<?php

function wptexturize($text) {
	$output = '';
	// Capture tags and everything inside them
	$textarr = preg_split("/(<.*>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE);
	$stop = count($textarr);
	$skip = 0; // loop stuff
	for($i = 0; $i < $stop; $i++) {
		$curl = $textarr [$i];

		if (isset($curl [0]) && '<' != $curl [0] && $skip == 0) { // If it's not a tag
			$curl = str_replace('---', '&#8212;', $curl);
			$curl = str_replace(' -- ', ' &#8212; ', $curl);
			$curl = str_replace('--', '&#8211;', $curl);
			$curl = str_replace('xn&#8211;', 'xn--', $curl);
			$curl = str_replace('...', '&#8230;', $curl);
			$curl = str_replace('``', '&#8220;', $curl);

			// This is a hack, look at this more later. It works pretty well though.
			$cockney = array(
				"'tain't",
				"'twere",
				"'twas",
				"'tis",
				"'twill",
				"'til",
				"'bout",
				"'nuff",
				"'round",
				"'cause"
			);
			$cockneyreplace = array(
				"&#8217;tain&#8217;t",
				"&#8217;twere",
				"&#8217;twas",
				"&#8217;tis",
				"&#8217;twill",
				"&#8217;til",
				"&#8217;bout",
				"&#8217;nuff",
				"&#8217;round",
				"&#8217;cause"
			);
			$curl = str_replace($cockney, $cockneyreplace, $curl);

			$curl = preg_replace("/'s/", '&#8217;s', $curl);
			$curl = preg_replace("/'(\d\d(?:&#8217;|')?s)/", "&#8217;$1", $curl);
			$curl = preg_replace('/(\s|\A|")\'/', '$1&#8216;', $curl);
			// $curl = preg_replace('/(\d+)"/', '$1&#8243;', $curl);

			$curl = preg_replace('/(\s|\A)("|&quot;)(?!\s)/', '$1&#8220;$3', $curl);

			$curl = preg_replace("/(\d+)'/", '$1&#8242;', $curl);
			$curl = preg_replace("/(\S)'([^'\s])/", "$1&#8217;$2", $curl);
			// $curl = preg_replace('/(\s|\A)"(?!\s)/', '$1&#8220;$2', $curl);

			$curl = preg_replace('/(\s|\A)("|&quot;)(?!\s)/', '$1&#8220;$3', $curl);

			$curl = preg_replace('/("|&quot;)(\s|\S|\Z)/', '&#8221;$2', $curl);
			$curl = preg_replace("/'([\s.]|\Z)/", '&#8217;$1', $curl);
			$curl = preg_replace("/ \(tm\)/i", ' &#8482;', $curl);
			$curl = str_replace("''", '&#8221;', $curl);

			$curl = preg_replace('/(\d+)x(\d+)/', "$1&#215;$2", $curl);
		} elseif (strstr($curl, '</') || strstr($curl, '/>')) {
			if ($skip > 0)
				$skip--;
		} elseif (strstr($curl, '<code') || strstr($curl, '<pre') || strstr($curl, '<kbd') || strstr($curl, '<style') || strstr($curl, '<script')) {
			// strstr is fast
			$skip++;
		} else {
			if (isset($curl [0]) && $curl [0] == "<" && $skip > 0)
				$skip++;
		}
		$curl = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&#038;$1', $curl);
		$output .= $curl;
	}
	return $output;
}

function clean_pre($matches) {
	if (is_array($matches))
		$text = $matches [1] . $matches [2] . "</pre>";
	else
		$text = $matches;

	/* NWM: a bit hackish? where are the slashes for double quotes added? */
	$text = str_replace('\"', '"', $text);
	$text = str_replace('<br />', '', $text);
	$text = str_replace('<p>', "\n", $text);
	$text = str_replace('</p>', '', $text);
	return $text;
}

/**
 * Replaces double line-breaks with paragraph elements.
 *
 * A group of regex replaces used to identify text formatted with newlines and
 * replace double line-breaks with HTML paragraph tags. The remaining
 * line-breaks after conversion become <<br />> tags, unless $br is set to '0'
 * or 'false'.
 *
 * @since 0.71
 *       
 * @param string $pee
 *        	The text which has to be formatted.
 * @param int|bool $br
 *        	Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
 * @return string Text which has been converted into correct paragraph tags.
 */
function wpautop($pee, $br = 1) {
	if (trim($pee) === '')
		return '';
	$pee = $pee . "\n"; // just to make things a little easier, pad the end
	$pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
	// Space things out a little
	$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|option|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
	$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
	$pee = str_replace(array(
		"\r\n",
		"\r"
	), "\n", $pee); // cross-platform newlines
	if (strpos($pee, '<object') !== false) {
		$pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
		$pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
	}
	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
	                                              // make paragraphs, including one at the end
	$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
	$pee = '';
	foreach ($pees as $tinkle)
		$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
	$pee = preg_replace('|<p>\s*</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
	$pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
	$pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
	$pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
	if ($br) {
		$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
		$pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
		$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
	}
	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
	$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
	if (strpos($pee, '<pre') !== false)
		$pee = preg_replace_callback('!(<pre[^>]*>)(.*?)</pre>!is', 'clean_pre', $pee);
	$pee = preg_replace("|\n</p>$|", '</p>', $pee);

	return $pee;
}

/**
 * Newline preservation help function for wpautop
 *
 * @since 3.1.0
 * @access private
 * @param array $matches
 *        	preg_replace_callback matches array
 * @returns string
 */
function _autop_newline_preservation_helper($matches) {
	return str_replace("\n", "<WPPreserveNewline />", $matches [0]);
}

function seems_utf8($Str) { // by bmorel at ssi dot fr
	for($i = 0; $i < strlen($Str); $i++) {
		if (ord($Str [$i]) < 0x80)
			continue; // 0bbbbbbb
		elseif ((ord($Str [$i]) & 0xE0) == 0xC0)
			$n = 1; // 110bbbbb
		elseif ((ord($Str [$i]) & 0xF0) == 0xE0)
			$n = 2; // 1110bbbb
		elseif ((ord($Str [$i]) & 0xF8) == 0xF0)
			$n = 3; // 11110bbb
		elseif ((ord($Str [$i]) & 0xFC) == 0xF8)
			$n = 4; // 111110bb
		elseif ((ord($Str [$i]) & 0xFE) == 0xFC)
			$n = 5; // 1111110b
		else
			return false; // Does not match any model
		for($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
			if ((++$i == strlen($Str)) || ((ord($Str [$i]) & 0xC0) != 0x80))
				return false;
		}
	}
	return true;
}

function fmt_escape_separator($text, $sep = '|') {
	return str_replace('|', '&#124;', $text);
}

function fmt_unescape_separator($text, $sep = '|') {
	return str_replace('&#124;', '|', $text);
}

function wp_specialchars($text, $quotes = 0) {
	// Like htmlspecialchars except don't double-encode HTML entities
	$text = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&#038;$1', $text);
	$text = str_replace('<', '&lt;', $text);
	$text = str_replace('>', '&gt;', $text);
	if ($quotes) {
		$text = str_replace('"', '&quot;', $text);
		$text = str_replace("'", '&#039;', $text);
	}

	return $text;
}

function utf8_uri_encode($utf8_string) {
	$unicode = '';
	$values = array();
	$num_octets = 1;

	for($i = 0; $i < strlen($utf8_string); $i++) {

		$value = ord($utf8_string [$i]);

		if ($value < 128) {
			$unicode .= chr($value);
		} else {
			if (count($values) == 0)
				$num_octets = ($value < 224) ? 2 : 3;

			$values [] = $value;

			if (count($values) == $num_octets) {
				if ($num_octets == 3) {
					$unicode .= '%' . dechex($values [0]) . '%' . dechex($values [1]) . '%' . dechex($values [2]);
				} else {
					$unicode .= '%' . dechex($values [0]) . '%' . dechex($values [1]);
				}

				$values = array();
				$num_octets = 1;
			}
		}
	}

	return $unicode;
}

function remove_accents($string) {
	if (seems_utf8($string)) {
		$chars = array(
			// Decompositions for Latin-1 Supplement
			chr(195) . chr(128) => 'A',
			chr(195) . chr(129) => 'A',
			chr(195) . chr(130) => 'A',
			chr(195) . chr(131) => 'A',
			chr(195) . chr(132) => 'A',
			chr(195) . chr(133) => 'A',
			chr(195) . chr(135) => 'C',
			chr(195) . chr(136) => 'E',
			chr(195) . chr(137) => 'E',
			chr(195) . chr(138) => 'E',
			chr(195) . chr(139) => 'E',
			chr(195) . chr(140) => 'I',
			chr(195) . chr(141) => 'I',
			chr(195) . chr(142) => 'I',
			chr(195) . chr(143) => 'I',
			chr(195) . chr(145) => 'N',
			chr(195) . chr(146) => 'O',
			chr(195) . chr(147) => 'O',
			chr(195) . chr(148) => 'O',
			chr(195) . chr(149) => 'O',
			chr(195) . chr(150) => 'O',
			chr(195) . chr(153) => 'U',
			chr(195) . chr(154) => 'U',
			chr(195) . chr(155) => 'U',
			chr(195) . chr(156) => 'U',
			chr(195) . chr(157) => 'Y',
			chr(195) . chr(159) => 's',
			chr(195) . chr(160) => 'a',
			chr(195) . chr(161) => 'a',
			chr(195) . chr(162) => 'a',
			chr(195) . chr(163) => 'a',
			chr(195) . chr(164) => 'a',
			chr(195) . chr(165) => 'a',
			chr(195) . chr(167) => 'c',
			chr(195) . chr(168) => 'e',
			chr(195) . chr(169) => 'e',
			chr(195) . chr(170) => 'e',
			chr(195) . chr(171) => 'e',
			chr(195) . chr(172) => 'i',
			chr(195) . chr(173) => 'i',
			chr(195) . chr(174) => 'i',
			chr(195) . chr(175) => 'i',
			chr(195) . chr(177) => 'n',
			chr(195) . chr(178) => 'o',
			chr(195) . chr(179) => 'o',
			chr(195) . chr(180) => 'o',
			chr(195) . chr(181) => 'o',
			chr(195) . chr(182) => 'o',
			chr(195) . chr(182) => 'o',
			chr(195) . chr(185) => 'u',
			chr(195) . chr(186) => 'u',
			chr(195) . chr(187) => 'u',
			chr(195) . chr(188) => 'u',
			chr(195) . chr(189) => 'y',
			chr(195) . chr(191) => 'y',
			// Decompositions for Latin Extended-A
			chr(196) . chr(128) => 'A',
			chr(196) . chr(129) => 'a',
			chr(196) . chr(130) => 'A',
			chr(196) . chr(131) => 'a',
			chr(196) . chr(132) => 'A',
			chr(196) . chr(133) => 'a',
			chr(196) . chr(134) => 'C',
			chr(196) . chr(134) => 'c',
			chr(196) . chr(136) => 'C',
			chr(196) . chr(137) => 'c',
			chr(196) . chr(138) => 'C',
			chr(196) . chr(139) => 'c',
			chr(196) . chr(140) => 'C',
			chr(196) . chr(141) => 'c',
			chr(196) . chr(142) => 'D',
			chr(196) . chr(143) => 'd',
			chr(196) . chr(144) => 'D',
			chr(196) . chr(145) => 'd',
			chr(196) . chr(146) => 'E',
			chr(196) . chr(147) => 'e',
			chr(196) . chr(148) => 'E',
			chr(196) . chr(149) => 'e',
			chr(196) . chr(150) => 'E',
			chr(196) . chr(151) => 'e',
			chr(196) . chr(152) => 'E',
			chr(196) . chr(153) => 'e',
			chr(196) . chr(154) => 'E',
			chr(196) . chr(155) => 'e',
			chr(196) . chr(156) => 'G',
			chr(196) . chr(157) => 'g',
			chr(196) . chr(158) => 'G',
			chr(196) . chr(159) => 'g',
			chr(196) . chr(160) => 'G',
			chr(196) . chr(161) => 'g',
			chr(196) . chr(162) => 'G',
			chr(196) . chr(163) => 'g',
			chr(196) . chr(164) => 'H',
			chr(196) . chr(165) => 'h',
			chr(196) . chr(166) => 'H',
			chr(196) . chr(167) => 'h',
			chr(196) . chr(168) => 'I',
			chr(196) . chr(169) => 'i',
			chr(196) . chr(170) => 'I',
			chr(196) . chr(171) => 'i',
			chr(196) . chr(172) => 'I',
			chr(196) . chr(173) => 'i',
			chr(196) . chr(174) => 'I',
			chr(196) . chr(175) => 'i',
			chr(196) . chr(176) => 'I',
			chr(196) . chr(177) => 'i',
			chr(196) . chr(178) => 'IJ',
			chr(196) . chr(179) => 'ij',
			chr(196) . chr(180) => 'J',
			chr(196) . chr(181) => 'j',
			chr(196) . chr(182) => 'K',
			chr(196) . chr(183) => 'k',
			chr(196) . chr(184) => 'k',
			chr(196) . chr(185) => 'L',
			chr(196) . chr(186) => 'l',
			chr(196) . chr(187) => 'L',
			chr(196) . chr(188) => 'l',
			chr(196) . chr(189) => 'L',
			chr(196) . chr(190) => 'l',
			chr(196) . chr(191) => 'L',
			chr(197) . chr(128) => 'l',
			chr(196) . chr(129) => 'L',
			chr(197) . chr(130) => 'l',
			chr(196) . chr(131) => 'N',
			chr(197) . chr(132) => 'n',
			chr(196) . chr(133) => 'N',
			chr(197) . chr(134) => 'n',
			chr(196) . chr(135) => 'N',
			chr(197) . chr(136) => 'n',
			chr(196) . chr(137) => 'N',
			chr(197) . chr(138) => 'n',
			chr(196) . chr(139) => 'N',
			chr(197) . chr(140) => 'O',
			chr(196) . chr(141) => 'o',
			chr(197) . chr(142) => 'O',
			chr(196) . chr(143) => 'o',
			chr(197) . chr(144) => 'O',
			chr(196) . chr(145) => 'o',
			chr(197) . chr(146) => 'OE',
			chr(197) . chr(147) => 'oe',
			chr(197) . chr(148) => 'R',
			chr(197) . chr(149) => 'r',
			chr(197) . chr(150) => 'R',
			chr(197) . chr(151) => 'r',
			chr(197) . chr(152) => 'R',
			chr(197) . chr(153) => 'r',
			chr(197) . chr(154) => 'S',
			chr(197) . chr(155) => 's',
			chr(197) . chr(156) => 'S',
			chr(197) . chr(157) => 's',
			chr(197) . chr(158) => 'S',
			chr(197) . chr(159) => 's',
			chr(197) . chr(160) => 'S',
			chr(197) . chr(161) => 's',
			chr(197) . chr(162) => 'T',
			chr(197) . chr(163) => 't',
			chr(197) . chr(164) => 'T',
			chr(197) . chr(165) => 't',
			chr(197) . chr(166) => 'T',
			chr(197) . chr(167) => 't',
			chr(197) . chr(168) => 'U',
			chr(197) . chr(169) => 'u',
			chr(197) . chr(170) => 'U',
			chr(197) . chr(171) => 'u',
			chr(197) . chr(172) => 'U',
			chr(197) . chr(173) => 'u',
			chr(197) . chr(174) => 'U',
			chr(197) . chr(175) => 'u',
			chr(197) . chr(176) => 'U',
			chr(197) . chr(177) => 'u',
			chr(197) . chr(178) => 'U',
			chr(197) . chr(179) => 'u',
			chr(197) . chr(180) => 'W',
			chr(197) . chr(181) => 'w',
			chr(197) . chr(182) => 'Y',
			chr(197) . chr(183) => 'y',
			chr(197) . chr(184) => 'Y',
			chr(197) . chr(185) => 'Z',
			chr(197) . chr(186) => 'z',
			chr(197) . chr(187) => 'Z',
			chr(197) . chr(188) => 'z',
			chr(197) . chr(189) => 'Z',
			chr(197) . chr(190) => 'z',
			chr(197) . chr(191) => 's',
			// Euro Sign
			chr(226) . chr(130) . chr(172) => 'E'
		);

		$string = strtr($string, $chars);
	} else {
		// Assume ISO-8859-1 if not UTF-8
		$chars ['in'] = chr(128) . chr(131) . chr(138) . chr(142) . chr(154) . chr(158) . chr(159) . chr(162) . chr(165) . chr(181) . chr(192) . chr(193) . chr(194) . chr(195) . chr(196) . chr(197) . chr(199) . chr(200) . chr(201) . chr(202) . chr(203) . chr(204) . chr(205) . chr(206) . chr(207) . chr(209) . chr(210) . chr(211) . chr(212) . chr(213) . chr(214) . chr(216) . chr(217) . chr(218) . chr(219) . chr(220) . chr(221) . chr(224) . chr(225) . chr(226) . chr(227) . chr(228) . chr(229) . chr(231) . chr(232) . chr(233) . chr(234) . chr(235) . chr(236) . chr(237) . chr(238) . chr(239) . chr(241) . chr(242) . chr(243) . chr(244) . chr(245) . chr(246) . chr(248) . chr(249) . chr(250) . chr(251) . chr(252) . chr(253) . chr(255);

		$chars ['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";

		$string = strtr($string, $chars ['in'], $chars ['out']);
		$double_chars ['in'] = array(
			chr(140),
			chr(156),
			chr(198),
			chr(208),
			chr(222),
			chr(223),
			chr(230),
			chr(240),
			chr(254)
		);
		$double_chars ['out'] = array(
			'OE',
			'oe',
			'AE',
			'DH',
			'TH',
			'ss',
			'ae',
			'dh',
			'th'
		);
		$string = str_replace($double_chars ['in'], $double_chars ['out'], $string);
	}

	return $string;
}

function sanitize_title($title, $fallback_title = '') {
	$title = strip_tags($title);

	$title = apply_filters('sanitize_title', $title);

	if (empty($title)) {
		$title = $fallback_title;
	}

	return $title;
}

function sanitize_title_with_dashes($title) {
	$title = strip_tags($title);

	if (seems_utf8($title)) {
		if (function_exists('mb_strtolower')) {
			$title = mb_strtolower($title, 'UTF-8');
		}
		$title = utf8_uri_encode($title);
	}

	// Preserve escaped octets.
	$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
	// Remove percent signs that are not part of an octet.
	$title = str_replace('%', '', $title);
	// Restore octets.
	$title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
	// and finally: Kill octets
	$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $title);

	// remove accents
	$title = remove_accents($title);

	// title is in lower case always
	$title = strtolower($title);

	// kill entities
	$title = preg_replace('/&.+?;/', '', $title);

	// kill special chars
	$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);

	// replace spaces by dash
	$title = preg_replace('/\s+/', '-', $title);
	// Kill multiple dashes
	$title = preg_replace('|-+|', '-', $title);
	// kill dashes at beginning and end of string
	$title = trim($title, '-');

	return $title;
}

function convert_chars($content, $flag = 'obsolete') {
	// Translation of invalid Unicode references range to valid range
	$wp_htmltranswinuni = array(
		'&#128;' => '&#8364;', // the Euro sign
		'&#129;' => '',
		'&#130;' => '&#8218;', // these are Windows CP1252 specific characters
		'&#131;' => '&#402;', // they would look weird on non-Windows browsers
		'&#132;' => '&#8222;',
		'&#133;' => '&#8230;',
		'&#134;' => '&#8224;',
		'&#135;' => '&#8225;',
		'&#136;' => '&#710;',
		'&#137;' => '&#8240;',
		'&#138;' => '&#352;',
		'&#139;' => '&#8249;',
		'&#140;' => '&#338;',
		'&#141;' => '',
		'&#142;' => '&#382;',
		'&#143;' => '',
		'&#144;' => '',
		'&#145;' => '&#8216;',
		'&#146;' => '&#8217;',
		'&#147;' => '&#8220;',
		'&#148;' => '&#8221;',
		'&#149;' => '&#8226;',
		'&#150;' => '&#8211;',
		'&#151;' => '&#8212;',
		'&#152;' => '&#732;',
		'&#153;' => '&#8482;',
		'&#154;' => '&#353;',
		'&#155;' => '&#8250;',
		'&#156;' => '&#339;',
		'&#157;' => '',
		'&#158;' => '',
		'&#159;' => '&#376;'
	);

	// Remove metadata tags
	$content = preg_replace('/<title>(.+?)<\/title>/', '', $content);
	$content = preg_replace('/<category>(.+?)<\/category>/', '', $content);

	// Converts lone & characters into &#38; (a.k.a. &amp;)
	$content = preg_replace('/&([^#])(?![a-z]{1,8};)/i', '&#038;$1', $content);

	// Fix Word pasting
	$content = strtr($content, $wp_htmltranswinuni);

	// Just a little XHTML help
	$content = str_replace('<br>', '<br />', $content);
	$content = str_replace('<hr>', '<hr />', $content);

	return $content;
}

function funky_javascript_fix($text) {
	// Fixes for browsers' javascript bugs
	global $is_macIE, $is_winIE;

	if ($is_winIE || $is_macIE)
		$text = preg_replace("/\%u([0-9A-F]{4,4})/e", "'&#'.base_convert('\\1',16,10).';'", $text);

	return $text;
}

/*
 * balanceTags
 *
 * Balances Tags of string using a modified stack.
 *
 * @param text Text to be balanced
 * @return Returns balanced text
 * @author Leonard Lin (leonard@acm.org)
 * @version v1.1
 * @date November 4, 2001
 * @license GPL v2.0
 * @notes
 * @changelog
 * --- Modified by Scott Reilly (coffee2code) 02 Aug 2004
 * 1.2 ***TODO*** Make better - change loop condition to $text
 * 1.1 Fixed handling of append/stack pop order of end text
 * Added Cleaning Hooks
 * 1.0 First Version
 */
function balanceTags($text, $is_comment = 0) {

	/*
	 * if (get_settings('use_balanceTags') == 0) {
	 * return $text;
	 * }
	 */
	$tagstack = array();
	$stacksize = 0;
	$tagqueue = '';
	$newtext = '';

	// WP bug fix for comments - in case you REALLY meant to type '< !--'
	$text = str_replace('< !--', '<    !--', $text);
	// WP bug fix for LOVE <3 (and other situations with '<' before a number)
	$text = preg_replace('#<([0-9]{1})#', '&lt;$1', $text);

	while (preg_match("/<(\/?\w*)\s*([^>]*)>/", $text, $regex)) {
		$newtext .= $tagqueue;

		$i = strpos($text, $regex [0]);
		$l = strlen($regex [0]);

		// clear the shifter
		$tagqueue = '';
		// Pop or Push
		if ($regex [1] [0] == "/") { // End Tag
			$tag = strtolower(substr($regex [1], 1));
			// if too many closing tags
			if ($stacksize <= 0) {
				$tag = '';
				// or close to be safe $tag = '/' . $tag;
			} // if stacktop value = tag close value then pop
			else if ($tagstack [$stacksize - 1] == $tag) { // found closing tag
				$tag = '</' . $tag . '>'; // Close Tag
				                          // Pop
				array_pop($tagstack);
				$stacksize--;
			} else { // closing tag not at top, search for it
				for($j = $stacksize - 1; $j >= 0; $j--) {
					if ($tagstack [$j] == $tag) {
						// add tag to tagqueue
						for($k = $stacksize - 1; $k >= $j; $k--) {
							$tagqueue .= '</' . array_pop($tagstack) . '>';
							$stacksize--;
						}
						break;
					}
				}
				$tag = '';
			}
		} else { // Begin Tag
			$tag = strtolower($regex [1]);

			// Tag Cleaning

			// If self-closing or '', don't do anything.
			if ((substr($regex [2], -1) == '/') || ($tag == '')) {
			} // ElseIf it's a known single-entity tag but it doesn't close itself, do so
			elseif ($tag == 'br' || $tag == 'img' || $tag == 'hr' || $tag == 'input') {
				$regex [2] .= '/';
			} else { // Push the tag onto the stack
			         // If the top of the stack is the same as the tag we want to push, close previous tag
				if (($stacksize > 0) && ($tag != 'div') && ($tagstack [$stacksize - 1] == $tag)) {
					$tagqueue = '</' . array_pop($tagstack) . '>';
					$stacksize--;
				}
				$stacksize = array_push($tagstack, $tag);
			}

			// Attributes
			$attributes = $regex [2];
			if ($attributes) {
				$attributes = ' ' . $attributes;
			}
			$tag = '<' . $tag . $attributes . '>';
			// If already queuing a close tag, then put this tag on, too
			if ($tagqueue) {
				$tagqueue .= $tag;
				$tag = '';
			}
		}
		$newtext .= substr($text, 0, $i) . $tag;
		$text = substr($text, $i + $l);
	}

	// Clear Tag Queue
	$newtext .= $tagqueue;

	// Add Remaining text
	$newtext .= $text;

	// Empty Stack
	while ($x = array_pop($tagstack)) {
		$newtext .= '</' . $x . '>'; // Add remaining tags to close
	}

	// WP fix for the bug with HTML comments
	$newtext = str_replace("< !--", "<!--", $newtext);
	$newtext = str_replace("<    !--", "< !--", $newtext);

	return $newtext;
}

function format_to_edit($content) {
	$content = apply_filters('format_to_edit', $content);
	$content = htmlspecialchars($content);
	return $content;
}

function format_to_post($content) {
	global $wpdb;
	$content = apply_filters('format_to_post', $content);
	return $content;
}

function zeroise($number, $threshold) { // function to add leading zeros when necessary
	return sprintf('%0' . $threshold . 's', $number);
}

function backslashit($string) {
	$string = preg_replace('/([a-z])/i', '\\\\\1', $string);
	return $string;
}

function trailingslashit($string) {
	if ('/' != substr($string, -1)) {
		$string .= '/';
	}
	return $string;
}

function addslashes_gpc($gpc) {
	if (!get_magic_quotes_gpc()) {
		$gpc = addslashes($gpc);
	}
	return $gpc;
}

function antispambot($emailaddy, $mailto = 0) {
	$emailNOSPAMaddy = '';
	srand((float) microtime() * 1000000);
	for($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
		$j = floor(rand(0, 1 + $mailto));
		if ($j == 0) {
			$emailNOSPAMaddy .= '&#' . ord(substr($emailaddy, $i, 1)) . ';';
		} elseif ($j == 1) {
			$emailNOSPAMaddy .= substr($emailaddy, $i, 1);
		} elseif ($j == 2) {
			$emailNOSPAMaddy .= '%' . zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
		}
	}
	$emailNOSPAMaddy = str_replace('@', '&#64;', $emailNOSPAMaddy);
	return $emailNOSPAMaddy;
}

function make_clickable($ret) {
	$ret = ' ' . $ret . ' ';
	$ret = preg_replace("#([\s>])(https?)://([^\s<>{}()]+[^\s.,<>{}()])#i", "$1<a href='$2://$3' rel='nofollow'>$2://$3</a>", $ret);
	$ret = preg_replace("#(\s)www\.([a-z0-9\-]+)\.([a-z0-9\-.\~]+)((?:/[^ <>{}()\n\r]*[^., <>{}()\n\r]?)?)#i", "$1<a href='http://www.$2.$3$4' rel='nofollow'>www.$2.$3$4</a>", $ret);
	$ret = preg_replace("#(\s)([a-z0-9\-_.]+)@([^,< \n\r]+)#i", "$1<a href=\"mailto:$2@$3\">$2@$3</a>", $ret);
	$ret = trim($ret);
	return $ret;
}

function wp_rel_nofollow($text) {
	$text = preg_replace('|<a (.+?)>|i', '<a $1 rel="nofollow">', $text);
	return $text;
}

/*
 * function convert_smilies($text) {
 * global $wp_smiliessearch, $wp_smiliesreplace;
 * $output = '';
 * if (get_settings('use_smilies')) {
 * // HTML loop taken from texturize function, could possible be consolidated
 * $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
 * $stop = count($textarr);// loop stuff
 * for ($i = 0; $i < $stop; $i++) {
 * $content = $textarr[$i];
 * if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag
 * $content = str_replace($wp_smiliessearch, $wp_smiliesreplace, $content);
 * }
 * $output .= $content;
 * }
 * } else {
 * // return default text.
 * $output = $text;
 * }
 * return $output;
 * }
 */
function is_email($user_email) {
	$chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i";
	if (strstr($user_email, '@') && strstr($user_email, '.')) {
		if (preg_match($chars, $user_email)) {
			return true;
		} else {
			return false;
		}
	} else {
		return false;
	}
}

function strip_all_but_one_link($text, $mylink) {
	$match_link = '#(<a.+?href.+?' . '>)(.+?)(</a>)#';
	preg_match_all($match_link, $text, $matches);
	$count = count($matches [0]);
	for($i = 0; $i < $count; $i++) {
		if (!strstr($matches [0] [$i], $mylink)) {
			$text = str_replace($matches [0] [$i], $matches [2] [$i], $text);
		}
	}
	return $text;
}

// used by wp-mail to handle charsets in email subjects
function wp_iso_descrambler($string) {
	/* this may only work with iso-8859-1, I'm afraid */
	if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
		return $string;
	} else {
		$subject = str_replace('_', ' ', $matches [2]);
		$subject = preg_replace('#\=([0-9a-f]{2})#ei', "chr(hexdec(strtolower('$1')))", $subject);
		return $subject;
	}
}

// give it a date, it will give you the same date as GMT
function get_gmt_from_date($string) {
	// note: this only substracts $time_difference from the given date
	preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches);
	$string_time = gmmktime($matches [4], $matches [5], $matches [6], $matches [2], $matches [3], $matches [1]);
	$string_gmt = gmdate('Y-m-d H:i:s', $string_time - get_settings('gmt_offset') * 3600);
	return $string_gmt;
}

// give it a GMT date, it will give you the same date with $time_difference added
function get_date_from_gmt($string) {
	// note: this only adds $time_difference to the given date
	preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches);
	$string_time = gmmktime($matches [4], $matches [5], $matches [6], $matches [2], $matches [3], $matches [1]);
	$string_localtime = gmdate('Y-m-d H:i:s', $string_time + get_settings('gmt_offset') * 3600);
	return $string_localtime;
}

// computes an offset in seconds from an iso8601 timezone
function iso8601_timezone_to_offset($timezone) {
	// $timezone is either 'Z' or '[+|-]hhmm'
	if ($timezone == 'Z') {
		$offset = 0;
	} else {
		$sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
		$hours = intval(substr($timezone, 1, 2));
		$minutes = intval(substr($timezone, 3, 4)) / 60;
		$offset = $sign * 3600 * ($hours + $minutes);
	}
	return $offset;
}

// converts an iso8601 date to MySQL DateTime format used by post_date[_gmt]
function iso8601_to_datetime($date_string, $timezone = USER) {
	if ($timezone == GMT) {
		preg_match('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', $date_string, $date_bits);
		if (!empty($date_bits [7])) { // we have a timezone, so let's compute an offset
			$offset = iso8601_timezone_to_offset($date_bits [7]);
		} else { // we don't have a timezone, so we assume user local timezone (not server's!)
			$offset = 3600 * get_settings('gmt_offset');
		}
		$timestamp = gmmktime($date_bits [4], $date_bits [5], $date_bits [6], $date_bits [2], $date_bits [3], $date_bits [1]);
		$timestamp -= $offset;
		return gmdate('Y-m-d H:i:s', $timestamp);
	} elseif ($timezone == USER) {
		return preg_replace('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', '$1-$2-$3 $4:$5:$6', $date_string);
	}
}

function popuplinks($text) {
	// Comment text in popup windows should be filtered through this.
	// Right now it's a moderately dumb function, ideally it would detect whether
	// a target or rel attribute was already there and adjust its actions accordingly.
	$text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
	return $text;
}

function sanitize_email($email) {
	return preg_replace('/[^a-z0-9+_.@-]/i', '', $email);
}

function human_time_diff($from, $to = '') {
	if (empty($to))
		$to = time();
	$diff = (int) abs($to - $from);
	if ($diff <= 3600) {
		$mins = round($diff / 60);
		if ($mins <= 1)
			$since = __('1 min');
		else
			$since = sprintf(__('%s mins'), $mins);
	} else if (($diff <= 86400) && ($diff > 3600)) {
		$hours = round($diff / 3600);
		if ($hours <= 1)
			$since = __('1 hour');
		else
			$since = sprintf(__('%s hours'), $hours);
	} elseif ($diff >= 86400) {
		$days = round($diff / 86400);
		if ($days <= 1)
			$since = __('1 day');
		else
			$since = sprintf(__('%s days'), $days);
	}
	return $since;
}

function wp_trim_excerpt($text) { // Fakes an excerpt if needed
	global $post;
	if ('' == $text) {
		$text = $post->post_content;
		$text = apply_filters('the_content', $text);
		$text = str_replace(']]>', ']]&gt;', $text);
		$text = strip_tags($text);
		$excerpt_length = 55;
		$words = explode(' ', $text, $excerpt_length + 1);
		if (count($words) > $excerpt_length) {
			array_pop($words);
			array_push($words, '[...]');
			$text = implode(' ', $words);
		}
	}
	return $text;
}

function ent2ncr($text) {
	$to_ncr = array(
		'&quot;' => '&#34;',
		'&amp;' => '&#38;',
		'&frasl;' => '&#47;',
		'&lt;' => '&#60;',
		'&gt;' => '&#62;',
		'&nbsp;' => '&#160;',
		'&iexcl;' => '&#161;',
		'&cent;' => '&#162;',
		'&pound;' => '&#163;',
		'&curren;' => '&#164;',
		'&yen;' => '&#165;',
		'|' => '&#166;',
		'&brvbar;' => '&#166;',
		'&brkbar;' => '&#166;',
		'&sect;' => '&#167;',
		'&uml;' => '&#168;',
		'&die;' => '&#168;',
		'&copy;' => '&#169;',
		'&ordf;' => '&#170;',
		'&laquo;' => '&#171;',
		'&not;' => '&#172;',
		'&shy;' => '&#173;',
		'&reg;' => '&#174;',
		'&macr;' => '&#175;',
		'&hibar;' => '&#175;',
		'&deg;' => '&#176;',
		'&plusmn;' => '&#177;',
		'&sup2;' => '&#178;',
		'&sup3;' => '&#179;',
		'&acute;' => '&#180;',
		'&micro;' => '&#181;',
		'&para;' => '&#182;',
		'&middot;' => '&#183;',
		'&cedil;' => '&#184;',
		'&sup1;' => '&#185;',
		'&ordm;' => '&#186;',
		'&raquo;' => '&#187;',
		'&frac14;' => '&#188;',
		'&frac12;' => '&#189;',
		'&frac34;' => '&#190;',
		'&iquest;' => '&#191;',
		'&Agrave;' => '&#192;',
		'&Aacute;' => '&#193;',
		'&Acirc;' => '&#194;',
		'&Atilde;' => '&#195;',
		'&Auml;' => '&#196;',
		'&Aring;' => '&#197;',
		'&AElig;' => '&#198;',
		'&Ccedil;' => '&#199;',
		'&Egrave;' => '&#200;',
		'&Eacute;' => '&#201;',
		'&Ecirc;' => '&#202;',
		'&Euml;' => '&#203;',
		'&Igrave;' => '&#204;',
		'&Iacute;' => '&#205;',
		'&Icirc;' => '&#206;',
		'&Iuml;' => '&#207;',
		'&ETH;' => '&#208;',
		'&Ntilde;' => '&#209;',
		'&Ograve;' => '&#210;',
		'&Oacute;' => '&#211;',
		'&Ocirc;' => '&#212;',
		'&Otilde;' => '&#213;',
		'&Ouml;' => '&#214;',
		'&times;' => '&#215;',
		'&Oslash;' => '&#216;',
		'&Ugrave;' => '&#217;',
		'&Uacute;' => '&#218;',
		'&Ucirc;' => '&#219;',
		'&Uuml;' => '&#220;',
		'&Yacute;' => '&#221;',
		'&THORN;' => '&#222;',
		'&szlig;' => '&#223;',
		'&agrave;' => '&#224;',
		'&aacute;' => '&#225;',
		'&acirc;' => '&#226;',
		'&atilde;' => '&#227;',
		'&auml;' => '&#228;',
		'&aring;' => '&#229;',
		'&aelig;' => '&#230;',
		'&ccedil;' => '&#231;',
		'&egrave;' => '&#232;',
		'&eacute;' => '&#233;',
		'&ecirc;' => '&#234;',
		'&euml;' => '&#235;',
		'&igrave;' => '&#236;',
		'&iacute;' => '&#237;',
		'&icirc;' => '&#238;',
		'&iuml;' => '&#239;',
		'&eth;' => '&#240;',
		'&ntilde;' => '&#241;',
		'&ograve;' => '&#242;',
		'&oacute;' => '&#243;',
		'&ocirc;' => '&#244;',
		'&otilde;' => '&#245;',
		'&ouml;' => '&#246;',
		'&divide;' => '&#247;',
		'&oslash;' => '&#248;',
		'&ugrave;' => '&#249;',
		'&uacute;' => '&#250;',
		'&ucirc;' => '&#251;',
		'&uuml;' => '&#252;',
		'&yacute;' => '&#253;',
		'&thorn;' => '&#254;',
		'&yuml;' => '&#255;',
		'&OElig;' => '&#338;',
		'&oelig;' => '&#339;',
		'&Scaron;' => '&#352;',
		'&scaron;' => '&#353;',
		'&Yuml;' => '&#376;',
		'&fnof;' => '&#402;',
		'&circ;' => '&#710;',
		'&tilde;' => '&#732;',
		'&Alpha;' => '&#913;',
		'&Beta;' => '&#914;',
		'&Gamma;' => '&#915;',
		'&Delta;' => '&#916;',
		'&Epsilon;' => '&#917;',
		'&Zeta;' => '&#918;',
		'&Eta;' => '&#919;',
		'&Theta;' => '&#920;',
		'&Iota;' => '&#921;',
		'&Kappa;' => '&#922;',
		'&Lambda;' => '&#923;',
		'&Mu;' => '&#924;',
		'&Nu;' => '&#925;',
		'&Xi;' => '&#926;',
		'&Omicron;' => '&#927;',
		'&Pi;' => '&#928;',
		'&Rho;' => '&#929;',
		'&Sigma;' => '&#931;',
		'&Tau;' => '&#932;',
		'&Upsilon;' => '&#933;',
		'&Phi;' => '&#934;',
		'&Chi;' => '&#935;',
		'&Psi;' => '&#936;',
		'&Omega;' => '&#937;',
		'&alpha;' => '&#945;',
		'&beta;' => '&#946;',
		'&gamma;' => '&#947;',
		'&delta;' => '&#948;',
		'&epsilon;' => '&#949;',
		'&zeta;' => '&#950;',
		'&eta;' => '&#951;',
		'&theta;' => '&#952;',
		'&iota;' => '&#953;',
		'&kappa;' => '&#954;',
		'&lambda;' => '&#955;',
		'&mu;' => '&#956;',
		'&nu;' => '&#957;',
		'&xi;' => '&#958;',
		'&omicron;' => '&#959;',
		'&pi;' => '&#960;',
		'&rho;' => '&#961;',
		'&sigmaf;' => '&#962;',
		'&sigma;' => '&#963;',
		'&tau;' => '&#964;',
		'&upsilon;' => '&#965;',
		'&phi;' => '&#966;',
		'&chi;' => '&#967;',
		'&psi;' => '&#968;',
		'&omega;' => '&#969;',
		'&thetasym;' => '&#977;',
		'&upsih;' => '&#978;',
		'&piv;' => '&#982;',
		'&ensp;' => '&#8194;',
		'&emsp;' => '&#8195;',
		'&thinsp;' => '&#8201;',
		'&zwnj;' => '&#8204;',
		'&zwj;' => '&#8205;',
		'&lrm;' => '&#8206;',
		'&rlm;' => '&#8207;',
		'&ndash;' => '&#8211;',
		'&mdash;' => '&#8212;',
		'&lsquo;' => '&#8216;',
		'&rsquo;' => '&#8217;',
		'&sbquo;' => '&#8218;',
		'&ldquo;' => '&#8220;',
		'&rdquo;' => '&#8221;',
		'&bdquo;' => '&#8222;',
		'&dagger;' => '&#8224;',
		'&Dagger;' => '&#8225;',
		'&bull;' => '&#8226;',
		'&hellip;' => '&#8230;',
		'&permil;' => '&#8240;',
		'&prime;' => '&#8242;',
		'&Prime;' => '&#8243;',
		'&lsaquo;' => '&#8249;',
		'&rsaquo;' => '&#8250;',
		'&oline;' => '&#8254;',
		'&frasl;' => '&#8260;',
		'&euro;' => '&#8364;',
		'&image;' => '&#8465;',
		'&weierp;' => '&#8472;',
		'&real;' => '&#8476;',
		'&trade;' => '&#8482;',
		'&alefsym;' => '&#8501;',
		'&crarr;' => '&#8629;',
		'&lArr;' => '&#8656;',
		'&uArr;' => '&#8657;',
		'&rArr;' => '&#8658;',
		'&dArr;' => '&#8659;',
		'&hArr;' => '&#8660;',
		'&forall;' => '&#8704;',
		'&part;' => '&#8706;',
		'&exist;' => '&#8707;',
		'&empty;' => '&#8709;',
		'&nabla;' => '&#8711;',
		'&isin;' => '&#8712;',
		'&notin;' => '&#8713;',
		'&ni;' => '&#8715;',
		'&prod;' => '&#8719;',
		'&sum;' => '&#8721;',
		'&minus;' => '&#8722;',
		'&lowast;' => '&#8727;',
		'&radic;' => '&#8730;',
		'&prop;' => '&#8733;',
		'&infin;' => '&#8734;',
		'&ang;' => '&#8736;',
		'&and;' => '&#8743;',
		'&or;' => '&#8744;',
		'&cap;' => '&#8745;',
		'&cup;' => '&#8746;',
		'&int;' => '&#8747;',
		'&there4;' => '&#8756;',
		'&sim;' => '&#8764;',
		'&cong;' => '&#8773;',
		'&asymp;' => '&#8776;',
		'&ne;' => '&#8800;',
		'&equiv;' => '&#8801;',
		'&le;' => '&#8804;',
		'&ge;' => '&#8805;',
		'&sub;' => '&#8834;',
		'&sup;' => '&#8835;',
		'&nsub;' => '&#8836;',
		'&sube;' => '&#8838;',
		'&supe;' => '&#8839;',
		'&oplus;' => '&#8853;',
		'&otimes;' => '&#8855;',
		'&perp;' => '&#8869;',
		'&sdot;' => '&#8901;',
		'&lceil;' => '&#8968;',
		'&rceil;' => '&#8969;',
		'&lfloor;' => '&#8970;',
		'&rfloor;' => '&#8971;',
		'&lang;' => '&#9001;',
		'&rang;' => '&#9002;',
		'&larr;' => '&#8592;',
		'&uarr;' => '&#8593;',
		'&rarr;' => '&#8594;',
		'&darr;' => '&#8595;',
		'&harr;' => '&#8596;',
		'&loz;' => '&#9674;',
		'&spades;' => '&#9824;',
		'&clubs;' => '&#9827;',
		'&hearts;' => '&#9829;',
		'&diams;' => '&#9830;'
	);

	foreach ($to_ncr as $entity => $ncr) {
		$text = str_replace($entity, $ncr, $text);
	}
	return $text;
}

?>
