<?php
/**
- * Main Wordpress Formatting API.
+ * Main WordPress Formatting API.
*
* Handles many functions for formatting output.
*
*/
function wptexturize($text) {
global $wp_cockneyreplace;
- $next = true;
- $has_pre_parent = false;
+ static $static_setup = false, $opening_quote, $closing_quote, $default_no_texturize_tags, $default_no_texturize_shortcodes, $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements;
$output = '';
$curl = '';
$textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
$stop = count($textarr);
- // if a plugin has provided an autocorrect array, use it
- if ( isset($wp_cockneyreplace) ) {
- $cockney = array_keys($wp_cockneyreplace);
- $cockneyreplace = array_values($wp_cockneyreplace);
- } else {
- $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
- $cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
+ // No need to set up these variables more than once
+ if (!$static_setup) {
+ /* translators: opening curly quote */
+ $opening_quote = _x('“', 'opening curly quote');
+ /* translators: closing curly quote */
+ $closing_quote = _x('”', 'closing curly quote');
+
+ $default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
+ $default_no_texturize_shortcodes = array('code');
+
+ // if a plugin has provided an autocorrect array, use it
+ if ( isset($wp_cockneyreplace) ) {
+ $cockney = array_keys($wp_cockneyreplace);
+ $cockneyreplace = array_values($wp_cockneyreplace);
+ } else {
+ $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
+ $cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
+ }
+
+ $static_characters = array_merge(array('---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)'), $cockney);
+ $static_replacements = array_merge(array('—', ' — ', '–', ' – ', 'xn--', '…', $opening_quote, $closing_quote, ' ™'), $cockneyreplace);
+
+ $dynamic_characters = array('/\'(\d\d(?:’|\')?s)/', '/\'(\d+)/', '/(\s|\A|[([{<]|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A|[([{<])"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/\b(\d+)x(\d+)\b/');
+ $dynamic_replacements = array('’$1','’$1', '$1‘', '$1″', '$1′', '$1’$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '’$1', '$1×$2');
+
+ $static_setup = true;
}
- $static_characters = array_merge(array('---', ' -- ', '--', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
- $static_replacements = array_merge(array('—', ' — ', '–', 'xn--', '…', '“', '’s', '”', ' ™'), $cockneyreplace);
+ // Transform into regexp sub-expression used in _wptexturize_pushpop_element
+ // Must do this everytime in case plugins use these filters in a context sensitive manner
+ $no_texturize_tags = '(' . implode('|', apply_filters('no_texturize_tags', $default_no_texturize_tags) ) . ')';
+ $no_texturize_shortcodes = '(' . implode('|', apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes) ) . ')';
- $dynamic_characters = array('/\'(\d\d(?:’|\')?s)/', '/(\s|\A|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A)"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
- $dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1“$2', '”$1', '’$1', '$1×$2');
+ $no_texturize_tags_stack = array();
+ $no_texturize_shortcodes_stack = array();
for ( $i = 0; $i < $stop; $i++ ) {
$curl = $textarr[$i];
- if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0} && $next && !$has_pre_parent) { // If it's not a tag
+ if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0}
+ && empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) {
+ // This is not a tag, nor is the texturization disabled
// static strings
$curl = str_replace($static_characters, $static_replacements, $curl);
// regular expressions
$curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
- } elseif (strpos($curl, '<code') !== false || strpos($curl, '<kbd') !== false || strpos($curl, '<style') !== false || strpos($curl, '<script') !== false) {
- $next = false;
- } elseif (strpos($curl, '<pre') !== false) {
- $has_pre_parent = true;
- } elseif (strpos($curl, '</pre>') !== false) {
- $has_pre_parent = false;
- } else {
- $next = true;
+ } elseif (!empty($curl)) {
+ /*
+ * Only call _wptexturize_pushpop_element if first char is correct
+ * tag opening
+ */
+ if ('<' == $curl{0})
+ _wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
+ elseif ('[' == $curl{0})
+ _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
}
$curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
return $output;
}
+/**
+ * Search for disabled element tags. Push element to stack on tag open and pop
+ * on tag close. Assumes first character of $text is tag opening.
+ *
+ * @access private
+ * @since 2.9.0
+ *
+ * @param string $text Text to check. First character is assumed to be $opening
+ * @param array $stack Array used as stack of opened tag elements
+ * @param string $disabled_elements Tags to match against formatted as regexp sub-expression
+ * @param string $opening Tag opening character, assumed to be 1 character long
+ * @param string $opening Tag closing character
+ * @return object
+ */
+function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
+ // Check if it is a closing tag -- otherwise assume opening tag
+ if (strncmp($opening . '/', $text, 2)) {
+ // Opening? Check $text+1 against disabled elements
+ if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {
+ /*
+ * This disables texturize until we find a closing tag of our type
+ * (e.g. <pre>) even if there was invalid nesting before that
+ *
+ * Example: in the case <pre>sadsadasd</code>"baba"</pre>
+ * "baba" won't be texturize
+ */
+
+ array_push($stack, $matches[1]);
+ }
+ } else {
+ // Closing? Check $text+2 against disabled elements
+ $c = preg_quote($closing, '/');
+ if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {
+ $last = array_pop($stack);
+
+ // Make sure it matches the opening tag
+ if ($last != $matches[1])
+ array_push($stack, $last);
+ }
+ }
+}
+
/**
* Accepts matches array from preg_replace_callback in wpautop() or a string.
*
* @return string Text which has been converted into correct paragraph tags.
*/
function wpautop($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|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)';
+ $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
$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>([^<]+)\s*?(</(?:div|address|form)[^>]*>)!', "<p>$1</p>$2", $pee);
- $pee = preg_replace( '|<p>|', "$1<p>", $pee );
+ $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 = 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_callback('!(<pre[^>]*>)(.*?)</pre>!is', 'clean_pre', $pee );
$pee = preg_replace( "|\n</p>$|", '</p>', $pee );
- $pee = preg_replace('/<p>\s*?(' . get_shortcode_regex() . ')\s*<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone
+
+ return $pee;
+}
+
+/**
+ * Don't auto-p wrap shortcodes that stand alone
+ *
+ * Ensures that shortcodes are not wrapped in <<p>>...<</p>>.
+ *
+ * @since 2.9.0
+ *
+ * @param string $pee The content.
+ * @return string The filtered content.
+ */
+function shortcode_unautop($pee) {
+ global $shortcode_tags;
+
+ if ( !empty($shortcode_tags) && is_array($shortcode_tags) ) {
+ $tagnames = array_keys($shortcode_tags);
+ $tagregexp = join( '|', array_map('preg_quote', $tagnames) );
+ $pee = preg_replace('/<p>\\s*?(\\[(' . $tagregexp . ')\\b.*?\\/?\\](?:.+?\\[\\/\\2\\])?)\\s*<\\/p>/s', '$1', $pee);
+ }
return $pee;
}
/**
* Checks to see if a string is utf8 encoded.
*
- * @author bmorel at ssi dot fr
+ * NOTE: This function checks for 5-Byte sequences, UTF8
+ * has Bytes Sequences with a maximum length of 4.
*
+ * @author bmorel at ssi dot fr (modified)
* @since 1.2.1
*
- * @param string $Str The string to be checked
- * @return bool True if $Str fits a UTF-8 model, false otherwise.
+ * @param string $str The string to be checked
+ * @return bool True if $str fits a UTF-8 model, false otherwise.
*/
-function seems_utf8($Str) { # by bmorel at ssi dot fr
- $length = strlen($Str);
+function seems_utf8($str) {
+ $length = strlen($str);
for ($i=0; $i < $length; $i++) {
- if (ord($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
+ $c = ord($str[$i]);
+ if ($c < 0x80) $n = 0; # 0bbbbbbb
+ elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
+ elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
+ elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
+ elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
+ elseif (($c & 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 == $length) || ((ord($Str[$i]) & 0xC0) != 0x80))
- return false;
+ if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
+ return false;
}
}
return true;
* @param string $string The text which is to be encoded.
* @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
* @param string $charset Optional. The character encoding of the string. Default is false.
- * @param boolean $double_encode Optional. Whether or not to encode existing html entities. Default is false.
+ * @param boolean $double_encode Optional. Whether to encode existing html entities. Default is false.
* @return string The encoded text with HTML entities.
*/
-function wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false )
-{
+function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
// Handle double encoding ourselves
if ( !$double_encode ) {
$string = wp_specialchars_decode( $string, $_quote_style );
- $string = preg_replace( '/&(#?x?[0-9]+|[a-z]+);/i', '|wp_entity|$1|/wp_entity|', $string );
+
+ /* Critical */
+ // The previous line decodes &phrase; into &phrase; We must guarantee that &phrase; is valid before proceeding.
+ $string = wp_kses_normalize_entities($string);
+
+ // Now proceed with custom double-encoding silliness
+ $string = preg_replace( '/&(#?x?[0-9a-z]+);/i', '|wp_entity|$1|/wp_entity|', $string );
}
$string = @htmlspecialchars( $string, $quote_style, $charset );
* @since 2.8
*
* @param string $string The text which is to be decoded.
- * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
+ * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
* @return string The decoded text without HTML entities.
*/
-function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES )
-{
+function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return $string;
}
- // Match the previous behaviour of wp_specialchars() when the $quote_style is not an accepted value
+ // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
* @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
* @return string The checked text.
*/
-function wp_check_invalid_utf8( $string, $strip = false )
-{
+function wp_check_invalid_utf8( $string, $strip = false ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
}
/**
- * Filters certain characters from the file name.
+ * Sanitizes a filename replacing whitespace with dashes
*
- * Turns all strings to lowercase removing most characters except alphanumeric
- * with spaces, dashes and periods. All spaces and underscores are converted to
- * dashes. Multiple dashes are converted to a single dash. Finally, if the file
- * name ends with a dash, it is removed.
+ * Removes special characters that are illegal in filenames on certain
+ * operating systems and special characters requiring special escaping
+ * to manipulate at the command line. Replaces spaces and consecutive
+ * dashes with a single dash. Trim period, dash and underscore from beginning
+ * and end of filename.
*
* @since 2.1.0
*
- * @param string $name The file name
- * @return string Sanitized file name
- */
-function sanitize_file_name( $name ) { // Like sanitize_title, but with periods
- $name = strtolower( $name );
- $name = preg_replace('/&.+?;/', '', $name); // kill entities
- $name = str_replace( '_', '-', $name );
- $name = preg_replace('/[^a-z0-9\s-.]/', '', $name);
- $name = preg_replace('/\s+/', '-', $name);
- $name = preg_replace('|-+|', '-', $name);
- $name = trim($name, '-');
- return $name;
+ * @param string $filename The filename to be sanitized
+ * @return string The sanitized filename
+ */
+function sanitize_file_name( $filename ) {
+ $filename_raw = $filename;
+ $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));
+ $special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
+ $filename = str_replace($special_chars, '', $filename);
+ $filename = preg_replace('/[\s-]+/', '-', $filename);
+ $filename = trim($filename, '.-_');
+
+ // Split the filename into a base and extension[s]
+ $parts = explode('.', $filename);
+
+ // Return if only one extension
+ if ( count($parts) <= 2 )
+ return apply_filters('sanitize_file_name', $filename, $filename_raw);
+
+ // Process multiple extensions
+ $filename = array_shift($parts);
+ $extension = array_pop($parts);
+ $mimes = get_allowed_mime_types();
+
+ // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character
+ // long alpha string not in the extension whitelist.
+ foreach ( (array) $parts as $part) {
+ $filename .= '.' . $part;
+
+ if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
+ $allowed = false;
+ foreach ( $mimes as $ext_preg => $mime_match ) {
+ $ext_preg = '!(^' . $ext_preg . ')$!i';
+ if ( preg_match( $ext_preg, $part ) ) {
+ $allowed = true;
+ break;
+ }
+ }
+ if ( !$allowed )
+ $filename .= '_';
+ }
+ }
+ $filename .= '.' . $extension;
+
+ return apply_filters('sanitize_file_name', $filename, $filename_raw);
}
/**
*/
function sanitize_user( $username, $strict = false ) {
$raw_username = $username;
- $username = strip_tags($username);
+ $username = wp_strip_all_tags( $username );
+ $username = remove_accents( $username );
// Kill octets
- $username = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $username);
- $username = preg_replace('/&.+?;/', '', $username); // Kill entities
+ $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);
+ $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
// Consolidate contiguous whitespace
- $username = preg_replace('|\s+|', ' ', $username);
+ $username = preg_replace( '|\s+|', ' ', $username );
- return apply_filters('sanitize_user', $username, $raw_username, $strict);
+ return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
+}
+
+/**
+ * Sanitize a string key.
+ *
+ * Keys are used as internal identifiers. They should be lowercase ASCII. Dashes and underscores are allowed.
+ *
+ * @since 3.0.0
+ *
+ * @param string $key String key
+ * @return string Sanitized key
+ */
+function sanitize_key( $key ) {
+ $raw_key = $key;
+ $key = wp_strip_all_tags($key);
+ // Kill octets
+ $key = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $key);
+ $key = preg_replace('/&.+?;/', '', $key); // Kill entities
+
+ $key = preg_replace('|[^a-z0-9 _.\-@]|i', '', $key);
+
+ // Consolidate contiguous whitespace
+ $key = preg_replace('|\s+|', ' ', $key);
+
+ return apply_filters('sanitize_key', $key, $raw_key);
}
/**
* @return string The sanitized string.
*/
function sanitize_title($title, $fallback_title = '') {
+ $raw_title = $title;
$title = strip_tags($title);
- $title = apply_filters('sanitize_title', $title);
+ $title = apply_filters('sanitize_title', $title, $raw_title);
if ( '' === $title || false === $title )
$title = $fallback_title;
$title = strtolower($title);
$title = preg_replace('/&.+?;/', '', $title); // kill entities
+ $title = str_replace('.', '-', $title);
$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
$title = preg_replace('/\s+/', '-', $title);
$title = preg_replace('|-+|', '-', $title);
return $orderby;
}
+/**
+ * Santizes a html classname to ensure it only contains valid characters
+ *
+ * Strips the string down to A-Z,a-z,0-9,'-' if this results in an empty
+ * string then it will return the alternative value supplied.
+ *
+ * @todo Expand to support the full range of CDATA that a class attribute can contain.
+ *
+ * @since 2.8.0
+ *
+ * @param string $class The classname to be sanitized
+ * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string.
+ * Defaults to an empty string.
+ * @return string The sanitized value
+ */
+function sanitize_html_class( $class, $fallback = '' ) {
+ //Strip out any % encoded octets
+ $sanitized = preg_replace('|%[a-fA-F0-9][a-fA-F0-9]|', '', $class);
+
+ //Limit to A-Z,a-z,0-9,'-'
+ $sanitized = preg_replace('/[^A-Za-z0-9-]/', '', $sanitized);
+
+ if ( '' == $sanitized )
+ $sanitized = $fallback;
+
+ return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
+}
+
/**
* Converts a number of characters from a string.
*
* @return string Converted string.
*/
function convert_chars($content, $deprecated = '') {
+ if ( !empty( $deprecated ) )
+ _deprecated_argument( __FUNCTION__, '0.71' );
+
// Translation of invalid Unicode references range to valid range
$wp_htmltranswinuni = array(
'€' => '€', // the Euro sign
return $content;
}
-/**
- * Fixes javascript bugs in browsers.
- *
- * Converts unicode characters to HTML numbered entities.
- *
- * @since 1.5.0
- * @uses $is_macIE
- * @uses $is_winIE
- *
- * @param string $text Text to be made safe.
- * @return string Fixed text.
- */
-function funky_javascript_fix($text) {
- // Fixes for browsers' javascript bugs
- global $is_macIE, $is_winIE;
-
- /** @todo use preg_replace_callback() instead */
- if ( $is_winIE || $is_macIE )
- $text = preg_replace("/\%u([0-9A-F]{4,4})/e", "'&#'.base_convert('\\1',16,10).';'", $text);
-
- return $text;
-}
-
/**
* Will only balance the tags if forced to and the option is set to balance tags.
*
* @return string Balanced text.
*/
function force_balance_tags( $text ) {
- $tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';
- $single_tags = array('br', 'hr', 'img', 'input'); //Known single-entity/self-closing tags
- $nestable_tags = array('blockquote', 'div', 'span'); //Tags that can be immediately nested within themselves
-
- # WP bug fix for comments - in case you REALLY meant to type '< !--'
+ $tagstack = array();
+ $stacksize = 0;
+ $tagqueue = '';
+ $newtext = '';
+ $single_tags = array('br', 'hr', 'img', 'input'); // Known single-entity/self-closing tags
+ $nestable_tags = array('blockquote', 'div', 'span'); // Tags that can be immediately nested within themselves
+
+ // 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)
+ // WP bug fix for LOVE <3 (and other situations with '<' before a number)
$text = preg_replace('#<([0-9]{1})#', '<$1', $text);
- while (preg_match("/<(\/?\w*)\s*([^>]*)>/",$text,$regex)) {
+ while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
$newtext .= $tagqueue;
- $i = strpos($text,$regex[0]);
+ $i = strpos($text, $regex[0]);
$l = strlen($regex[0]);
// clear the shifter
$tagqueue = '';
// Pop or Push
- if ($regex[1][0] == "/") { // End Tag
+ if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
$tag = strtolower(substr($regex[1],1));
// if too many closing tags
- if($stacksize <= 0) {
+ if( $stacksize <= 0 ) {
$tag = '';
- //or close to be safe $tag = '/' . $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
+ else if ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
$tag = '</' . $tag . '>'; // Close Tag
// Pop
- array_pop ($tagstack);
+ array_pop( $tagstack );
$stacksize--;
} else { // closing tag not at top, search for it
- for ($j=$stacksize-1;$j>=0;$j--) {
- if ($tagstack[$j] == $tag) {
+ 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) . '>';
+ for ( $k = $stacksize-1; $k >= $j; $k--) {
+ $tagqueue .= '</' . array_pop( $tagstack ) . '>';
$stacksize--;
}
break;
// Tag Cleaning
// If self-closing or '', don't do anything.
- if((substr($regex[2],-1) == '/') || ($tag == '')) {
+ if ( substr($regex[2],-1) == '/' || $tag == '' ) {
+ // do nothing
}
// ElseIf it's a known single-entity tag but it doesn't close itself, do so
elseif ( in_array($tag, $single_tags) ) {
$regex[2] .= '/';
} else { // Push the tag onto the stack
// If the top of the stack is the same as the tag we want to push, close previous tag
- if (($stacksize > 0) && !in_array($tag, $nestable_tags) && ($tagstack[$stacksize - 1] == $tag)) {
+ if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
$tagqueue = '</' . array_pop ($tagstack) . '>';
$stacksize--;
}
// Attributes
$attributes = $regex[2];
- if($attributes) {
+ if( !empty($attributes) )
$attributes = ' '.$attributes;
- }
- $tag = '<'.$tag.$attributes.'>';
+
+ $tag = '<' . $tag . $attributes . '>';
//If already queuing a close tag, then put this tag on, too
- if ($tagqueue) {
+ if ( !empty($tagqueue) ) {
$tagqueue .= $tag;
$tag = '';
}
}
- $newtext .= substr($text,0,$i) . $tag;
- $text = substr($text,$i+$l);
+ $newtext .= substr($text, 0, $i) . $tag;
+ $text = substr($text, $i + $l);
}
// Clear Tag Queue
$newtext .= $text;
// Empty Stack
- while($x = array_pop($tagstack)) {
+ while( $x = array_pop($tagstack) )
$newtext .= '</' . $x . '>'; // Add remaining tags to close
- }
// WP fix for the bug with HTML comments
$newtext = str_replace("< !--","<!--",$newtext);
* @since 0.71
*
* @param string $content The text about to be edited.
- * @param bool $richedit Whether or not the $content should pass through htmlspecialchars(). Default false.
+ * @param bool $richedit Whether the $content should pass through htmlspecialchars(). Default false.
* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
*/
function format_to_edit($content, $richedit = false) {
* @return string Returns a string escaped with slashes.
*/
function addslashes_gpc($gpc) {
- global $wpdb;
-
- if (get_magic_quotes_gpc()) {
+ if ( get_magic_quotes_gpc() )
$gpc = stripslashes($gpc);
- }
- return $wpdb->escape($gpc);
+ return esc_sql($gpc);
}
/**
* @return array|string Stripped array (or string in the callback).
*/
function stripslashes_deep($value) {
- $value = is_array($value) ? array_map('stripslashes_deep', $value) : stripslashes($value);
+ if ( is_array($value) ) {
+ $value = array_map('stripslashes_deep', $value);
+ } elseif ( is_object($value) ) {
+ $vars = get_object_vars( $value );
+ foreach ($vars as $key=>$data) {
+ $value->{$key} = stripslashes_deep( $data );
+ }
+ } else {
+ $value = stripslashes($value);
+ }
+
return $value;
}
* @return string HTML A element with URI address.
*/
function _make_url_clickable_cb($matches) {
- $ret = '';
$url = $matches[2];
- $url = clean_url($url);
+
+ $url = esc_url($url);
if ( empty($url) )
return $matches[0];
- // removed trailing [.,;:] from URL
- if ( in_array(substr($url, -1), array('.', ',', ';', ':')) === true ) {
- $ret = substr($url, -1);
- $url = substr($url, 0, strlen($url)-1);
- }
- return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $ret;
+
+ return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>";
}
/**
$ret = '';
$dest = $matches[2];
$dest = 'http://' . $dest;
- $dest = clean_url($dest);
+ $dest = esc_url($dest);
if ( empty($dest) )
return $matches[0];
- // removed trailing [,;:] from URL
- if ( in_array(substr($dest, -1), array('.', ',', ';', ':')) === true ) {
+
+ // removed trailing [.,;:)] from URL
+ if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
$ret = substr($dest, -1);
$dest = substr($dest, 0, strlen($dest)-1);
}
- return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>" . $ret;
+ return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
}
/**
function make_clickable($ret) {
$ret = ' ' . $ret;
// in testing, using arrays here was found to be faster
- $ret = preg_replace_callback('#([\s>])([\w]+?://[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]*)#is', '_make_url_clickable_cb', $ret);
- $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]*)#is', '_make_web_ftp_clickable_cb', $ret);
+ $ret = preg_replace_callback('#(?<=[\s>])(\()?([\w]+?://(?:[\w\\x80-\\xff\#$%&~/=?@\[\](+-]|[.,;:](?![\s<]|(\))?([\s]|$))|(?(1)\)(?![\s<.,;:]|$)|\)))+)#is', '_make_url_clickable_cb', $ret);
+ $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret);
$ret = preg_replace_callback('#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret);
// this one is not in an array because we need it to run last, for cleanup of accidental links within links
$ret = preg_replace("#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i", "$1$3</a>", $ret);
* @return string Converted content.
*/
function wp_rel_nofollow( $text ) {
- global $wpdb;
// This is a pre save filter, so text is already escaped.
$text = stripslashes($text);
$text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
- $text = $wpdb->escape($text);
+ $text = esc_sql($text);
return $text;
}
return "<a $text rel=\"nofollow\">";
}
+/**
+ * Convert one smiley code to the icon graphic file equivalent.
+ *
+ * Looks up one smiley code in the $wpsmiliestrans global array and returns an
+ * <img> string for that smiley.
+ *
+ * @global array $wpsmiliestrans
+ * @since 2.8.0
+ *
+ * @param string $smiley Smiley code to convert to image.
+ * @return string Image string for smiley.
+ */
+function translate_smiley($smiley) {
+ global $wpsmiliestrans;
+
+ if (count($smiley) == 0) {
+ return '';
+ }
+
+ $siteurl = get_option( 'siteurl' );
+
+ $smiley = trim(reset($smiley));
+ $img = $wpsmiliestrans[$smiley];
+ $smiley_masked = esc_attr($smiley);
+
+ $srcurl = apply_filters('smilies_src', "$siteurl/wp-includes/images/smilies/$img", $img, $siteurl);
+
+ return " <img src='$srcurl' alt='$smiley_masked' class='wp-smiley' /> ";
+}
+
/**
* Convert text equivalent of smilies to images.
*
- * Will only convert smilies if the option 'use_smilies' is true and the globals
- * used in the function aren't empty.
+ * Will only convert smilies if the option 'use_smilies' is true and the global
+ * used in the function isn't empty.
*
* @since 0.71
- * @uses $wp_smiliessearch, $wp_smiliesreplace Smiley replacement arrays.
+ * @uses $wp_smiliessearch
*
* @param string $text Content to convert smilies from text.
* @return string Converted content with text smilies replaced with images.
*/
function convert_smilies($text) {
- global $wp_smiliessearch, $wp_smiliesreplace;
+ global $wp_smiliessearch;
$output = '';
- if ( get_option('use_smilies') && !empty($wp_smiliessearch) && !empty($wp_smiliesreplace) ) {
+ if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
// 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
- $content = preg_replace($wp_smiliessearch, $wp_smiliesreplace, $content);
+ $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
}
$output .= $content;
}
}
/**
- * Checks to see if the text is a valid email address.
+ * Verifies that an email is valid.
+ *
+ * Does not grok i18n domains. Not RFC compliant.
*
* @since 0.71
*
- * @param string $user_email The email address to be checked.
- * @return bool Returns true if valid, otherwise false.
+ * @param string $email Email address to verify.
+ * @param boolean $deprecated. Deprecated.
+ * @return string|bool Either false or the valid email address.
*/
-function is_email($user_email) {
- $chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i";
- if (strpos($user_email, '@') !== false && strpos($user_email, '.') !== false) {
- if (preg_match($chars, $user_email)) {
- return true;
- } else {
- return false;
+function is_email( $email, $deprecated = false ) {
+ if ( ! empty( $deprecated ) )
+ _deprecated_argument( __FUNCTION__, '3.0' );
+
+ // Test for the minimum length the email can be
+ if ( strlen( $email ) < 3 ) {
+ return apply_filters( 'is_email', false, $email, 'email_too_short' );
+ }
+
+ // Test for an @ character after the first position
+ if ( strpos( $email, '@', 1 ) === false ) {
+ return apply_filters( 'is_email', false, $email, 'email_no_at' );
+ }
+
+ // Split out the local and domain parts
+ list( $local, $domain ) = explode( '@', $email, 2 );
+
+ // LOCAL PART
+ // Test for invalid characters
+ if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
+ return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
+ }
+
+ // DOMAIN PART
+ // Test for sequences of periods
+ if ( preg_match( '/\.{2,}/', $domain ) ) {
+ return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
+ }
+
+ // Test for leading and trailing periods and whitespace
+ if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
+ return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
+ }
+
+ // Split the domain into subs
+ $subs = explode( '.', $domain );
+
+ // Assume the domain will have at least two subs
+ if ( 2 > count( $subs ) ) {
+ return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
+ }
+
+ // Loop through each sub
+ foreach ( $subs as $sub ) {
+ // Test for leading and trailing hyphens and whitespace
+ if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
+ return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
+ }
+
+ // Test for invalid characters
+ if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
+ return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
}
- } else {
- return false;
}
+
+ // Congratulations your email made it!
+ return apply_filters( 'is_email', $email, $email, null );
}
/**
* Returns a date in the GMT equivalent.
*
* Requires and returns a date in the Y-m-d H:i:s format. Simply subtracts the
- * value of the 'gmt_offset' option.
+ * value of the 'gmt_offset' option. Return format can be overridden using the
+ * $format parameter. If PHP5 is supported, the function uses the DateTime and
+ * DateTimeZone objects to respect time zone differences in DST.
*
* @since 1.2.0
*
* @uses get_option() to retrieve the the value of 'gmt_offset'.
* @param string $string The date to be converted.
+ * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
* @return string GMT version of the date provided.
*/
-function get_gmt_from_date($string) {
+function get_gmt_from_date($string, $format = 'Y-m-d H:i:s') {
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_option('gmt_offset') * 3600);
+ $tz = get_option('timezone_string');
+ if( class_exists('DateTime') && $tz ) {
+ //PHP5
+ date_default_timezone_set( $tz );
+ $datetime = new DateTime( $string );
+ $datetime->setTimezone( new DateTimeZone('UTC') );
+ $offset = $datetime->getOffset();
+ $datetime->modify( '+' . $offset / 3600 . ' hours');
+ $string_gmt = gmdate($format, $datetime->format('U'));
+
+ date_default_timezone_set('UTC');
+ }
+ else {
+ //PHP4
+ $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
+ $string_gmt = gmdate($format, $string_time - get_option('gmt_offset') * 3600);
+ }
return $string_gmt;
}
* Converts a GMT date into the correct format for the blog.
*
* Requires and returns in the Y-m-d H:i:s format. Simply adds the value of
- * gmt_offset.
+ * gmt_offset.Return format can be overridden using the $format parameter
*
* @since 1.2.0
*
* @param string $string The date to be converted.
+ * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
* @return string Formatted date relative to the GMT offset.
*/
-function get_date_from_gmt($string) {
+function get_date_from_gmt($string, $format = 'Y-m-d H:i:s') {
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_option('gmt_offset')*3600);
+ $string_localtime = gmdate($format, $string_time + get_option('gmt_offset')*3600);
return $string_localtime;
}
* @param string $email Email address to filter.
* @return string Filtered email address.
*/
-function sanitize_email($email) {
- return preg_replace('/[^a-z0-9+_.@-]/i', '', $email);
+function sanitize_email( $email ) {
+ // Test for the minimum length the email can be
+ if ( strlen( $email ) < 3 ) {
+ return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
+ }
+
+ // Test for an @ character after the first position
+ if ( strpos( $email, '@', 1 ) === false ) {
+ return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
+ }
+
+ // Split out the local and domain parts
+ list( $local, $domain ) = explode( '@', $email, 2 );
+
+ // LOCAL PART
+ // Test for invalid characters
+ $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
+ if ( '' === $local ) {
+ return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
+ }
+
+ // DOMAIN PART
+ // Test for sequences of periods
+ $domain = preg_replace( '/\.{2,}/', '', $domain );
+ if ( '' === $domain ) {
+ return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
+ }
+
+ // Test for leading and trailing periods and whitespace
+ $domain = trim( $domain, " \t\n\r\0\x0B." );
+ if ( '' === $domain ) {
+ return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
+ }
+
+ // Split the domain into subs
+ $subs = explode( '.', $domain );
+
+ // Assume the domain will have at least two subs
+ if ( 2 > count( $subs ) ) {
+ return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
+ }
+
+ // Create an array that will contain valid subs
+ $new_subs = array();
+
+ // Loop through each sub
+ foreach ( $subs as $sub ) {
+ // Test for leading and trailing hyphens
+ $sub = trim( $sub, " \t\n\r\0\x0B-" );
+
+ // Test for invalid characters
+ $sub = preg_replace( '/^[^a-z0-9-]+$/i', '', $sub );
+
+ // If there's anything left, add it to the valid subs
+ if ( '' !== $sub ) {
+ $new_subs[] = $sub;
+ }
+ }
+
+ // If there aren't 2 or more valid subs
+ if ( 2 > count( $new_subs ) ) {
+ return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
+ }
+
+ // Join valid subs into the new domain
+ $domain = join( '.', $new_subs );
+
+ // Put the email back together
+ $email = $local . '@' . $domain;
+
+ // Congratulations your email made it!
+ return apply_filters( 'sanitize_email', $email, $email, null );
}
/**
if ($mins <= 1) {
$mins = 1;
}
- $since = sprintf(__ngettext('%s min', '%s mins', $mins), $mins);
+ /* translators: min=minute */
+ $since = sprintf(_n('%s min', '%s mins', $mins), $mins);
} else if (($diff <= 86400) && ($diff > 3600)) {
$hours = round($diff / 3600);
if ($hours <= 1) {
$hours = 1;
}
- $since = sprintf(__ngettext('%s hour', '%s hours', $hours), $hours);
+ $since = sprintf(_n('%s hour', '%s hours', $hours), $hours);
} elseif ($diff >= 86400) {
$days = round($diff / 86400);
if ($days <= 1) {
$days = 1;
}
- $since = sprintf(__ngettext('%s day', '%s days', $days), $days);
+ $since = sprintf(_n('%s day', '%s days', $days), $days);
}
return $since;
}
* Generates an excerpt from the content, if needed.
*
* The excerpt word amount will be 55 words and if the amount is greater than
- * that, then the string '[...]' will be appended to the excerpt. If the string
+ * that, then the string ' [...]' will be appended to the excerpt. If the string
* is less than 55 words, then the content will be returned as is.
*
+ * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
+ * The ' [...]' string can be modified by plugins/themes using the excerpt_more filter
+ *
* @since 1.5.0
*
- * @param string $text The exerpt. If set to empty an excerpt is generated.
+ * @param string $text The excerpt. If set to empty an excerpt is generated.
* @return string The excerpt.
*/
function wp_trim_excerpt($text) {
+ $raw_excerpt = $text;
if ( '' == $text ) {
$text = get_the_content('');
$text = str_replace(']]>', ']]>', $text);
$text = strip_tags($text);
$excerpt_length = apply_filters('excerpt_length', 55);
- $words = explode(' ', $text, $excerpt_length + 1);
- if (count($words) > $excerpt_length) {
+ $excerpt_more = apply_filters('excerpt_more', ' ' . '[...]');
+ $words = preg_split("/[\n\r\t ]+/", $text, $excerpt_length + 1, PREG_SPLIT_NO_EMPTY);
+ if ( count($words) > $excerpt_length ) {
array_pop($words);
- array_push($words, '[...]');
+ $text = implode(' ', $words);
+ $text = $text . $excerpt_more;
+ } else {
$text = implode(' ', $words);
}
}
- return $text;
+ return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
}
/**
return apply_filters('htmledit_pre', $output);
}
+/**
+ * Perform a deep string replace operation to ensure the values in $search are no longer present
+ *
+ * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
+ * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
+ * str_replace would return
+ *
+ * @since 2.8.1
+ * @access private
+ *
+ * @param string|array $search
+ * @param string $subject
+ * @return string The processed string
+ */
+function _deep_replace( $search, $subject ) {
+ $found = true;
+ $subject = (string) $subject;
+ while ( $found ) {
+ $found = false;
+ foreach ( (array) $search as $val ) {
+ while ( strpos( $subject, $val ) !== false ) {
+ $found = true;
+ $subject = str_replace( $val, '', $subject );
+ }
+ }
+ }
+
+ return $subject;
+}
+
+/**
+ * Escapes data for use in a MySQL query
+ *
+ * This is just a handy shortcut for $wpdb->escape(), for completeness' sake
+ *
+ * @since 2.8.0
+ * @param string $sql Unescaped SQL data
+ * @return string The cleaned $sql
+ */
+function esc_sql( $sql ) {
+ global $wpdb;
+ return $wpdb->escape( $sql );
+}
+
/**
* Checks and cleans a URL.
*
* (the default behaviour) amperstands are also replaced. The 'clean_url' filter
* is applied to the returned cleaned URL.
*
- * @since 1.2.0
+ * @since 2.8.0
* @uses wp_kses_bad_protocol() To only permit protocols in the URL set
* via $protocols or the common ones set in the function.
*
* @param string $url The URL to be cleaned.
* @param array $protocols Optional. An array of acceptable protocols.
* Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet' if not set.
- * @param string $context Optional. How the URL will be used. Default is 'display'.
- * @return string The cleaned $url after the 'cleaned_url' filter is applied.
+ * @param string $_context Private. Use esc_url_raw() for database usage.
+ * @return string The cleaned $url after the 'clean_url' filter is applied.
*/
-function clean_url( $url, $protocols = null, $context = 'display' ) {
+function esc_url( $url, $protocols = null, $_context = 'display' ) {
$original_url = $url;
- if ('' == $url) return $url;
- $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$*\'()\\x80-\\xff]|i', '', $url);
- $strip = array('%0d', '%0a');
- $url = str_replace($strip, '', $url);
+ if ( '' == $url )
+ return $url;
+ $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url);
+ $strip = array('%0d', '%0a', '%0D', '%0A');
+ $url = _deep_replace($strip, $url);
$url = str_replace(';//', '://', $url);
/* If the URL doesn't appear to contain a scheme, we
* presume it needs http:// appended (unless a relative
* link starting with / or a php file).
*/
if ( strpos($url, ':') === false &&
- substr( $url, 0, 1 ) != '/' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) )
+ substr( $url, 0, 1 ) != '/' && substr( $url, 0, 1 ) != '#' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) )
$url = 'http://' . $url;
// Replace ampersands and single quotes only when displaying.
- if ( 'display' == $context ) {
- $url = preg_replace('/&([^#])(?![a-z]{2,8};)/', '&$1', $url);
+ if ( 'display' == $_context ) {
+ $url = wp_kses_normalize_entities( $url );
+ $url = str_replace( '&', '&', $url );
$url = str_replace( "'", ''', $url );
}
if ( !is_array($protocols) )
- $protocols = array('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet');
+ $protocols = array ('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn');
if ( wp_kses_bad_protocol( $url, $protocols ) != $url )
return '';
- return apply_filters('clean_url', $url, $original_url, $context);
+ return apply_filters('clean_url', $url, $original_url, $_context);
}
/**
- * Performs clean_url() for database usage.
- *
- * @see clean_url()
+ * Performs esc_url() for database usage.
*
- * @since 2.3.1
+ * @since 2.8.0
+ * @uses esc_url()
*
* @param string $url The URL to be cleaned.
* @param array $protocols An array of acceptable protocols.
* @return string The cleaned URL.
*/
-function sanitize_url( $url, $protocols = null ) {
- return clean_url( $url, $protocols, 'db' );
+function esc_url_raw( $url, $protocols = null ) {
+ return esc_url( $url, $protocols, 'db' );
}
/**
}
/**
- * Escape single quotes, specialchar double quotes, and fix line endings.
+ * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
*
- * The filter 'js_escape' is also applied here.
+ * Escapes text strings for echoing in JS. It is intended to be used for inline JS
+ * (in a tag attribute, for example onclick="..."). Note that the strings have to
+ * be in single quotes. The filter 'js_escape' is also applied here.
*
- * @since 2.0.4
+ * @since 2.8.0
*
* @param string $text The text to be escaped.
* @return string Escaped text.
*/
-function js_escape($text) {
+function esc_js( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
- $safe_text = wp_specialchars( $safe_text, ENT_COMPAT );
+ $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
$safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
- $safe_text = preg_replace( "/\r?\n/", "\\n", addslashes( $safe_text ) );
+ $safe_text = str_replace( "\r", '', $safe_text );
+ $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
return apply_filters( 'js_escape', $safe_text, $text );
}
+/**
+ * Escaping for HTML blocks.
+ *
+ * @since 2.8.0
+ *
+ * @param string $text
+ * @return string
+ */
+function esc_html( $text ) {
+ $safe_text = wp_check_invalid_utf8( $text );
+ $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
+ return apply_filters( 'esc_html', $safe_text, $text );
+}
+
/**
* Escaping for HTML attributes.
*
- * @since 2.0.6
+ * @since 2.8.0
*
* @param string $text
* @return string
*/
-function attribute_escape( $text ) {
+function esc_attr( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
- $safe_text = wp_specialchars( $safe_text, ENT_QUOTES );
+ $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
return apply_filters( 'attribute_escape', $safe_text, $text );
}
*/
function sanitize_option($option, $value) {
- switch ($option) {
+ switch ( $option ) {
case 'admin_email':
$value = sanitize_email($value);
+ if ( !is_email($value) ) {
+ $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
+ if ( function_exists('add_settings_error') )
+ add_settings_error('admin_email', 'invalid_admin_email', __('The email address entered did not appear to be a valid email address. Please enter a valid email address.'));
+ }
break;
case 'thumbnail_size_w':
case 'medium_size_h':
case 'large_size_w':
case 'large_size_h':
+ case 'embed_size_h':
case 'default_post_edit_rows':
case 'mailserver_port':
case 'comment_max_links':
case 'page_on_front':
+ case 'page_for_posts':
case 'rss_excerpt_length':
case 'default_category':
case 'default_email_category':
case 'close_comments_days_old':
case 'comments_per_page':
case 'thread_comments_depth':
- $value = abs((int) $value);
+ case 'users_can_register':
+ case 'start_of_week':
+ $value = absint( $value );
+ break;
+
+ case 'embed_size_w':
+ if ( '' !== $value )
+ $value = absint( $value );
break;
case 'posts_per_page':
case 'posts_per_rss':
$value = (int) $value;
- if ( empty($value) ) $value = 1;
- if ( $value < -1 ) $value = abs($value);
+ if ( empty($value) )
+ $value = 1;
+ if ( $value < -1 )
+ $value = abs($value);
break;
case 'default_ping_status':
$value = addslashes($value);
$value = wp_filter_post_kses( $value ); // calls stripslashes then addslashes
$value = stripslashes($value);
- $value = wp_specialchars( $value );
+ $value = esc_html( $value );
break;
case 'blog_charset':
break;
case 'siteurl':
+ if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
+ $value = esc_url_raw($value);
+ } else {
+ $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
+ if ( function_exists('add_settings_error') )
+ add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.'));
+ }
+ break;
+
case 'home':
- $value = stripslashes($value);
- $value = clean_url($value);
+ if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
+ $value = esc_url_raw($value);
+ } else {
+ $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
+ if ( function_exists('add_settings_error') )
+ add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.'));
+ }
break;
+
default :
$value = apply_filters("sanitize_option_{$option}", $value, $option);
break;
/**
* Callback function used by preg_replace.
*
- * @uses wp_specialchars to format the $matches text.
+ * @uses esc_html to format the $matches text.
* @since 2.3.0
*
* @param array $matches Populated by matches to preg_replace.
- * @return string The text returned after wp_specialchars if needed.
+ * @return string The text returned after esc_html if needed.
*/
function wp_pre_kses_less_than_callback( $matches ) {
if ( false === strpos($matches[0], '>') )
- return wp_specialchars($matches[0]);
+ return esc_html($matches[0]);
return $matches[0];
}
// Translate and filter the delimiter set (avoid ampersands and entities here)
$l = apply_filters('wp_sprintf_l', array(
- 'between' => _c(', |between list items'),
- 'between_last_two' => _c(', and |between last two list items'),
- 'between_only_two' => _c(' and |between only two list items'),
+ /* translators: used between list items, there is a space after the coma */
+ 'between' => __(', '),
+ /* translators: used between list items, there is a space after the and */
+ 'between_last_two' => __(', and '),
+ /* translators: used between only two list items, there is a space after the and */
+ 'between_only_two' => __(' and '),
));
$args = (array) $args;
while ( $i ) {
$arg = array_shift($args);
$i--;
- if ( $i == 1 )
+ if ( 0 == $i )
$result .= $l['between_last_two'] . $arg;
else
$result .= $l['between'] . $arg;
* @return string The excerpt.
*/
function wp_html_excerpt( $str, $count ) {
- $str = strip_tags( $str );
- $str = mb_strcut( $str, 0, $count );
+ $str = wp_strip_all_tags( $str, true );
+ $str = mb_substr( $str, 0, $count );
// remove part of an entity at the end
$str = preg_replace( '/&[^;\s]{0,6}$/', '', $str );
return $str;
create_function('$m', 'return _links_add_target($m, "' . $target . '");'),
$content);
}
+
/**
* Callback to add a target attribute to all links in passed content.
*
return $str;
}
+/**
+ * Properly strip all HTML tags including script and style
+ *
+ * @since 2.9.0
+ *
+ * @param string $string String containing HTML tags
+ * @param bool $remove_breaks optional Whether to remove left over line breaks and white space chars
+ * @return string The processed string.
+ */
+function wp_strip_all_tags($string, $remove_breaks = false) {
+ $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
+ $string = strip_tags($string);
+
+ if ( $remove_breaks )
+ $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
+
+ return trim($string);
+}
+
+/**
+ * Sanitize a string from user input or from the db
+ *
+ * check for invalid UTF-8,
+ * Convert single < characters to entity,
+ * strip all tags,
+ * remove line breaks, tabs and extra white space,
+ * strip octets.
+ *
+ * @since 2.9.0
+ *
+ * @param string $str
+ * @return string
+ */
+function sanitize_text_field($str) {
+ $filtered = wp_check_invalid_utf8( $str );
+
+ if ( strpos($filtered, '<') !== false ) {
+ $filtered = wp_pre_kses_less_than( $filtered );
+ // This will strip extra whitespace for us.
+ $filtered = wp_strip_all_tags( $filtered, true );
+ } else {
+ $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
+ }
+
+ $match = array();
+ $found = false;
+ while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
+ $filtered = str_replace($match[0], '', $filtered);
+ $found = true;
+ }
+
+ if ( $found ) {
+ // Strip out the whitespace that may now exist after removing the octets.
+ $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
+ }
+
+ return apply_filters('sanitize_text_field', $filtered, $str);
+}
+
+/**
+ * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
+ *
+ * Violating our coding standards for a good function name.
+ *
+ * @since 3.0.0
+ */
+
+function capital_P_dangit( $text ) {
+ // Simple replacement for titles
+ if ( 'the_title' === current_filter() )
+ return str_replace( 'Wordpress', 'WordPress', $text );
+ // Still here? Use the more judicious replacement
+ static $dblq = false;
+ if ( false === $dblq )
+ $dblq = _x('“', 'opening curly quote');
+ return str_replace(
+ array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
+ array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
+ $text );
+
+}
+
?>