<?php

error_reporting(E_ALL);
ini_set('display_errors', 1);

function iseven($i) {
	return (($i % 2) ? false : true);
}

//Andrews functions
function GetByte(&$data) {
	$d = $data[0];
	$data = substr($data, 1);
	return ord($d);
}

function GetHeader(&$data) {
	$header = substr($data, 0, 20);
	$data   = substr($data, 0, 20);
	return $header;
}

function GetInt16(&$data) {
	for($i=0, $s=""; $i<2; $i++) {
		$s = dechex(GetByte($data)) . $s;
		$data = substr($data, 1);
	}
	return hexdec($s);
}

function GetInt32(&$data) {
	for($i=0, $s=""; $i<4; $i++) {
		$s = dechex(GetByte($data)) . $s;
		$data = substr($data, 1);
	}
	return hexdec($s);
}

function GetPascalString(&$data) {
	$len  = GetByte($data);
	$str  = ($len>0)?substr($data,0,$len):"";
	$data = ($len>0)?substr($data,$len):$data;
	return $str;
}

function display_data($in) {
	if ( is_array($in) ) {
		$in = join('', $in);
	}
	for($i=0; $i<strlen($in); $i++) {
		echo "\t\t\t#{$i}  ".$in[$i]." = \x" .bin2hex($in[$i])."\n";
	}
}

function display_packets($packets) {
	ksort($packets);
	foreach ( $packets AS $packet_id => $packet ) {
		echo "Packet Number ".($packet_id+1)."\n";
		display_packet($packet);
	}
}

function display_packet($packet, $bits=16, $offset=0) {
	for( $i=$offset; $i<strlen($packet); $i+=$bits ) {
		echo str_pad($i, 6, '0', STR_PAD_LEFT), ' ', 
		     str_pad(sprintf("%X", $i), 6, '0', STR_PAD_LEFT), ' ';

		$display = '';

		for ( $b=0; $b<$bits; $b++ ) {
			if ( isset($packet[($i+$b)]) ) {
/*
				if ( iseven($b) ) 
					echo ' ';
				if ( ($b % 8) == 0 ) {
					echo ' ';
					$display .= ' ';
				}
*/
				$chr = $packet[($i+$b)];
				$ord = ord($chr);
				echo str_pad(sprintf("%X", $ord), 2, '0', STR_PAD_LEFT);

				if ( preg_match('![\w\d\!@#$%^&*\(\)/\`~<>?.,;:"\'\[\]\{\}|\\_=+-]!', $chr) ) {
					$display .= $chr;
				} else {
					$display .= '.';
				}

			} else {
				echo '   ';
			}
		}
		echo ' ';
		echo str_pad($display, $bits, ' ');
		echo " \n";
	}
}

$filename = './lorem_ipsum.doc';

#echo display_packet(file_get_contents($filename), 32);

if ( ($fh = fopen($filename, 'r')) !== false ) {

	# Grab header information & place pointer at the start of the plain text
	$headers = fread($fh, 0xA00);
		
	# 1 = (ord(n)*1) ; Document has from 0 to 255 characters
	$n1 =     ( ord($headers[0x21C]) - 1 );

	# 1 = ((ord(n)-8)*256) ; Document has from 256 to 63743 characters
	$n2 =   ( ( ord($headers[0x21D]) - 8 ) * 256 );

	# 1 = ((ord(n)*256)*256) ; Document has from 63744 to 16775423 characters
	$n3 =   ( ( ord($headers[0x21E]) * 256 ) * 256 );

	# (((ord(n)*256)*256)*256) ; Document has from 16775424 to 4294965504 characters
	$n4 = ( ( ( ord($headers[0x21F]) * 256 ) * 256 ) * 256 );

	# Total length of text in the document
	$textLength = ($n1 + $n2 + $n3 + $n4);
		
	# Read full length of plain text into variable
	$extracted_plaintext = fread($fh, $textLength);
		
	# if you want the plain text with no formatting, do this
	echo $extracted_plaintext.PHP_EOL;
		
	fclose($fh);

}