>...<> HTML block are not - * converted into paragraphs or line-breaks. - * - * @since 1.2.0 - * - * @param array|string $matches The array or string - * @return string The pre block without paragraph/line-break conversion. - */ -function clean_pre($matches) { - if ( is_array($matches) ) - $text = $matches[1] . $matches[2] . ""; - else - $text = $matches; - - $text = str_replace('
', "\n", $text); - $text = str_replace('
', '', $text); - - return $text; -} - /** * Replaces double line-breaks with paragraph elements. * @@ -164,17 +182,45 @@ function clean_pre($matches) { * @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. + * @param 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, $br = 1) { +function wpautop($pee, $br = true) { + $pre_tags = array(); if ( trim($pee) === '' ) return ''; + $pee = $pee . "\n"; // just to make things a little easier, pad the end + + if ( strpos($pee, '\s*(]*>)!', "$1", $pee); $pee = preg_replace('!(]*>)\s*
!', "$1", $pee); - if ($br) { + if ( $br ) { $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee); $pee = preg_replace('|(?)\s*\n|', "\\s*?(\\[(' . $tagregexp . ')\\b.*?\\/?\\](?:.+?\\[\\/\\2\\])?)\\s*<\\/p>/s', '$1', $pee); - } - - return $pee; + if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) { + return $pee; + } + + $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) ); + + $pattern = + '/' + . '
' // Opening paragraph
+ . '\\s*+' // Optional leading whitespace
+ . '(' // 1: The shortcode
+ . '\\[' // Opening bracket
+ . "($tagregexp)" // 2: Shortcode name
+ . '(?![\\w-])' // Not followed by word character or hyphen
+ // Unroll the loop: Inside the opening shortcode tag
+ . '[^\\]\\/]*' // Not a closing bracket or forward slash
+ . '(?:'
+ . '\\/(?!\\])' // A forward slash not followed by a closing bracket
+ . '[^\\]\\/]*' // Not a closing bracket or forward slash
+ . ')*?'
+ . '(?:'
+ . '\\/\\]' // Self closing tag and closing bracket
+ . '|'
+ . '\\]' // Closing bracket
+ . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
+ . '[^\\[]*+' // Not an opening bracket
+ . '(?:'
+ . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
+ . '[^\\[]*+' // Not an opening bracket
+ . ')*+'
+ . '\\[\\/\\2\\]' // Closing shortcode tag
+ . ')?'
+ . ')'
+ . ')'
+ . '\\s*+' // optional trailing whitespace
+ . '<\\/p>' // closing paragraph
+ . '/s';
+
+ return preg_replace( $pattern, '$1', $pee );
}
/**
@@ -294,34 +373,31 @@ function seems_utf8($str) {
function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
$string = (string) $string;
- if ( 0 === strlen( $string ) ) {
+ if ( 0 === strlen( $string ) )
return '';
- }
// Don't bother if there are no specialchars - saves some processing
- if ( !preg_match( '/[&<>"\']/', $string ) ) {
+ if ( ! preg_match( '/[&<>"\']/', $string ) )
return $string;
- }
// Account for the previous behaviour of the function when the $quote_style is not an accepted value
- if ( empty( $quote_style ) ) {
+ if ( empty( $quote_style ) )
$quote_style = ENT_NOQUOTES;
- } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
+ elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
$quote_style = ENT_QUOTES;
- }
// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
- if ( !$charset ) {
+ if ( ! $charset ) {
static $_charset;
- if ( !isset( $_charset ) ) {
+ if ( ! isset( $_charset ) ) {
$alloptions = wp_load_alloptions();
$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
}
$charset = $_charset;
}
- if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) {
+
+ if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
$charset = 'UTF-8';
- }
$_quote_style = $quote_style;
@@ -333,28 +409,27 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals
}
// Handle double encoding ourselves
- if ( !$double_encode ) {
+ if ( $double_encode ) {
+ $string = @htmlspecialchars( $string, $quote_style, $charset );
+ } else {
+ // Decode & into &
$string = wp_specialchars_decode( $string, $_quote_style );
- /* Critical */
- // The previous line decodes &phrase; into &phrase; We must guarantee that &phrase; is valid before proceeding.
- $string = wp_kses_normalize_entities($string);
+ // Guarantee every &entity; is valid or re-encode the &
+ $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 );
- }
+ // Now re-encode everything except &entity;
+ $string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE );
- $string = @htmlspecialchars( $string, $quote_style, $charset );
+ for ( $i = 0; $i < count( $string ); $i += 2 )
+ $string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset );
- // Handle double encoding ourselves
- if ( !$double_encode ) {
- $string = str_replace( array( '|wp_entity|', '|/wp_entity|' ), array( '&', ';' ), $string );
+ $string = implode( '', $string );
}
// Backwards compatibility
- if ( 'single' === $_quote_style ) {
+ if ( 'single' === $_quote_style )
$string = str_replace( "'", ''', $string );
- }
return $string;
}
@@ -536,6 +611,7 @@ function remove_accents($string) {
if (seems_utf8($string)) {
$chars = array(
// Decompositions for Latin-1 Supplement
+ chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
@@ -566,7 +642,7 @@ function remove_accents($string) {
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(190) => 'th',
- chr(195).chr(191) => 'y',
+ chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
// 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',
@@ -638,7 +714,76 @@ function remove_accents($string) {
// Euro Sign
chr(226).chr(130).chr(172) => 'E',
// GBP (Pound) Sign
- chr(194).chr(163) => '');
+ chr(194).chr(163) => '',
+ // Vowels with diacritic (Vietnamese)
+ // unmarked
+ chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
+ chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
+ // grave accent
+ chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
+ chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
+ chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
+ chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
+ chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
+ chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
+ chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
+ // hook
+ chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
+ chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
+ chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
+ chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
+ chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
+ chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
+ chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
+ chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
+ chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
+ chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
+ chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
+ chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
+ // tilde
+ chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
+ chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
+ chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
+ chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
+ chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
+ chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
+ chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
+ chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
+ // acute accent
+ chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
+ chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
+ chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
+ chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
+ chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
+ chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
+ // dot below
+ chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
+ chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
+ chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
+ chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
+ chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
+ chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
+ chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
+ chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
+ chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
+ chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
+ chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
+ chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
+ // Vowels with diacritic (Chinese, Hanyu Pinyin)
+ chr(201).chr(145) => 'a',
+ // macron
+ chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
+ // acute accent
+ chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
+ // caron
+ chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
+ chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
+ chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
+ chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
+ chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
+ // grave accent
+ chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
+ );
$string = strtr($string, $chars);
} else {
@@ -699,7 +844,7 @@ function sanitize_file_name( $filename ) {
$extension = array_pop($parts);
$mimes = get_allowed_mime_types();
- // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character
+ // 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 .= '.' . $part;
@@ -807,7 +952,7 @@ function sanitize_title_for_query($title) {
}
/**
- * Sanitizes title, replacing whitespace with dashes.
+ * Sanitizes title, replacing whitespace and a few other characters with dashes.
*
* Limits the output to alphanumeric characters, underscore (_) and dash (-).
* Whitespace becomes a dash.
@@ -815,9 +960,11 @@ function sanitize_title_for_query($title) {
* @since 1.2.0
*
* @param string $title The title to be sanitized.
+ * @param string $raw_title Optional. Not used.
+ * @param string $context Optional. The operation for which the string is sanitized.
* @return string The sanitized title.
*/
-function sanitize_title_with_dashes($title) {
+function sanitize_title_with_dashes($title, $raw_title = '', $context = 'display') {
$title = strip_tags($title);
// Preserve escaped octets.
$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
@@ -836,6 +983,30 @@ function sanitize_title_with_dashes($title) {
$title = strtolower($title);
$title = preg_replace('/&.+?;/', '', $title); // kill entities
$title = str_replace('.', '-', $title);
+
+ if ( 'save' == $context ) {
+ // Convert nbsp, ndash and mdash to hyphens
+ $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
+
+ // Strip these characters entirely
+ $title = str_replace( array(
+ // iexcl and iquest
+ '%c2%a1', '%c2%bf',
+ // angle quotes
+ '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
+ // curly quotes
+ '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
+ '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
+ // copy, reg, deg, hellip and trade
+ '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
+ // grave accent, acute accent, macron, caron
+ '%cc%80', '%cc%81', '%cc%84', '%cc%8c',
+ ), '', $title );
+
+ // Convert times to x
+ $title = str_replace( '%c3%97', 'x', $title );
+ }
+
$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
$title = preg_replace('/\s+/', '-', $title);
$title = preg_replace('|-+|', '-', $title);
@@ -853,7 +1024,7 @@ function sanitize_title_with_dashes($title) {
* @since 2.5.1
*
* @param string $orderby Order by string to be checked.
- * @return string|false Returns the order by clause if it is a match, false otherwise.
+ * @return string|bool Returns the order by clause if it is a match, false otherwise.
*/
function sanitize_sql_orderby( $orderby ){
preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);
@@ -923,7 +1094,7 @@ function convert_chars($content, $deprecated = '') {
'‹' => '‹',
'Œ' => 'Œ',
'' => '',
- 'Ž' => 'ž',
+ 'Ž' => 'Ž',
'' => '',
'' => '',
'‘' => '‘',
@@ -939,7 +1110,7 @@ function convert_chars($content, $deprecated = '') {
'›' => '›',
'œ' => 'œ',
'' => '',
- 'ž' => '',
+ 'ž' => 'ž',
'Ÿ' => 'Ÿ'
);
@@ -963,14 +1134,12 @@ function convert_chars($content, $deprecated = '') {
/**
* Will only balance the tags if forced to and the option is set to balance tags.
*
- * The option 'use_balanceTags' is used for whether the tags will be balanced.
- * Both the $force parameter and 'use_balanceTags' option will have to be true
- * before the tags will be balanced.
+ * The option 'use_balanceTags' is used to determine whether the tags will be balanced.
*
* @since 0.71
*
* @param string $text Text to be balanced
- * @param bool $force Forces balancing, ignoring the value of the option. Default false.
+ * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
* @return string Balanced text
*/
function balanceTags( $text, $force = false ) {
@@ -1002,8 +1171,10 @@ function force_balance_tags( $text ) {
$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
+ // Known single-entity/self-closing tags
+ $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
+ // Tags that can be immediately nested within themselves
+ $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
// WP bug fix for comments - in case you REALLY meant to type '< !--'
$text = str_replace('< !--', '< !--', $text);
@@ -1050,26 +1221,35 @@ function force_balance_tags( $text ) {
// Tag Cleaning
- // If self-closing or '', don't do anything.
- if ( substr($regex[2],-1) == '/' || $tag == '' ) {
+ // If it's an empty tag "< >", do nothing
+ if ( '' == $tag ) {
// do nothing
}
+ // ElseIf it presents itself as a self-closing tag...
+ elseif ( substr( $regex[2], -1 ) == '/' ) {
+ // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
+ // immediately close it with a closing tag (the tag will encapsulate no text as a result)
+ if ( ! in_array( $tag, $single_tags ) )
+ $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "> 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
- $tagqueue = '';
+ $tagqueue = '';
$stacksize--;
}
- $stacksize = array_push ($tagstack, $tag);
+ $stacksize = array_push( $tagstack, $tag );
}
// Attributes
$attributes = $regex[2];
- if( !empty($attributes) )
- $attributes = ' '.$attributes;
+ if( ! empty( $attributes ) && $attributes[0] != '>' )
+ $attributes = ' ' . $attributes;
$tag = '<' . $tag . $attributes . '>';
//If already queuing a close tag, then put this tag on, too
@@ -1102,14 +1282,14 @@ function force_balance_tags( $text ) {
/**
* Acts on text which is about to be edited.
*
- * Unless $richedit is set, it is simply a holder for the 'format_to_edit'
- * filter. If $richedit is set true htmlspecialchars(), through esc_textarea(),
- * will be run on the content, converting special characters to HTML entities.
+ * The $content is run through esc_textarea(), which uses htmlspecialchars()
+ * to convert special characters to HTML entities. If $richedit is set to true,
+ * it is simply a holder for the 'format_to_edit' filter.
*
* @since 0.71
*
* @param string $content The text about to be edited.
- * @param bool $richedit Whether the $content should pass through htmlspecialchars(). Default false.
+ * @param bool $richedit Whether the $content should not pass through htmlspecialchars(). Default false (meaning it will be passed).
* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
*/
function format_to_edit( $content, $richedit = false ) {
@@ -1136,7 +1316,7 @@ function format_to_post($content) {
* Add leading zeros when necessary.
*
* If you set the threshold to '4' and the number is '10', then you will get
- * back '0010'. If you set the number to '4' and the number is '5000', then you
+ * back '0010'. If you set the threshold to '4' and the number is '5000', then you
* will get back '5000'.
*
* Uses sprintf to append the amount of zeros based on the $threshold parameter
@@ -1227,8 +1407,8 @@ function addslashes_gpc($gpc) {
*
* @since 2.0.0
*
- * @param array|string $value The array or string to be stripped.
- * @return array|string Stripped array (or string in the callback).
+ * @param mixed $value The value to be stripped.
+ * @return mixed Stripped value.
*/
function stripslashes_deep($value) {
if ( is_array($value) ) {
@@ -1238,7 +1418,7 @@ function stripslashes_deep($value) {
foreach ($vars as $key=>$data) {
$value->{$key} = stripslashes_deep( $data );
}
- } else {
+ } elseif ( is_string( $value ) ) {
$value = stripslashes($value);
}
@@ -1248,8 +1428,6 @@ function stripslashes_deep($value) {
/**
* Navigates through an array and encodes the values to be used in a URL.
*
- * Uses a callback to pass the value of the array back to the function as a
- * string.
*
* @since 2.2.0
*
@@ -1261,6 +1439,18 @@ function urlencode_deep($value) {
return $value;
}
+/**
+ * Navigates through an array and raw encodes the values to be used in a URL.
+ *
+ * @since 3.4.0
+ *
+ * @param array|string $value The array or string to be encoded.
+ * @return array|string $value The encoded array (or string from the callback).
+ */
+function rawurlencode_deep( $value ) {
+ return is_array( $value ) ? array_map( 'rawurlencode_deep', $value ) : rawurlencode( $value );
+}
+
/**
* Converts email addresses characters to HTML entities to block spam bots.
*
@@ -1301,9 +1491,17 @@ function antispambot($emailaddy, $mailto=0) {
*/
function _make_url_clickable_cb($matches) {
$url = $matches[2];
- $suffix = '';
- /** Include parentheses in the URL only if paired **/
+ if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
+ // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
+ // Then we can let the parenthesis balancer do its thing below.
+ $url .= $matches[3];
+ $suffix = '';
+ } else {
+ $suffix = $matches[3];
+ }
+
+ // Include parentheses in the URL only if paired
while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
$suffix = strrchr( $url, ')' ) . $suffix;
$url = substr( $url, 0, strrpos( $url, ')' ) );
@@ -1369,23 +1567,117 @@ function _make_email_clickable_cb($matches) {
*
* @since 0.71
*
- * @param string $ret Content to convert URIs.
+ * @param string $text Content to convert URIs.
* @return string Content with converted URIs.
*/
-function make_clickable($ret) {
- $ret = ' ' . $ret;
- // in testing, using arrays here was found to be faster
- $save = @ini_set('pcre.recursion_limit', 10000);
- $retval = preg_replace_callback('#(?])(\()?([\w]+?://(?:[\w\\x80-\\xff\#%~/?@\[\]-]{1,2000}|[\'*(+.,;:!=&$](?![\b\)]|(\))?([\s]|$))|(?(1)\)(?![\s<.,;:]|$)|\)))+)#is', '_make_url_clickable_cb', $ret);
- if (null !== $retval )
- $ret = $retval;
- @ini_set('pcre.recursion_limit', $save);
- $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#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("#(
+ * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
+ * array (
+ * 0 => '1234 67890 ', // 11 characters: Perfect split
+ * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
+ * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
+ * 3 => '1234 890 ', // 11 characters: Perfect split
+ * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
+ * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
+ * 6 => ' 45678 ', // 11 characters: Perfect split
+ * 7 => '1 3 5 7 9', // 9 characters: End of $string
+ * );
+ *
+ *
+ * @since 3.4.0
+ * @access private
+ *
+ * @param string $string The string to split.
+ * @param int $goal The desired chunk length.
+ * @return array Numeric array of chunks.
+ */
+function _split_str_by_whitespace( $string, $goal ) {
+ $chunks = array();
+
+ $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
+
+ while ( $goal < strlen( $string_nullspace ) ) {
+ $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
+
+ if ( false === $pos ) {
+ $pos = strpos( $string_nullspace, "\000", $goal + 1 );
+ if ( false === $pos ) {
+ break;
+ }
+ }
+
+ $chunks[] = substr( $string, 0, $pos + 1 );
+ $string = substr( $string, $pos + 1 );
+ $string_nullspace = substr( $string_nullspace, $pos + 1 );
+ }
+
+ if ( $string ) {
+ $chunks[] = $string;
+ }
+
+ return $chunks;
}
/**
@@ -1556,7 +1848,6 @@ function is_email( $email, $deprecated = false ) {
* Convert to ASCII from email subjects.
*
* @since 1.2.0
- * @usedby wp_mail() handles charsets in email subjects
*
* @param string $string Subject line
* @return string Converted string to ASCII
@@ -1573,11 +1864,12 @@ function wp_iso_descrambler($string) {
}
/**
- * Helper function to convert hex encoded chars to ascii
+ * Helper function to convert hex encoded chars to ASCII
*
* @since 3.1.0
* @access private
- * @param array $match the preg_replace_callback matches array
+ * @param array $match The preg_replace_callback matches array
+ * @return array Converted chars
*/
function _wp_iso_convert( $match ) {
return chr( hexdec( strtolower( $match[1] ) ) );
@@ -1600,19 +1892,25 @@ function _wp_iso_convert( $match ) {
*/
function get_gmt_from_date($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);
+ if ( ! $matches )
+ return date( $format, 0 );
+
$tz = get_option('timezone_string');
if ( $tz ) {
date_default_timezone_set( $tz );
- $datetime = new DateTime( $string );
+ $datetime = date_create( $string );
+ if ( ! $datetime )
+ return date( $format, 0 );
+
$datetime->setTimezone( new DateTimeZone('UTC') );
$offset = $datetime->getOffset();
- $datetime->modify( '+' . $offset / 3600 . ' hours');
+ $datetime->modify( '+' . $offset / HOUR_IN_SECONDS . ' hours');
$string_gmt = gmdate($format, $datetime->format('U'));
date_default_timezone_set('UTC');
} else {
$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
- $string_gmt = gmdate($format, $string_time - get_option('gmt_offset') * 3600);
+ $string_gmt = gmdate($format, $string_time - get_option('gmt_offset') * HOUR_IN_SECONDS);
}
return $string_gmt;
}
@@ -1632,7 +1930,7 @@ function get_gmt_from_date($string, $format = 'Y-m-d H:i:s') {
function get_date_from_gmt($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]);
- $string_localtime = gmdate($format, $string_time + get_option('gmt_offset')*3600);
+ $string_localtime = gmdate($format, $string_time + get_option('gmt_offset') * HOUR_IN_SECONDS);
return $string_localtime;
}
@@ -1652,7 +1950,7 @@ function iso8601_timezone_to_offset($timezone) {
$sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
$hours = intval(substr($timezone, 1, 2));
$minutes = intval(substr($timezone, 3, 4)) / 60;
- $offset = $sign * 3600 * ($hours + $minutes);
+ $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
}
return $offset;
}
@@ -1676,7 +1974,7 @@ function iso8601_to_datetime($date_string, $timezone = 'user') {
if (!empty($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_option('gmt_offset');
+ $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
}
$timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
@@ -1801,28 +2099,28 @@ function sanitize_email( $email ) {
* @return string Human readable time difference.
*/
function human_time_diff( $from, $to = '' ) {
- if ( empty($to) )
+ if ( empty( $to ) )
$to = time();
- $diff = (int) abs($to - $from);
- if ($diff <= 3600) {
- $mins = round($diff / 60);
- if ($mins <= 1) {
+ $diff = (int) abs( $to - $from );
+ if ( $diff <= HOUR_IN_SECONDS ) {
+ $mins = round( $diff / MINUTE_IN_SECONDS );
+ if ( $mins <= 1 ) {
$mins = 1;
}
/* 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) {
+ $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
+ } elseif ( ( $diff <= DAY_IN_SECONDS ) && ( $diff > HOUR_IN_SECONDS ) ) {
+ $hours = round( $diff / HOUR_IN_SECONDS );
+ if ( $hours <= 1 ) {
$hours = 1;
}
- $since = sprintf(_n('%s hour', '%s hours', $hours), $hours);
- } elseif ($diff >= 86400) {
- $days = round($diff / 86400);
- if ($days <= 1) {
+ $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
+ } elseif ( $diff >= DAY_IN_SECONDS ) {
+ $days = round( $diff / DAY_IN_SECONDS );
+ if ( $days <= 1 ) {
$days = 1;
}
- $since = sprintf(_n('%s day', '%s days', $days), $days);
+ $since = sprintf( _n( '%s day', '%s days', $days ), $days );
}
return $since;
}
@@ -1839,10 +2137,10 @@ function human_time_diff( $from, $to = '' ) {
*
* @since 1.5.0
*
- * @param string $text The excerpt. If set to empty an excerpt is generated.
+ * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
* @return string The excerpt.
*/
-function wp_trim_excerpt($text) {
+function wp_trim_excerpt($text = '') {
$raw_excerpt = $text;
if ( '' == $text ) {
$text = get_the_content('');
@@ -1851,21 +2149,53 @@ function wp_trim_excerpt($text) {
$text = apply_filters('the_content', $text);
$text = str_replace(']]>', ']]>', $text);
- $text = strip_tags($text);
$excerpt_length = apply_filters('excerpt_length', 55);
$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);
- $text = implode(' ', $words);
- $text = $text . $excerpt_more;
- } else {
- $text = implode(' ', $words);
- }
+ $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
}
return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
}
+/**
+ * Trims text to a certain number of words.
+ *
+ * This function is localized. For languages that count 'words' by the individual
+ * character (such as East Asian languages), the $num_words argument will apply
+ * to the number of individual characters.
+ *
+ * @since 3.3.0
+ *
+ * @param string $text Text to trim.
+ * @param int $num_words Number of words. Default 55.
+ * @param string $more What to append if $text needs to be trimmed. Default '…'.
+ * @return string Trimmed text.
+ */
+function wp_trim_words( $text, $num_words = 55, $more = null ) {
+ if ( null === $more )
+ $more = __( '…' );
+ $original_text = $text;
+ $text = wp_strip_all_tags( $text );
+ /* translators: If your word count is based on single characters (East Asian characters),
+ enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
+ if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
+ $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
+ preg_match_all( '/./u', $text, $words_array );
+ $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
+ $sep = '';
+ } else {
+ $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
+ $sep = ' ';
+ }
+ if ( count( $words_array ) > $num_words ) {
+ array_pop( $words_array );
+ $text = implode( $sep, $words_array );
+ $text = $text . $more;
+ } else {
+ $text = implode( $sep, $words_array );
+ }
+ return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
+}
+
/**
* Converts named entities into numbered entities.
*
@@ -1875,6 +2205,12 @@ function wp_trim_excerpt($text) {
* @return string Text with converted entities.
*/
function ent2ncr($text) {
+
+ // Allow a plugin to short-circuit and override the mappings.
+ $filtered = apply_filters( 'pre_ent2ncr', null, $text );
+ if( null !== $filtered )
+ return $filtered;
+
$to_ncr = array(
'"' => '"',
'&' => '&',
@@ -2226,7 +2562,7 @@ function esc_sql( $sql ) {
* Checks and cleans a URL.
*
* A number of characters are removed from the URL. If the URL is for displaying
- * (the default behaviour) amperstands are also replaced. The 'clean_url' filter
+ * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
* is applied to the returned cleaned URL.
*
* @since 2.8.0
@@ -2235,7 +2571,7 @@ function esc_sql( $sql ) {
*
* @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.
+ * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn' if not set.
* @param string $_context Private. Use esc_url_raw() for database usage.
* @return string The cleaned $url after the 'clean_url' filter is applied.
*/
@@ -2250,10 +2586,10 @@ function esc_url( $url, $protocols = null, $_context = 'display' ) {
$url = str_replace(';//', '://', $url);
/* If the URL doesn't appear to contain a scheme, we
* presume it needs http:// appended (unless a relative
- * link starting with / or a php file).
+ * link starting with /, # or ? or a php file).
*/
- if ( strpos($url, ':') === false &&
- substr( $url, 0, 1 ) != '/' && substr( $url, 0, 1 ) != '#' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) )
+ if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
+ ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
$url = 'http://' . $url;
// Replace ampersands and single quotes only when displaying.
@@ -2263,12 +2599,13 @@ function esc_url( $url, $protocols = null, $_context = 'display' ) {
$url = str_replace( "'", ''', $url );
}
- if ( !is_array($protocols) )
- $protocols = array ('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn');
- if ( wp_kses_bad_protocol( $url, $protocols ) != $url )
+ if ( ! is_array( $protocols ) )
+ $protocols = wp_allowed_protocols();
+ $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
+ if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
return '';
- return apply_filters('clean_url', $url, $original_url, $_context);
+ return apply_filters('clean_url', $good_protocol_url, $original_url, $_context);
}
/**
@@ -2372,7 +2709,7 @@ function esc_textarea( $text ) {
* @return string
*/
function tag_escape($tag_name) {
- $safe_tag = strtolower( preg_replace('/[^a-zA-Z_:]/', '', $tag_name) );
+ $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
return apply_filters('tag_escape', $safe_tag, $tag_name);
}
@@ -2418,30 +2755,22 @@ function wp_make_link_relative( $link ) {
function sanitize_option($option, $value) {
switch ( $option ) {
- case 'admin_email':
- $value = sanitize_email($value);
- if ( !is_email($value) ) {
+ case 'admin_email' :
+ case 'new_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 'new_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('new_admin_email', 'invalid_admin_email', __('The email address entered did not appear to be a valid email address. Please enter a valid email address.'));
+ if ( function_exists( 'add_settings_error' ) )
+ add_settings_error( $option, 'invalid_admin_email', __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ) );
}
break;
+
case 'thumbnail_size_w':
case 'thumbnail_size_h':
case 'medium_size_w':
case 'medium_size_h':
case 'large_size_w':
case 'large_size_h':
- case 'embed_size_h':
- case 'default_post_edit_rows':
case 'mailserver_port':
case 'comment_max_links':
case 'page_on_front':
@@ -2458,11 +2787,6 @@ function sanitize_option($option, $value) {
$value = absint( $value );
break;
- case 'embed_size_w':
- if ( '' !== $value )
- $value = absint( $value );
- break;
-
case 'posts_per_page':
case 'posts_per_rss':
$value = (int) $value;
@@ -2481,9 +2805,7 @@ function sanitize_option($option, $value) {
case 'blogdescription':
case 'blogname':
- $value = addslashes($value);
- $value = wp_filter_post_kses( $value ); // calls stripslashes then addslashes
- $value = stripslashes($value);
+ $value = wp_kses_post( $value );
$value = esc_html( $value );
break;
@@ -2491,17 +2813,29 @@ function sanitize_option($option, $value) {
$value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
break;
+ case 'blog_public':
+ // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
+ if ( null === $value )
+ $value = 1;
+ else
+ $value = intval( $value );
+ break;
+
case 'date_format':
case 'time_format':
case 'mailserver_url':
case 'mailserver_login':
case 'mailserver_pass':
- case 'ping_sites':
case 'upload_path':
- $value = strip_tags($value);
- $value = addslashes($value);
- $value = wp_filter_kses($value); // calls stripslashes then addslashes
- $value = stripslashes($value);
+ $value = strip_tags( $value );
+ $value = wp_kses_data( $value );
+ break;
+
+ case 'ping_sites':
+ $value = explode( "\n", $value );
+ $value = array_filter( array_map( 'trim', $value ) );
+ $value = array_filter( array_map( 'esc_url_raw', $value ) );
+ $value = implode( "\n", $value );
break;
case 'gmt_offset':
@@ -2527,12 +2861,39 @@ function sanitize_option($option, $value) {
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;
+
case 'WPLANG':
$allowed = get_available_languages();
if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
$value = get_option( $option );
break;
+ case 'illegal_names':
+ if ( ! is_array( $value ) )
+ $value = explode( ' ', $value );
+
+ $value = array_values( array_filter( array_map( 'trim', $value ) ) );
+
+ if ( ! $value )
+ $value = '';
+ break;
+
+ case 'limited_email_domains':
+ case 'banned_email_domains':
+ if ( ! is_array( $value ) )
+ $value = explode( "\n", $value );
+
+ $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
+ $value = array();
+
+ foreach ( $domains as $domain ) {
+ if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) )
+ $value[] = $domain;
+ }
+ if ( ! $value )
+ $value = '';
+ break;
+
case 'timezone_string':
$allowed_zones = timezone_identifiers_list();
if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
@@ -2542,11 +2903,16 @@ function sanitize_option($option, $value) {
}
break;
- default :
- $value = apply_filters("sanitize_option_{$option}", $value, $option);
+ case 'permalink_structure':
+ case 'category_base':
+ case 'tag_base':
+ $value = esc_url_raw( $value );
+ $value = str_replace( 'http://', '', $value );
break;
}
+ $value = apply_filters("sanitize_option_{$option}", $value, $option);
+
return $value;
}
@@ -2764,9 +3130,9 @@ function _links_add_base($m) {
global $_links_add_base;
//1 = attribute name 2 = quotation mark 3 = URL
return $m[1] . '=' . $m[2] .
- (strpos($m[3], 'http://') === false ?
- path_join($_links_add_base, $m[3]) :
- $m[3])
+ ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
+ $m[3] :
+ path_join( $_links_add_base, $m[3] ) )
. $m[2];
}
@@ -2832,7 +3198,7 @@ function wp_strip_all_tags($string, $remove_breaks = false) {
if ( $remove_breaks )
$string = preg_replace('/[\r\n\t ]+/', ' ', $string);
- return trim($string);
+ return trim( $string );
}
/**
@@ -2885,7 +3251,7 @@ function sanitize_text_field($str) {
* @return string
*/
function wp_basename( $path, $suffix = '' ) {
- return urldecode( basename( str_replace( '%2F', '/', urlencode( $path ) ), $suffix ) );
+ return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
}
/**
@@ -2902,7 +3268,7 @@ function capital_P_dangit( $text ) {
// Still here? Use the more judicious replacement
static $dblq = false;
if ( false === $dblq )
- $dblq = _x('“', 'opening curly quote');
+ $dblq = _x( '“', 'opening curly double quote' );
return str_replace(
array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
@@ -2923,4 +3289,21 @@ function sanitize_mime_type( $mime_type ) {
return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
}
-?>
+/**
+ * Sanitize space or carriage return separated URLs that are used to send trackbacks.
+ *
+ * @since 3.4.0
+ *
+ * @param string $to_ping Space or carriage return separated URLs
+ * @return string URLs starting with the http or https protocol, separated by a carriage return.
+ */
+function sanitize_trackback_urls( $to_ping ) {
+ $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
+ foreach ( $urls_to_ping as $k => $url ) {
+ if ( !preg_match( '#^https?://.#i', $url ) )
+ unset( $urls_to_ping[$k] );
+ }
+ $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
+ $urls_to_ping = implode( "\n", $urls_to_ping );
+ return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
+}