rtfclass.php

The goal with this project was to make it possible for almost any mobile-phone to use ICQ and be abl

<?
	// use tabstop=4 

	/*
		Rich Text Format - Parsing Class
		================================

		(c) 2000 Markus Fischer
		<[e-mail]>
		   http://josefine.ben.tuwien.ac.at/~mfischer/

		Latest versions of this class can always be found at
			http://josefine.ben.tuwien.ac.at/~mfischer/developing/php/rtf/rtfclass.phps
		Testing suite is available at
			http://josefine.ben.tuwien.ac.at/~mfischer/developing/php/rtf/

		License: GPLv2

		Specification:
			http://msdn.microsoft.com/library/default.asp?URL=/library/specs/rtfspec.htm

		General Notes:
		==============
		Unknown or unspupported control symbols are silently ignored

		Group stacking is still not supported :(
			group stack logic implemented; however not really used yet

		Example on how to use this class:
		=================================

		$r = new rtf( stripslashes( $rtf));
		$r->output( "xml");
		$r->parse();
		if( count( $r->err) == 0) // no errors detected
			echo $r->out;
			
		History:
		========
		Sat Nov 25 09:52:12 CET 2000	mfischer
			First version which has useable but only well-formed xml output; rtf
			data structure is only logically rebuild, no real parsing yet

		Mon Nov 27 16:17:18 CET 2000	mfischer
			Wrote handler for \plain control word (thanks to Peter Kursawe for this
			one)

		Tue Nov 28 02:22:16 CET 2000	mfischer
			Implemented alignment (left, center, right) with HTML <DIV .. tags
			Also implemented translation for < and > character when outputting html or xml

		Remarks:
		========
		This class and all work done here is dedicated to Tatjana.
	*/

	/* was just a brainlag suggestion of my inner link; don't know if I'll use it */
	class rtfState {
		var $bold;
		var $italic;
		var $underlined;
	}

	class rtf {
		var $rtf;		// rtf core stream
		var $len;		// length in characters of the stream (get performace due avoiding calling strlen everytime)
		var $err = array();		// array of error message, no entities on no error

		var $wantXML;	// convert to XML
		var $wantHTML;	// convert to HTML

		// the only variable which should be accessed from the outside
		var $out;		// output data stream (depends on which $wantXXXXX is set to true
		var $outstyles;	// htmlified styles (generated after parsing if wantHTML
		var $styles;	// if wantHTML, stylesheet definitions are put in here

		// internal parser variables --------------------------------
		// control word variables
		var $cword;		// holds the current (or last) control word, depending on $cw
		var $cw;		// are we currently parsing a control word ?
		var $cfirst;	// could this be the first character ? so watch out for control symbols

		var $flags = array();		// parser flags

		var $queue;		// every character which is no sepcial char, not belongs to a control word/symbol; is generally considered being 'plain'

		var $stack = array();	// group stack

		/* keywords which don't follw the specification (used by Word '97 - 2000) */
		// not yet used
		var $control_exception = array(
			"clFitText",
			"clftsWidth(-?[0-9]+)?",
			"clNoWrap(-?[0-9]+)?",
			"clwWidth(-?[0-9]+)?",
			"tdfrmtxtBottom(-?[0-9]+)?",
			"tdfrmtxtLeft(-?[0-9]+)?",
			"tdfrmtxtRight(-?[0-9]+)?",
			"tdfrmtxtTop(-?[0-9]+)?",
			"trftsWidthA(-?[0-9]+)?",
			"trftsWidthB(-?[0-9]+)?",
			"trftsWidth(-?[0-9]+)?",
			"trwWithA(-?[0-9]+)?",
			"trwWithB(-?[0-9]+)?",
			"trwWith(-?[0-9]+)?",
			"spectspecifygen(-?[0-9]+)?"
			);

		var $charset_table = array(
			"0"	=>	"ANSI",
			"1"	=>	"Default",
			"2"	=>	"Symbol",
			"77" =>	"Mac",
			"128" =>	"Shift Jis",
			"129" =>	"Hangul",
			"130" =>	"Johab",
			"134" =>	"GB2312",
			"136" =>	"Big5",
			"161" =>	"Greek",
			"162" =>	"Turkish",
			"163" =>	"Vietnamese",
			"177" =>	"Hebrew",
			"178" =>	"Arabic",
			"179" =>	"Arabic Traditional",
			"180" =>	"Arabic user",
			"181" =>	"Hebrew user",
			"186" =>	"Baltic",
			"204" =>	"Russion",
			"222" =>	"Thai",
			"238" =>	"Eastern European",
			"255" =>	"PC 437",
			"255" =>	"OEM"
		);

		/* note: the only conversion table used */
		var $fontmodifier_table = array(
			"bold"	=>	"b",
			"italic"	=> "i",
			"underlined"	=> "u",
			"strikethru"	=> "strike"
		);

		/*
			Class Constructor:
			Takes as argument the raw RTF stream
			(Note under certain circumstances the stream has to be stripslash'ed before handling over)
			Initialises some class-global variables
		*/
		function rtf( $data) {
			$this->len = strlen( $data);
			$this->rtf = $data;

			$this->wantXML = false;
			$this->wantHTML = false;

			$this->out = "";
			$this->outstyles = "";
			$this->styles = array();
			$this->text = "";

			if( $this->len == 0)
				array_push( $this->err, "No data in stream found");
		}

		function parserInit() {
			/*
				Default values according to the specs
			*/
			$this->flags = array(
				"fontsize"	=>	24,
				"beginparagraph"	=> true
			);
		}
		
		/*
			Sets the output type
		*/
		function output( $typ) {
			switch( $typ) {
				case "xml": $this->wantXML = true; break;
				case "html": $this->wantHTML = true; break;
				default: break;
			}
		}

		function parseControl( $control, $parameter) {
			switch( $control) {
				// font table definition start
				case "fonttbl":
					$this->flags["fonttbl"] = true;	// signal fonttable control words they are allowed to behave as expected
					break;
				// define or set font
				case "f":
					if( $this->flags["fonttbl"]) {	// if its set, the fonttable definition is written to; else its read from
						$this->flags["fonttbl_current_write"] = $parameter;
					} else {
						$this->flags["fonttbl_current_read"] = $parameter;
					}
					break;
				case "fcharset":
					// this is for preparing flushQueue; it then moves the Queue to $this->fonttable .. instead to formatted output
					$this->flags["fonttbl_want_fcharset"] = $parameter;
					break;
				case "fs":
					// sets the current fontsize; is used by stylesheets (which are therefore generated on the fly
					$this->flags["fontsize"] = $parameter;
					break;
				// handle alignment
				case "qc":
					$this->flags["alignment"] = "center";
					break;
				case "qr":
					$this->flags["alignment"] = "right";
					break;
				// reset paragraph settings ( only alignment)
				case "pard":
					$this->flags["alignment"] = "";
					break;
				// define new paragraph (for now, thats a simple break in html)
				case "par":
					// begin new line
					$this->flags["beginparagraph"] = true;
					if( $this->wantHTML) {
						$this->out .= "</div>";
					}
					break;
				// bold
				case "bnone":
					$parameter = "0";
				case "b":
					// haven'y yet figured out WHY I need a (string)-cast here ... hm
					if( (string)$parameter == "0")
						$this->flags["bold"] = false;
					else
						$this->flags["bold"] = true;
					break;

				// underlined
				case "ulnone":
					$parameter = "0";
				case "ul":
					if( (string)$parameter == "0")
						$this->flags["underlined"] = false;
					else
						$this->flags["underlined"] = true;
					break;
				
				// italic
				case "inone":
					$parameter = "0";
				case "i":
					if( (string)$parameter == "0")
						$this->flags["italic"] = false;
					else
						$this->flags["italic"] = true;
					break;

				// strikethru
				case "strikenone":
					$parameter = "0";
				case "strike":
					if( (string)$parameter == "0")
						$this->flags["strikethru"] = false;
					else
						$this->flags["strikethru"] = true;
					break;

				// reset all font modifiers and fontsize to 12
				case "plain":
					$this->flags["bold"] = false;
					$this->flags["italic"] = false;
					$this->flags["underlined"] = false;
					$this->flags["strikethru"] = false;
					$this->flags["fontsize"] = 12;

					$this->flags["subscription"] = false;
					$this->flags["superscription"] = false;
					break;

				// sub and superscription
				case "subnone":
					$parameter = "0";
				case "sub":
					if( (string)$parameter == "0")
						$this->flags["subscription"] = false;
					else
						$this->flags["subscription"] = true;
					break;

				case "supernone":
					$parameter = "0";
				case "super":
					if( (string)$parameter == "0")
						$this->flags["superscription"] = false;
					else
						$this->flags["superscription"] = true;
					break;
					
			}
		}

		/*
			Dispatch the control word to the output stream
		*/
		function flushControl() {