xref: /dokuwiki/inc/parser/parser.php (revision e7464db8d3ba31a1707af9321295699d17fff19f)

<?php

if(!defined('DOKU_INC')) define('DOKU_INC',realpath(dirname(__FILE__).'/../../').'/');

require_once DOKU_INC . 'inc/parser/lexer.php';
require_once DOKU_INC . 'inc/parser/handler.php';


/**
 * Define various types of modes used by the parser - they are used to
 * populate the list of modes another mode accepts
 */
global $PARSER_MODES;
$PARSER_MODES = array(
    // containers are complex modes that can contain many other modes
    // hr breaks the principle but they shouldn't be used in tables / lists
    // so they are put here
    'container'    => array('listblock','table','quote','hr'),

    // some mode are allowed inside the base mode only
    'baseonly'     => array('header'),

    // modes for styling text -- footnote behaves similar to styling
    'formatting'   => array('strong', 'emphasis', 'underline', 'monospace',
                            'subscript', 'superscript', 'deleted', 'footnote'),

    // modes where the token is simply replaced - they can not contain any
    // other modes
    'substition'   => array('acronym','smiley','wordblock','entity',
                            'camelcaselink', 'internallink','media',
                            'externallink','linebreak','emaillink',
                            'windowssharelink','filelink','notoc',
                            'nocache','multiplyentity','quotes','rss'),

    // modes which have a start and end token but inside which
    // no other modes should be applied
    'protected'    => array('preformatted','code','file','php','html'),

    // inside this mode no wiki markup should be applied but lineendings
    // and whitespace isn't preserved
    'disabled'     => array('unformatted'),

    // used to mark paragraph boundaries
    'paragraphs'   => array('eol')
);

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

/**
* Sets up the Lexer with modes and points it to the Handler
* For an intro to the Lexer see: wiki:parser
*/
class Doku_Parser {

    var $Handler;

    var $Lexer;

    var $modes = array();

    var $connected = FALSE;

    function addBaseMode(& $BaseMode) {
        $this->modes['base'] = & $BaseMode;
        if ( !$this->Lexer ) {
            $this->Lexer = & new Doku_Lexer($this->Handler,'base', TRUE);
        }
        $this->modes['base']->Lexer = & $this->Lexer;
    }

    /**
    * PHP preserves order of associative elements
    * Mode sequence is important
    */
    function addMode($name, & $Mode) {
        if ( !isset($this->modes['base']) ) {
            $this->addBaseMode(new Doku_Parser_Mode_base());
        }
        $Mode->Lexer = & $this->Lexer;
        $this->modes[$name] = & $Mode;
    }

    function connectModes() {

        if ( $this->connected ) {
            return;
        }

        foreach ( array_keys($this->modes) as $mode ) {

            // Base isn't connected to anything
            if ( $mode == 'base' ) {
                continue;
            }

            $this->modes[$mode]->preConnect();

            foreach ( array_keys($this->modes) as $cm ) {

                if ( $this->modes[$cm]->accepts($mode) ) {
                    $this->modes[$mode]->connectTo($cm);
                }

            }

            $this->modes[$mode]->postConnect();
        }

        $this->connected = TRUE;
    }

    function parse($doc) {
        if ( $this->Lexer ) {
            $this->connectModes();
            // Normalize CRs and pad doc
            $doc = "\n".str_replace("\r\n","\n",$doc)."\n";
            $this->Lexer->parse($doc);
            $this->Handler->_finalize();
            return $this->Handler->calls;
        } else {
            return FALSE;
        }
    }

}

//-------------------------------------------------------------------
/**
 * This class and all the subclasses below are
 * used to reduce the effort required to register
 * modes with the Lexer. For performance these
 * could all be eliminated later perhaps, or
 * the Parser could be serialized to a file once
 * all modes are registered
 *
 * @author Harry Fuecks <hfuecks@gmail.com>
*/
class Doku_Parser_Mode {

    var $Lexer;

    var $allowedModes = array();

    // returns a number used to determine in which order modes are added
    function getSort() {
        trigger_error('getSort() not implemented in '.get_class($this), E_USER_WARNING);
    }

    // Called before any calls to connectTo
    function preConnect() {}

    // Connects the mode
    function connectTo($mode) {}

    // Called after all calls to connectTo
    function postConnect() {}

    function accepts($mode) {
        return in_array($mode, $this->allowedModes );
    }

}

//-------------------------------------------------------------------
class Doku_Parser_Mode_base extends Doku_Parser_Mode {

    function Doku_Parser_Mode_base() {
        global $PARSER_MODES;

        $this->allowedModes = array_merge (
                $PARSER_MODES['container'],
                $PARSER_MODES['baseonly'],
                $PARSER_MODES['paragraphs'],
                $PARSER_MODES['formatting'],
                $PARSER_MODES['substition'],
                $PARSER_MODES['protected'],
                $PARSER_MODES['disabled']
            );
    }

    function getSort() {
        return 0;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_footnote extends Doku_Parser_Mode {

    function Doku_Parser_Mode_footnote() {
        global $PARSER_MODES;

        $this->allowedModes = array_merge (
                $PARSER_MODES['container'],
                $PARSER_MODES['formatting'],
                $PARSER_MODES['substition'],
                $PARSER_MODES['protected'],
                $PARSER_MODES['disabled']
            );

    }

    function connectTo($mode) {
        $this->Lexer->addEntryPattern(
            '\x28\x28(?=.*\x29\x29)',$mode,'footnote'
            );
    }

    function postConnect() {
        $this->Lexer->addExitPattern(
            '\x29\x29','footnote'
            );

    }

    function getSort() {
        return 150;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_header extends Doku_Parser_Mode {

    function preConnect() {
        //we're not picky about the closing ones, two are enough

        // Header 1 is special case - match 6 or more
        $this->Lexer->addSpecialPattern(
                            '[ \t]*={6,}[^\n]+={2,}[ \t]*(?=\n)',
                            'base',
                            'header'
                        );

        // For the rest, match exactly
        for ( $i = 5; $i > 1; $i--) {
            $this->Lexer->addSpecialPattern(
                                '[ \t]*={'.$i.'}[^\n]+={2,}[ \t]*(?=\n)',
                                'base',
                                'header'
                            );
        }
    }

    function getSort() {
        return 50;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_notoc extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern('~~NOTOC~~',$mode,'notoc');
    }

    function getSort() {
        return 30;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_nocache extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern('~~NOCACHE~~',$mode,'nocache');
    }

    function getSort() {
        return 40;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_linebreak extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern('\x5C{2}(?=\s)',$mode,'linebreak');
    }

    function getSort() {
        return 140;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_eol extends Doku_Parser_Mode {

    function connectTo($mode) {
        $badModes = array('listblock','table');
        if ( in_array($mode, $badModes) ) {
            return;
        }
        $this->Lexer->addSpecialPattern('\n',$mode,'eol');
    }

    function getSort() {
        return 370;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_hr extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern('\n[ \t]*-{4,}[ \t]*(?=\n)',$mode,'hr');
    }

    function getSort() {
        return 160;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_formatting extends Doku_Parser_Mode {
    var $type;

    var $formatting = array (
        'strong' => array (
            'entry'=>'\*\*(?=.*\*\*)',
            'exit'=>'\*\*',
            'sort'=>70
            ),

        'emphasis'=> array (
            'entry'=>'//(?=.*(?<!http:|ftp:)//)', //hack for bug #384
            'exit'=>'//',
            'sort'=>80
            ),

        'underline'=> array (
            'entry'=>'__(?=.*__)',
            'exit'=>'__',
            'sort'=>90
            ),

        'monospace'=> array (
            'entry'=>'\x27\x27(?=.*\x27\x27)',
            'exit'=>'\x27\x27',
            'sort'=>100
            ),

        'subscript'=> array (
            'entry'=>'<sub>(?=.*\x3C/sub\x3E)',
            'exit'=>'</sub>',
            'sort'=>110
            ),

        'superscript'=> array (
            'entry'=>'<sup>(?=.*\x3C/sup\x3E)',
            'exit'=>'</sup>',
            'sort'=>120
            ),

        'deleted'=> array (
            'entry'=>'<del>(?=.*\x3C/del\x3E)',
            'exit'=>'</del>',
            'sort'=>130
            ),
        );

    function Doku_Parser_Mode_formatting($type) {
        global $PARSER_MODES;

        if ( !array_key_exists($type, $this->formatting) ) {
            trigger_error('Invalid formatting type '.$type, E_USER_WARNING);
        }

        $this->type = $type;

        // formatting may contain other formatting but not it self
        $modes = $PARSER_MODES['formatting'];
        $key = array_search($type, $modes);
        if ( is_int($key) ) {
            unset($modes[$key]);
        }

        $this->allowedModes = array_merge (
                $modes,
                $PARSER_MODES['substition'],
                $PARSER_MODES['disabled']
            );
    }

    function connectTo($mode) {

        // Can't nest formatting in itself
        if ( $mode == $this->type ) {
            return;
        }

        $this->Lexer->addEntryPattern(
                $this->formatting[$this->type]['entry'],
                $mode,
                $this->type
            );
    }

    function postConnect() {

        $this->Lexer->addExitPattern(
            $this->formatting[$this->type]['exit'],
            $this->type
            );

    }

    function getSort() {
        return $this->formatting[$this->type]['sort'];
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_listblock extends Doku_Parser_Mode {

    function Doku_Parser_Mode_listblock() {
        global $PARSER_MODES;

        $this->allowedModes = array_merge (
                $PARSER_MODES['formatting'],
                $PARSER_MODES['substition'],
                $PARSER_MODES['disabled'],
                $PARSER_MODES['protected'] #XXX new
            );

    //    $this->allowedModes[] = 'footnote';
    }

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('\n {2,}[\-\*]',$mode,'listblock');
        $this->Lexer->addEntryPattern('\n\t{1,}[\-\*]',$mode,'listblock');

        $this->Lexer->addPattern('\n {2,}[\-\*]','listblock');
        $this->Lexer->addPattern('\n\t{1,}[\-\*]','listblock');

    }

    function postConnect() {
        $this->Lexer->addExitPattern('\n','listblock');
    }

    function getSort() {
        return 10;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_table extends Doku_Parser_Mode {

    function Doku_Parser_Mode_table() {
        global $PARSER_MODES;

        $this->allowedModes = array_merge (
                $PARSER_MODES['formatting'],
                $PARSER_MODES['substition'],
                $PARSER_MODES['disabled'],
                $PARSER_MODES['protected']
            );
    }

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('\n\^',$mode,'table');
        $this->Lexer->addEntryPattern('\n\|',$mode,'table');
    }

    function postConnect() {
        $this->Lexer->addPattern('\n\^','table');
        $this->Lexer->addPattern('\n\|','table');
        $this->Lexer->addPattern(' {2,}','table');
        $this->Lexer->addPattern('\^','table');
        $this->Lexer->addPattern('\|','table');
        $this->Lexer->addExitPattern('\n','table');
    }

    function getSort() {
        return 60;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_unformatted extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('<nowiki>(?=.*\x3C/nowiki\x3E)',$mode,'unformatted');
        $this->Lexer->addEntryPattern('%%(?=.*%%)',$mode,'unformattedalt');
    }

    function postConnect() {
        $this->Lexer->addExitPattern('</nowiki>','unformatted');
        $this->Lexer->addExitPattern('%%','unformattedalt');
        $this->Lexer->mapHandler('unformattedalt','unformatted');
    }

    function getSort() {
        return 170;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_php extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('<php>(?=.*\x3C/php\x3E)',$mode,'php');
    }

    function postConnect() {
        $this->Lexer->addExitPattern('</php>','php');
    }

    function getSort() {
        return 180;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_html extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('<html>(?=.*\x3C/html\x3E)',$mode,'html');
    }

    function postConnect() {
        $this->Lexer->addExitPattern('</html>','html');
    }

    function getSort() {
        return 190;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_preformatted extends Doku_Parser_Mode {

    function connectTo($mode) {
        // Has hard coded awareness of lists...
        $this->Lexer->addEntryPattern('\n  (?![\*\-])',$mode,'preformatted');
        $this->Lexer->addEntryPattern('\n\t(?![\*\-])',$mode,'preformatted');

        // How to effect a sub pattern with the Lexer!
        $this->Lexer->addPattern('\n  ','preformatted');
        $this->Lexer->addPattern('\n\t','preformatted');

    }

    function postConnect() {
        $this->Lexer->addExitPattern('\n','preformatted');
    }

    function getSort() {
        return 20;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_code extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('<code(?=.*\x3C/code\x3E)',$mode,'code');
    }

    function postConnect() {
        $this->Lexer->addExitPattern('</code>','code');
    }

    function getSort() {
        return 200;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_file extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('<file>(?=.*\x3C/file\x3E)',$mode,'file');
    }

    function postConnect() {
        $this->Lexer->addExitPattern('</file>','file');
    }

    function getSort() {
        return 210;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_quote extends Doku_Parser_Mode {

    function Doku_Parser_Mode_quote() {
        global $PARSER_MODES;

        $this->allowedModes = array_merge (
                $PARSER_MODES['formatting'],
                $PARSER_MODES['substition'],
                $PARSER_MODES['disabled'],
                $PARSER_MODES['protected'] #XXX new
            );
            #$this->allowedModes[] = 'footnote';
            #$this->allowedModes[] = 'preformatted';
            #$this->allowedModes[] = 'unformatted';
    }

    function connectTo($mode) {
        $this->Lexer->addEntryPattern('\n>{1,}',$mode,'quote');
    }

    function postConnect() {
        $this->Lexer->addPattern('\n>{1,}','quote');
        $this->Lexer->addExitPattern('\n','quote');
    }

    function getSort() {
        return 220;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_acronym extends Doku_Parser_Mode {
    // A list
    var $acronyms = array();
    var $pattern = '';

    function Doku_Parser_Mode_acronym($acronyms) {
        $this->acronyms = $acronyms;
    }

    function preConnect() {
        $sep = '';
        foreach ( $this->acronyms as $acronym ) {
            $this->pattern .= $sep.'(?<=\b)'.Doku_Lexer_Escape($acronym).'(?=\b)';
            $sep = '|';
        }
    }

    function connectTo($mode) {
        if ( strlen($this->pattern) > 0 ) {
            $this->Lexer->addSpecialPattern($this->pattern,$mode,'acronym');
        }
    }

    function getSort() {
        return 240;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_smiley extends Doku_Parser_Mode {
    // A list
    var $smileys = array();
    var $pattern = '';

    function Doku_Parser_Mode_smiley($smileys) {
        $this->smileys = $smileys;
    }

    function preConnect() {
        $sep = '';
        foreach ( $this->smileys as $smiley ) {
            $this->pattern .= $sep.Doku_Lexer_Escape($smiley);
            $sep = '|';
        }
    }

    function connectTo($mode) {
        if ( strlen($this->pattern) > 0 ) {
            $this->Lexer->addSpecialPattern($this->pattern,$mode,'smiley');
        }
    }

    function getSort() {
        return 230;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_wordblock extends Doku_Parser_Mode {
    // A list
    var $badwords = array();
    var $pattern = '';

    function Doku_Parser_Mode_wordblock($badwords) {
        $this->badwords = $badwords;
    }

    function preConnect() {

        if ( count($this->badwords) == 0 ) {
            return;
        }

        $sep = '';
        foreach ( $this->badwords as $badword ) {
            $this->pattern .= $sep.'(?<=\b)(?i)'.Doku_Lexer_Escape($badword).'(?-i)(?=\b)';
            $sep = '|';
        }

    }

    function connectTo($mode) {
        if ( strlen($this->pattern) > 0 ) {
            $this->Lexer->addSpecialPattern($this->pattern,$mode,'wordblock');
        }
    }

    function getSort() {
        return 250;
    }
}

//-------------------------------------------------------------------
/**
* @TODO Quotes and 640x480 are not supported - just straight replacements here
*/
class Doku_Parser_Mode_entity extends Doku_Parser_Mode {
    // A list
    var $entities = array();
    var $pattern = '';

    function Doku_Parser_Mode_entity($entities) {
        $this->entities = $entities;
    }

    function preConnect() {
        $sep = '';
        foreach ( $this->entities as $entity ) {
            $this->pattern .= $sep.Doku_Lexer_Escape($entity);
            $sep = '|';
        }
    }

    function connectTo($mode) {
        if ( strlen($this->pattern) > 0 ) {
            $this->Lexer->addSpecialPattern($this->pattern,$mode,'entity');
        }
    }

    function getSort() {
        return 260;
    }
}

//-------------------------------------------------------------------
// Implements the 640x480 replacement
class Doku_Parser_Mode_multiplyentity extends Doku_Parser_Mode {

    function connectTo($mode) {

        $this->Lexer->addSpecialPattern(
                    '(?<=\b)\d+[xX]\d+(?=\b)',$mode,'multiplyentity'
                );

    }

    function getSort() {
        return 270;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_quotes extends Doku_Parser_Mode {

    function connectTo($mode) {

        $this->Lexer->addSpecialPattern(
                    '(?<=^|\s)\'(?=\S)',$mode,'singlequoteopening'
                );
        $this->Lexer->addSpecialPattern(
                    '(?<=^|\S)\'',$mode,'singlequoteclosing'
                );
        $this->Lexer->addSpecialPattern(
                    '(?<=^|\s)"(?=\S)',$mode,'doublequoteopening'
                );
        $this->Lexer->addSpecialPattern(
                    '(?<=^|\S)"',$mode,'doublequoteclosing'
                );

    }

    function getSort() {
        return 280;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_camelcaselink extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern(
                '\b[A-Z]+[a-z]+[A-Z][A-Za-z]*\b',$mode,'camelcaselink'
            );
    }

    function getSort() {
        return 290;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_internallink extends Doku_Parser_Mode {

    function connectTo($mode) {
        // Word boundaries?
        $this->Lexer->addSpecialPattern("\[\[.+?\]\]",$mode,'internallink');
    }

    function getSort() {
        return 300;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_media extends Doku_Parser_Mode {

    function connectTo($mode) {
        // Word boundaries?
        $this->Lexer->addSpecialPattern("\{\{[^\}]+\}\}",$mode,'media');
    }

    function getSort() {
        return 320;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_rss extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern("\{\{rss>[^\}]+\}\}",$mode,'rss');
    }

    function getSort() {
        return 310;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_externallink extends Doku_Parser_Mode {
    var $schemes = array('http','https','telnet','gopher','wais','ftp','ed2k','irc');
    var $patterns = array();

    function preConnect() {

        $ltrs = '\w';
        $gunk = '/\#~:.?+=&%@!\-';
        $punc = '.:?\-;,';
        $host = $ltrs.$punc;
        $any  = $ltrs.$gunk.$punc;

        foreach ( $this->schemes as $scheme ) {
            $this->patterns[] = '\b(?i)'.$scheme.'(?-i)://['.$any.']+?(?=['.$punc.']*[^'.$any.'])';
        }

        $this->patterns[] = '\b(?i)www?(?-i)\.['.$host.']+?\.['.$host.']+?['.$any.']+?(?=['.$punc.']*[^'.$any.'])';
        $this->patterns[] = '\b(?i)ftp?(?-i)\.['.$host.']+?\.['.$host.']+?['.$any.']+?(?=['.$punc.']*[^'.$any.'])';

    }

    function connectTo($mode) {
        foreach ( $this->patterns as $pattern ) {
            $this->Lexer->addSpecialPattern($pattern,$mode,'externallink');
        }
    }

    function getSort() {
        return 330;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_filelink extends Doku_Parser_Mode {

    var $pattern;

    function preConnect() {

        $ltrs = '\w';
        $gunk = '/\#~:.?+=&%@!\-';
        $punc = '.:?\-;,';
        $host = $ltrs.$punc;
        $any  = $ltrs.$gunk.$punc;

        $this->pattern = '\b(?i)file(?-i)://['.$any.']+?['.
            $punc.']*[^'.$any.']';
    }

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern(
            $this->pattern,$mode,'filelink');
    }

    function getSort() {
        return 360;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_windowssharelink extends Doku_Parser_Mode {

    var $pattern;

    function preConnect() {
        $this->pattern = "\\\\\\\\\w+?(?:\\\\[\w$]+)+";
    }

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern(
            $this->pattern,$mode,'windowssharelink');
    }

    function getSort() {
        return 350;
    }
}

//-------------------------------------------------------------------
class Doku_Parser_Mode_emaillink extends Doku_Parser_Mode {

    function connectTo($mode) {
        $this->Lexer->addSpecialPattern("<[\w0-9\-_.]+?@[\w\-]+\.[\w\-\.]+\.*[\w]+>",$mode,'emaillink');
    }

    function getSort() {
        return 340;
    }
}


//Setup VIM: ex: et ts=4 enc=utf-8 :