $line = preg_replace("/^[ ]*:/", ">", $line);
        $line = preg_replace("/>:/", ">>", $line);
        $line = preg_replace("/>>:/", ">>>", $line);
        $line = preg_replace("/>>>:/", ">>>>", $line);
        $line = preg_replace("/>>>>:/", ">>>>>", $line);
        $line = preg_replace("/>>>>>:/", ">>>>>>", $line);
        $line = preg_replace("/>>>>>>:/", ">>>>>>>", $line);
 
        //code
        $line = preg_replace("/<pre>/", "<code>", $line);
        $line = preg_replace("/<\/pre>/", "<\/code>", $line);
 
        $out[$i] = $line;
    }
 
    $page = implode(PHP_EOL, $out);
 
    saveWikiText($record['page_title'],
        con('', $page, ''),
        'created');
}
 
/**
* Inject image.
*
* @param array $record Info on page.
*/
function processImage(array $record) {
    echo 'Skipping.';
}
 
/**
* Connect to the DB and return handle.
*
* @param array $mwikiDb DB attributes.
*
* @return PDO DB handle.
*/
function dbConnect(array $mwikiDb) {
    $dsn = $mwikiDb['wgDBtype'] . ':dbname=' . $mwikiDb['wgDBname'] . ';'
         . 'host=' . $mwikiDb['wgDBserver'];
 
    try {
        $db = new PDO($dsn, $mwikiDb['wgDBuser'], $mwikiDb['wgDBpassword']);
    } catch (PDOException $e) {
        exit('DB connection failed: ' . $e->getMessage());
    }
    return $db;
}
 
/**
* Strip DB connection settings from LocalSettings.php.
*
* @param array $mwikiSettings Content of LocalSettings.php with each line as
* an element in the array.
*
* @return array DB attributes.
*/
function dbConnectionSettings(array $mwikiSettings) {
    foreach ($mwikiSettings as $line) {
        if (substr($line, 0, 5) != '$wgDB') {
            continue;
        }
 
        $x = explode('=', $line, 2);
 
        if (!is_array($x) || count($x) != 2) {
            continue;
        }
 
        $val = trim($x[1]);
 
        // Strip leading dollar sign from key. Strip leading quote, trailing
        // quote and semicolon from value.
        $db[substr(trim($x[0]), 1)] = substr($val, 1, -2);
    }
 
    return $db;
}
?>