<?php /* -*- coding: utf-8 -*- */
header('Content-Type: text/plain; charset=UTF-8');
include('./wp-config.php');
error_reporting(E_ALL);
echo "Converting Wiki News to WordPress\n\n";
mysql_connect('', '', '');
mysql_select_db('');
$query = '
SELECT phpwiki_page.id, pagename, version, mtime, content
FROM phpwiki_version JOIN phpwiki_page USING ( id )
WHERE pagename LIKE "HomePage/200_-__-__"
AND pagename >= "HomePage/2004-01-01"
ORDER BY phpwiki_page.id, version
';
$result = mysql_query($query);
if (!$result)
     die("Error: " . mysql_error());
$post = array('id' => -1);
$links = array();
while ($row = mysql_fetch_array($result, MYSQL_ASSOC)) {
  if ($row['id'] != $post['id']) {
    // Insert last post.
    insert_post($post);
    // Start of next post.
    $post = $row;
  } else {
    // Newer content for current post.
    $post['content'] = $row['content'];
  } 
}
insert_post($post);
function insert_post($post) {
  if ($post['id'] == -1)
    return;
  $content = $post['content'];
  preg_match('{!!!\s*(.*)}', $content, $matches);
  $title = clean_wiki($matches[1]);
  $GLOBALS['links'] = array();
  $content = convert_wiki(trim(strstr($content, "\n"))) . "\n\n";
  foreach ($GLOBALS['links'] as $n => $link) {
    $content .= '[' . ($n+1) . ']: ' . $link . "\n";
  }
  $date = gmdate('Y-m-d H:i:s', $post['mtime']+3600);
  $pagename = $post['pagename'];
  echo "Inserting $pagename...\n";
  flush();
  wp_insert_post(array('post_title'    => $title,
                       'post_excerpt'  => '',
                       'post_content'  => $content,
                       'post_author'   => 1,
                       'post_date'     => $date,
                       'post_category' => array(1),
                       'post_status'   => 'publish'));
  /*
  echo "************************************************************************\n";
  echo $post['content'] . "\n";
  echo "========================================================================\n";
  echo "$title\n";
  echo "------------------------------------------------------------------------\n";
  echo "Date: $date\n";
  echo "------------------------------------------------------------------------\n";
  echo "$content\n";
  echo "========================================================================\n";
  echo "\n";
  */
}
function clean_wiki($str) {
  $str = preg_replace('{\[\s?(.*?)\s+\|\s+(.*?)\s+right\s*\]}s', '', $str);
  $str = preg_replace('{\[\s?(.*?)\s?\|\s?.*?\]}', '$1', $str);
  $str = preg_replace('{\s\'\'(\w+(\s\w+)*?)\'\'\s}s', '*$1*', $str);
  $str = preg_replace('{\s_(\w+(\s\w+)*?)_\s}s', '*$1*', $str);
  $str = preg_replace('{<code>(.*?)</code>}s', '`$1`', $str);
  $str = preg_replace('{=(\w+(\s\w+)*?)=}s', '`$1`', $str);
  $str = preg_replace('{mailto:(.*?@.*?)\w}', '<$1>', $str);
  $str = preg_replace('{(http://.*?)\w}', '<$1>', $str);
  $str = preg_replace('{\[IMDB:(.*?)\]}s', 'IMDB:$1', $str);
  $str = preg_replace('{\[ISBN:(.*?)\]}s', 'ISBN:$1', $str);
  $str = preg_replace('{\[DAIMI:(.*?)\]}s', 'DAIMI:$1', $str);
  $str = preg_replace('{\[RFC:(.*?)\]}s', 'RFC:$1', $str);
  $str = preg_replace('{\[PhpWiki:(.*?)\]}s', 'PhpWiki:$1', $str);
  return $str;
}
function convert_link($matches) {
  if (false !== ($key = array_search($matches[2], $GLOBALS['links']))) {
    return '[' . $matches[1] . '][' . ($key+1) . ']';
  } else {
    $GLOBALS['links'][] = $matches[2];
    return '[' . $matches[1] . '][' . count($GLOBALS['links']) . ']';
  }
}
function convert_verbatim($matches) {
  return implode("\n    ", explode("\n", $matches[1]));
}
function imdb_callback($matches) {
  return '[IMDB:' . $matches[1] . ' | ' .
    'http://imdb.com/Title?' . rawurlencode($matches[1]) . ']';
}
function convert_wiki($str) {
  $str = preg_replace_callback('{<verbatim>(.*?)</verbatim>}s',
                               'convert_verbatim', $str);
  $str = preg_replace_callback('{<\?plugin PhpHighlight(.*?)\?>}s',
                               'convert_verbatim', $str);
  $str = preg_replace('{http://gimpster.com/images(/news)?}', '/images', $str);
  $str = str_replace('gimpster@gimpster.com', 'mgeisler@mgeisler.net', $str);
  $str = preg_replace('{\[(.*?)\s?\|\s?MartinGeisler/Machine\]}s', '$1', $str);
  $str = preg_replace('{\[\s*(.*?)\s+\|\s+(.*?)\s+right\s*\]}',
                      '',
                      $str);
  $str = preg_replace('{(\s)\'\'(\w+(?:\s[\w?!.,]+)*?)\'\'(\s)}s',
                      '$1*$2*$3', $str);
  $str = preg_replace('{(\s)_(\w+(?:\s[\w?!.,]+)*?)_(\s)}s', '$1*$2*$3', $str);
  $str = preg_replace('{<code>(.*?)</code>}s', '`$1`', $str);
  $str = preg_replace('{(\s)=(\w+(?:\s[\w?!.,]+)*?)=(\s)}s', '$1`$2`$3', $str);
  $str = preg_replace('{(?<!\|\s)mailto:([\w.-]+\@(?:[\w-]+\.)+\w+)}',
                      '<$1>', $str);
  $str = preg_replace('{(?<!\|\s)(http://[\w.-/_]+)}', '<$1>', $str);
  $str = preg_replace_callback('{\[IMDB:(.*?)\]}s', 'imdb_callback', $str);
  $str = preg_replace('{\[?ISBN:(\d+)\]?}s', '[ISBN:$1 | http://isbn.nu/$1]',
                      $str);
  $str = preg_replace('{DAIMI:([\w~]+)}', '[DAIMI:$1]', $str);
  $str = preg_replace('{\[DAIMI:(.*?)\]}s', '[DAIMI:$1 | ' .
                      'http://daimi.au.dk/$1/]', $str);
  $str = preg_replace('{RFC:(\d+)?}s', '[RFC:$1 | ' .
                      'http://www.faqs.org/rfcs/rfc$1.html]', $str);
  $str = preg_replace('{PhpWiki:(\w+)}', '[PhpWiki:$1]', $str);
  $str = preg_replace('{\[PhpWiki:(.*?)\]}', '[PhpWiki:$1 | ' .
                      'http://phpwiki.sourceforge.net/phpwiki/$1]', $str);
  $str = preg_replace('{\bWiki:(\w+)}', '[Wiki:$1]', $str);
  $str = preg_replace('{\[Wiki:(.*?)\]}',
                      '[Wiki:$1 | http://c2.com/cgi/wiki?$1]',
                      $str);
  $str = preg_replace('{PhpShell}', '[PHP Shell][]', $str);
  $str = preg_replace('{PhpWeather}', '[PHP Weather][]', $str);
  $str = preg_replace('{SkejbyGård}', '[Skejbygård][]', $str);
  $str = preg_replace('{UniversityOfAarhus\]}', 'http://www.au.dk/]', $str);
  $str = preg_replace('{UniversityOfAarhus}',
                      '[University of Aarhus | http://www.au.dk/]',
                      $str);
  $str = preg_replace('{HomePage/(\d{4})-(\d\d)-(\d\d)\]}', '/$1/$2/$3/]',
                      $str);
  $str = preg_replace('{PhpTutorial\]}', '/php-tutorial/]', $str);
  $str = preg_replace('{PhpTutorial}', '[PHP Tutorial | /php-tutorial/]',
                      $str);
  $str = preg_replace('{MartinGeisler\]}', '/martin-geisler/]', $str);
  $str = preg_replace('{MartinGeisler/Schedule\]}',
                      '/martin-geisler/schedule/]', $str);
  foreach (array(array('Martin', 'Geisler', '/martin-geisler/'),
                 array('Mikkel', 'Krøigård', 'http://daimi.au.dk/~mk/'),
                 array('Thomas', 'Mølhave', 'http://moelhave.dk/'),
                 array('Lars', 'Petersen', 'http://daimi.au.dk/~aveng/'),
                 array('Andreas', 'Danielsen'),
                 array('Camilla', 'Johnsen'),
                 array('Christina', 'Strøhl'),
                 array('Martin', 'Justesen'),
                 array('Svend', 'Sørensen', 'http://demosophia.net/'),
                 array('Mia', 'Schneider'),
                 array('Kristian', 'Kristensen', 'http://zianet.dk/'),
                 array('Torben', 'Classen'),
                 array('Jesper', 'Klintø'),
                 array('Hanne', 'Enemark'),
                 array('Olle', 'Hansen'),
                 array('Nina', 'Ratenburg'),
                 array('Mette', 'Bukhave'),
                 array('Hilmar', 'Magnusson'),
                 array('Kristoffer', 'Geisler'),
                 array('Lars', 'Geisler', 'http://lgsoftware.dk/'),
                 array('Marianne', 'Geisler', 'http://x-psyk.dk/'),
                 array('The', 'Party', 'http://theparty.dk/')
                 )
           as $data) {
    if (count($data) == 3) {
      $a = '[$1 | ' . $data[2] . ']';
      $b = '[' . $data[0] . ' ' . $data[1] . ' | ' . $data[2] . ']';
    } else {
      $a = '$1';
      $b = $data[0] . ' ' . $data[1];
    }
    $str = preg_replace('{\[\s*(.*?)\s*\|\s*' . $data[0] .
                        $data[1] . '\s*\]}s', $a, $str);
    $str = preg_replace('{' . $data[0] . $data[1] . '}', $b, $str);
  }
  $str = str_replace('~~', '~', $str);
  $str = preg_replace_callback('{\[\s*(.*?)\s*\|\s*(.*?)\s*\]}s',
                               'convert_link', $str);
  $pars = explode("\n\n", $str);
  $str = '';
  foreach ($pars as $par) {
    $str .= "\n\n";
    if (substr(trim($par, "\n"), 0, 4) == '    ')
      $str .= $par;
    else
      $str .= wordwrap(str_replace("\n", ' ', $par));
  }
  return trim($str);
}
echo "\n\nAll done!\n";
?>