WordPress/wp-includes/functions-formatting.php
2004-02-09 06:57:02 +00:00

400 lines
14 KiB
PHP

<?php
function wptexturize($text) {
$output = "";
$textarr = preg_split("/(<.*>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
$stop = count($textarr); $next = true; // loop stuff
for ($i = 0; $i < $stop; $i++) {
$curl = $textarr[$i];
if (!strstr($_SERVER['HTTP_USER_AGENT'], 'Gecko')) {
$curl = str_replace('<q>', '&#8220;', $curl);
$curl = str_replace('</q>', '&#8221;', $curl);
}
if (isset($curl{0}) && '<' != $curl{0} && $next) { // If it's not a tag
$curl = str_replace('---', '&#8212;', $curl);
$curl = str_replace('--', '&#8211;', $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");
$cockneyreplace = array("&#8217;tain&#8217;t","&#8217;twere","&#8217;twas","&#8217;tis","&#8217;twill","&#8217;til","&#8217;bout","&#8217;nuff","&#8217;round");
$curl = str_replace($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&Prime;", $curl);
$curl = preg_replace("/(\d+)'/", "$1&prime;", $curl);
$curl = preg_replace("/(\S)'([^'\s])/", "$1&#8217;$2", $curl);
$curl = preg_replace('/"([\s.,!?;:&\']|\Z)/', '&#8221;$1', $curl);
$curl = preg_replace('/(\s|\A)"/', '$1&#8220;', $curl);
$curl = preg_replace("/'([\s.]|\Z)/", '&#8217;$1', $curl);
$curl = preg_replace("/\(tm\)/i", '&#8482;', $curl);
$curl = preg_replace("/\(c\)/i", '&#169;', $curl);
$curl = preg_replace("/\(r\)/i", '&#174;', $curl);
$curl = preg_replace('/&([^#])(?![a-z]{1,8};)/', '&#038;$1', $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;
}
$output .= $curl;
}
return $output;
}
function wpautop($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);
$pee = preg_replace('!(<(?:table|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|p|h[1-6])[^>]*>)!', "\n$1", $pee); // Space things out a little
$pee = preg_replace('!(</(?:table|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|p|h[1-6])>)!', "$1\n", $pee); // Space things out a little
$pee = preg_replace("/(\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', "\t<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|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|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|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|p|h[1-6])[^>]*>)!', "$1", $pee);
$pee = preg_replace('!(</?(?:table|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|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|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|p|h[1-6])[^>]*>)\s*<br />!', "$1", $pee);
$pee = preg_replace('!<br />(\s*</?(?:p|li|div|th|pre|td|ul|ol)>)!', '$1', $pee);
$pee = preg_replace('/&([^#])(?![a-z]{1,8};)/', '&#038;$1', $pee);
return $pee;
}
function sanitize_title($title) {
$title = strtolower($title);
$title = preg_replace('/&.+?;/', '', $title); // kill entities
$title = preg_replace('/[^a-z0-9 -]/', '', $title);
$title = preg_replace('/\s+/', ' ', $title);
$title = trim($title);
$title = str_replace(' ', '-', $title);
$title = preg_replace('|-+|', '-', $title);
return $title;
}
function convert_chars($content, $flag='obsolete attribute left there for backwards compatibility') { // html/unicode entities output
global $use_htmltrans, $wp_htmltrans, $wp_htmltranswinuni;
// removes metadata tags
$content = preg_replace('/<title>(.+?)<\/title>/','',$content);
$content = preg_replace('/<category>(.+?)<\/category>/','',$content);
if ($use_htmltrans) {
// converts lone & characters into &#38; (a.k.a. &amp;)
$content = preg_replace('/&[^#](?![a-z]*;)/ie', '"&#38;".substr("\0",1)', $content);
// converts HTML-entities to their display values in order to convert them again later
$content = preg_replace('/['.chr(127).'-'.chr(255).']/e', '"&#".ord(\'\0\').";"', $content );
$content = strtr($content, $wp_htmltrans);
// now converting: Windows CP1252 => Unicode (valid HTML)
// (if you've ever pasted text from MSWord, you'll understand)
$content = strtr($content, $wp_htmltranswinuni);
}
// you can delete these 2 lines if you don't like <br /> and <hr />
$content = str_replace("<br>","<br />",$content);
$content = str_replace("<hr>","<hr />",$content);
return $content;
}
/**
** sanitise HTML attributes, remove frame/applet/*script/mouseovers,etc. tags
** so that this kind of thing cannot be done:
** This is how we can do <b onmouseover="alert('badbadbad')">bad stuff</b>!
**/
function sanitise_html_attributes($text) {
$text = preg_replace('#(([\s"\'])on[a-z]{1,}|style|class|id)="(.*?)"#i', '$1', $text);
$text = preg_replace('#(([\s"\'])on[a-z]{1,}|style|class|id)=\'(.*?)\'#i', '$1', $text);
$text = preg_replace('#(([\s"\'])on[a-z]{1,}|style|class|id)[ \t]*=[ \t]*([^ \t\>]*?)#i', '$1', $text);
$text = preg_replace('#([a-z]{1,})="(( |\t)*?)(javascript|vbscript|about):(.*?)"#i', '$1=""', $text);
$text = preg_replace('#([a-z]{1,})=\'(( |\t)*?)(javascript|vbscript|about):(.*?)\'#i', '$1=""', $text);
$text = preg_replace('#\<(\/{0,1})([a-z]{0,2})(frame|applet)(.*?)\>#i', '', $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
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) {
global $use_balanceTags;
if ($is_comment) {
$text = sanitise_html_attributes($text);
}
if ($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 = $newtext . $tagqueue;
$i = strpos($text,$regex[0]);
$l = strlen($tagqueue) + 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
// Push if not img or br or hr
if($tag != 'br' && $tag != 'img' && $tag != 'hr') {
$stacksize = array_push ($tagstack, $tag);
}
// Attributes
// $attributes = $regex[2];
$attributes = $regex[2];
if($attributes) {
$attributes = ' '.$attributes;
}
$tag = '<'.$tag.$attributes.'>';
}
$newtext .= substr($text,0,$i) . $tag;
$text = substr($text,$i+$l);
}
// Clear Tag Queue
$newtext = $newtext . $tagqueue;
// Add Remaining text
$newtext .= $text;
// Empty Stack
while($x = array_pop($tagstack)) {
$newtext = $newtext . '</' . $x . '>'; // Add remaining tags to close
}
# WP fix for the bug with HTML comments
$newtext = str_replace("< !--","<!--",$newtext);
$newtext = str_replace("< !--","< !--",$newtext);
return $newtext;
}
function autobrize($content) {
$content = preg_replace("/<br>\n/", "\n", $content);
$content = preg_replace("/<br \/>\n/", "\n", $content);
$content = preg_replace("/(\015\012)|(\015)|(\012)/", "<br />\n", $content);
return $content;
}
function unautobrize($content) {
$content = preg_replace("/<br>\n/", "\n", $content); //for PHP versions before 4.0.5
$content = preg_replace("/<br \/>\n/", "\n", $content);
return $content;
}
function format_to_edit($content) {
global $autobr;
$content = stripslashes($content);
if ($autobr) { $content = unautobrize($content); }
$content = htmlspecialchars($content);
return $content;
}
function format_to_post($content) {
global $post_autobr,$comment_autobr;
$content = addslashes($content);
if ($post_autobr || $comment_autobr) { $content = autobrize($content); }
return $content;
}
function zeroise($number,$threshold) { // function to add leading zeros when necessary
$l=strlen($number);
if ($l<$threshold)
for ($i=0; $i<($threshold-$l); $i=$i+1) { $number='0'.$number; }
return $number;
}
function backslashit($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 $emailNOSPAMaddy;
}
function make_clickable($text) { // original function: phpBB, extended here for AIM & ICQ
$ret = " " . $text;
$ret = preg_replace("#([\n ])([a-z]+?)://([^, <>{}\n\r]+)#i", "\\1<a href=\"\\2://\\3\" target=\"_blank\">\\2://\\3</a>", $ret);
$ret = preg_replace("#([\n ])aim:([^,< \n\r]+)#i", "\\1<a href=\"aim:goim?screenname=\\2\\3&message=Hello\">\\2\\3</a>", $ret);
$ret = preg_replace("#([\n ])icq:([^,< \n\r]+)#i", "\\1<a href=\"http://wwp.icq.com/scripts/search.dll?to=\\2\\3\">\\2\\3</a>", $ret);
$ret = preg_replace("#([\n ])www\.([a-z0-9\-]+)\.([a-z0-9\-.\~]+)((?:/[^,< \n\r]*)?)#i", "\\1<a href=\"http://www.\\2.\\3\\4\" target=\"_blank\">www.\\2.\\3\\4</a>", $ret);
$ret = preg_replace("#([\n ])([a-z0-9\-_.]+?)@([^,< \n\r]+)#i", "\\1<a href=\"mailto:\\2@\\3\">\\2@\\3</a>", $ret);
$ret = substr($ret, 1);
return $ret;
}
function convert_bbcode($content) {
global $wp_bbcode, $use_bbcode;
if ($use_bbcode) {
$content = preg_replace($wp_bbcode["in"], $wp_bbcode["out"], $content);
}
$content = convert_bbcode_email($content);
return $content;
}
function convert_bbcode_email($content) {
global $use_bbcode;
$bbcode_email["in"] = array(
'#\[email](.+?)\[/email]#eis',
'#\[email=(.+?)](.+?)\[/email]#eis'
);
$bbcode_email["out"] = array(
"'<a href=\"mailto:'.antispambot('\\1').'\">'.antispambot('\\1').'</a>'", // E-mail
"'<a href=\"mailto:'.antispambot('\\1').'\">\\2</a>'"
);
$content = preg_replace($bbcode_email["in"], $bbcode_email["out"], $content);
return $content;
}
function convert_gmcode($content) {
global $wp_gmcode, $use_gmcode;
if ($use_gmcode) {
$content = preg_replace($wp_gmcode["in"], $wp_gmcode["out"], $content);
}
return $content;
}
function convert_smilies($text) {
global $smilies_directory, $use_smilies;
global $wp_smiliessearch, $wp_smiliesreplace;
$output = '';
if ($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) {
$chars = "/^([a-z0-9_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,4}\$/i";
if(strstr($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;
}
?>