functions-formatting.php

来自「php 开发的内容管理系统」· PHP 代码 · 共 1,037 行 · 第 1/3 页

<?php

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

		if (isset($curl{0}) && '<' != $curl{0} && $next) { // 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("/(\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|\S|\Z)/', '&#8221;$1', $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($curl, '<code') || strstr($curl, '<pre') || strstr($curl, '<kbd' || strstr($curl, '<style') || strstr($curl, '<script'))) {
			// strstr is fast
			$next = false;
		} else {
			$next = true;
		}
		$curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&#038;$1', $curl);
		$output .= $curl;
	}
	return $output;
}

function clean_pre($text) {
	$text = str_replace('<br />', '', $text);
	$text = str_replace('<p>', "\n", $text);
	$text = str_replace('</p>', '', $text);
	return $text;
}

function wpautop($pee, $br = 1) {
	$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
	$pee = preg_replace('!(<(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|math|p|h[1-6])[^>]*>)!', "\n$1", $pee); 
	$pee = preg_replace('!(</(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|math|p|h[1-6])>)!', "$1\n\n", $pee);
	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines 
	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
	$pee = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "<p>$1</p>\n", $pee); // make paragraphs, including one at the end 
	$pee = preg_replace('|<p>\s*?</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace 
	$pee = preg_replace('!<p>\s*(</?(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|hr|pre|select|form|blockquote|address|math|p|h[1-6])[^>]*>)\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*(</?(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|hr|pre|select|form|blockquote|address|math|p|h[1-6])[^>]*>)!', "$1", $pee);
	$pee = preg_replace('!(</?(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|math|p|h[1-6])[^>]*>)\s*</p>!', "$1", $pee); 
	if ($br) $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
	$pee = preg_replace('!(</?(?:table|thead|tfoot|caption|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|math|p|h[1-6])[^>]*>)\s*<br />!', "$1", $pee);
	$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)>)!', '$1', $pee);
	$pee = preg_replace('!(<pre.*?>)(.*?)</pre>!ise', " stripslashes('$1') .  stripslashes(clean_pre('$2'))  . '</pre>' ", $pee);
	
	return $pee; 
}


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 wp_specialchars( $text, $quotes = 0 ) {
	// Like htmlspecialchars except don't double-encode HTML entities
	$text = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/', '&#038;$1', $text);
	$text = str_replace('<', '&lt;', $text);
	$text = str_replace('>', '&gt;', $text);
	if ( 'double' === $quotes ) {
		$text = str_replace('"', '&quot;', $text);
	} elseif ( 'single' === $quotes ) {
		$text = str_replace("'", '&#039;', $text);
	} elseif ( $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 ( !preg_match('/[\x80-\xff]/', $string) )
		return $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(135) => '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(197).chr(129) => 'L',
		chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
		chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
		chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
		chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
		chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
		chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
		chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
		chr(197).chr(144) => 'O', chr(197).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_user( $username, $strict = false ) {
	$raw_username = $username;
	$username = strip_tags($username);
	// Kill octets
	$username = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $username);
	$username = preg_replace('/&.+?;/', '', $username); // Kill entities

	// If strict, reduce to ASCII for max portability.
	if ( $strict )
		$username = preg_replace('|[^a-z0-9 _.\-@]|i', '', $username);

	return apply_filters('sanitize_user', $username, $raw_username, $strict);
}

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);
	// 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);

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

	$title = strtolower($title);
	$title = preg_replace('/&.+?;/', '', $title); // kill entities
	$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
	$title = preg_replace('/\s+/', '-', $title);
	$title = preg_replace('|-+|', '-', $title);
	$title = trim($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;' => '',