X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/138998bbd8f7a1ac38b2f1eacbdf7cd522be4b13..HEAD:/wp-includes/formatting.php?ds=sidebyside diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php index ff4167d2..85d4e7e4 100644 --- a/wp-includes/formatting.php +++ b/wp-includes/formatting.php @@ -20,7 +20,7 @@ * * Code within certain html blocks are skipped. * - * Do not use this function before the 'init' action hook; everything will break. + * Do not use this function before the {@see 'init'} action hook; everything will break. * * @since 0.71 * @@ -66,7 +66,7 @@ function wptexturize( $text, $reset = false ) { // Set up static variables. Run once only. if ( $reset || ! isset( $static_characters ) ) { /** - * Filter whether to skip running wptexturize(). + * Filters whether to skip running wptexturize(). * * Passing false to the filter will effectively short-circuit wptexturize(). * returning the original text passed to the function instead. @@ -195,7 +195,7 @@ function wptexturize( $text, $reset = false ) { // Must do this every time in case plugins use these filters in a context sensitive manner /** - * Filter the list of HTML elements not to texturize. + * Filters the list of HTML elements not to texturize. * * @since 2.8.0 * @@ -203,7 +203,7 @@ function wptexturize( $text, $reset = false ) { */ $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags ); /** - * Filter the list of shortcodes not to texturize. + * Filters the list of shortcodes not to texturize. * * @since 2.8.0 * @@ -216,7 +216,7 @@ function wptexturize( $text, $reset = false ) { // Look for shortcodes and HTML elements. - preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20]++)@', $text, $matches ); + preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches ); $tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] ); $found_shortcodes = ! empty( $tagnames ); $shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : ''; @@ -233,6 +233,10 @@ function wptexturize( $text, $reset = false ) { continue; } else { // This is an HTML element delimiter. + + // Replace each & with & unless it already looks like an entity. + $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl ); + _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags ); } @@ -370,7 +374,7 @@ function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quo */ function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) { // Is it an opening tag or closing tag? - if ( '/' !== $text[1] ) { + if ( isset( $text[1] ) && '/' !== $text[1] ) { $opening_tag = true; $name_offset = 1; } elseif ( 0 == count( $stack ) ) { @@ -464,8 +468,8 @@ function wpautop( $pee, $br = true ) { $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)'; - // Add a single line break above block-level opening tags. - $pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n$1", $pee); + // Add a double line break above block-level opening tags. + $pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n\n$1", $pee); // Add a double line break below block-level closing tags. $pee = preg_replace('!(' . $allblocks . '>)!', "$1\n\n", $pee); @@ -930,7 +934,7 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode ); - // Backwards compatibility + // Back-compat. if ( 'single' === $_quote_style ) $string = str_replace( "'", ''', $string ); @@ -1120,7 +1124,382 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) { * * If there are no accent characters, then the string given is just returned. * + * **Accent characters converted:** + * + * Currency signs: + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | ------------------- | + * | U+00A3 | £ | (empty) | British Pound sign | + * | U+20AC | ⬠| E | Euro sign | + * + * Decompositions for Latin-1 Supplement: + * + * | Code | Glyph | Replacement | Description | + * | ------- | ----- | ----------- | -------------------------------------- | + * | U+00AA | ª | a | Feminine ordinal indicator | + * | U+00BA | º | o | Masculine ordinal indicator | + * | U+00C0 | à | A | Latin capital letter A with grave | + * | U+00C1 | à | A | Latin capital letter A with acute | + * | U+00C2 | à | A | Latin capital letter A with circumflex | + * | U+00C3 | à | A | Latin capital letter A with tilde | + * | U+00C4 | à | A | Latin capital letter A with diaeresis | + * | U+00C5 | à | A | Latin capital letter A with ring above | + * | U+00C6 | à | AE | Latin capital letter AE | + * | U+00C7 | à | C | Latin capital letter C with cedilla | + * | U+00C8 | à | E | Latin capital letter E with grave | + * | U+00C9 | à | E | Latin capital letter E with acute | + * | U+00CA | à | E | Latin capital letter E with circumflex | + * | U+00CB | à | E | Latin capital letter E with diaeresis | + * | U+00CC | à | I | Latin capital letter I with grave | + * | U+00CD | à | I | Latin capital letter I with acute | + * | U+00CE | à | I | Latin capital letter I with circumflex | + * | U+00CF | à | I | Latin capital letter I with diaeresis | + * | U+00D0 | à | D | Latin capital letter Eth | + * | U+00D1 | à | N | Latin capital letter N with tilde | + * | U+00D2 | à | O | Latin capital letter O with grave | + * | U+00D3 | à | O | Latin capital letter O with acute | + * | U+00D4 | à | O | Latin capital letter O with circumflex | + * | U+00D5 | à | O | Latin capital letter O with tilde | + * | U+00D6 | à | O | Latin capital letter O with diaeresis | + * | U+00D8 | à | O | Latin capital letter O with stroke | + * | U+00D9 | à | U | Latin capital letter U with grave | + * | U+00DA | à | U | Latin capital letter U with acute | + * | U+00DB | à | U | Latin capital letter U with circumflex | + * | U+00DC | à | U | Latin capital letter U with diaeresis | + * | U+00DD | à | Y | Latin capital letter Y with acute | + * | U+00DE | à | TH | Latin capital letter Thorn | + * | U+00DF | à | s | Latin small letter sharp s | + * | U+00E0 | à | a | Latin small letter a with grave | + * | U+00E1 | á | a | Latin small letter a with acute | + * | U+00E2 | â | a | Latin small letter a with circumflex | + * | U+00E3 | ã | a | Latin small letter a with tilde | + * | U+00E4 | ä | a | Latin small letter a with diaeresis | + * | U+00E5 | Ã¥ | a | Latin small letter a with ring above | + * | U+00E6 | æ | ae | Latin small letter ae | + * | U+00E7 | ç | c | Latin small letter c with cedilla | + * | U+00E8 | è | e | Latin small letter e with grave | + * | U+00E9 | é | e | Latin small letter e with acute | + * | U+00EA | ê | e | Latin small letter e with circumflex | + * | U+00EB | ë | e | Latin small letter e with diaeresis | + * | U+00EC | ì | i | Latin small letter i with grave | + * | U+00ED | à | i | Latin small letter i with acute | + * | U+00EE | î | i | Latin small letter i with circumflex | + * | U+00EF | ï | i | Latin small letter i with diaeresis | + * | U+00F0 | ð | d | Latin small letter Eth | + * | U+00F1 | ñ | n | Latin small letter n with tilde | + * | U+00F2 | ò | o | Latin small letter o with grave | + * | U+00F3 | ó | o | Latin small letter o with acute | + * | U+00F4 | ô | o | Latin small letter o with circumflex | + * | U+00F5 | õ | o | Latin small letter o with tilde | + * | U+00F6 | ö | o | Latin small letter o with diaeresis | + * | U+00F8 | ø | o | Latin small letter o with stroke | + * | U+00F9 | ù | u | Latin small letter u with grave | + * | U+00FA | ú | u | Latin small letter u with acute | + * | U+00FB | û | u | Latin small letter u with circumflex | + * | U+00FC | ü | u | Latin small letter u with diaeresis | + * | U+00FD | ý | y | Latin small letter y with acute | + * | U+00FE | þ | th | Latin small letter Thorn | + * | U+00FF | ÿ | y | Latin small letter y with diaeresis | + * + * Decompositions for Latin Extended-A: + * + * | Code | Glyph | Replacement | Description | + * | ------- | ----- | ----------- | ------------------------------------------------- | + * | U+0100 | Ä | A | Latin capital letter A with macron | + * | U+0101 | Ä | a | Latin small letter a with macron | + * | U+0102 | Ä | A | Latin capital letter A with breve | + * | U+0103 | Ä | a | Latin small letter a with breve | + * | U+0104 | Ä | A | Latin capital letter A with ogonek | + * | U+0105 | Ä | a | Latin small letter a with ogonek | + * | U+01006 | Ä | C | Latin capital letter C with acute | + * | U+0107 | Ä | c | Latin small letter c with acute | + * | U+0108 | Ä | C | Latin capital letter C with circumflex | + * | U+0109 | Ä | c | Latin small letter c with circumflex | + * | U+010A | Ä | C | Latin capital letter C with dot above | + * | U+010B | Ä | c | Latin small letter c with dot above | + * | U+010C | Ä | C | Latin capital letter C with caron | + * | U+010D | Ä | c | Latin small letter c with caron | + * | U+010E | Ä | D | Latin capital letter D with caron | + * | U+010F | Ä | d | Latin small letter d with caron | + * | U+0110 | Ä | D | Latin capital letter D with stroke | + * | U+0111 | Ä | d | Latin small letter d with stroke | + * | U+0112 | Ä | E | Latin capital letter E with macron | + * | U+0113 | Ä | e | Latin small letter e with macron | + * | U+0114 | Ä | E | Latin capital letter E with breve | + * | U+0115 | Ä | e | Latin small letter e with breve | + * | U+0116 | Ä | E | Latin capital letter E with dot above | + * | U+0117 | Ä | e | Latin small letter e with dot above | + * | U+0118 | Ä | E | Latin capital letter E with ogonek | + * | U+0119 | Ä | e | Latin small letter e with ogonek | + * | U+011A | Ä | E | Latin capital letter E with caron | + * | U+011B | Ä | e | Latin small letter e with caron | + * | U+011C | Ä | G | Latin capital letter G with circumflex | + * | U+011D | Ä | g | Latin small letter g with circumflex | + * | U+011E | Ä | G | Latin capital letter G with breve | + * | U+011F | Ä | g | Latin small letter g with breve | + * | U+0120 | Ä | G | Latin capital letter G with dot above | + * | U+0121 | Ä¡ | g | Latin small letter g with dot above | + * | U+0122 | Ä¢ | G | Latin capital letter G with cedilla | + * | U+0123 | Ä£ | g | Latin small letter g with cedilla | + * | U+0124 | Ĥ | H | Latin capital letter H with circumflex | + * | U+0125 | Ä¥ | h | Latin small letter h with circumflex | + * | U+0126 | Ħ | H | Latin capital letter H with stroke | + * | U+0127 | ħ | h | Latin small letter h with stroke | + * | U+0128 | Ĩ | I | Latin capital letter I with tilde | + * | U+0129 | Ä© | i | Latin small letter i with tilde | + * | U+012A | Ī | I | Latin capital letter I with macron | + * | U+012B | Ä« | i | Latin small letter i with macron | + * | U+012C | Ĭ | I | Latin capital letter I with breve | + * | U+012D | Ä | i | Latin small letter i with breve | + * | U+012E | Ä® | I | Latin capital letter I with ogonek | + * | U+012F | į | i | Latin small letter i with ogonek | + * | U+0130 | Ä° | I | Latin capital letter I with dot above | + * | U+0131 | ı | i | Latin small letter dotless i | + * | U+0132 | IJ | IJ | Latin capital ligature IJ | + * | U+0133 | ij | ij | Latin small ligature ij | + * | U+0134 | Ä´ | J | Latin capital letter J with circumflex | + * | U+0135 | ĵ | j | Latin small letter j with circumflex | + * | U+0136 | Ķ | K | Latin capital letter K with cedilla | + * | U+0137 | Ä· | k | Latin small letter k with cedilla | + * | U+0138 | ĸ | k | Latin small letter Kra | + * | U+0139 | Ĺ | L | Latin capital letter L with acute | + * | U+013A | ĺ | l | Latin small letter l with acute | + * | U+013B | Ä» | L | Latin capital letter L with cedilla | + * | U+013C | ļ | l | Latin small letter l with cedilla | + * | U+013D | Ľ | L | Latin capital letter L with caron | + * | U+013E | ľ | l | Latin small letter l with caron | + * | U+013F | Ä¿ | L | Latin capital letter L with middle dot | + * | U+0140 | Å | l | Latin small letter l with middle dot | + * | U+0141 | Å | L | Latin capital letter L with stroke | + * | U+0142 | Å | l | Latin small letter l with stroke | + * | U+0143 | Å | N | Latin capital letter N with acute | + * | U+0144 | Å | n | Latin small letter N with acute | + * | U+0145 | Å | N | Latin capital letter N with cedilla | + * | U+0146 | Å | n | Latin small letter n with cedilla | + * | U+0147 | Å | N | Latin capital letter N with caron | + * | U+0148 | Å | n | Latin small letter n with caron | + * | U+0149 | Å | n | Latin small letter n preceded by apostrophe | + * | U+014A | Å | N | Latin capital letter Eng | + * | U+014B | Å | n | Latin small letter Eng | + * | U+014C | Å | O | Latin capital letter O with macron | + * | U+014D | Å | o | Latin small letter o with macron | + * | U+014E | Å | O | Latin capital letter O with breve | + * | U+014F | Å | o | Latin small letter o with breve | + * | U+0150 | Å | O | Latin capital letter O with double acute | + * | U+0151 | Å | o | Latin small letter o with double acute | + * | U+0152 | Å | OE | Latin capital ligature OE | + * | U+0153 | Å | oe | Latin small ligature oe | + * | U+0154 | Å | R | Latin capital letter R with acute | + * | U+0155 | Å | r | Latin small letter r with acute | + * | U+0156 | Å | R | Latin capital letter R with cedilla | + * | U+0157 | Å | r | Latin small letter r with cedilla | + * | U+0158 | Å | R | Latin capital letter R with caron | + * | U+0159 | Å | r | Latin small letter r with caron | + * | U+015A | Å | S | Latin capital letter S with acute | + * | U+015B | Å | s | Latin small letter s with acute | + * | U+015C | Å | S | Latin capital letter S with circumflex | + * | U+015D | Å | s | Latin small letter s with circumflex | + * | U+015E | Å | S | Latin capital letter S with cedilla | + * | U+015F | Å | s | Latin small letter s with cedilla | + * | U+0160 | Å | S | Latin capital letter S with caron | + * | U+0161 | Å¡ | s | Latin small letter s with caron | + * | U+0162 | Å¢ | T | Latin capital letter T with cedilla | + * | U+0163 | Å£ | t | Latin small letter t with cedilla | + * | U+0164 | Ť | T | Latin capital letter T with caron | + * | U+0165 | Å¥ | t | Latin small letter t with caron | + * | U+0166 | Ŧ | T | Latin capital letter T with stroke | + * | U+0167 | ŧ | t | Latin small letter t with stroke | + * | U+0168 | Ũ | U | Latin capital letter U with tilde | + * | U+0169 | Å© | u | Latin small letter u with tilde | + * | U+016A | Ū | U | Latin capital letter U with macron | + * | U+016B | Å« | u | Latin small letter u with macron | + * | U+016C | Ŭ | U | Latin capital letter U with breve | + * | U+016D | Å | u | Latin small letter u with breve | + * | U+016E | Å® | U | Latin capital letter U with ring above | + * | U+016F | ů | u | Latin small letter u with ring above | + * | U+0170 | Å° | U | Latin capital letter U with double acute | + * | U+0171 | ű | u | Latin small letter u with double acute | + * | U+0172 | Ų | U | Latin capital letter U with ogonek | + * | U+0173 | ų | u | Latin small letter u with ogonek | + * | U+0174 | Å´ | W | Latin capital letter W with circumflex | + * | U+0175 | ŵ | w | Latin small letter w with circumflex | + * | U+0176 | Ŷ | Y | Latin capital letter Y with circumflex | + * | U+0177 | Å· | y | Latin small letter y with circumflex | + * | U+0178 | Ÿ | Y | Latin capital letter Y with diaeresis | + * | U+0179 | Ź | Z | Latin capital letter Z with acute | + * | U+017A | ź | z | Latin small letter z with acute | + * | U+017B | Å» | Z | Latin capital letter Z with dot above | + * | U+017C | ż | z | Latin small letter z with dot above | + * | U+017D | Ž | Z | Latin capital letter Z with caron | + * | U+017E | ž | z | Latin small letter z with caron | + * | U+017F | Å¿ | s | Latin small letter long s | + * | U+01A0 | Æ | O | Latin capital letter O with horn | + * | U+01A1 | Æ¡ | o | Latin small letter o with horn | + * | U+01AF | Ư | U | Latin capital letter U with horn | + * | U+01B0 | Æ° | u | Latin small letter u with horn | + * | U+01CD | Ç | A | Latin capital letter A with caron | + * | U+01CE | Ç | a | Latin small letter a with caron | + * | U+01CF | Ç | I | Latin capital letter I with caron | + * | U+01D0 | Ç | i | Latin small letter i with caron | + * | U+01D1 | Ç | O | Latin capital letter O with caron | + * | U+01D2 | Ç | o | Latin small letter o with caron | + * | U+01D3 | Ç | U | Latin capital letter U with caron | + * | U+01D4 | Ç | u | Latin small letter u with caron | + * | U+01D5 | Ç | U | Latin capital letter U with diaeresis and macron | + * | U+01D6 | Ç | u | Latin small letter u with diaeresis and macron | + * | U+01D7 | Ç | U | Latin capital letter U with diaeresis and acute | + * | U+01D8 | Ç | u | Latin small letter u with diaeresis and acute | + * | U+01D9 | Ç | U | Latin capital letter U with diaeresis and caron | + * | U+01DA | Ç | u | Latin small letter u with diaeresis and caron | + * | U+01DB | Ç | U | Latin capital letter U with diaeresis and grave | + * | U+01DC | Ç | u | Latin small letter u with diaeresis and grave | + * + * Decompositions for Latin Extended-B: + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | ----------------------------------------- | + * | U+0218 | È | S | Latin capital letter S with comma below | + * | U+0219 | È | s | Latin small letter s with comma below | + * | U+021A | È | T | Latin capital letter T with comma below | + * | U+021B | È | t | Latin small letter t with comma below | + * + * Vowels with diacritic (Chinese, Hanyu Pinyin): + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | ----------------------------------------------------- | + * | U+0251 | É | a | Latin small letter alpha | + * | U+1EA0 | Ạ| A | Latin capital letter A with dot below | + * | U+1EA1 | ạ | a | Latin small letter a with dot below | + * | U+1EA2 | Ả | A | Latin capital letter A with hook above | + * | U+1EA3 | ả | a | Latin small letter a with hook above | + * | U+1EA4 | Ấ | A | Latin capital letter A with circumflex and acute | + * | U+1EA5 | ấ | a | Latin small letter a with circumflex and acute | + * | U+1EA6 | Ầ | A | Latin capital letter A with circumflex and grave | + * | U+1EA7 | ầ | a | Latin small letter a with circumflex and grave | + * | U+1EA8 | Ẩ | A | Latin capital letter A with circumflex and hook above | + * | U+1EA9 | ẩ | a | Latin small letter a with circumflex and hook above | + * | U+1EAA | Ẫ | A | Latin capital letter A with circumflex and tilde | + * | U+1EAB | ẫ | a | Latin small letter a with circumflex and tilde | + * | U+1EA6 | Ậ | A | Latin capital letter A with circumflex and dot below | + * | U+1EAD | Ạ| a | Latin small letter a with circumflex and dot below | + * | U+1EAE | Ắ | A | Latin capital letter A with breve and acute | + * | U+1EAF | ắ | a | Latin small letter a with breve and acute | + * | U+1EB0 | Ằ | A | Latin capital letter A with breve and grave | + * | U+1EB1 | ằ | a | Latin small letter a with breve and grave | + * | U+1EB2 | Ẳ | A | Latin capital letter A with breve and hook above | + * | U+1EB3 | ẳ | a | Latin small letter a with breve and hook above | + * | U+1EB4 | Ẵ | A | Latin capital letter A with breve and tilde | + * | U+1EB5 | ẵ | a | Latin small letter a with breve and tilde | + * | U+1EB6 | Ặ | A | Latin capital letter A with breve and dot below | + * | U+1EB7 | ặ | a | Latin small letter a with breve and dot below | + * | U+1EB8 | Ẹ | E | Latin capital letter E with dot below | + * | U+1EB9 | ẹ | e | Latin small letter e with dot below | + * | U+1EBA | Ẻ | E | Latin capital letter E with hook above | + * | U+1EBB | ẻ | e | Latin small letter e with hook above | + * | U+1EBC | Ẽ | E | Latin capital letter E with tilde | + * | U+1EBD | ẽ | e | Latin small letter e with tilde | + * | U+1EBE | Ế | E | Latin capital letter E with circumflex and acute | + * | U+1EBF | ế | e | Latin small letter e with circumflex and acute | + * | U+1EC0 | á» | E | Latin capital letter E with circumflex and grave | + * | U+1EC1 | á» | e | Latin small letter e with circumflex and grave | + * | U+1EC2 | á» | E | Latin capital letter E with circumflex and hook above | + * | U+1EC3 | á» | e | Latin small letter e with circumflex and hook above | + * | U+1EC4 | á» | E | Latin capital letter E with circumflex and tilde | + * | U+1EC5 | á» | e | Latin small letter e with circumflex and tilde | + * | U+1EC6 | á» | E | Latin capital letter E with circumflex and dot below | + * | U+1EC7 | á» | e | Latin small letter e with circumflex and dot below | + * | U+1EC8 | á» | I | Latin capital letter I with hook above | + * | U+1EC9 | á» | i | Latin small letter i with hook above | + * | U+1ECA | á» | I | Latin capital letter I with dot below | + * | U+1ECB | á» | i | Latin small letter i with dot below | + * | U+1ECC | á» | O | Latin capital letter O with dot below | + * | U+1ECD | á» | o | Latin small letter o with dot below | + * | U+1ECE | á» | O | Latin capital letter O with hook above | + * | U+1ECF | á» | o | Latin small letter o with hook above | + * | U+1ED0 | á» | O | Latin capital letter O with circumflex and acute | + * | U+1ED1 | á» | o | Latin small letter o with circumflex and acute | + * | U+1ED2 | á» | O | Latin capital letter O with circumflex and grave | + * | U+1ED3 | á» | o | Latin small letter o with circumflex and grave | + * | U+1ED4 | á» | O | Latin capital letter O with circumflex and hook above | + * | U+1ED5 | á» | o | Latin small letter o with circumflex and hook above | + * | U+1ED6 | á» | O | Latin capital letter O with circumflex and tilde | + * | U+1ED7 | á» | o | Latin small letter o with circumflex and tilde | + * | U+1ED8 | á» | O | Latin capital letter O with circumflex and dot below | + * | U+1ED9 | á» | o | Latin small letter o with circumflex and dot below | + * | U+1EDA | á» | O | Latin capital letter O with horn and acute | + * | U+1EDB | á» | o | Latin small letter o with horn and acute | + * | U+1EDC | á» | O | Latin capital letter O with horn and grave | + * | U+1EDD | á» | o | Latin small letter o with horn and grave | + * | U+1EDE | á» | O | Latin capital letter O with horn and hook above | + * | U+1EDF | á» | o | Latin small letter o with horn and hook above | + * | U+1EE0 | á» | O | Latin capital letter O with horn and tilde | + * | U+1EE1 | ỡ | o | Latin small letter o with horn and tilde | + * | U+1EE2 | Ợ | O | Latin capital letter O with horn and dot below | + * | U+1EE3 | ợ | o | Latin small letter o with horn and dot below | + * | U+1EE4 | Ụ | U | Latin capital letter U with dot below | + * | U+1EE5 | ụ | u | Latin small letter u with dot below | + * | U+1EE6 | Ủ | U | Latin capital letter U with hook above | + * | U+1EE7 | ủ | u | Latin small letter u with hook above | + * | U+1EE8 | Ứ | U | Latin capital letter U with horn and acute | + * | U+1EE9 | ứ | u | Latin small letter u with horn and acute | + * | U+1EEA | Ừ | U | Latin capital letter U with horn and grave | + * | U+1EEB | ừ | u | Latin small letter u with horn and grave | + * | U+1EEC | Ử | U | Latin capital letter U with horn and hook above | + * | U+1EED | á» | u | Latin small letter u with horn and hook above | + * | U+1EEE | á»® | U | Latin capital letter U with horn and tilde | + * | U+1EEF | ữ | u | Latin small letter u with horn and tilde | + * | U+1EF0 | á»° | U | Latin capital letter U with horn and dot below | + * | U+1EF1 | á»± | u | Latin small letter u with horn and dot below | + * | U+1EF2 | Ỳ | Y | Latin capital letter Y with grave | + * | U+1EF3 | ỳ | y | Latin small letter y with grave | + * | U+1EF4 | á»´ | Y | Latin capital letter Y with dot below | + * | U+1EF5 | ỵ | y | Latin small letter y with dot below | + * | U+1EF6 | Ỷ | Y | Latin capital letter Y with hook above | + * | U+1EF7 | á»· | y | Latin small letter y with hook above | + * | U+1EF8 | Ỹ | Y | Latin capital letter Y with tilde | + * | U+1EF9 | ỹ | y | Latin small letter y with tilde | + * + * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`), + * and German (Switzerland) informal (`de_CH_informal`) locales: + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | --------------------------------------- | + * | U+00C4 | à | Ae | Latin capital letter A with diaeresis | + * | U+00E4 | ä | ae | Latin small letter a with diaeresis | + * | U+00D6 | à | Oe | Latin capital letter O with diaeresis | + * | U+00F6 | ö | oe | Latin small letter o with diaeresis | + * | U+00DC | à | Ue | Latin capital letter U with diaeresis | + * | U+00FC | ü | ue | Latin small letter u with diaeresis | + * | U+00DF | à | ss | Latin small letter sharp s | + * + * Danish (`da_DK`) locale: + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | --------------------------------------- | + * | U+00C6 | à | Ae | Latin capital letter AE | + * | U+00E6 | æ | ae | Latin small letter ae | + * | U+00D8 | à | Oe | Latin capital letter O with stroke | + * | U+00F8 | ø | oe | Latin small letter o with stroke | + * | U+00C5 | à | Aa | Latin capital letter A with ring above | + * | U+00E5 | Ã¥ | aa | Latin small letter a with ring above | + * + * Catalan (`ca`) locale: + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | --------------------------------------- | + * | U+00B7 | l·l | ll | Flown dot (between two Ls) | + * + * Serbian (`sr_RS`) locale: + * + * | Code | Glyph | Replacement | Description | + * | -------- | ----- | ----------- | --------------------------------------- | + * | U+0110 | Ä | DJ | Latin capital letter D with stroke | + * | U+0111 | Ä | dj | Latin small letter d with stroke | + * * @since 1.2.1 + * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`. + * @since 4.7.0 Added locale support for `sr_RS`. * * @param string $string Text that might have accent characters * @return string Filtered string with replaced "nice" characters. @@ -1132,220 +1511,225 @@ 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', - chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C', - chr(195).chr(136) => 'E', chr(195).chr(137) => 'E', - chr(195).chr(138) => 'E', chr(195).chr(139) => 'E', - chr(195).chr(140) => 'I', chr(195).chr(141) => 'I', - chr(195).chr(142) => 'I', chr(195).chr(143) => 'I', - chr(195).chr(144) => 'D', chr(195).chr(145) => 'N', - chr(195).chr(146) => 'O', chr(195).chr(147) => 'O', - chr(195).chr(148) => 'O', chr(195).chr(149) => 'O', - chr(195).chr(150) => 'O', chr(195).chr(153) => 'U', - chr(195).chr(154) => 'U', chr(195).chr(155) => 'U', - chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y', - chr(195).chr(158) => 'TH',chr(195).chr(159) => 's', - chr(195).chr(160) => 'a', chr(195).chr(161) => 'a', - chr(195).chr(162) => 'a', chr(195).chr(163) => 'a', - chr(195).chr(164) => 'a', chr(195).chr(165) => 'a', - chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c', - chr(195).chr(168) => 'e', chr(195).chr(169) => 'e', - chr(195).chr(170) => 'e', chr(195).chr(171) => 'e', - chr(195).chr(172) => 'i', chr(195).chr(173) => 'i', - chr(195).chr(174) => 'i', chr(195).chr(175) => 'i', - chr(195).chr(176) => 'd', chr(195).chr(177) => 'n', - chr(195).chr(178) => 'o', chr(195).chr(179) => 'o', - chr(195).chr(180) => 'o', chr(195).chr(181) => 'o', - chr(195).chr(182) => 'o', chr(195).chr(184) => 'o', - chr(195).chr(185) => 'u', chr(195).chr(186) => 'u', - chr(195).chr(187) => 'u', chr(195).chr(188) => 'u', - chr(195).chr(189) => 'y', chr(195).chr(190) => 'th', - chr(195).chr(191) => 'y', chr(195).chr(152) => 'O', + 'ª' => 'a', 'º' => 'o', + 'Ã' => 'A', 'Ã' => 'A', + 'Ã' => 'A', 'Ã' => 'A', + 'Ã' => 'A', 'à ' => 'A', + 'Ã' => 'AE','Ã' => 'C', + 'Ã' => 'E', 'Ã' => 'E', + 'Ã' => 'E', 'Ã' => 'E', + 'Ã' => 'I', 'Ã' => 'I', + 'Ã' => 'I', 'Ã' => 'I', + 'Ã' => 'D', 'Ã' => 'N', + 'Ã' => 'O', 'Ã' => 'O', + 'Ã' => 'O', 'Ã' => 'O', + 'Ã' => 'O', 'Ã' => 'U', + 'Ã' => 'U', 'Ã' => 'U', + 'Ã' => 'U', 'Ã' => 'Y', + 'Ã' => 'TH','Ã' => 's', + 'à ' => 'a', 'á' => 'a', + 'â' => 'a', 'ã' => 'a', + 'ä' => 'a', 'Ã¥' => 'a', + 'æ' => 'ae','ç' => 'c', + 'è' => 'e', 'é' => 'e', + 'ê' => 'e', 'ë' => 'e', + 'ì' => 'i', 'Ã' => 'i', + 'î' => 'i', 'ï' => 'i', + 'ð' => 'd', 'ñ' => 'n', + 'ò' => 'o', 'ó' => 'o', + 'ô' => 'o', 'õ' => 'o', + 'ö' => 'o', 'ø' => 'o', + 'ù' => 'u', 'ú' => 'u', + 'û' => 'u', 'ü' => 'u', + 'ý' => 'y', 'þ' => 'th', + 'ÿ' => 'y', 'Ã' => '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', - chr(196).chr(132) => 'A', chr(196).chr(133) => 'a', - chr(196).chr(134) => 'C', chr(196).chr(135) => 'c', - chr(196).chr(136) => 'C', chr(196).chr(137) => 'c', - chr(196).chr(138) => 'C', chr(196).chr(139) => 'c', - chr(196).chr(140) => 'C', chr(196).chr(141) => 'c', - chr(196).chr(142) => 'D', chr(196).chr(143) => 'd', - chr(196).chr(144) => 'D', chr(196).chr(145) => 'd', - chr(196).chr(146) => 'E', chr(196).chr(147) => 'e', - chr(196).chr(148) => 'E', chr(196).chr(149) => 'e', - chr(196).chr(150) => 'E', chr(196).chr(151) => 'e', - chr(196).chr(152) => 'E', chr(196).chr(153) => 'e', - chr(196).chr(154) => 'E', chr(196).chr(155) => 'e', - chr(196).chr(156) => 'G', chr(196).chr(157) => 'g', - chr(196).chr(158) => 'G', chr(196).chr(159) => 'g', - chr(196).chr(160) => 'G', chr(196).chr(161) => 'g', - chr(196).chr(162) => 'G', chr(196).chr(163) => 'g', - chr(196).chr(164) => 'H', chr(196).chr(165) => 'h', - chr(196).chr(166) => 'H', chr(196).chr(167) => 'h', - chr(196).chr(168) => 'I', chr(196).chr(169) => 'i', - chr(196).chr(170) => 'I', chr(196).chr(171) => 'i', - chr(196).chr(172) => 'I', chr(196).chr(173) => 'i', - chr(196).chr(174) => 'I', chr(196).chr(175) => 'i', - chr(196).chr(176) => 'I', chr(196).chr(177) => 'i', - chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij', - chr(196).chr(180) => 'J', chr(196).chr(181) => 'j', - chr(196).chr(182) => 'K', chr(196).chr(183) => 'k', - chr(196).chr(184) => 'k', chr(196).chr(185) => 'L', - chr(196).chr(186) => 'l', chr(196).chr(187) => 'L', - chr(196).chr(188) => 'l', chr(196).chr(189) => 'L', - chr(196).chr(190) => 'l', chr(196).chr(191) => 'L', - chr(197).chr(128) => 'l', chr(197).chr(129) => 'L', - chr(197).chr(130) => 'l', chr(197).chr(131) => 'N', - chr(197).chr(132) => 'n', chr(197).chr(133) => 'N', - chr(197).chr(134) => 'n', chr(197).chr(135) => 'N', - chr(197).chr(136) => 'n', chr(197).chr(137) => 'N', - chr(197).chr(138) => 'n', chr(197).chr(139) => 'N', - chr(197).chr(140) => 'O', chr(197).chr(141) => 'o', - chr(197).chr(142) => 'O', chr(197).chr(143) => 'o', - chr(197).chr(144) => 'O', chr(197).chr(145) => 'o', - chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe', - chr(197).chr(148) => 'R',chr(197).chr(149) => 'r', - chr(197).chr(150) => 'R',chr(197).chr(151) => 'r', - chr(197).chr(152) => 'R',chr(197).chr(153) => 'r', - chr(197).chr(154) => 'S',chr(197).chr(155) => 's', - chr(197).chr(156) => 'S',chr(197).chr(157) => 's', - chr(197).chr(158) => 'S',chr(197).chr(159) => 's', - chr(197).chr(160) => 'S', chr(197).chr(161) => 's', - chr(197).chr(162) => 'T', chr(197).chr(163) => 't', - chr(197).chr(164) => 'T', chr(197).chr(165) => 't', - chr(197).chr(166) => 'T', chr(197).chr(167) => 't', - chr(197).chr(168) => 'U', chr(197).chr(169) => 'u', - chr(197).chr(170) => 'U', chr(197).chr(171) => 'u', - chr(197).chr(172) => 'U', chr(197).chr(173) => 'u', - chr(197).chr(174) => 'U', chr(197).chr(175) => 'u', - chr(197).chr(176) => 'U', chr(197).chr(177) => 'u', - chr(197).chr(178) => 'U', chr(197).chr(179) => 'u', - chr(197).chr(180) => 'W', chr(197).chr(181) => 'w', - chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y', - chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z', - chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z', - chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z', - chr(197).chr(190) => 'z', chr(197).chr(191) => 's', + 'Ä' => 'A', 'Ä' => 'a', + 'Ä' => 'A', 'Ä' => 'a', + 'Ä' => 'A', 'Ä ' => 'a', + 'Ä' => 'C', 'Ä' => 'c', + 'Ä' => 'C', 'Ä' => 'c', + 'Ä' => 'C', 'Ä' => 'c', + 'Ä' => 'C', 'Ä' => 'c', + 'Ä' => 'D', 'Ä' => 'd', + 'Ä' => 'D', 'Ä' => 'd', + 'Ä' => 'E', 'Ä' => 'e', + 'Ä' => 'E', 'Ä' => 'e', + 'Ä' => 'E', 'Ä' => 'e', + 'Ä' => 'E', 'Ä' => 'e', + 'Ä' => 'E', 'Ä' => 'e', + 'Ä' => 'G', 'Ä' => 'g', + 'Ä' => 'G', 'Ä' => 'g', + 'Ä ' => 'G', 'Ä¡' => 'g', + 'Ä¢' => 'G', 'Ä£' => 'g', + 'Ĥ' => 'H', 'Ä¥' => 'h', + 'Ħ' => 'H', 'ħ' => 'h', + 'Ĩ' => 'I', 'Ä©' => 'i', + 'Ī' => 'I', 'Ä«' => 'i', + 'Ĭ' => 'I', 'Ä' => 'i', + 'Ä®' => 'I', 'į' => 'i', + 'Ä°' => 'I', 'ı' => 'i', + 'IJ' => 'IJ','ij' => 'ij', + 'Ä´' => 'J', 'ĵ' => 'j', + 'Ķ' => 'K', 'Ä·' => 'k', + 'ĸ' => 'k', 'Ĺ' => 'L', + 'ĺ' => 'l', 'Ä»' => 'L', + 'ļ' => 'l', 'Ľ' => 'L', + 'ľ' => 'l', 'Ä¿' => 'L', + 'Å' => 'l', 'Å' => 'L', + 'Å' => 'l', 'Å' => 'N', + 'Å' => 'n', 'Å ' => 'N', + 'Å' => 'n', 'Å' => 'N', + 'Å' => 'n', 'Å' => 'n', + 'Å' => 'N', 'Å' => 'n', + 'Å' => 'O', 'Å' => 'o', + 'Å' => 'O', 'Å' => 'o', + 'Å' => 'O', 'Å' => 'o', + 'Å' => 'OE','Å' => 'oe', + 'Å' => 'R','Å' => 'r', + 'Å' => 'R','Å' => 'r', + 'Å' => 'R','Å' => 'r', + 'Å' => 'S','Å' => 's', + 'Å' => 'S','Å' => 's', + 'Å' => 'S','Å' => 's', + 'Å ' => 'S', 'Å¡' => 's', + 'Å¢' => 'T', 'Å£' => 't', + 'Ť' => 'T', 'Å¥' => 't', + 'Ŧ' => 'T', 'ŧ' => 't', + 'Ũ' => 'U', 'Å©' => 'u', + 'Ū' => 'U', 'Å«' => 'u', + 'Ŭ' => 'U', 'Å' => 'u', + 'Å®' => 'U', 'ů' => 'u', + 'Å°' => 'U', 'ű' => 'u', + 'Ų' => 'U', 'ų' => 'u', + 'Å´' => 'W', 'ŵ' => 'w', + 'Ŷ' => 'Y', 'Å·' => 'y', + 'Ÿ' => 'Y', 'Ź' => 'Z', + 'ź' => 'z', 'Å»' => 'Z', + 'ż' => 'z', 'Ž' => 'Z', + 'ž' => 'z', 'Å¿' => 's', // Decompositions for Latin Extended-B - chr(200).chr(152) => 'S', chr(200).chr(153) => 's', - chr(200).chr(154) => 'T', chr(200).chr(155) => 't', + 'È' => 'S', 'È' => 's', + 'È' => 'T', 'È' => 't', // Euro Sign - chr(226).chr(130).chr(172) => 'E', + 'â¬' => 'E', // GBP (Pound) Sign - 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', + 'Æ ' => 'O', 'Æ¡' => 'o', + 'Ư' => 'U', 'Æ°' => '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', + 'Ầ' => 'A', 'ầ' => 'a', + 'Ằ' => 'A', 'ằ' => 'a', + 'á»' => 'E', 'á»' => 'e', + 'á»' => 'O', 'á»' => 'o', + 'á»' => 'O', 'á»' => 'o', + 'Ừ' => 'U', 'ừ' => 'u', + 'Ỳ' => 'Y', 'ỳ' => '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', + 'Ả' => 'A', 'ả' => 'a', + 'Ẩ' => 'A', 'ẩ' => 'a', + 'Ẳ' => 'A', 'ẳ' => 'a', + 'Ẻ' => 'E', 'ẻ' => 'e', + 'á»' => 'E', 'á»' => 'e', + 'á»' => 'I', 'á»' => 'i', + 'á»' => 'O', 'á»' => 'o', + 'á»' => 'O', 'á»' => 'o', + 'á»' => 'O', 'á»' => 'o', + 'Ủ' => 'U', 'ủ' => 'u', + 'Ử' => 'U', 'á»' => 'u', + 'Ỷ' => 'Y', 'á»·' => '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', + 'Ẫ' => 'A', 'ẫ' => 'a', + 'Ẵ' => 'A', 'ẵ' => 'a', + 'Ẽ' => 'E', 'ẽ' => 'e', + 'á»' => 'E', 'á» ' => 'e', + 'á»' => 'O', 'á»' => 'o', + 'á» ' => 'O', 'ỡ' => 'o', + 'á»®' => 'U', 'ữ' => 'u', + 'Ỹ' => 'Y', 'ỹ' => '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', + 'Ấ' => 'A', 'ấ' => 'a', + 'Ắ' => 'A', 'ắ' => 'a', + 'Ế' => 'E', 'ế' => 'e', + 'á»' => 'O', 'á»' => 'o', + 'á»' => 'O', 'á»' => 'o', + 'Ứ' => 'U', 'ứ' => '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', + 'Ạ' => 'A', 'ạ' => 'a', + 'Ậ' => 'A', 'áº' => 'a', + 'Ặ' => 'A', 'ặ' => 'a', + 'Ẹ' => 'E', 'ẹ' => 'e', + 'á»' => 'E', 'á»' => 'e', + 'á»' => 'I', 'á»' => 'i', + 'á»' => 'O', 'á»' => 'o', + 'á»' => 'O', 'á»' => 'o', + 'Ợ' => 'O', 'ợ' => 'o', + 'Ụ' => 'U', 'ụ' => 'u', + 'á»°' => 'U', 'á»±' => 'u', + 'á»´' => 'Y', 'ỵ' => 'y', // Vowels with diacritic (Chinese, Hanyu Pinyin) - chr(201).chr(145) => 'a', + 'É' => 'a', // macron - chr(199).chr(149) => 'U', chr(199).chr(150) => 'u', + 'Ç' => 'U', 'Ç' => 'u', // acute accent - chr(199).chr(151) => 'U', chr(199).chr(152) => 'u', + 'Ç' => 'U', 'Ç' => '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', + 'Ç' => 'A', 'Ç' => 'a', + 'Ç' => 'I', 'Ç' => 'i', + 'Ç' => 'O', 'Ç' => 'o', + 'Ç' => 'U', 'Ç' => 'u', + 'Ç' => 'U', 'Ç' => 'u', // grave accent - chr(199).chr(155) => 'U', chr(199).chr(156) => 'u', + 'Ç' => 'U', 'Ç' => 'u', ); // Used for locale-specific rules $locale = get_locale(); - if ( 'de_DE' == $locale || 'de_DE_formal' == $locale ) { - $chars[ chr(195).chr(132) ] = 'Ae'; - $chars[ chr(195).chr(164) ] = 'ae'; - $chars[ chr(195).chr(150) ] = 'Oe'; - $chars[ chr(195).chr(182) ] = 'oe'; - $chars[ chr(195).chr(156) ] = 'Ue'; - $chars[ chr(195).chr(188) ] = 'ue'; - $chars[ chr(195).chr(159) ] = 'ss'; + if ( 'de_DE' == $locale || 'de_DE_formal' == $locale || 'de_CH' == $locale || 'de_CH_informal' == $locale ) { + $chars[ 'Ã' ] = 'Ae'; + $chars[ 'ä' ] = 'ae'; + $chars[ 'Ã' ] = 'Oe'; + $chars[ 'ö' ] = 'oe'; + $chars[ 'Ã' ] = 'Ue'; + $chars[ 'ü' ] = 'ue'; + $chars[ 'Ã' ] = 'ss'; } elseif ( 'da_DK' === $locale ) { - $chars[ chr(195).chr(134) ] = 'Ae'; - $chars[ chr(195).chr(166) ] = 'ae'; - $chars[ chr(195).chr(152) ] = 'Oe'; - $chars[ chr(195).chr(184) ] = 'oe'; - $chars[ chr(195).chr(133) ] = 'Aa'; - $chars[ chr(195).chr(165) ] = 'aa'; + $chars[ 'Ã' ] = 'Ae'; + $chars[ 'æ' ] = 'ae'; + $chars[ 'Ã' ] = 'Oe'; + $chars[ 'ø' ] = 'oe'; + $chars[ 'à ' ] = 'Aa'; + $chars[ 'Ã¥' ] = 'aa'; + } elseif ( 'ca' === $locale ) { + $chars[ 'l·l' ] = 'll'; + } elseif ( 'sr_RS' === $locale ) { + $chars[ 'Ä' ] = 'DJ'; + $chars[ 'Ä' ] = 'dj'; } $string = strtr($string, $chars); } else { $chars = array(); // Assume ISO-8859-1 if not UTF-8 - $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158) - .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194) - .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202) - .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210) - .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218) - .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227) - .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235) - .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243) - .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251) - .chr(252).chr(253).chr(255); + $chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e" + ."\x9f\xa2\xa5\xb5\xc0\xc1\xc2" + ."\xc3\xc4\xc5\xc7\xc8\xc9\xca" + ."\xcb\xcc\xcd\xce\xcf\xd1\xd2" + ."\xd3\xd4\xd5\xd6\xd8\xd9\xda" + ."\xdb\xdc\xdd\xe0\xe1\xe2\xe3" + ."\xe4\xe5\xe7\xe8\xe9\xea\xeb" + ."\xec\xed\xee\xef\xf1\xf2\xf3" + ."\xf4\xf5\xf6\xf8\xf9\xfa\xfb" + ."\xfc\xfd\xff"; $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy"; $string = strtr($string, $chars['in'], $chars['out']); $double_chars = array(); - $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254)); + $double_chars['in'] = array("\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe"); $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'); $string = str_replace($double_chars['in'], $double_chars['out'], $string); } @@ -1360,7 +1744,8 @@ function remove_accents( $string ) { * operating systems and special characters requiring special escaping * to manipulate at the command line. Replaces spaces and consecutive * dashes with a single dash. Trims period, dash and underscore from beginning - * and end of filename. + * and end of filename. It is not guaranteed that this function will return a + * filename that is allowed to be uploaded. * * @since 2.1.0 * @@ -1371,7 +1756,7 @@ function sanitize_file_name( $filename ) { $filename_raw = $filename; $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%", "+", chr(0)); /** - * Filter the list of characters to remove from a filename. + * Filters the list of characters to remove from a filename. * * @since 2.8.0 * @@ -1385,13 +1770,21 @@ function sanitize_file_name( $filename ) { $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename ); $filename = trim( $filename, '.-_' ); + if ( false === strpos( $filename, '.' ) ) { + $mime_types = wp_get_mime_types(); + $filetype = wp_check_filetype( 'test.' . $filename, $mime_types ); + if ( $filetype['ext'] === $filename ) { + $filename = 'unnamed-file.' . $filetype['ext']; + } + } + // Split the filename into a base and extension[s] $parts = explode('.', $filename); // Return if only one extension if ( count( $parts ) <= 2 ) { /** - * Filter a sanitized filename string. + * Filters a sanitized filename string. * * @since 2.8.0 * @@ -1437,7 +1830,7 @@ function sanitize_file_name( $filename ) { * Removes tags, octets, entities, and if strict is enabled, will only keep * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username, * raw username (the username in the parameter), and the value of $strict as - * parameters for the 'sanitize_user' filter. + * parameters for the {@see 'sanitize_user'} filter. * * @since 2.0.0 * @@ -1462,7 +1855,7 @@ function sanitize_user( $username, $strict = false ) { $username = preg_replace( '|\s+|', ' ', $username ); /** - * Filter a sanitized username string. + * Filters a sanitized username string. * * @since 2.0.1 * @@ -1489,7 +1882,7 @@ function sanitize_key( $key ) { $key = preg_replace( '/[^a-z0-9_\-]/', '', $key ); /** - * Filter a sanitized key string. + * Filters a sanitized key string. * * @since 3.0.0 * @@ -1520,7 +1913,7 @@ function sanitize_title( $title, $fallback_title = '', $context = 'save' ) { $title = remove_accents($title); /** - * Filter a sanitized title string. + * Filters a sanitized title string. * * @since 1.2.0 * @@ -1580,12 +1973,12 @@ function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'displa } $title = strtolower($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 ); + // Convert nbsp, ndash and mdash HTML entities to hyphens + $title = str_replace( array( ' ', ' ', '–', '–', '—', '—' ), '-', $title ); // Strip these characters entirely $title = str_replace( array( @@ -1608,6 +2001,9 @@ function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'displa $title = str_replace( '%c3%97', 'x', $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); @@ -1662,7 +2058,7 @@ function sanitize_html_class( $class, $fallback = '' ) { return sanitize_html_class( $fallback ); } /** - * Filter a sanitized HTML class string. + * Filters a sanitized HTML class string. * * @since 2.8.0 * @@ -1897,8 +2293,8 @@ function force_balance_tags( $text ) { * Acts on text which is about to be edited. * * The $content is run through esc_textarea(), which uses htmlspecialchars() - * to convert special characters to HTML entities. If $richedit is set to true, - * it is simply a holder for the 'format_to_edit' filter. + * to convert special characters to HTML entities. If `$richedit` is set to true, + * it is simply a holder for the {@see 'format_to_edit'} filter. * * @since 0.71 * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity. @@ -1911,7 +2307,7 @@ function force_balance_tags( $text ) { */ function format_to_edit( $content, $rich_text = false ) { /** - * Filter the text to be formatted for editing. + * Filters the text to be formatted for editing. * * @since 1.2.0 * @@ -1995,7 +2391,7 @@ function untrailingslashit( $string ) { * Adds slashes to escape strings. * * Slashes will first be removed if magic_quotes_gpc is set, see {@link - * http://www.php.net/magic_quotes} for more details. + * https://secure.php.net/magic_quotes} for more details. * * @since 0.71 * @@ -2097,8 +2493,7 @@ function antispambot( $email_address, $hex_encoding = 0 ) { /** * Callback to convert URI match to HTML A element. * - * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link - * make_clickable()}. + * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). * * @since 2.3.2 * @access private @@ -2134,8 +2529,7 @@ function _make_url_clickable_cb( $matches ) { /** * Callback to convert URL match to HTML A element. * - * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link - * make_clickable()}. + * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). * * @since 2.3.2 * @access private @@ -2164,8 +2558,7 @@ function _make_web_ftp_clickable_cb( $matches ) { /** * Callback to convert email address match to HTML A element. * - * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link - * make_clickable()}. + * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). * * @since 2.3.2 * @access private @@ -2195,9 +2588,9 @@ function make_clickable( $text ) { $nested_code_pre = 0; // Keep track of how many levels link is nested inside
or
foreach ( $textarr as $piece ) {
- if ( preg_match( '|^]|i', $piece ) || preg_match( '|^]|i', $piece ) )
+ if ( preg_match( '|^]|i', $piece ) || preg_match( '|^]|i', $piece ) || preg_match( '|^' === strtolower( $piece ) || '' === strtolower( $piece ) ) )
$nested_code_pre--;
if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
@@ -2332,7 +2725,14 @@ function wp_rel_nofollow( $text ) {
function wp_rel_nofollow_callback( $matches ) {
$text = $matches[1];
$atts = shortcode_parse_atts( $matches[1] );
- $rel = 'nofollow';
+ $rel = 'nofollow';
+
+ if ( preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'http' ) ) . ')%i', $text ) ||
+ preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'https' ) ) . ')%i', $text )
+ ) {
+ return "";
+ }
+
if ( ! empty( $atts['rel'] ) ) {
$parts = array_map( 'trim', explode( ' ', $atts['rel'] ) );
if ( false === array_search( 'nofollow', $parts ) ) {
@@ -2353,7 +2753,8 @@ function wp_rel_nofollow_callback( $matches ) {
/**
* Convert one smiley code to the icon graphic file equivalent.
*
- * Callback handler for {@link convert_smilies()}.
+ * Callback handler for convert_smilies().
+ *
* Looks up one smiley code in the $wpsmiliestrans global array and returns an
* `` string for that smiley.
*
@@ -2383,7 +2784,7 @@ function translate_smiley( $matches ) {
}
/**
- * Filter the Smiley image URL before it's used in the image element.
+ * Filters the Smiley image URL before it's used in the image element.
*
* @since 2.9.0
*
@@ -2461,12 +2862,12 @@ function convert_smilies( $text ) {
*/
function is_email( $email, $deprecated = false ) {
if ( ! empty( $deprecated ) )
- _deprecated_argument( __FUNCTION__, '3.0' );
+ _deprecated_argument( __FUNCTION__, '3.0.0' );
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
/**
- * Filter whether an email address is valid.
+ * Filters whether an email address is valid.
*
* This filter is evaluated under several different contexts, such as 'email_too_short',
* 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
@@ -2664,7 +3065,7 @@ function iso8601_timezone_to_offset( $timezone ) {
*
* @since 1.5.0
*
- * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
+ * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}.
* @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
* @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
*/
@@ -2691,23 +3092,6 @@ function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
}
}
-/**
- * Adds a element attributes to open links in new windows.
- *
- * Comment text in popup windows should be filtered through this. Right now it's
- * a moderately dumb function, ideally it would detect whether a target or rel
- * attribute was already there and adjust its actions accordingly.
- *
- * @since 0.71
- *
- * @param string $text Content to replace links to open in a new window.
- * @return string Content that has filtered links.
- */
-function popuplinks( $text ) {
- $text = preg_replace('//i', "", $text);
- return $text;
-}
-
/**
* Strips out all characters that are not allowable in an email.
*
@@ -2720,7 +3104,7 @@ function sanitize_email( $email ) {
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
/**
- * Filter a sanitized email address.
+ * Filters a sanitized email address.
*
* This filter is evaluated under several contexts, including 'email_too_short',
* 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
@@ -2833,37 +3217,42 @@ function human_time_diff( $from, $to = '' ) {
$mins = round( $diff / MINUTE_IN_SECONDS );
if ( $mins <= 1 )
$mins = 1;
- /* translators: min=minute */
+ /* translators: Time difference between two dates, in minutes (min=minute). 1: Number of minutes */
$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;
+ /* translators: Time difference between two dates, in hours. 1: Number of hours */
$since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
} elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
$days = round( $diff / DAY_IN_SECONDS );
if ( $days <= 1 )
$days = 1;
+ /* translators: Time difference between two dates, in days. 1: Number of days */
$since = sprintf( _n( '%s day', '%s days', $days ), $days );
} elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
$weeks = round( $diff / WEEK_IN_SECONDS );
if ( $weeks <= 1 )
$weeks = 1;
+ /* translators: Time difference between two dates, in weeks. 1: Number of weeks */
$since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
} elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
$months = round( $diff / MONTH_IN_SECONDS );
if ( $months <= 1 )
$months = 1;
+ /* translators: Time difference between two dates, in months. 1: Number of months */
$since = sprintf( _n( '%s month', '%s months', $months ), $months );
} elseif ( $diff >= YEAR_IN_SECONDS ) {
$years = round( $diff / YEAR_IN_SECONDS );
if ( $years <= 1 )
$years = 1;
+ /* translators: Time difference between two dates, in years. 1: Number of years */
$since = sprintf( _n( '%s year', '%s years', $years ), $years );
}
/**
- * Filter the human readable difference between two timestamps.
+ * Filters the human readable difference between two timestamps.
*
* @since 4.0.0
*
@@ -2882,8 +3271,8 @@ function human_time_diff( $from, $to = '' ) {
* 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
+ * The 55 word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter
+ * The ' […]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter
*
* @since 1.5.0
*
@@ -2902,7 +3291,7 @@ function wp_trim_excerpt( $text = '' ) {
$text = str_replace(']]>', ']]>', $text);
/**
- * Filter the number of words in an excerpt.
+ * Filters the number of words in an excerpt.
*
* @since 2.7.0
*
@@ -2910,7 +3299,7 @@ function wp_trim_excerpt( $text = '' ) {
*/
$excerpt_length = apply_filters( 'excerpt_length', 55 );
/**
- * Filter the string in the "more" link displayed after a trimmed excerpt.
+ * Filters the string in the "more" link displayed after a trimmed excerpt.
*
* @since 2.9.0
*
@@ -2920,7 +3309,7 @@ function wp_trim_excerpt( $text = '' ) {
$text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
}
/**
- * Filter the trimmed excerpt string.
+ * Filters the trimmed excerpt string.
*
* @since 2.8.0
*
@@ -2976,7 +3365,7 @@ function wp_trim_words( $text, $num_words = 55, $more = null ) {
}
/**
- * Filter the text content after words have been trimmed.
+ * Filters the text content after words have been trimmed.
*
* @since 3.3.0
*
@@ -2999,7 +3388,7 @@ function wp_trim_words( $text, $num_words = 55, $more = null ) {
function ent2ncr( $text ) {
/**
- * Filter text before named entities are converted into numbered entities.
+ * Filters text before named entities are converted into numbered entities.
*
* A non-null string must be returned for the filter to be evaluated.
*
@@ -3285,7 +3674,11 @@ function ent2ncr( $text ) {
*
* @since 4.3.0
*
- * @param string $text The text to be formatted.
+ * @see _WP_Editors::editor()
+ *
+ * @param string $text The text to be formatted.
+ * @param string $default_editor The default editor for the current user.
+ * It is usually either 'html' or 'tinymce'.
* @return string The formatted text after filter is applied.
*/
function format_for_editor( $text, $default_editor = null ) {
@@ -3294,11 +3687,13 @@ function format_for_editor( $text, $default_editor = null ) {
}
/**
- * Filter the text after it is formatted for the editor.
+ * Filters the text after it is formatted for the editor.
*
* @since 4.3.0
*
- * @param string $text The formatted text.
+ * @param string $text The formatted text.
+ * @param string $default_editor The default editor for the current user.
+ * It is usually either 'html' or 'tinymce'.
*/
return apply_filters( 'format_for_editor', $text, $default_editor );
}
@@ -3352,7 +3747,7 @@ function esc_sql( $data ) {
* Checks and cleans a URL.
*
* A number of characters are removed from the URL. If the URL is for displaying
- * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
+ * (the default behaviour) ampersands are also replaced. The {@see 'clean_url'} filter
* is applied to the returned cleaned URL.
*
* @since 2.8.0
@@ -3361,7 +3756,7 @@ function esc_sql( $data ) {
* @param array $protocols Optional. An array of acceptable protocols.
* Defaults to return value of wp_allowed_protocols()
* @param string $_context Private. Use esc_url_raw() for database usage.
- * @return string The cleaned $url after the 'clean_url' filter is applied.
+ * @return string The cleaned $url after the {@see 'clean_url'} filter is applied.
*/
function esc_url( $url, $protocols = null, $_context = 'display' ) {
$original_url = $url;
@@ -3445,7 +3840,7 @@ function esc_url( $url, $protocols = null, $_context = 'display' ) {
}
/**
- * Filter a string cleaned and escaped for output as a URL.
+ * Filters a string cleaned and escaped for output as a URL.
*
* @since 2.3.0
*
@@ -3472,7 +3867,7 @@ function esc_url_raw( $url, $protocols = null ) {
/**
* Convert entities, while preserving already-encoded entities.
*
- * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
+ * @link https://secure.php.net/htmlentities Borrowed from the PHP Manual user notes.
*
* @since 1.2.2
*
@@ -3490,7 +3885,7 @@ function htmlentities2( $myHTML ) {
*
* 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.
+ * be in single quotes. The {@see 'js_escape'} filter is also applied here.
*
* @since 2.8.0
*
@@ -3504,7 +3899,7 @@ function esc_js( $text ) {
$safe_text = str_replace( "\r", '', $safe_text );
$safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
/**
- * Filter a string cleaned and escaped for output in JavaScript.
+ * Filters a string cleaned and escaped for output in JavaScript.
*
* Text passed to esc_js() is stripped of invalid or special characters,
* and properly slashed for output.
@@ -3529,7 +3924,7 @@ function esc_html( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
/**
- * Filter a string cleaned and escaped for output in HTML.
+ * Filters a string cleaned and escaped for output in HTML.
*
* Text passed to esc_html() is stripped of invalid or special characters
* before output.
@@ -3554,7 +3949,7 @@ function esc_attr( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
/**
- * Filter a string cleaned and escaped for output in an HTML attribute.
+ * Filters a string cleaned and escaped for output in an HTML attribute.
*
* Text passed to esc_attr() is stripped of invalid or special characters
* before output.
@@ -3578,7 +3973,7 @@ function esc_attr( $text ) {
function esc_textarea( $text ) {
$safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
/**
- * Filter a string cleaned and escaped for output in a textarea element.
+ * Filters a string cleaned and escaped for output in a textarea element.
*
* @since 3.1.0
*
@@ -3599,7 +3994,7 @@ function esc_textarea( $text ) {
function tag_escape( $tag_name ) {
$safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
/**
- * Filter a string cleaned and escaped for output as an HTML tag.
+ * Filters a string cleaned and escaped for output as an HTML tag.
*
* @since 2.8.0
*
@@ -3703,10 +4098,13 @@ function sanitize_option( $option, $value ) {
case 'blogdescription':
case 'blogname':
$value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( $value !== $original_value ) {
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) );
+ }
+
if ( is_wp_error( $value ) ) {
$error = $value->get_error_message();
} else {
- $value = wp_kses_post( $value );
$value = esc_html( $value );
}
break;
@@ -3839,6 +4237,14 @@ function sanitize_option( $option, $value ) {
$value = esc_url_raw( $value );
$value = str_replace( 'http://', '', $value );
}
+
+ if ( 'permalink_structure' === $option && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value ) ) {
+ $error = sprintf(
+ /* translators: %s: Codex URL */
+ __( 'A structure tag is required when using custom permalinks. Learn more' ),
+ __( 'https://codex.wordpress.org/Using_Permalinks#Choosing_your_permalink_structure' )
+ );
+ }
break;
case 'default_role' :
@@ -3868,7 +4274,7 @@ function sanitize_option( $option, $value ) {
}
/**
- * Filter an option value following sanitization.
+ * Filters an option value following sanitization.
*
* @since 2.3.0
* @since 4.3.0 Added the `$original_value` parameter.
@@ -3889,24 +4295,30 @@ function sanitize_option( $option, $value ) {
*
* @param mixed $value The array, object, or scalar.
* @param callable $callback The function to map onto $value.
- * @return The value with the callback applied to all non-arrays and non-objects inside it.
+ * @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
*/
function map_deep( $value, $callback ) {
- if ( is_array( $value ) || is_object( $value ) ) {
- foreach ( $value as &$item ) {
- $item = map_deep( $item, $callback );
+ if ( is_array( $value ) ) {
+ foreach ( $value as $index => $item ) {
+ $value[ $index ] = map_deep( $item, $callback );
+ }
+ } elseif ( is_object( $value ) ) {
+ $object_vars = get_object_vars( $value );
+ foreach ( $object_vars as $property_name => $property_value ) {
+ $value->$property_name = map_deep( $property_value, $callback );
}
- return $value;
} else {
- return call_user_func( $callback, $value );
+ $value = call_user_func( $callback, $value );
}
+
+ return $value;
}
/**
* Parses a string into variables to be stored in an array.
*
- * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
- * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
+ * Uses {@link https://secure.php.net/parse_str parse_str()} and stripslashes if
+ * {@link https://secure.php.net/magic_quotes magic_quotes_gpc} is on.
*
* @since 2.2.1
*
@@ -3918,7 +4330,7 @@ function wp_parse_str( $string, &$array ) {
if ( get_magic_quotes_gpc() )
$array = stripslashes_deep( $array );
/**
- * Filter the array of variables derived from a parsed string.
+ * Filters the array of variables derived from a parsed string.
*
* @since 2.3.0
*
@@ -3959,7 +4371,7 @@ function wp_pre_kses_less_than_callback( $matches ) {
* WordPress implementation of PHP sprintf() with filters.
*
* @since 2.5.0
- * @link http://www.php.net/sprintf
+ * @link https://secure.php.net/sprintf
*
* @param string $pattern The string which formatted args are inserted.
* @param mixed $args ,... Arguments to be formatted into the $pattern string.
@@ -4003,7 +4415,7 @@ function wp_sprintf( $pattern ) {
}
/**
- * Filter a fragment from the pattern passed to wp_sprintf().
+ * Filters a fragment from the pattern passed to wp_sprintf().
*
* If the fragment is unchanged, then sprintf() will be run on the fragment.
*
@@ -4049,7 +4461,7 @@ function wp_sprintf_l( $pattern, $args ) {
return '';
/**
- * Filter the translated delimiters used by wp_sprintf_l().
+ * Filters the translated delimiters used by wp_sprintf_l().
* Placeholders (%s) are included to assist translators and then
* removed before the array of strings reaches the filter.
*
@@ -4236,30 +4648,93 @@ function wp_strip_all_tags($string, $remove_breaks = false) {
}
/**
- * Sanitize a string from user input or from the db
+ * Sanitizes a string from user input or from the database.
*
- * check for invalid UTF-8,
- * Convert single < characters to entity,
- * strip all tags,
- * remove line breaks, tabs and extra white space,
- * strip octets.
+ * - Checks for invalid UTF-8,
+ * - Converts single `<` characters to entities
+ * - Strips all tags
+ * - Removes line breaks, tabs, and extra whitespace
+ * - Strips octets
*
* @since 2.9.0
*
- * @param string $str
- * @return string
+ * @see sanitize_textarea_field()
+ * @see wp_check_invalid_utf8()
+ * @see wp_strip_all_tags()
+ *
+ * @param string $str String to sanitize.
+ * @return string Sanitized string.
*/
function sanitize_text_field( $str ) {
+ $filtered = _sanitize_text_fields( $str, false );
+
+ /**
+ * Filters a sanitized text field string.
+ *
+ * @since 2.9.0
+ *
+ * @param string $filtered The sanitized string.
+ * @param string $str The string prior to being sanitized.
+ */
+ return apply_filters( 'sanitize_text_field', $filtered, $str );
+}
+
+/**
+ * Sanitizes a multiline string from user input or from the database.
+ *
+ * The function is like sanitize_text_field(), but preserves
+ * new lines (\n) and other whitespace, which are legitimate
+ * input in textarea elements.
+ *
+ * @see sanitize_text_field()
+ *
+ * @since 4.7.0
+ *
+ * @param string $str String to sanitize.
+ * @return string Sanitized string.
+ */
+function sanitize_textarea_field( $str ) {
+ $filtered = _sanitize_text_fields( $str, true );
+
+ /**
+ * Filters a sanitized textarea field string.
+ *
+ * @since 4.7.0
+ *
+ * @param string $filtered The sanitized string.
+ * @param string $str The string prior to being sanitized.
+ */
+ return apply_filters( 'sanitize_textarea_field', $filtered, $str );
+}
+
+/**
+ * Internal helper function to sanitize a string from user input or from the db
+ *
+ * @since 4.7.0
+ * @access private
+ *
+ * @param string $str String to sanitize.
+ * @param bool $keep_newlines optional Whether to keep newlines. Default: false.
+ * @return string Sanitized string.
+ */
+function _sanitize_text_fields( $str, $keep_newlines = false ) {
$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) );
+ $filtered = wp_strip_all_tags( $filtered, false );
+
+ // Use html entities in a special case to make sure no later
+ // newline stripping stage could lead to a functional tag
+ $filtered = str_replace("<\n", "<\n", $filtered);
}
+ if ( ! $keep_newlines ) {
+ $filtered = preg_replace( '/[\r\n\t ]+/', ' ', $filtered );
+ }
+ $filtered = trim( $filtered );
+
$found = false;
while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
$filtered = str_replace($match[0], '', $filtered);
@@ -4271,15 +4746,7 @@ function sanitize_text_field( $str ) {
$filtered = trim( preg_replace('/ +/', ' ', $filtered) );
}
- /**
- * Filter a sanitized text field string.
- *
- * @since 2.9.0
- *
- * @param string $filtered The sanitized string.
- * @param string $str The string prior to being sanitized.
- */
- return apply_filters( 'sanitize_text_field', $filtered, $str );
+ return $filtered;
}
/**
@@ -4303,6 +4770,9 @@ function wp_basename( $path, $suffix = '' ) {
* @since 3.0.0
*
* @staticvar string|false $dblq
+ *
+ * @param string $text The text to be modified.
+ * @return string The modified text.
*/
function capital_P_dangit( $text ) {
// Simple replacement for titles
@@ -4331,7 +4801,7 @@ function capital_P_dangit( $text ) {
function sanitize_mime_type( $mime_type ) {
$sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
/**
- * Filter a mime type following sanitization.
+ * Filters a mime type following sanitization.
*
* @since 3.1.3
*
@@ -4358,7 +4828,7 @@ function sanitize_trackback_urls( $to_ping ) {
$urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
$urls_to_ping = implode( "\n", $urls_to_ping );
/**
- * Filter a list of trackback URLs following sanitization.
+ * Filters a list of trackback URLs following sanitization.
*
* The string returned here consists of a space or carriage return-delimited list
* of trackback URLs.
@@ -4451,7 +4921,7 @@ function wp_spaces_regexp() {
if ( empty( $spaces ) ) {
/**
- * Filter the regexp for common whitespace characters.
+ * Filters the regexp for common whitespace characters.
*
* This string is substituted for the \s sequence as needed in regular
* expressions. For websites not written in English, different characters
@@ -4502,12 +4972,12 @@ img.emoji {
}
/**
+ * Print the inline Emoji detection script if it is not already printed.
*
- * @global string $wp_version
+ * @since 4.2.0
* @staticvar bool $printed
*/
function print_emoji_detection_script() {
- global $wp_version;
static $printed = false;
if ( $printed ) {
@@ -4516,27 +4986,56 @@ function print_emoji_detection_script() {
$printed = true;
+ _print_emoji_detection_script();
+}
+
+/**
+ * Prints inline Emoji dection script
+ *
+ * @ignore
+ * @since 4.6.0
+ * @access private
+ */
+function _print_emoji_detection_script() {
$settings = array(
/**
- * Filter the URL where emoji images are hosted.
+ * Filters the URL where emoji png images are hosted.
*
* @since 4.2.0
*
- * @param string The emoji base URL.
+ * @param string The emoji base URL for png images.
*/
- 'baseUrl' => apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) ),
+ 'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/2.2.1/72x72/' ),
/**
- * Filter the extension of the emoji files.
+ * Filters the extension of the emoji png files.
*
* @since 4.2.0
*
- * @param string The emoji extension. Default .png.
+ * @param string The emoji extension for png files. Default .png.
*/
'ext' => apply_filters( 'emoji_ext', '.png' ),
+
+ /**
+ * Filters the URL where emoji SVG images are hosted.
+ *
+ * @since 4.6.0
+ *
+ * @param string The emoji base URL for svg images.
+ */
+ 'svgUrl' => apply_filters( 'emoji_svg_url', 'https://s.w.org/images/core/emoji/2.2.1/svg/' ),
+
+ /**
+ * Filters the extension of the emoji SVG files.
+ *
+ * @since 4.6.0
+ *
+ * @param string The emoji extension for svg files. Default .svg.
+ */
+ 'svgExt' => apply_filters( 'emoji_svg_ext', '.svg' ),
);
- $version = 'ver=' . $wp_version;
+ $version = 'ver=' . get_bloginfo( 'version' );
if ( SCRIPT_DEBUG ) {
$settings['source'] = array(
@@ -4571,7 +5070,7 @@ function print_emoji_detection_script() {
?>