Re: [cowiki-dev] Extension to coWiki text formatting

<?php

/**
 *
 * $Id: class.WikiParser.php,v 1.36 2005/02/14 22:23:53 dgorski Exp $
 *
 * This file is part of coWiki. coWiki is free software under the terms of
 * the GNU General Public License (GPL). Read the LICENSE file. If you did
 * not receive a copy of the license and are not able to obtain it through
 * the internet, please send a note to <[email protected]> so we can mail
 * you a copy immediately.
 *
 * <pre>
 * Helping hands: Matt Ho <[email protected]>
 * </pre>
 *
 * @package     parse
 * @subpackage  class
 * @access      public
 *
 * @author      Daniel T. Gorski, <[email protected]>
 * @copyright   (C) Daniel T. Gorski, {@link http://www.develnet.org}
 * @license     http://www.gnu.org/licenses/gpl.html
 * @version     $Revision: 1.36 $
 *
 */

/**
 * coWiki - Wiki parser class
 *
 * @package     parse
 * @subpackage  class
 * @access      public
 *
 * @author      Daniel T. Gorski, <[email protected]>
 * @since       coWiki 0.3.0
 * @author      Archie Campbell <[email protected]>
 * @since       coWiki 0.3.5
 */
class WikiParser extends Object {

    protected static
        $Instance = null;
    protected $aToc = array(),
	      $aRows = array(),
              $iRow = 0;
    protected $aEmph = array();
    protected $RefNodes = null;
  private $snug = 0;
    // --------------------------------------------------------------------

    /**
     * Collect referenced nodes to where the document is linking to
     *
     * @access  protected
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     */
    protected function addReferencedNode($Obj) {
        $this->RefNodes->add($Obj);
    }

    // --------------------------------------------------------------------

    /**
     * Get referenced nodes
     *
     * @access  public
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     */
    public function getReferencedNodes() {
        return $this->RefNodes;
    }

    /**
     * Get instance
     *
     * @access  public
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     */
    public function getInstance() {
        if (!self::$Instance) {
            self::$Instance = new WikiParser;
        }
        return self::$Instance;
    }

    // --------------------------------------------------------------------

    /**
     * @access  protected
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     */
    protected function __construct() {
        $this->resetEmphasis();
    }

    // --- Helper methods -------------------------------------------------

    /**
     * @access  protected
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     */
    protected function restoreTokens($sStr){ return $sStr; }

    /**
     * Generate "toc" (Document Table of Contents)
     *
     * @access  protected
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     */
    protected function buildToc(&$i, &$nDepth) {
        $sStr = '';

        // Iterate though all toc-entries
        while (isset($this->aToc[$i]['DEPTH'])
               && $this->aToc[$i]['DEPTH'] == $nDepth) {

	    $sAlias = $this->aToc[$i]['TEXT'];
            $sStr .= '<li>';
            $sStr .=    '<link topicref="'.($i+1).'">'.$sAlias.'</link>';

            $i++;

            // Recurse (indent) if toc-entry is nested
            if (isset($this->aToc[$i]['DEPTH'])) {

                if ($this->aToc[$i]['DEPTH'] > $nDepth) {
                    $sStr .= '<ul>';
                    $sStr .=   $this->buildToc($i, $this->aToc[$i]['DEPTH']);
                    $sStr .= '</ul>';
                }
            }

            $sStr .= '</li>';
        }

        return $sStr;
    }

    // --------------------------------------------------------------------

    /**
     * parse
     *
     * @access  public
     * @param   string  The wiki source string
     * @return  string  Wiki XML
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     */
    public function parse($sStr) {

	$sRet = '';
	$sContent = '';
	$bList = false;
	$bTable = false;
	$bBegin = false;
	$aList = array();
	$aTable = array();

        // {{{ DEBUG }}}
        Logger::info('Start parsing wiki document.');

        // Init reference collection
        $this->RefNodes = new Vector;

        $this->resetEmphasis();

        // ---

        $sStr = trim(escape($sStr));

        // Replace possible tabulators
        $sStr = str_replace("\t", '    ', $sStr);

        // Replace possible \r\n or \n\r with \n
        $sStr = str_replace("\r\n", "\n", $sStr);
        $sStr = str_replace("\n\r", "\n", $sStr);

	$this->aRows = explode( "\n",$sStr."\n" );


        $this->iRow = 0;
	$sRow = $this->aRows[$this->iRow];
	$bBegin = true;

	$t = 0; $l = -1;

	while( true ) {
	    $sContent = '';
	    $aMatches = array();
	    //table of contents alone ^<toc/>$
	    if( $bBegin && preg_match( '=^&lt;toc(/?)&gt;$=',
					$sRow, $aMatches )) {
		$sRet .= "\n\t\t\n";
   	    //plugins
	    }else if( $bBegin && preg_match(
			'=^&lt;plugin +([A-Za-z0-9_.]+)( +([^&]*))?&gt;=i',
				    $sRow, $aMatches )) {
	        if(isset($aMatches[3])){
		    $sRet .= '<plugin name="'.
				$aMatches[1].'" '.$aMatches[3].'/>';
		}else{
		    $sRet .= '<plugin name="'.$aMatches[1].'"/>';
		}
	    //headings
	    }else if( $bBegin && preg_match( '=^(\+{1,})\s*(.*)$=s',
				    $sRow, $aMatches )) {
                $sContent = $this->processContent($aMatches[2]);
		if( preg_match( '=<link\s+strref\="([^>]+)">
						([^<]*)</link>=USx',
				$sContent, $aLinkMatches ) ) {
		    $sAlias = !empty($aLinkMatches[2])
                               ? $aLinkMatches[2]
                               : $aLinkMatches[1]
                               ;
		} else {
		    $sAlias = $sContent;
		}
		$i = sizeof($this->aToc);
		$this->aToc[$i]['TEXT'] = $sAlias;
		$this->aToc[$i]['DEPTH'] = strlen( $aMatches[1] );		
		$sTag = 'h'.strlen($aMatches[1]);
		$sRet .= '<'. $sTag .'>'.
			 $sContent .
			 '</'. $sTag .'>';
	    //end of table
	    } else if( $bBegin && ($t > 0) && 
			    preg_match( '=^&lt;/table&gt;=i',
						$sRow, $aMatches  )) {
	        $sParam = trim($aTable[$t][0]);
		if( $sParam == '') {
		    $sRet .= "\n".'<table>'.$this->buildTable($aTable[$t]).
		             '</table>'."\n";
		} else {
		    $sRet .= "\n".'<table '.trim(unescape($sParam)).'>'.
			         $this->buildTable($aTable[$t]).'</table>'."\n";
		}
		if( --$t == 0 ){
  		    $bTable = false;
		}
	    //beginning of table
	    } else if( $bBegin &&
			preg_match( '=^&lt;table([^>]*)&gt;$=Ui',
					$sRow, $aMatches )) {
		$bTable = true;
		$aTable[++$t] = array();
		array_push( $aTable[$t], $aMatches[1] );
	    //beginning of list
	    } else if( $bBegin && 
			preg_match( '=^([\s*#]{0,}[*#]) ([^\n]*)$=',
				    $sRow, $aMatches )) {
	        $bList = true;
		$aList[++$l] = array();
		$aList[$l]['TEXT'] = $this->processContent( $aMatches[2] );
		$aList[$l]['DEPTH'] = strlen( $aMatches[1] );
		$aList[$l]['TYPE'] = (substr($aMatches[1],-1)=='*'?
							      'ul':'ol');
	    //horizontal rule
	    } else if ($bBegin && 
			preg_match( '=^-{3,}(\s|$)=',
				    $sRow, $aMatches ) ) {
	        $sRet .= '<hr/>'."\n";
		/*
	    //noop 
	    } else if (preg_match( '=((.*)&lt;noop&gt;)=i',
					$sRow, $aMatches )) {
		$sContent = $this->processContent( $aMatches[2], false )
				. '<noop>';
		$sRow = substr( $sRow, strlen($aMatches[1]) );
		do {
		    if (preg_match( '=(.*)&lt;/noop&gt;=' , 
				    $sRow, $aMatches )) {
  		        $sContent .= $aMatches[1] . '</noop>';
			break;
		    } else {
		        $sContent .= $sRow;
		    }
		    if(++$this->iRow<sizeof($this->aRows)){
		        $sRow = $this->aRows[$this->iRow];
		    } else {
		        break;
		    }
		} while(true);
		$sRet .= $sContent;
		*/
	    } else {
		//end of list
		if($bList) {
		    $d = 0;
		    $sListType = $aList[$d]['TYPE'];
		    $nDepth = $aList[$d]['DEPTH'];
		    $sContent .= "\n".'<list>'.
				    '<'.$sListType.'>'.
				      $this->buildList($d,$nDepth,$aList).
				    '</'.$sListType.'>'.
		             '</list>'."\n";
    		    $bList = false;
		    $aList = array();
		    $l = -1;
		    if($bTable){
		        array_push( $aTable[$t], $sContent );
		    }else{
			$sRet .= $sContent;
		    }
		//more table
		}else if($bTable) {
		    array_push( $aTable[$t], $sRow );
		    $sRow = '';
		//non table/list row
		}else{
		    $sContent = $this->processContent( $sRow );
		    if( $sContent != '' ){
		      $sRet .= /*'<p>'.*/$sContent/*.'</p>'*/;
		    }
		    $sRow = '';
		}
	    }
	    if(isset($aMatches[0])) {
		$sRow = substr( $sRow, strlen( $aMatches[0] ) );
		$bBegin = false;
	    }
	    if ( trim($sRow) == '' ) {
		if( ++$this->iRow < sizeof($this->aRows) ) {
		    $sRow = $this->aRows[$this->iRow];
		    $bBegin = true;
		} else {
		    break;
		}
	    }
	}
	
	if( preg_match( '=^(.*)\n\t\t\n(.*)$=s', $sRet, $aMatches )) {
   	    $t = 0;
	    if (sizeof($this->aToc) > 0) {
		$sToc = $this->buildToc($t, $this->aToc[$t]['DEPTH']);
		if ($sToc != '') {
		    $sToc = '<toc><ul>' . $sToc . '</ul></toc>';
		} else {
		    $sToc = '<toc/>';
		}
	    }
	    return $aMatches[1] . $sToc . $aMatches[2];
	}

        // {{{ DEBUG }}}
        Logger::info('Finished parsing wiki document.');

	return $sRet;
    }

    /**
     * reset Emphasis
     *
     * @access  protected
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     */
    protected function resetEmphasis() {
        $this->aEmph = array(
		       "b" => false,
		       "u" => false,
		       "i" => false,
		       "f" => false,
		       "s" => false,
		       "j" => '',
		       "p" => ''
		);
    }

    /**
     * processContent
     *
     * @access  protected
     * @return  string
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     */
    protected function processContent( $sStr ) {
        $sRet = '';
       	$aMatches = array();
	$this->resetEmphasis();

	$sStr = ltrim( $sStr );

	while( trim( $sStr ) != '' ) {
	    //noop
	    if (preg_match( '=^&lt;noop&gt;=is',
					$sStr, $aMatches )) {
	        //greedily munch all until </noop>
	        $sStr = substr( $sStr, strlen( $aMatches[0] ) );
	        $sContent = '';
	        while( !preg_match( '=^&lt;/noop&gt;=is', $sStr, $aMatches ) ) {
		    preg_match( '=([^&]|(\&(?![lg])))*=is', $sStr, $aMatches );
		    $sContent .= $aMatches[0];
		    $sStr = substr( $sStr, strlen( $aMatches[0] ) );
		    if ( $sStr == "\n" ) {
			if ( ++$this->iRow < sizeof($this->aRows) ) {
			    $sStr = $this->aRows[$this->iRow];
			} else {
			    $sStr = '';
			    break;
			}
		    }
	        }
	        $sRet .= '<noop>' . $sContent . '</noop>';
	    //justification
 	    } else if( preg_match( '=^&lt;(/?)(left|center|right)&gt;=i',
 				  $sStr, $aMatches )) {
	        $sRet .= '<'.$aMatches[1].$aMatches[2].'>';
	      /*
 	        if( $aMatches[1] == '/' &&
 		    $this->aEmph['j'] == $aMatches[2]{0} ) {
		    $sRet .= '</'. $aMatches[2] .'>';
 		    $this->aEmph['j'] = '';
		} else if ( $aMatches[1] == '' &&
 			    $this->aEmph['j'] == '' ) {
 		    $sRet .= '<'. $aMatches[2] .'>';
 		    $this->aEmph['j'] = $aMatches[2]{0};
 		}
	      */
	    //pre code posting q start at BOL, are greedy until 
	    // closing tag anywhere on a line
	    } else if (preg_match( '=^&lt;(pre|code|posting|q)&gt;=i',
				    $sStr, $aMatch ) ) {
	        $sStr = substr( $sStr, strlen($aMatch[0]) );
		do {
		    if (preg_match( '=(.*)&lt;/'.$aMatch[1].'&gt;=i',
				    $sStr, $aMatches )) {
			$sRet .= '<'.$aMatch[1].'>'.$sContent . 
				$aMatches[1].'</'.$aMatch[1].'>';
			break;
		    } else {
			$sContent .= $sStr ."\n";
		    }
		    if( ++$this->iRow < sizeof($this->aRows) ){
		        $sStr = $this->aRows[$this->iRow];
		    }else{
		        break;
		    }
		} while(true);
		if( $this->iRow == sizeof($this->aRows) ) {
		    $sRet .= '<'.$aMatch[1].'>'.
				$sContent .
				 '</'.$aMatch[1].'>';
		    break;
		}
	    //line-break
	    }else if( preg_match( '=^&lt;br([ /]+)&gt;=is', $sStr, $aMatches )) {
	        $sRet .= '<br/>';
	    //variables
	    }else if( preg_match( '=^%([A-Z0-9_]+)%=U', $sStr, $aMatches )) {
	        $sRet .= '<var name="'.$aMatches[1].'"/>';
	    //links (()()) & [[][]]
	    }else if( preg_match( '=^\(\(([^\(\)]+|[^\(\)]+' .
				    '\([^\(\)]+\)[^\(\)]*|' .
			            '[^\(\)]+\)\([^\(\)]+)\)\)=Usx',
				  $sStr, $aMatches )) {
	        $sRet .= $this->createLinkElement( $aMatches[1] );
	      /*
	        $aLink = explode( ')(', $aMatches[1] );
		$aLink[0] = str_replace( '|', '¦', $aLink[0] );
	        $sRet .= '<link strref="' . trim($aLink[0]) . '">';
		if ( isset( $aLink[1]) ) {
		    $sRet .= trim($aLink[1]);
		} else {
		    $sRet .= trim($aLink[0]);
		}
	        $sRet .= '</link>';
	      */
		/*
	    //WikiWords
	    }else if( preg_match( '=^([A-Z][a-z]+([A-Z][a-z]+)+)=s',
				    $sStr, $aMatches )) {
	      $sLink = trim(preg_replace( '=([A-Z])=', ' \1',
						$aMatches[1] ));
		$sRet .= '<link strref="' . $sLink . '">' .
				 $sLink . '</link>';
		*/
		/*
	    //urls
	    }else if( preg_match( '=^&lt;url(\s+)(
                   (http://|https://|ftp://|mailto:|news:)
                   ([-_A-Z0-9\S]*)
                   (\*\s|\=\s|&quot;|&lt;|&gt;|<|>|\(|\)|\s|$)??
				    )&gt;=six',
		    $sStr, $aMatches ) ) {
		*/
	    //URIs
	    }else if( preg_match(
		'=^(http://|https://|ftp://|mailto:|news:)
                   ([-_A-Z0-9\S]*)
                   (\*\s|\=\s|&quot;|&lt;|&gt;|<|>|\(|\)|\s|$)??
                 =six',
				  $sStr, $aMatches )) {
	        $sRet .= '<uri strref="' . 
				$aMatches[1].$aMatches[2] . '"/>';
	    //subscript, superscript
	    }else if( preg_match( '=^&lt;(/??)(sub|sup)&gt;=is',
				  $sStr, $aMatches ) ) {
	        if( $aMatches[1] == '/' &&
		    $this->aEmph['p'] == $aMatches[2] ) {
		    $sRet .= '</' . $aMatches[2] . '>';
		    $this->aEmph['p'] = '';
		}else if ( $aMatches[1] == '' &&
			   $this->aEmph['p'] == '' ) {
		    $sRet .= '<' . $aMatches[2] . '>';
		    $this->aEmph['p'] = $aMatches[2];
		}
	    //emphasis						
	    }else if( preg_match( '#^([-=\*_/]{2})#',
	 	      $sStr, $aMatches ) ) {
	        $sEmph = '';
	        switch($aMatches[1]{0}){
		    case '-':
			$sEmph=($this->aEmph["s"]?'/':'').'strike';
			$this->aEmph["s"] = !$this->aEmph["s"];
			break;
		    case '=':
			$sEmph=($this->aEmph["f"]?'/':'').'tt';
			$this->aEmph["f"] = !$this->aEmph["f"];
			break;
		    case '*':
			$sEmph=($this->aEmph["b"]?'/':'').'b';
			$this->aEmph["b"] = !$this->aEmph["b"];
			break;
		    case '_':
			$sEmph=($this->aEmph["u"]?'/':'').'u';
			$this->aEmph["u"] = !$this->aEmph["u"];
			break;
		    case '/':
			$sEmph=($this->aEmph["i"]?'/':'').'i';
			$this->aEmph["i"] = !$this->aEmph["i"];
		    break;
	        }
		$sRet .= '<'.$sEmph.'>';
            }else if( preg_match( '#^((([-=\*_/]{1})(?!\3))|[^-=\*_/&]|(&(?![lg])))*#',
				    $sStr, $aMatches ) ) {
	        $sRet .= $aMatches[0];
	    }
	    if( isset($aMatches[0]) ) {
	        $sStr = substr( $sStr, strlen($aMatches[0]) );
	    }
	}
	return $sRet;
    }

    /**
     * &build table
     *
     * @access  protected
     * @return  string
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     */
    protected function buildTable( &$aTable ) {

	$sRet = '';
	$sContent = '';
	$sRow = '';
	$bPriorRow = false;
	$aMatches = array();

	$j = 0;
	$v = sizeof($aTable);

	while( ++$j < $v ) {

	  /*
            if (!strlen(trim($aTable[$j]))) {
                return '<tr valign="top"><td colspan="1">'.$sStr.'</td></tr>';
            }
	  */

	    //rows expected to hold table syntax (pipes), may instead
	    //make room for ongoing content (tables, lists, etc)
	    $sRow = $aTable[$j];

	    //find table syntax within a (long?) row
	    while( strlen($sRow) && preg_match(
		    '=^([\|!][-+]?)( {0,1}[^\|!\n]*)?=',
		    $sRow,
		    $aMatches) ) {

		//found exploded row begins with pipe syntax, poss params
		$sRow = substr( $sRow, strlen($aMatches[0]) );
		$nType = 0;
		//tables made of cells, headers, rows, caption
		if ($aMatches[1]=="|") {
		    $sRet .= '<td';
		    $nType = 1;
		}else if ($aMatches[1]=="!") {
		    $sRet .= '<th';
		    $nType = 2;
		}else if ($aMatches[1]=="|-") {
		    if ($bPriorRow) {
		        $sRet .= "</tr>\n<tr";
		    } else {
			$sRet .= '<tr';
		    }
		    $nType = 3;
		    $bPriorRow = true;
		}else if ($aMatches[1]=="|+") {
		    $sRet .= '<caption>'.trim($aMatches[2])."</caption>\n";
		    continue 1;
		}

		//content can be large, room for it here
		$sContent = '';

		if (isset($aMatches[2]) && $aMatches[2]{0}==' ') {
		  //left a space to denote no params
		    $sRet .= '>';
		    $sContent .= substr($aMatches[2],1);
		    //expect double pipe, bang or newline
		} elseif (isset($aMatches[2])) {
		  //got params. look for pipe syntax that blocked last preg
		    $sRet .= ' '.unescape($aMatches[2]).'>';
		    if (preg_match('=^\|([^\|!\n]*)=',$sRow,$aMatches)) {
		      //got rest of pipe syntax (...|text)
			$sContent .= $aMatches[1];
			$sRow = substr( $sRow, strlen($aMatches[0]) );
		    }
		} else {
		    $sRet .= '>';
		}

		//look ahead now.
		if (trim($sRow) == '') {
		  //look ahead to close our content
		    while( ++$j<$v ){
			$sRow = $aTable[$j];
			//pipe syntax (will force $sContent) to continue
			if ($sRow{0} == '|' || $sRow{0} == '!') {
			    $sRet .= $this->processContent($sContent);
			    switch($nType){
			      case 1:
			        $sRet .= "</td>\n";
			        break;
			      case 2:
			        $sRet .= "</th>\n";
			        break;
			    }
			    --$j;
			    continue 3;
			} else {
			    //non-pipe (ever-increasing) content
			    $sContent .= $sRow;
			}
		    }

		    $j = $v;
		    $sRet .= $this->processContent($sContent);
		    switch($nType){
		      case 1:
		        $sRet .= "</td>\n";
		        break;
		      case 2:
		        $sRet .= "</th>\n";
		        break;
		    }
		    continue 2;
		} elseif ( ( $sRow{0} == "|" || $sRow{0} == "!") && 
			($sRow{1} == "|" || $sRow{1} == "!") ) {
		    $sRow = substr($sRow, 1);
		    $sRet .= $this->processContent($sContent);
		    switch($nType){
		      case 1:
			$sRet .= "</td>\n";
			break;
		      case 2:
			$sRet .= "</th>\n";
			break;
		    }
		    continue 1;
	        }
	    }
	}
	if( $bPriorRow ) {
	    return $sRet."</tr>";
	} else {
	    return $sRet;
	}
    }

    /**
     * &build list
     *
     * @access  protected
     * @return  string
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     */
    protected function buildList(&$i, &$nDepth, &$aList) {
        $sStr = '';

        // Iterate though all list-entries
        while (isset($aList[$i]['DEPTH'])
               && $aList[$i]['DEPTH'] == $nDepth) {

            $sStr .= '<li>';
            $sStr .=    $aList[$i]['TEXT'];

            $i++;

            // Recurse (indent) if list-entry is nested
            if (isset($aList[$i]['DEPTH'])) {

                if ($aList[$i]['DEPTH'] > $nDepth) {

                    // Correct items that are indented too deep
                    $aList[$i]['DEPTH'] = $nDepth + 1;
                
                    $sListType = $aList[$i]['TYPE'];

                    $sStr .=  '<'.$sListType.'>';
                    $sStr .=    $this->buildList(
                                    $i,
                                    $aList[$i]['DEPTH'],
				    $aList
                                );
                    $sStr .=  '</'.$sListType.'>';
                }
            }

            $sStr .= '</li>';
        }

        return $sStr;
    }

    // --------------------------------------------------------------------

} // of class

/*
    Prospero:  That cross you wear around your neck; is it only a decoration,
               or are you a true Christian believer?

    Francesca: Yes, I believe - truly.

    Prospero:  Then I want you to remove it at once! - and never to wear it
               within this castle again! Do you know how a falcon is trained
               my dear? Her eyes are sown shut. Blinded temporarily she
               suffers the whims of her God patiently, until her will is
               submerged and she learns to serve - as your God taught and
               blinded you with crosses.

    Francesca: You had me take off my cross because it offended ...

    Prospero:  It offended no-one. No - it simply appears to me to be
               discourteous to ... to wear the symbol of a deity long dead.
               My ancestors tried to find it. And to open the door that
               seperates us from our Creator.

    Francesca: But you need no doors to find God. If you believe ...

    Prospero:  Believe?! If you believe you are gullible. Can you look
               around this world and believe in the goodness of a god who
               rules it? Famine, Pestilence, War, Disease and Death!
               They rule this world.

    Francesca: There is also love and life and hope.

    Prospero:  Very little hope I assure you. No. If a god of love and life
               ever did exist ... he is long since dead. Someone ...
               something rules in his place.
*/

?>

<?php

/**
 *
 * $Id: class.WikiReverseParser.php,v 1.17 2005/04/09 23:34:07 dgorski Exp $
 *
 * This file is part of coWiki. coWiki is free software under the terms of
 * the GNU General Public License (GPL). Read the LICENSE file. If you did
 * not receive a copy of the license and are not able to obtain it through
 * the internet, please send a note to <[email protected]> so we can mail
 * you a copy immediately.
 *
 * @package     parse
 * @subpackage  class
 * @access      public
 *
 * @author      Daniel T. Gorski, <[email protected]>
 * @copyright   (C) Daniel T. Gorski, {@link http://www.develnet.org}
 * @license     http://www.gnu.org/licenses/gpl.html
 * @version     $Revision: 1.17 $
 *
 */

/**
 * coWiki - Wiki reverse parser class
 *
 * @package     parse
 * @subpackage  class
 * @access      public
 *
 * @author      Daniel T. Gorski, <[email protected]>
 * @since       coWiki 0.3.0
 * @author      Archie Campbell <[email protected]>
 * @since       coWiki 0.3.5
 *
 * @todo        [D11N]  Complete documentation
 */
class WikiReverseParser extends Object {
    protected static
        $Instance = null,
	$Context = null,
	$DocDAO = null;
    private
        $rParser = null;
    private
    $ignoreToc = false,
        $aList = array(),
      $nDepth = 0,
      $aType = array(),
      $aTable = array(),
      //      $nTable = null;
      $sLink = array(),
      $fLink = array(),
        $aState = array(0),
        $sContent = '',
        $aRow = array(),
      $nListIndent = null;

    // --------------------------------------------------------------------

    /**
     * Get instance
     *
     * @access  public
     * @return  mixed
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     *
     * @todo    [D11N]  Check description
     * @todo    [D11N]  Check return type
     */
    public function getInstance() {
        if (!self::$Instance) {
            self::$Instance = new WikiReverseParser;
        }
        return self::$Instance;
    }

    // --------------------------------------------------------------------

    /**
     * Parse
     *
     * @access  protected
     * @param   string
     * @return  void
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     *
     * @todo    [D11N]  Check description
     */
    protected function __construct() {
	$this->Context = RuntimeContext::getInstance();
        $this->DocDAO = $this->Context->getDocumentDAO();
    }


    // --------------------------------------------------------------------

    // FIX: THIS METHOD DO NOT COVER ALL POSSIBLE OCCURANCES OF DELIMITERS
    // YET! THIS HAS TO BE CHECKED AND FIXED.

    /**
     * If a string reference contains delimiters, escape them with <noop>
     *
     * @access  protected
     * @param   string
     * @return  mixed
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     *
     * @todo    [D11N]  Check return type
     */
    protected function noopDelimiters(&$sStr) {

        // Escape leading delimiters
        if (substr($sStr, 0, 2) == '()') {
            $sStr = '&lt;noop&gt;()&lt;/noop&gt;'.substr($sStr, 2);
        } else if (substr($sStr, 0, 1) == '(') {
            $sStr = '&lt;noop&gt;(&lt;/noop&gt;'. substr($sStr, 1);
        }

        // Escape trailing delimiters
        if (substr($sStr, -2) == '()') {
            $sStr = substr($sStr, 0, -2).'&lt;noop&gt;()&lt;/noop&gt;';
        } else if (substr($sStr, -1) == ')') {
            $sStr = substr($sStr, 0, -1).'&lt;noop&gt;)&lt;/noop&gt;';
        }

        // Escape double closing
        $sStr = str_replace('))', '&lt;noop&gt;))&lt;/noop&gt;', $sStr);

        // Replace web/document delimiter
        return str_replace('¦', '|', $sStr);
    }

    // --------------------------------------------------------------------

    /**
     * Helper functions
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     *
     */
    protected function appendRow($sStr){
	array_push($this->aRow,$sStr);
	$this->clearContent();
    }
    protected function clearContent(){
	$this->sContent = '';
    }
    protected function clearRow() {
        if($this->sContent!=''){
	    $this->appendRow($this->sContent);
	}
    }
    protected function textListItem( $sData ) {
	$this->aList[sizeof($this->aList)-1]['TEXT'] .= $sData;
    }
    protected function pushTableItem( $sData ) {
        array_push($this->aTable[sizeof($this->aTable)-1],$sData);
    }


    /**
     * Parse
     *
     * @access  public
     * @param   string
     * @return  mixed
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     *
     */
    public function parse($sStr) {

      //return $this->dummy($sStr);

        if (!function_exists('xml_parser_create')) {
            return false;
        }

        $this->rParser = @xml_parser_create();

        if (!$this->rParser) {
            return false;
        }

        xml_parser_set_option($this->rParser, XML_OPTION_CASE_FOLDING, 0);
        xml_parser_set_option($this->rParser, XML_OPTION_SKIP_WHITE, 1);

        // Replace possible tabulators
        $sStr = str_replace("\t", '    ', $sStr);

        // Replace possible \r\n or \n\r with \n
        $sStr = str_replace("\r\n", "\n", $sStr);
        $sStr = str_replace("\n\r", "\n", $sStr);

	// Prepare XML, add root element
	$sStr = '<document>' . $sStr . '</document>';

	xml_set_default_handler( $this->rParser, 
				array(&$this,'xml_default_handler') );
	xml_set_element_handler( $this->rParser,
				array(&$this,'xml_start_handler'),
				array(&$this,'xml_end_handler') );
	xml_set_character_data_handler( $this->rParser,
				array(&$this,'xml_cdata_handler') );

	if(!xml_parse( $this->rParser, $sStr )){
	  echo xml_error_string(xml_get_error_code($this->rParser));
	}

	return implode("\n",$this->aRow);

    }

    /**
     * xml element start handler
     *
     * @access  protected
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     *
     */
    protected function xml_start_handler( &$parser, $sName, $aAttrib ) {
        if($this->ignoreToc){ return; }
        switch($sName){
	case 'document':
	    $this->aRow = array();
	    break;
	case 'toc':
	    $this->clearRow();
	    $this->ignoreToc = true;
	    break;
	case 'plugin':
	    $this->clearRow();
	    $sStr = '<plugin '.$aAttrib['name'];
	    if(sizeof($aAttrib)>1){
	        foreach($aAttrib as $attr => $value){
		    if($attr != 'name'){
		        $sStr .= ' '.$attr.'='.$value;
		    }
		}
	    }
	    $sStr .= '>';
	    $this->appendRow($sStr);
  	    break;
	//table syntax
	case 'table':
	    $this->clearRow();
	    array_push($this->aState,6);/*WRP_TABL*/
	    array_push($this->aTable,array($aAttrib));//[][0]
	    break;
	case 'caption':
	    array_push($this->aState,7);/*WRP_CAPN*/
	    $this->clearContent();
	    break;
	case 'tr':
   	    array_push($this->aState,8);/*WRP_TROW*/
	    $sStr = '|-';
	    if(sizeof($aAttrib)){
  	        foreach($aAttrib as $attr => $value){
		    $sStr .= $attr.'="'.$value.'" ';
 		}
	    }
	    $this->pushTableItem( $sStr );
	    break;
	case 'th':
	    array_push($this->aState,9);/*WRP_THED*/
	    $sStr = '!';
	    if(sizeof($aAttrib)){
  	        foreach($aAttrib as $attr => $value){
		    $sStr .= $attr.'="'.$value.'" ';
 		}
	    }
	    $sStr .= ' ';
	    $this->pushTableItem( $sStr );	    
	    break;
	case 'td':
	    array_push($this->aState,10);/*WRP_TCEL*/
	    $sStr = '|';
	    if(sizeof($aAttrib)){
  	        foreach($aAttrib as $attr => $value){
		    $sStr .= $attr.'="'.$value.'" ';
 		}
	    }
	    $sStr .= ' ';
	    $this->pushTableItem( $sStr );	    
	    break;
	//list syntax
	case 'list':
	    $this->clearRow();
	    array_push($this->aState,1);/*WRP_LIST*/
	    break;
	case 'ol':
	case 'ul': 
	    $this->nDepth++;
	    array_push($this->aType,$sName);
	    break;
	case 'li':
	    switch(end($this->aState)){
	    case 1:
	        if(strlen($this->sContent)){
		    $this->textListItem($this->sContent);
	        }
		array_push( $this->aList, 
			    array(  'DEPTH'=>$this->nDepth,
				    'TYPE'=>(end($this->aType)=='ol'?
							         "#":"*"),
				    'TEXT'=>''  ));
		break;
	    default:
	      echo $sName . "insanity";
	      exit;
	    }
	    $this->clearContent();
	    break;
        //paragraphs
	case 'p':
	    $this->clearRow();
	    break;
	//noop
	case 'noop':
	    $this->sContent .= '<noop>';
	    array_push($this->aState,5);
	    break;
        //justification
	case 'left':
	case 'right':
	case 'center':
	    $this->sContent .= '<'.$sName.'>';
	    break;
        //pre, code, posting, quote
	case 'pre':
	case 'code':
	case 'posting':
	case 'q':
	    $this->clearRow();
	    array_push($this->aState,4);
	    break;
	//line-break
	case 'br':
	    $this->clearRow();
	    break;
        //variables
	case 'var':
	    $this->sContent .= "%".$aAttrib['name']."%";
	    break;
	//headings
	case 'h1':
	case 'h2':
	case 'h3':
	case 'h4':
	case 'h5':
	case 'h6':
	    array_push($this->aState,3);
            break;
	//wiki links
	case 'uri':
	    $this->sContent .= $aAttrib['strref'];
	    break;
	case 'link':
	    array_push($this->aState,2);
	    if( isset($aAttrib['strref']) ) {
		$this->fLink = array(&$this, 'buildStrRefLink');
		$this->sLink[1] = $aAttrib['strref'];
	    }else if( isset($aAttrib['href']) ) {
		$this->fLink = array(&$this, 'buildHyperRefLink');
		$this->sLink[1] = $aAttrib['href'];
	    }else if( isset($aAttrib['idref']) ) {
		$this->fLink = array(&$this, 'buildIdRefLink');
		$this->sLink[1] = $aAttrib['idref'];
	    }
    	    break;
	//subscript & superscript
	case 'sub':
	case 'sup':
	    $this->sContent .= '<'.$sName.'>';
	    break;
	//horizontal rule
	case 'hr':break;
	//emphasis (strike,tt,b,u,i)
	case 'strike':
	    $this->sContent .= "--";
	    break;
	case 'tt':
	    $this->sContent .= "==";
	    break;
	case 'b':
	    $this->sContent .= "**";
	    break;
	case 'u':
	    $this->sContent .= "__";
	    break;
	case 'i':
	    $this->sContent .= '//';
	    break;
	default:
            echo $sName . " start" . "\n";
	}
    }

    /**
     * xml element end handler
     *
     * @access  protected
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     *
     */
    protected function xml_end_handler( &$parser, $sName ) {
        if($this->ignoreToc){
	    if($sName == 'toc'){
		$this->appendRow("<toc>");
		$this->ignoreToc = false;
		return;
	    }
	}
        switch($sName){
	case 'document': 
	    $this->clearRow();
	    break;
	case 'plugin':
	    break;
	//table syntax
	case 'table':
	    if(array_pop($this->aState)!=6) {
	        echo "insanity in table";
	        exit;
	    }
	    $aTable = array_pop($this->aTable);
	    $sStr = '<table';
	    foreach($aTable[0] as $attr => $value ){
	        $sStr .= " ".$attr.'="'.$value.'"';
	    }
	    $sStr .= (sizeof($aTable)==1?'/>':'>');
	    $this->appendRow( $sStr );
	    for ($i = 1; $i < sizeof($aTable) ; $i++){
	        $this->appendRow( $aTable[$i] );
	    }
	    $this->appendRow('</table>');
	    break;
        //caption
	case 'caption':
            if(array_pop($this->aState)!=7) {
	        echo "insanity in caption";
	        exit;
	    }
	    $this->pushTableItem( "|+ ".$this->sContent );
	    $this->clearContent();
	    break;
	case 'tr':
	    if(array_pop($this->aState)!=8) {
  	        echo "insanity in trow";
	        exit;
	    }
  	    break;
	case 'th':
	    if(array_pop($this->aState)!=9) {
	        echo "insanity in thead";
		exit;
	    }
	    if($this->sContent != ''){
	        $this->pushTableItem($this->sContent);
		$this->clearContent();
	    }
	    break;
	case 'td':
	    if(array_pop($this->aState)!=10) {
	        echo "insanity in tcell";
		exit;
	    }
	    if($this->sContent != ''){
	        $this->pushTableItem($this->sContent);
		$this->clearContent();
	    }
	    break;
	//list syntax
	case 'list':
	    if(array_pop($this->aState)!=1) {
	        echo "insanity in list";
	        exit;
	    };
	    foreach($this->aList as $li){
		$sStr = str_repeat($li['TYPE'],$li['DEPTH']).
		  " ".$li['TEXT'];
	      switch(end($this->aState)){
	      case 9:
	      case 10:
		  $this->pushTableItem( $sStr );
		  break;
	      default:
		  $this->appendRow( $sStr );
	      }
	    }
	    $this->clearContent();
	    $this->aList = array();
	    break;
	case 'ol':
	case 'ul':
	    $this->nDepth--;
	    array_pop($this->aType);
	    break;
	case 'li':
	    $this->textListItem($this->sContent);
	    $this->clearContent();
	    break;
        //paragraphs
	case 'p':
	    $this->appendRow( $this->sContent );
	    break;
	//noop
	case 'noop':
	    $this->sContent .= '</noop>';
	    array_pop($this->aState);
	    break;
        //justification
	case 'left':
	case 'right':
	case 'center':
	    $this->sContent .= '</'.$sName.'>';
	    break;
        //pre, code, posting, quote
	case 'pre':
	case 'code':
	case 'posting':
	case 'q':
	    $this->sContent = '<'.$sName.'>'.
				$this->sContent.
			      '</'.$sName.'>';
	    array_pop($this->aState);
	    if(end($this->aState)!=1){
	        $this->clearRow();
	    }
	    break;
	//line-break
	case 'br':
	    $this->appendRow( '<br/>' );
	    break;
        //variables
	case 'var':
	    break;
	//headings
	case 'h1':
	case 'h2':
	case 'h3':
	case 'h4':
	case 'h5':
	case 'h6':
	    $this->appendRow( str_repeat("+",substr($sName,1,1)).
				" ". $this->sContent);
	    array_pop( $this->aState );
	    break;
	//wiki links
	case 'uri':
	    break;
	case 'link':
	    array_pop($this->aState);
	    $sStr = call_user_func($this->fLink, $this->sLink);
            $this->sContent .= $sStr;
	    break;
	//subscript & superscript
	case 'sub':
	case 'sup':
	    $this->sContent .= '</'.$sName.'>';
	    break;
	//horizontal rule
	case 'hr':
	    $this->appendRow("---");
	    break;
	//emphasis (strike,tt,b,u,i)
	case 'strike':
	    $this->sContent .= "--";
	    break;
	case 'tt':
	    $this->sContent .= "==";
	    break;
	case 'b':
	    $this->sContent .= "**";
	    break;
	case 'u':
	    $this->sContent .= "__";
	    break;
	case 'i':
	    $this->sContent .= '//';
	    break;
	default:
	    echo $sName . " end" . "\n";
        }
    }

    /**
     * xml element default handler
     *
     * @access  protected
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     *
     */
    protected function xml_default_handler( &$parser, $sData ) {
        if(!$this->ignoreToc){
            $this->sContent .= html_entity_decode($sData);
	}
    }

    /**
     * xml cdata handler
     *
     * @access  protected
     *
     * @author  Archie Campbell <[email protected]>
     * @since   coWiki 0.3.5
     *
     */
    protected function xml_cdata_handler( &$parser, $sData ) {
        if($this->ignoreToc){ return; }
        if( trim($sData) != '' ) {
	    switch( end($this->aState) ){
	    case 1:/*WRP_LIST*/
	    case 3:/*WRP_HEAD*/
	    case 4:/*WRP_PCPQ*/
	    case 5:/*WRP_NOOP*/
	    case 7:/*WRP_CAPT*/
	    case 9:/*WRP_THED*/
		$this->sContent .= $sData;
 		break;
	    case 2:/*WRP_LINK*/
	        $this->sLink[2]=trim($sData);
	        break;
	    default:/*text*/
	        $this->sContent .= $sData;
	    }
        }
    }

    // --------------------------------------------------------------------

    /**
     * Build str ref link
     *
     * @access  protected
     * @param   array
     * @return  mixed
     *
     * @author  Daniel T. Gorski, <[email protected]>
     * @since   coWiki 0.3.0
     *
     * @todo    [D11N]  Check description
     */
    protected function buildStrRefLink(&$aMatches) {
        if ($aMatches[1] == $aMatches[2] || trim($aMatches[2]) == '') {
            return '((' . $this->noopDelimiters($aMatches[1]) . '))';
        }

        return '((' . $this->noopDelimiters($aMatches[1]) . ')'
                .'(' . $aMatches[2] . '))';
    }

} // of class

?>