<?php if (!defined('PmWiki')) exit();

# This is a PhpWiki to PmWiki converter.
# It was created to convert a 900-page wiki.
# The conversion was successful, but the wiki didn't use much features (and the 
# markup used was rather consistent).
#
# Requirements: UTF-8 and the iconv PHP extension (wasn't tested with PHPv4)
#
# To use this script,
# 1. Put your exported PhpWiki files in a "phpwiki.in" directory and create 
#    a writable "phpwiki.out" directory for the resulting PmWiki pages.
# 2. Change the defaults of variables defined below (if needed). E.g., before 
#    including this script in "config.php", define the default group for converted 
#    pages and specify an additional markup conversion:
#    $OutGroup = 'Main';
#    $PWC_MarkupConversions=array('/wolf/'=>'lupus');
# 3. Include this script in "config.php" and call your wiki with
#    "?action=phpwikic":
#    include_once("$FarmD/cookbook/phpwikiconv.php");
#
# Notes:
# 1. Files in $OutWikiDir will be overwritten!
# 2. WikiWords will be disabled.
# 3. No PhpWiki plugins are converted (extend the $PWC_MarkupConversions array 
#    to convert them).
# 4. Only Old Style and Definition Style tables are supported.
# 5. Definition style table conversion might be quirky. Moreover, tables within 
#    tables and spanning is not supported for these.
# 6. There are 3 arrays that control the behaviour of markup conversion:
#    * main conversion happens for markup specified in $PWC_MarkupConversions,
#    * $PWC_MarkupConversionsPre might be used for things requiring a 2 step conversion,
#    * $PWC_MarkupConversionsPost might be used to change the resulting markup 
#      (MarkupRestore() is called before doing these)
# 7. One can create a $PWC_MarkupTestString variable and put some PhpWiki markup in
#    it, and run PmWiki with ?action=phpwikit to test markup conversion.
#
# History:
#   2010-06-20:  found in the attic, published.
#   2010-01:     added some comments, a description.
#   2009-spring: created for a one-time convertion.

SDV($InWikiDir,'phpwiki.in');
SDV($OutWikiDir,'phpwiki.out');

SDV($InEncoding,'windows-1252');
SDV($OutEncoding,'utf-8');

# $SkipPageFilenames shall specify which PhpWiki pagenames should be skipped
# during the conversion (the argument is passed to MatchPageNames() PmWiki 
# function).
SDV($SkipPageFilenames,'PhpWiki*');

# Converted pages will be put to this group
# (except the exceptions defined in $PWC_PageNameConversions)
SDV($OutGroup,'PhpWiki');

# A facility to rename pages, or put them to a group other than $OutGroup
SDVA($PWC_PageNameConversions, array(
  # example: '/^(John|Judas)$/' => 'Profiles.$1'
));

SDV($PHPWikiWikiWordPattern, '(?<![[:alnum:]])(?:[[:upper:]][[:lower:]]+){2,}(?![[:alnum:]])');

SDV($PWC_MarkupConversionsPre, array());
SDVA($PWC_MarkupConversions, array(
  ## Anchors:
  ## #[foo]: An anchor around the text "foo" with id "foo"
  '/(?>#\[([A-Za-z][-\w:.]*)\])/e' => "Keep('$1[[#$1]]')"
  ## #[|foo]: An empty anchor with id "foo"
  ## #[howdy|foo]: An anchor around the text "howdy" with id "foo"
  ,'/(?>#\[([^\|\]]*)\|([A-Za-z][-\w:.]+)\])/e' => "Keep('$1'=='' ? '[[#$2]]' : '$1[[#$2]]')"
  ## image links [http://site.com/xxx.jpg|bla bla]
  ,"#t?\[\ *((?:https?|ftp)://(?:[^\s$UrlExcludeChars]*))\.(jpg|png|gif)\ *(?:\\n\|{1,2} | \|{1,2}\\n | \| |) ([^\[\]|\\n]*) \]#xie" => "pwc_convertImageLinks('$1', '$2', '$3')"
  ## apply styling to link text before Keep()
  #,'!\[\ *_([^\|\]\n_]+)_!' => "[''$1''" # emphasis, pmwiki
  ,'!\[\ *_([^\|\]\n_]+)_!' => "[//$1//" # emphasis, creole
  ##,'!\[\ *\*([^\|\]\n*]+)\*!' => "['''$1'''" # strong, pmwiki
  ,'!\[\ *\*([^\|\]\n*]+)\*!' => "[**$1**" # strong, creole
  ## links [bla bla | local/url link]
  ,'!\[ ([^\|\]\n]+) \| \s* ([^\[\]]+) \]!xe' => "Keep('[[$2 | $1]]')"
  ## [free links]
  ,'!(?>\[\s*(.+?)\ *\])!e' => "Keep('[[$1]]')"
  ## bare links
  ,"#\b(?:https?|ftp)://[^\s$UrlExcludeChars]*[^\s.,?!$UrlExcludeChars]#e" => "Keep('$0')"
  ## old style tables
  ,'!<\?plugin OldStyleTable\s*(.+?)\?>!se' => "pwc_OldStyleTableConvert('$1', \$pagename)"
  ## get rid of WikiWords
  #,"/(~*)($PHPWikiWikiWordPattern)/e" => "('$1'==''||strlen('$1')%2==0) ? Keep('[[$2]]') : '$2'"
  ,"/(~*)($PHPWikiWikiWordPattern)/e" => "('$1'==''||strlen('$1')%2==0) ? '[['.AsSpaced('$2').']]' : '$2'"
  ## get rid of WikiWord escaping ~
  ,'/~~/' => '~' 
  ## bold
  ,'!\*(.*?)\*!' => "'''$1'''" # pmwiki
  ,'!<b>(.*?)</b>!' => "'''$1'''" # pmwiki
  #,'!\*(.*?)\*!' => "**$1**" # creole
  #,'!<b>(.*?)</b>!' => "**$1**" # creole
  ## italics
  ,'!_(.*?)_!' => "''$1''" # pmwiki
  ,'!<i>(.*?)</i>!' => "''$1''" # pmwiki
  #,'!_(.*?)_!' => "//$1//" # creole
  #,'!<i>(.*?)</i>!' => "//$1//" # creole
  ## bold italics
  ,'!(?:_\*|\*_)(.+?)(?:_\*|\*_)!' => "'''''$1'''''" # pmwiki
  #,'!(?:_\*|\*_)(.+?)(?:_\*|\*_)!' => "//**$1**//" # creole
  ## fixed width
  ,'!=(.+?)=!' => '@@\1@@'
  ## headings
  ,'/^(!{1,3})\s?(.*)$/me' => "'$1'=='!' ? '!!! $2' : ('$1'=='!!' ? '!!! $2' : '!! $2' )"
  ## line breaks
  ,'/(?<!%)%%%(?!%)|<br>/' => "\\\\\\\\\n"
  ## Definition list style tables
  ,'/(^[^|\n]*\| *(?:\n(?: *\n)*(?:  *[^|\n ][^|\n]*\|?|[^|\n]*\|) *)+)/me' => "pwc_DefStyleTableConvert('$1', \$pagename)"
));

SDV($PWC_MarkupConversionsPost, array());

SDV($PHPWikiConvertAction,'phpwikic');
SDV($PHPWikiMarkupTestAction,'phpwikit');
SDV($HandleActions[$PHPWikiConvertAction],'HandlePHPWikiMigrate');
SDV($HandleActions[$PHPWikiMarkupTestAction],'HandlePHPWikiMarkupTest');

if (!is_dir($OutWikiDir) || !is_writable($OutWikiDir)) {
  echo "OutWikiDir ($OutWikiDir) must be a writable directory!";
  exit;
}

array_unshift($WikiLibDirs, new PageStore($OutWikiDir.'/{$FullName}', 1));

$PWC_MarkupConversions = array_diff_key($PWC_MarkupConversions,$PWC_MarkupConversionsPre,$PWC_MarkupConversionsPost);

function HandlePHPWikiMigrate($pagename) {
  global $FarmD
    , $InWikiDir, $OutWikiDir
    , $InEncoding, $OutEncoding
    , $OutGroup
    , $PWC_MarkupConversionsPre, $PWC_MarkupConversions, $PWC_MarkupConversionsPost
    , $PWC_PageNameConversions
    , $SkipPageFilenames;

  header('Content-Type: text/html; charset=UTF-8'); 
  iconv_set_encoding('internal_encoding', 'utf-8');
  include_once($FarmD.'/scripts/xlpage-utf-8.php');

  $infiles = glob("$InWikiDir/*");

  if (empty($infiles)) {
    echo "No files found for $InWikiDir/*\n";
    exit;
  }

  foreach ($infiles as $k=>$f) {
    unset($infiles[$k]);
    $infiles[basename($f)] = $f;
  }
  $skippages = MatchPageNames(array_keys($infiles), $SkipPageFilenames); 
  
  $converted = 0;
  $skipped = 0;
  foreach ($infiles as $pagefile=>$pagepath) {
    if (in_array($pagefile, $skippages)) {
      $skipped++;
      pwc_show("match with SkipPageFilenames...", 'skip', $pagefile);
      continue;
    }
    pwc_show('Processing file <span style="color: blue;">'.$pagepath."</span>...");

    if (!$inpagestr=file_get_contents($pagepath)) {
      pwc_show("couldn't read it!", 'error', $pagepath); continue;
    }
    $pagefile=basename($pagepath);
    $inpagestr=iconv($InEncoding, $OutEncoding, $inpagestr);
    $inpagestr=str_replace("\r", '', $inpagestr);

    $sep=strpos($inpagestr, "\n\n");
    $pageattr=substr($inpagestr, 0, $sep);
    $pagetext=substr($inpagestr, $sep+2);
    if (empty($pageattr) || empty($pagetext)) {
      pwc_show("couldn't separate headers from text!", 'error', $pagefile); continue;
    }
    if (substr($pageattr, -33)!="Content-Transfer-Encoding: binary") {
      pwc_show("page attributes ended with an unexpected string", 'error', $pagefile); continue;
    }

    $mime=iconv_mime_decode_headers($pageattr);
    if (isset($mime['Content-Type'])) {
      $mime=$mime['Content-Type'];
      $mime=iconv($InEncoding, $OutEncoding, urldecode($mime));
      $mime=explode(';', $mime);

      $page = array();
      $pagename='';
      foreach ($mime as $m) {
        if (!$m=explode('=', trim($m), 2)) continue;
        if (count($m)!=2) continue;
        
        list ($k, $v) = $m;
        switch ($k) {
        case 'pagename':
          # PmWiki wants pagenames to start with lowercase letters and have no spaces nor slashes...
          $pn = $pn0 = urldecode($v);
          if (!empty($PWC_PageNameConversions)) {
            $pn = preg_replace(array_keys($PWC_PageNameConversions), array_values($PWC_PageNameConversions), $pn, -1, $rcount);
            if ($rcount > 0) pwc_show("$pn0 has been renamed to $pn", 'rename', $pagefile);
          }
          else
            $pn = "$OutGroup.$pn";

          $pagename=MakePageName("$OutGroup.$OutGroup", $pn);
          if (empty($pagename)) pwc_show("couldn't convert pagename $pn", 'error', $pagefile);
          else pwc_show("\tpagename: $pagename");
          break;
        case 'flags':
          if ($v!='""' && $v!='PAGE_LOCKED')
            pwc_show("unknown flags found: $v ", 'error', $pagefile);
          break;
        case 'author':
          if (trim($v)=='The PhpWiki programming team') {
            $skipped++;
            pwc_show("author string indicates this an untouched sys page...", 'skip', $pagefile); continue 3;
          }
          $page['author']=$v; pwc_show("\tauthor: $v ");
          break;
        case 'version': $page['rev']=$v; break;
        case 'lastmodified': $page['time']=$v; break;
        case 'created': $page['ctime']=$v; break;
        case 'author_id':
          if (long2ip(ip2long($v)==$v)) $page['host']=$v;
          elseif ($page['author']!=$v) pwc_show("author_id!=author ($v!=$page[author])", 'error', $pagefile);
          break;
        case 'markup': if ($v!=2) pwc_show("markup!=2", 'error', $pagefile); break;
        case 'summary': $page['csum']=$v; break;
        case 'charset': 
          $page['charset'] = 'UTF-8';
          if ($v!='iso-8859-1') pwc_show("charset!=iso-8859-1 ($v)", 'error', $pagefile);
          break;
        case 'hits': case 'acl':
          break;
        default: pwc_show("unknown key: $k ($v)", 'error', $pagefile);
        }
      }
      if (empty($pagename)) {
        pwc_show("couldn't find pagename attribute!", 'error', $pagefile); continue;
      }
      if (empty($page['author'])) {
        pwc_show("couldn't find author attribute!", 'error', $pagefile); continue;
      }
    }
    else {
      pwc_show("couldn't process page headers!", 'error', $pagefile); continue;
    }

    if (!empty($PWC_MarkupConversionsPre))
      $pagetext=preg_replace(array_keys($PWC_MarkupConversionsPre), array_values($PWC_MarkupConversionsPre), $pagetext);
    
    $pagetext=preg_replace(array_keys($PWC_MarkupConversions), array_values($PWC_MarkupConversions), $pagetext);
    $pagetext=MarkupRestore($pagetext);

    if (!empty($PWC_MarkupConversionsPost))
      $pagetext=preg_replace(array_keys($PWC_MarkupConversionsPost), array_values($PWC_MarkupConversionsPost), $pagetext);

    $page['text'] = $pagetext;
    $page['name'] = $pagename;
    ksort($page);
    $page=array_merge(array('version'=>'pmwiki-2.2.0 ordered=1 urlencoded=1'), $page);

    if (!pwc_write($pagename, $page))
      pwc_show("couldn't save the converted page", 'error', $pagefile);
    else
      $converted++;
  }
  $missing = count($infiles)-$skipped-$converted;
  pwc_show("total files considered: ".count($infiles), '');
  pwc_show("total converted: $converted", '');
  pwc_show('', 'errors');
  pwc_show('', 'skips');
  pwc_show('', 'renames');
  pwc_show('', 'infos');
  exit; 
}
## Formats and display messages
function pwc_show($msg, $type='info', $context='') {
  static $errors=array(), $infos=array(), $skips=array(), $renames=array();
  switch ($type) {
  case 'info':
    $infos[]=empty($context)?"$msg\n":"$msg ($context)\n";
    break;
  case 'error':
    $msg = "<span style='color:red;'>$msg</span>";
    if (!empty($context)) $msg="$msg ($context)";
    $errors[]="$msg\n";
    break;
  case 'skip': case 'rename':
    ${$type.'s'}[]=empty($context)?"$msg\n":"$msg ($context)\n";
    break; 
  case 'errors': case 'infos': case 'skips': case 'renames':
    $count=count(${$type});
    echo '<pre>';
    echo "\n$type ($count lines)\n=======================\n"
      .implode('', ${$type});
    echo '</pre>';
    break;
  default:
    echo "<pre>".print_r($msg, true);
    if (!empty($context)) echo '('.print_r($context, true).')';
    echo "</pre>\n";
  }
}
## Gets called by ?action=phpwikit (useful for testing markup conversion)
function HandlePHPWikiMarkupTest($pagename) {
  global $PWC_MarkupTestString,
    $PWC_MarkupConversionsPre, $PWC_MarkupConversions, $PWC_MarkupConversionsPost;

  header('Content-Type: text/html; charset=UTF-8'); 
  $text=$PWC_MarkupTestString;

  echo "<pre>before conversion:\n"
    .print_r(htmlspecialchars($text),true);
  
  if (!empty($PWC_MarkupConversionsPre))
    $text=preg_replace(array_keys($PWC_MarkupConversionsPre), array_values($PWC_MarkupConversionsPre), $text);
  
  $text=preg_replace(array_keys($PWC_MarkupConversions), array_values($PWC_MarkupConversions), $text);
  $text=MarkupRestore($text);

  if (!empty($PWC_MarkupConversionsPost))
    $text=preg_replace(array_keys($PWC_MarkupConversionsPost), array_values($PWC_MarkupConversionsPost), $text);

  echo "\n\n\nafter conversion:\n";
  echo htmlspecialchars($text);
  echo '</pre>';
  exit;
} 
## Writes pages to disk
function pwc_write($pagename, $page) {
  global $OutWikiDir;
  $str='';
  foreach ($page as $k=>$v) {
    if ($k=='text') $v=str_replace(array('%', "\n", '<'), array('%25', '%0a', '%3c'), $v);
    $str.="$k=$v\n";
  }
  if (file_put_contents("$OutWikiDir/$pagename", $str)) return true;
  return false;
}
## Gets called when converting image links
## (a hook should be added here to enable conversion to gallery recipes).
function pwc_convertImageLinks($link, $ext, $title) {
  $link.=strtolower(".$ext");
  # The two lines below could be used to convert some links to Mini: markup
  #if (preg_match('!/phpwiki/files!', $link))
  #  return Keep('Mini:'.basename($l).(empty($text)?'':'"'.$text.'"'));
  if (!empty($title)) $link.='"'.$title.'"';
  return Keep($link);
}
## Gets called when converting old style tables
function pwc_OldStyleTableConvert($table, $pagename) {
  global $OldStyleTableColPattern, $OldStyleTableColReplacement;
  SDV($OldStyleTableColPattern, '/\s*\|(v+|>|<|\^|)\s*([^\|$]*)/e');
  SDV($OldStyleTableColReplacement,
    "'||'.(('$2'=='') ? '__' :
    (
      (('$1'=='>' || '$1'=='^') ? ' ' : '')
      .'$2'
      .(('$1'=='<' || '$1'=='^') ? ' ' : (substr('$1',0,1)=='v'?str_repeat('+',strlen('$1')+1):''))
    ))"
  );

  $table=explode("\n", $table);
  foreach($table as $k=>&$v) {
    $v=trim($v);
    if (empty($v)) unset($table[$k]);
  }
  unset($v);
  $table=preg_replace($OldStyleTableColPattern, $OldStyleTableColReplacement, $table);

  return ("\n|| class=border\n".implode("||\n", $table)."||\n");
}
## Gets called when converting definition style tables
function pwc_DefStyleTableConvert($table, $pagename) {
  #return "\n<--------------------START--->\n$table\n<---END------------------------>\n";
  $lines = explode("\n", $table);

  foreach ($lines as $lno=>$line)
    if (trim($line)=='') unset($lines[$lno]);

  $lcount = count($lines);
  $lines = array_values($lines);

  # new row lines - all the lines not starting with space, but ending with '|'
  $linespec=array();
  $prev_nr=0; # line number of the previous new row
  $ccol=2; # column count for the current row batch
  $rows=0;
  $cols=0; # table column count
  foreach ($lines as $lno=>$line) {
    $lilen=strlen($line);
    $linespec[$lno]=array('text'=>trim($line, "| \n"));

    # count the spaces (indent)
    $indent = 0;
    while ($line[$indent]==' ') $indent++;
    $linespec[$lno]['indent']=$indent;

    # gather new row lines
    if ($indent==0 && $line[$lilen-1]=='|') {
      $linespec[$lno]['newrow']=$lno-$prev_nr;
      $prev_nr=$lno;
      $rows++;
      if ($cols<$ccol) $cols=$ccol;
      $ccol=2;
    }
    # gather the new column lines
    elseif ($line[$lilen-1]=='|') {
      $linespec[$lno]['newcol']=1;
      $ccol++;
    }
  }

  $tablestr = '';
  foreach ($linespec as $row) {
    if (isset($row['newrow'])) $tablestr .= '(:cellnr';
    else $tablestr .= '(:cell';
    #$tablestr .= '(:'.$row['cmd'];
    if (isset($row['colspan'])) $tablestr.=' colspan='.($row['colspan']+1);
    if (isset($row['rowspan'])) $tablestr.=' rowspan='.($row['rowspan']+1);
    $tablestr .= ':) '.$row['text']."\n";
  }
  return "(:table class=border:)\n$tablestr(:tableend:)";
}