. foreach ( $pees as $tinkle ) { $pee .= '
' . trim($tinkle, "\n") . "
\s*
inside
([^<]+)!', "
$1
\s*(]*>)\s*
(|", "$1", $pee); // problem with nested lists + + // If an opening or closing block element tag is wrapped in a , unwrap it. + $pee = preg_replace('!\s*(]*>)\s*!', "$1", $pee); + + // In some cases may get wrapped in , fix them. + $pee = preg_replace("|(|", "$1", $pee); + + // If a is wrapped with a , move it inside the . $pee = preg_replace('|]*)>|i', "", $pee); $pee = str_replace('', '
, unwrap it. + $pee = preg_replace('!
, fix them. + $pee = preg_replace("|
(|", "$1", $pee); + + // If a is wrapped with a , move it inside the . $pee = preg_replace('|]*)>|i', "", $pee); $pee = str_replace('
is wrapped with a , move it inside the . $pee = preg_replace('|]*)>|i', "", $pee); $pee = str_replace('
, move it inside the
. $pee = preg_replace('|]*)>|i', "", $pee); $pee = str_replace('
]*)>|i', "", $pee); $pee = str_replace('
", $pee); $pee = str_replace('
tag, remove it. $pee = preg_replace('!
\s*(]*>)!', "$1", $pee); + + // If an opening or closing block element tag is followed by a closing
tag, remove it. $pee = preg_replace('!(]*>)\s*
tags with their original content. if ( !empty($pre_tags) ) $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee); + // Restore newlines in all elements. + if ( false !== strpos( $pee, '' ) ) { + $pee = str_replace( array( ' ', '' ), "\n", $pee ); + } + return $pee; } +/** + * Separate HTML elements and comments from the text. + * + * @since 4.2.4 + * + * @param string $input The text which has to be formatted. + * @return array The formatted text. + */ +function wp_html_split( $input ) { + static $regex; + + if ( ! isset( $regex ) ) { + $comments = + '!' // Start of comment, after the <. + . '(?:' // Unroll the loop: Consume everything until --> is found. + . '-(?!->)' // Dash not followed by end of comment. + . '[^\-]*+' // Consume non-dashes. + . ')*+' // Loop possessively. + . '(?:-->)?'; // End of comment. If not found, match all input. + + $cdata = + '!\[CDATA\[' // Start of comment, after the <. + . '[^\]]*+' // Consume non-]. + . '(?:' // Unroll the loop: Consume everything until ]]> is found. + . '](?!]>)' // One ] not followed by end of comment. + . '[^\]]*+' // Consume non-]. + . ')*+' // Loop possessively. + . '(?:]]>)?'; // End of comment. If not found, match all input. + + $regex = + '/(' // Capture the entire match. + . '<' // Find start of element. + . '(?(?=!--)' // Is this a comment? + . $comments // Find end of comment. + . '|' + . '(?(?=!\[CDATA\[)' // Is this a comment? + . $cdata // Find end of comment. + . '|' + . '[^>]*>?' // Find end of element. If not found, match all input. + . ')' + . ')' + . ')/s'; + } + + return preg_split( $regex, $input, -1, PREG_SPLIT_DELIM_CAPTURE ); +} + +/** + * Replace characters or phrases within HTML elements only. + * + * @since 4.2.3 + * + * @param string $haystack The text which has to be formatted. + * @param array $replace_pairs In the form array('from' => 'to', ...). + * @return string The formatted text. + */ +function wp_replace_in_html_tags( $haystack, $replace_pairs ) { + // Find all elements. + $textarr = wp_html_split( $haystack ); + $changed = false; + + // Optimize when searching for one item. + if ( 1 === count( $replace_pairs ) ) { + // Extract $needle and $replace. + foreach ( $replace_pairs as $needle => $replace ); + + // Loop through delimeters (elements) only. + for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) { + if ( false !== strpos( $textarr[$i], $needle ) ) { + $textarr[$i] = str_replace( $needle, $replace, $textarr[$i] ); + $changed = true; + } + } + } else { + // Extract all $needles. + $needles = array_keys( $replace_pairs ); + + // Loop through delimeters (elements) only. + for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) { + foreach ( $needles as $needle ) { + if ( false !== strpos( $textarr[$i], $needle ) ) { + $textarr[$i] = strtr( $textarr[$i], $replace_pairs ); + $changed = true; + // After one strtr() break out of the foreach loop and look at next element. + break; + } + } + } + } + + if ( $changed ) { + $haystack = implode( $textarr ); + } + + return $haystack; +} + /** * Newline preservation help function for wpautop * @@ -474,7 +710,7 @@ function wpautop($pee, $br = true) { * @return string */ function _autop_newline_preservation_helper( $matches ) { - return str_replace("\n", "", $matches[0]); + return str_replace( "\n", "", $matches[0] ); } /** @@ -484,6 +720,8 @@ function _autop_newline_preservation_helper( $matches ) { * * @since 2.9.0 * + * @global array $shortcode_tags + * * @param string $pee The content. * @return string The filtered content. */ @@ -544,20 +782,20 @@ function shortcode_unautop( $pee ) { * @param string $str The string to be checked * @return bool True if $str fits a UTF-8 model, false otherwise. */ -function seems_utf8($str) { +function seems_utf8( $str ) { mbstring_binary_safe_encoding(); $length = strlen($str); reset_mbstring_encoding(); for ($i=0; $i < $length; $i++) { $c = ord($str[$i]); - if ($c < 0x80) $n = 0; # 0bbbbbbb - elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb - elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb - elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb - elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb - elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b - else return false; # Does not match any model - for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? + if ($c < 0x80) $n = 0; // 0bbbbbbb + elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb + elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb + elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb + elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb + elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b + else return false; // Does not match any model + for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ? if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) return false; } @@ -576,10 +814,12 @@ function seems_utf8($str) { * @since 1.2.2 * @access private * - * @param string $string The text which is to be encoded. - * @param int $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. - * @param string $charset Optional. The character encoding of the string. Default is false. - * @param boolean $double_encode Optional. Whether to encode existing html entities. Default is false. + * @staticvar string $_charset + * + * @param string $string The text which is to be encoded. + * @param int $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. + * @param string $charset Optional. The character encoding of the string. Default is false. + * @param bool $double_encode Optional. Whether to encode existing html entities. Default is false. * @return string The encoded text with HTML entities. */ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) { @@ -600,7 +840,7 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals // Store the site charset as a static to avoid multiple calls to wp_load_alloptions() if ( ! $charset ) { - static $_charset; + static $_charset = null; if ( ! isset( $_charset ) ) { $alloptions = wp_load_alloptions(); $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : ''; @@ -620,25 +860,14 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals $quote_style = ENT_NOQUOTES; } - // Handle double encoding ourselves - if ( $double_encode ) { - $string = @htmlspecialchars( $string, $quote_style, $charset ); - } else { - // Decode & into & - $string = wp_specialchars_decode( $string, $_quote_style ); - - // Guarantee every &entity; is valid or re-encode the & + if ( ! $double_encode ) { + // Guarantee every &entity; is valid, convert &garbage; into &garbage; + // This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable. $string = wp_kses_normalize_entities( $string ); - - // Now re-encode everything except &entity; - $string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE ); - - for ( $i = 0; $i < count( $string ); $i += 2 ) - $string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset ); - - $string = implode( '', $string ); } + $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode ); + // Backwards compatibility if ( 'single' === $_quote_style ) $string = str_replace( "'", ''', $string ); @@ -656,8 +885,14 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals * * @since 2.8.0 * - * @param string $string The text which is to be decoded. - * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. + * @param string $string The text which is to be decoded. + * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT, + * both single and double if set to ENT_QUOTES or + * none if set to ENT_NOQUOTES. + * Also compatible with old _wp_specialchars() values; + * converting single quotes if set to 'single', + * double if set to 'double' or both if otherwise set. + * Default is ENT_NOQUOTES. * @return string The decoded text without HTML entities. */ function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) { @@ -713,8 +948,11 @@ function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) { * * @since 2.8.0 * - * @param string $string The text which is to be checked. - * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false. + * @staticvar bool $is_utf8 + * @staticvar bool $utf8_pcre + * + * @param string $string The text which is to be checked. + * @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false. * @return string The checked text. */ function wp_check_invalid_utf8( $string, $strip = false ) { @@ -725,17 +963,17 @@ function wp_check_invalid_utf8( $string, $strip = false ) { } // Store the site charset as a static to avoid multiple calls to get_option() - static $is_utf8; - if ( !isset( $is_utf8 ) ) { + static $is_utf8 = null; + if ( ! isset( $is_utf8 ) ) { $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ); } - if ( !$is_utf8 ) { + if ( ! $is_utf8 ) { return $string; } // Check for support for utf8 in the installed PCRE library once and store the result in a static - static $utf8_pcre; - if ( !isset( $utf8_pcre ) ) { + static $utf8_pcre = null; + if ( ! isset( $utf8_pcre ) ) { $utf8_pcre = @preg_match( '/^./u', 'a' ); } // We can't demand utf8 in the PCRE installation, so just return the string in those cases @@ -762,7 +1000,7 @@ function wp_check_invalid_utf8( $string, $strip = false ) { * @since 1.5.0 * * @param string $utf8_string - * @param int $length Max length of the string + * @param int $length Max length of the string * @return string String with Unicode encoded for URI. */ function utf8_uri_encode( $utf8_string, $length = 0 ) { @@ -785,21 +1023,27 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) { $unicode .= chr($value); $unicode_length++; } else { - if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3; + if ( count( $values ) == 0 ) { + if ( $value < 224 ) { + $num_octets = 2; + } elseif ( $value < 240 ) { + $num_octets = 3; + } else { + $num_octets = 4; + } + } $values[] = $value; if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length ) break; if ( count( $values ) == $num_octets ) { - if ($num_octets == 3) { - $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]); - $unicode_length += 9; - } else { - $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]); - $unicode_length += 6; + for ( $j = 0; $j < $num_octets; $j++ ) { + $unicode .= '%' . dechex( $values[ $j ] ); } + $unicode_length += $num_octets * 3; + $values = array(); $num_octets = 1; } @@ -819,7 +1063,7 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) { * @param string $string Text that might have accent characters * @return string Filtered string with replaced "nice" characters. */ -function remove_accents($string) { +function remove_accents( $string ) { if ( !preg_match('/[\x80-\xff]/', $string) ) return $string; @@ -1003,7 +1247,7 @@ function remove_accents($string) { // Used for locale-specific rules $locale = get_locale(); - if ( 'de_DE' == $locale ) { + if ( 'de_DE' == $locale || 'de_DE_formal' == $locale ) { $chars[ chr(195).chr(132) ] = 'Ae'; $chars[ chr(195).chr(164) ] = 'ae'; $chars[ chr(195).chr(150) ] = 'Oe'; @@ -1022,6 +1266,7 @@ function remove_accents($string) { $string = strtr($string, $chars); } else { + $chars = array(); // Assume ISO-8859-1 if not UTF-8 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158) .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194) @@ -1037,6 +1282,7 @@ function remove_accents($string) { $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['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'); $string = str_replace($double_chars['in'], $double_chars['out'], $string); @@ -1134,7 +1380,7 @@ function sanitize_file_name( $filename ) { * @since 2.0.0 * * @param string $username The username to be sanitized. - * @param bool $strict If set limits $username to specific characters. Default false. + * @param bool $strict If set limits $username to specific characters. Default false. * @return string The sanitized username, after passing through filters. */ function sanitize_user( $username, $strict = false ) { @@ -1200,9 +1446,9 @@ function sanitize_key( $key ) { * * @since 1.0.0 * - * @param string $title The string to be sanitized. + * @param string $title The string to be sanitized. * @param string $fallback_title Optional. A title to use if $title is empty. - * @param string $context Optional. The operation for which the string is sanitized + * @param string $context Optional. The operation for which the string is sanitized * @return string The sanitized string. */ function sanitize_title( $title, $fallback_title = '', $context = 'save' ) { @@ -1250,9 +1496,9 @@ function sanitize_title_for_query( $title ) { * * @since 1.2.0 * - * @param string $title The title to be sanitized. + * @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. + * @param string $context Optional. The operation for which the string is sanitized. * @return string The sanitized title. */ function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) { @@ -1309,21 +1555,23 @@ function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'displa } /** - * Ensures a string is a valid SQL order by clause. + * Ensures a string is a valid SQL 'order by' clause. * - * Accepts one or more columns, with or without ASC/DESC, and also accepts - * RAND(). + * Accepts one or more columns, with or without a sort order (ASC / DESC). + * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc. + * + * Also accepts 'RAND()'. * * @since 2.5.1 * - * @param string $orderby Order by string to be checked. - * @return false|string Returns the order by clause if it is a match, false otherwise. + * @param string $orderby Order by clause to be validated. + * @return string|false Returns $orderby if valid, 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, $obmatches); - if ( !$obmatches ) - return false; - return $orderby; +function sanitize_sql_orderby( $orderby ) { + if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) { + return $orderby; + } + return false; } /** @@ -1336,7 +1584,7 @@ function sanitize_sql_orderby( $orderby ){ * * @since 2.8.0 * - * @param string $class The classname to be sanitized + * @param string $class The classname to be sanitized * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string. * Defaults to an empty string. * @return string The sanitized value @@ -1364,71 +1612,73 @@ function sanitize_html_class( $class, $fallback = '' ) { } /** - * Converts a number of characters from a string. - * - * Metadata tags `` and `<category>` are removed, `<br>` and `<hr>` are - * converted into correct XHTML and Unicode characters are converted to the - * valid range. + * Converts lone & characters into `&` (a.k.a. `&`) * * @since 0.71 * - * @param string $content String of characters to be converted. + * @param string $content String of characters to be converted. * @param string $deprecated Not used. * @return string Converted string. */ -function convert_chars($content, $deprecated = '') { - if ( !empty( $deprecated ) ) +function convert_chars( $content, $deprecated = '' ) { + if ( ! empty( $deprecated ) ) { _deprecated_argument( __FUNCTION__, '0.71' ); + } - // Translation of invalid Unicode references range to valid range - $wp_htmltranswinuni = array( - '€' => '€', // the Euro sign - '' => '', - '‚' => '‚', // these are Windows CP1252 specific characters - 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers - '„' => '„', - '…' => '…', - '†' => '†', - '‡' => '‡', - 'ˆ' => 'ˆ', - '‰' => '‰', - 'Š' => 'Š', - '‹' => '‹', - 'Œ' => 'Œ', - '' => '', - 'Ž' => 'Ž', - '' => '', - '' => '', - '‘' => '‘', - '’' => '’', - '“' => '“', - '”' => '”', - '•' => '•', - '–' => '–', - '—' => '—', - '˜' => '˜', - '™' => '™', - 'š' => 'š', - '›' => '›', - 'œ' => 'œ', - '' => '', - 'ž' => 'ž', - 'Ÿ' => 'Ÿ' - ); - - // Remove metadata tags - $content = preg_replace('/<title>(.+?)<\/title>/','',$content); - $content = preg_replace('/<category>(.+?)<\/category>/','',$content); + if ( strpos( $content, '&' ) !== false ) { + $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content ); + } - // Converts lone & characters into & (a.k.a. &) - $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content); + return $content; +} - // Fix Word pasting - $content = strtr($content, $wp_htmltranswinuni); +/** + * Converts invalid Unicode references range to valid range. + * + * @since 4.3.0 + * + * @param string $content String with entities that need converting. + * @return string Converted string. + */ +function convert_invalid_entities( $content ) { + $wp_htmltranswinuni = array( + '€' => '€', // the Euro sign + '' => '', + '‚' => '‚', // these are Windows CP1252 specific characters + 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers + '„' => '„', + '…' => '…', + '†' => '†', + '‡' => '‡', + 'ˆ' => 'ˆ', + '‰' => '‰', + 'Š' => 'Š', + '‹' => '‹', + 'Œ' => 'Œ', + '' => '', + 'Ž' => 'Ž', + '' => '', + '' => '', + '‘' => '‘', + '’' => '’', + '“' => '“', + '”' => '”', + '•' => '•', + '–' => '–', + '—' => '—', + '˜' => '˜', + '™' => '™', + 'š' => 'š', + '›' => '›', + 'œ' => 'œ', + '' => '', + 'ž' => 'ž', + 'Ÿ' => 'Ÿ' + ); - // Just a little XHTML help - $content = str_replace('<br>', '<br />', $content); - $content = str_replace('<hr>', '<hr />', $content); + if ( strpos( $content, '' ) !== false ) { + $content = strtr( $content, $wp_htmltranswinuni ); + } return $content; } @@ -1438,8 +1688,8 @@ function convert_chars($content, $deprecated = '') { * * @since 0.71 * - * @param string $text Text to be balanced - * @param bool $force If true, forces balancing, ignoring the value of the option. Default false. + * @param string $text Text to be balanced + * @param bool $force If true, forces balancing, ignoring the value of the option. Default false. * @return string Balanced text */ function balanceTags( $text, $force = false ) { @@ -1495,12 +1745,12 @@ function force_balance_tags( $text ) { if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag $tag = strtolower(substr($regex[1],1)); // if too many closing tags - if( $stacksize <= 0 ) { + if ( $stacksize <= 0 ) { $tag = ''; // or close to be safe $tag = '/' . $tag; } // if stacktop value = tag close value then pop - else if ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag + elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag $tag = '</' . $tag . '>'; // Close Tag // Pop array_pop( $tagstack ); @@ -1550,7 +1800,7 @@ function force_balance_tags( $text ) { // Attributes $attributes = $regex[2]; - if( ! empty( $attributes ) && $attributes[0] != '>' ) + if ( ! empty( $attributes ) && $attributes[0] != '>' ) $attributes = ' ' . $attributes; $tag = '<' . $tag . $attributes . '>'; @@ -1590,8 +1840,8 @@ function force_balance_tags( $text ) { * * @since 0.71 * - * @param string $content The text about to be edited. - * @param bool $richedit Whether the $content should not pass through htmlspecialchars(). Default false (meaning it will be passed). + * @param string $content The text about to be edited. + * @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 ) { @@ -1621,12 +1871,12 @@ function format_to_edit( $content, $richedit = false ) { * * @since 0.71 * - * @param mixed $number Number to append zeros to if not greater than threshold. - * @param int $threshold Digit places number needs to be to not have zeros added. + * @param int $number Number to append zeros to if not greater than threshold. + * @param int $threshold Digit places number needs to be to not have zeros added. * @return string Adds leading zeros to number if needed. */ -function zeroise($number, $threshold) { - return sprintf('%0'.$threshold.'s', $number); +function zeroise( $number, $threshold ) { + return sprintf( '%0' . $threshold . 's', $number ); } /** @@ -1637,7 +1887,7 @@ function zeroise($number, $threshold) { * @param string $string Value to which backslashes will be added. * @return string String with backslashes inserted. */ -function backslashit($string) { +function backslashit( $string ) { if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' ) $string = '\\\\' . $string; return addcslashes( $string, 'A..Za..z' ); @@ -1705,7 +1955,7 @@ function addslashes_gpc($gpc) { * @param mixed $value The value to be stripped. * @return mixed Stripped value. */ -function stripslashes_deep($value) { +function stripslashes_deep( $value ) { if ( is_array($value) ) { $value = array_map('stripslashes_deep', $value); } elseif ( is_object($value) ) { @@ -1729,9 +1979,8 @@ function stripslashes_deep($value) { * @param array|string $value The array or string to be encoded. * @return array|string $value The encoded array (or string from the callback). */ -function urlencode_deep($value) { - $value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value); - return $value; +function urlencode_deep( $value ) { + return is_array( $value ) ? array_map( 'urlencode_deep', $value ) : urlencode( $value ); } /** @@ -1752,12 +2001,12 @@ function rawurlencode_deep( $value ) { * @since 0.71 * * @param string $email_address Email address. - * @param int $hex_encoding Optional. Set to 1 to enable hex encoding. + * @param int $hex_encoding Optional. Set to 1 to enable hex encoding. * @return string Converted email address. */ function antispambot( $email_address, $hex_encoding = 0 ) { $email_no_spam_address = ''; - for ( $i = 0; $i < strlen( $email_address ); $i++ ) { + for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) { $j = rand( 0, 1 + $hex_encoding ); if ( $j == 0 ) { $email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';'; @@ -1768,9 +2017,7 @@ function antispambot( $email_address, $hex_encoding = 0 ) { } } - $email_no_spam_address = str_replace( '@', '@', $email_no_spam_address ); - - return $email_no_spam_address; + return str_replace( '@', '@', $email_no_spam_address ); } /** @@ -1785,7 +2032,7 @@ function antispambot( $email_address, $hex_encoding = 0 ) { * @param array $matches Single Regex Match. * @return string HTML A element with URI address. */ -function _make_url_clickable_cb($matches) { +function _make_url_clickable_cb( $matches ) { $url = $matches[2]; if ( ')' == $matches[3] && strpos( $url, '(' ) ) { @@ -1822,7 +2069,7 @@ function _make_url_clickable_cb($matches) { * @param array $matches Single Regex Match. * @return string HTML A element with URL address. */ -function _make_web_ftp_clickable_cb($matches) { +function _make_web_ftp_clickable_cb( $matches ) { $ret = ''; $dest = $matches[2]; $dest = 'http://' . $dest; @@ -1850,7 +2097,7 @@ function _make_web_ftp_clickable_cb($matches) { * @param array $matches Single Regex Match. * @return string HTML A element with email address. */ -function _make_email_clickable_cb($matches) { +function _make_email_clickable_cb( $matches ) { $email = $matches[2] . '@' . $matches[3]; return $matches[1] . "<a href=\"mailto:$email\">$email</a>"; } @@ -1921,8 +2168,7 @@ function make_clickable( $text ) { } // Cleanup of accidental links within links - $r = preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r ); - return $r; + return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r ); } /** @@ -1951,7 +2197,7 @@ function make_clickable( $text ) { * @access private * * @param string $string The string to split. - * @param int $goal The desired chunk length. + * @param int $goal The desired chunk length. * @return array Numeric array of chunks. */ function _split_str_by_whitespace( $string, $goal ) { @@ -1993,8 +2239,7 @@ function wp_rel_nofollow( $text ) { // This is a pre save filter, so text is already escaped. $text = stripslashes($text); $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text); - $text = wp_slash($text); - return $text; + return wp_slash( $text ); } /** @@ -2021,9 +2266,10 @@ function wp_rel_nofollow_callback( $matches ) { * Looks up one smiley code in the $wpsmiliestrans global array and returns an * `<img>` string for that smiley. * - * @global array $wpsmiliestrans * @since 2.8.0 * + * @global array $wpsmiliestrans + * * @param array $matches Single match. Smiley code to convert to image. * @return string Image string for smiley. */ @@ -2036,6 +2282,15 @@ function translate_smiley( $matches ) { $smiley = trim( reset( $matches ) ); $img = $wpsmiliestrans[ $smiley ]; + $matches = array(); + $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false; + $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' ); + + // Don't convert smilies that aren't images - they're probably emoji. + if ( ! in_array( $ext, $image_exts ) ) { + return $img; + } + /** * Filter the Smiley image URL before it's used in the image element. * @@ -2047,7 +2302,7 @@ function translate_smiley( $matches ) { */ $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() ); - return sprintf( '<img src="%s" alt="%s" class="wp-smiley" />', esc_url( $src_url ), esc_attr( $smiley ) ); + return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) ); } /** @@ -2057,7 +2312,8 @@ function translate_smiley( $matches ) { * used in the function isn't empty. * * @since 0.71 - * @uses $wp_smiliessearch + * + * @global string|array $wp_smiliessearch * * @param string $text Content to convert smilies from text. * @return string Converted content with text smilies replaced with images. @@ -2108,8 +2364,8 @@ function convert_smilies( $text ) { * * @since 0.71 * - * @param string $email Email address to verify. - * @param boolean $deprecated Deprecated. + * @param string $email Email address to verify. + * @param bool $deprecated Deprecated. * @return string|bool Either false or the valid email address. */ function is_email( $email, $deprecated = false ) { @@ -2201,14 +2457,13 @@ function is_email( $email, $deprecated = false ) { * @param string $string Subject line * @return string Converted string to ASCII */ -function wp_iso_descrambler($string) { +function wp_iso_descrambler( $string ) { /* this may only work with iso-8859-1, I'm afraid */ if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) { return $string; } else { $subject = str_replace('_', ' ', $matches[2]); - $subject = preg_replace_callback('#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject); - return $subject; + return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject ); } } @@ -2295,7 +2550,7 @@ function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) { * @param string $timezone Either 'Z' for 0 offset or '±hhmm'. * @return int|float The offset in seconds. */ -function iso8601_timezone_to_offset($timezone) { +function iso8601_timezone_to_offset( $timezone ) { // $timezone is either 'Z' or '[+|-]hhmm' if ($timezone == 'Z') { $offset = 0; @@ -2314,10 +2569,10 @@ function iso8601_timezone_to_offset($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 $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'. + * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'. * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s. */ -function iso8601_to_datetime($date_string, $timezone = 'user') { +function iso8601_to_datetime( $date_string, $timezone = 'user' ) { $timezone = strtolower($timezone); if ($timezone == 'gmt') { @@ -2335,7 +2590,7 @@ function iso8601_to_datetime($date_string, $timezone = 'user') { return gmdate('Y-m-d H:i:s', $timestamp); - } else if ($timezone == 'user') { + } elseif ($timezone == 'user') { return preg_replace('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', '$1-$2-$3 $4:$5:$6', $date_string); } } @@ -2352,7 +2607,7 @@ function iso8601_to_datetime($date_string, $timezone = 'user') { * @param string $text Content to replace links to open in a new window. * @return string Content that has filtered links. */ -function popuplinks($text) { +function popuplinks( $text ) { $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text); return $text; } @@ -2468,7 +2723,7 @@ function sanitize_email( $email ) { * @since 1.5.0 * * @param int $from Unix timestamp from which the difference begins. - * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set. + * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set. * @return string Human readable time difference. */ function human_time_diff( $from, $to = '' ) { @@ -2539,7 +2794,7 @@ function human_time_diff( $from, $to = '' ) { * @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 ) { $text = get_the_content(''); @@ -2588,19 +2843,25 @@ function wp_trim_excerpt($text = '') { * * @since 3.3.0 * - * @param string $text Text to trim. - * @param int $num_words Number of words. Default 55. - * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'. + * @param string $text Text to trim. + * @param int $num_words Number of words. Default 55. + * @param string $more Optional. 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 ) + 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' ) ) ) { + + /* + * translators: If your word count is based on single characters (e.g. East Asian characters), + * enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'. + * Do not translate into your own language. + */ + if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && 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 ); @@ -2609,6 +2870,7 @@ function wp_trim_words( $text, $num_words = 55, $more = null ) { $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 ); @@ -2616,6 +2878,7 @@ function wp_trim_words( $text, $num_words = 55, $more = null ) { } else { $text = implode( $sep, $words_array ); } + /** * Filter the text content after words have been trimmed. * @@ -2637,7 +2900,7 @@ function wp_trim_words( $text, $num_words = 55, $more = null ) { * @param string $text The text within which entities will be converted. * @return string Text with converted entities. */ -function ent2ncr($text) { +function ent2ncr( $text ) { /** * Filter text before named entities are converted into numbered entities. @@ -2650,7 +2913,7 @@ function ent2ncr($text) { * @param string $text The text prior to entity conversion. */ $filtered = apply_filters( 'pre_ent2ncr', null, $text ); - if( null !== $filtered ) + if ( null !== $filtered ) return $filtered; $to_ncr = array( @@ -2916,66 +3179,32 @@ function ent2ncr($text) { } /** - * Formats text for the rich text editor. + * Formats text for the editor. * - * The filter 'richedit_pre' is applied here. If $text is empty the filter will - * be applied to an empty string. + * Generally the browsers treat everything inside a textarea as text, but + * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content. * - * @since 2.0.0 + * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the + * filter will be applied to an empty string. + * + * @since 4.3.0 * * @param string $text The text to be formatted. * @return string The formatted text after filter is applied. */ -function wp_richedit_pre($text) { - if ( empty( $text ) ) { - /** - * Filter text returned for the rich text editor. - * - * This filter is first evaluated, and the value returned, if an empty string - * is passed to wp_richedit_pre(). If an empty string is passed, it results - * in a break tag and line feed. - * - * If a non-empty string is passed, the filter is evaluated on the wp_richedit_pre() - * return after being formatted. - * - * @since 2.0.0 - * - * @param string $output Text for the rich text editor. - */ - return apply_filters( 'richedit_pre', '' ); +function format_for_editor( $text, $default_editor = null ) { + if ( $text ) { + $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) ); } - $output = convert_chars($text); - $output = wpautop($output); - $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) ); - - /** This filter is documented in wp-includes/formatting.php */ - return apply_filters( 'richedit_pre', $output ); -} - -/** - * Formats text for the HTML editor. - * - * Unless $output is empty it will pass through htmlspecialchars before the - * 'htmledit_pre' filter is applied. - * - * @since 2.5.0 - * - * @param string $output The text to be formatted. - * @return string Formatted text after filter applied. - */ -function wp_htmledit_pre($output) { - if ( !empty($output) ) - $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) ); // convert only < > & - /** - * Filter the text before it is formatted for the HTML editor. + * Filter the text after it is formatted for the editor. * - * @since 2.5.0 + * @since 4.3.0 * - * @param string $output The HTML-formatted text. + * @param string $text The formatted text. */ - return apply_filters( 'htmledit_pre', $output ); + return apply_filters( 'format_for_editor', $text, $default_editor ); } /** @@ -2988,8 +3217,9 @@ function wp_htmledit_pre($output) { * @since 2.8.1 * @access private * - * @param string|array $search The value being searched for, otherwise known as the needle. An array may be used to designate multiple needles. - * @param string $subject The string being searched and replaced on, otherwise known as the haystack. + * @param string|array $search The value being searched for, otherwise known as the needle. + * An array may be used to designate multiple needles. + * @param string $subject The string being searched and replaced on, otherwise known as the haystack. * @return string The string with the replaced svalues. */ function _deep_replace( $search, $subject ) { @@ -3011,6 +3241,9 @@ function _deep_replace( $search, $subject ) { * is preparing an array for use in an IN clause. * * @since 2.8.0 + * + * @global wpdb $wpdb + * * @param string|array $data Unescaped data * @return string|array Escaped data */ @@ -3028,10 +3261,10 @@ function esc_sql( $data ) { * * @since 2.8.0 * - * @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', 'mms', 'rtsp', 'svn' if not set. - * @param string $_context Private. Use esc_url_raw() for database usage. + * @param string $url The URL to be cleaned. + * @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. */ function esc_url( $url, $protocols = null, $_context = 'display' ) { @@ -3040,8 +3273,10 @@ function esc_url( $url, $protocols = null, $_context = 'display' ) { if ( '' == $url ) return $url; $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url); - $strip = array('%0d', '%0a', '%0D', '%0A'); - $url = _deep_replace($strip, $url); + if ( 0 !== stripos( $url, 'mailto:' ) ) { + $strip = array('%0d', '%0a', '%0D', '%0A'); + $url = _deep_replace($strip, $url); + } $url = str_replace(';//', '://', $url); /* If the URL doesn't appear to contain a scheme, we * presume it needs http:// appended (unless a relative @@ -3085,8 +3320,8 @@ function esc_url( $url, $protocols = null, $_context = 'display' ) { * * @since 2.8.0 * - * @param string $url The URL to be cleaned. - * @param array $protocols An array of acceptable protocols. + * @param string $url The URL to be cleaned. + * @param array $protocols An array of acceptable protocols. * @return string The cleaned URL. */ function esc_url_raw( $url, $protocols = null ) { @@ -3103,7 +3338,7 @@ function esc_url_raw( $url, $protocols = null ) { * @param string $myHTML The text to be converted. * @return string Converted text. */ -function htmlentities2($myHTML) { +function htmlentities2( $myHTML ) { $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES ); $translation_table[chr(38)] = '&'; return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) ); @@ -3220,7 +3455,7 @@ function esc_textarea( $text ) { * @param string $tag_name * @return string */ -function tag_escape($tag_name) { +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. @@ -3257,20 +3492,29 @@ function wp_make_link_relative( $link ) { * * @since 2.0.5 * + * @global wpdb $wpdb + * * @param string $option The name of the option. - * @param string $value The unsanitised value. + * @param string $value The unsanitised value. * @return string Sanitized value. */ -function sanitize_option($option, $value) { +function sanitize_option( $option, $value ) { + global $wpdb; + + $original_value = $value; + $error = ''; switch ( $option ) { 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( $option, 'invalid_admin_email', __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ) ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + $value = sanitize_email( $value ); + if ( ! is_email( $value ) ) { + $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ); + } } break; @@ -3293,6 +3537,7 @@ function sanitize_option($option, $value) { case 'thread_comments_depth': case 'users_can_register': case 'start_of_week': + case 'site_icon': $value = absint( $value ); break; @@ -3314,8 +3559,13 @@ function sanitize_option($option, $value) { case 'blogdescription': case 'blogname': - $value = wp_kses_post( $value ); - $value = esc_html( $value ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + $value = wp_kses_post( $value ); + $value = esc_html( $value ); + } break; case 'blog_charset': @@ -3336,8 +3586,13 @@ function sanitize_option($option, $value) { case 'mailserver_login': case 'mailserver_pass': case 'upload_path': - $value = strip_tags( $value ); - $value = wp_kses_data( $value ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + $value = strip_tags( $value ); + $value = wp_kses_data( $value ); + } break; case 'ping_sites': @@ -3352,22 +3607,28 @@ function sanitize_option($option, $value) { break; case 'siteurl': - if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) { - $value = esc_url_raw($value); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); } else { - $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization - if ( function_exists('add_settings_error') ) - add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.')); + if ( preg_match( '#http(s?)://(.+)#i', $value ) ) { + $value = esc_url_raw( $value ); + } else { + $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' ); + } } break; case 'home': - if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) { - $value = esc_url_raw($value); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); } else { - $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization - if ( function_exists('add_settings_error') ) - add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.')); + if ( preg_match( '#http(s?)://(.+)#i', $value ) ) { + $value = esc_url_raw( $value ); + } else { + $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' ); + } } break; @@ -3382,45 +3643,59 @@ function sanitize_option($option, $value) { break; case 'illegal_names': - if ( ! is_array( $value ) ) - $value = explode( ' ', $value ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + if ( ! is_array( $value ) ) + $value = explode( ' ', $value ); - $value = array_values( array_filter( array_map( 'trim', $value ) ) ); + $value = array_values( array_filter( array_map( 'trim', $value ) ) ); - if ( ! $value ) - $value = ''; + if ( ! $value ) + $value = ''; + } break; case 'limited_email_domains': case 'banned_email_domains': - if ( ! is_array( $value ) ) - $value = explode( "\n", $value ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + if ( ! is_array( $value ) ) + $value = explode( "\n", $value ); - $domains = array_values( array_filter( array_map( 'trim', $value ) ) ); - $value = array(); + $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; + foreach ( $domains as $domain ) { + if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) { + $value[] = $domain; + } + } + if ( ! $value ) + $value = ''; } - if ( ! $value ) - $value = ''; break; case 'timezone_string': $allowed_zones = timezone_identifiers_list(); if ( ! in_array( $value, $allowed_zones ) && ! empty( $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('timezone_string', 'invalid_timezone_string', __('The timezone you have entered is not valid. Please select a valid timezone.') ); + $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' ); } break; case 'permalink_structure': case 'category_base': case 'tag_base': - $value = esc_url_raw( $value ); - $value = str_replace( 'http://', '', $value ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + $value = esc_url_raw( $value ); + $value = str_replace( 'http://', '', $value ); + } break; case 'default_role' : @@ -3430,24 +3705,36 @@ function sanitize_option($option, $value) { case 'moderation_keys': case 'blacklist_keys': - $value = explode( "\n", $value ); - $value = array_filter( array_map( 'trim', $value ) ); - $value = array_unique( $value ); - $value = implode( "\n", $value ); + $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); + if ( is_wp_error( $value ) ) { + $error = $value->get_error_message(); + } else { + $value = explode( "\n", $value ); + $value = array_filter( array_map( 'trim', $value ) ); + $value = array_unique( $value ); + $value = implode( "\n", $value ); + } break; } + if ( ! empty( $error ) ) { + $value = get_option( $option ); + if ( function_exists( 'add_settings_error' ) ) { + add_settings_error( $option, "invalid_{$option}", $error ); + } + } + /** * Filter an option value following sanitization. * * @since 2.3.0 + * @since 4.3.0 Added the `$original_value` parameter. * - * @param string $value The sanitized option value. - * @param string $option The option name. + * @param string $value The sanitized option value. + * @param string $option The option name. + * @param string $original_value The original value passed to the function. */ - $value = apply_filters( "sanitize_option_{$option}", $value, $option ); - - return $value; + return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value ); } /** @@ -3459,7 +3746,7 @@ function sanitize_option($option, $value) { * @since 2.2.1 * * @param string $string The string to be parsed. - * @param array $array Variables will be stored in this array. + * @param array $array Variables will be stored in this array. */ function wp_parse_str( $string, &$array ) { parse_str( $string, $array ); @@ -3509,8 +3796,8 @@ function wp_pre_kses_less_than_callback( $matches ) { * @since 2.5.0 * @link http://www.php.net/sprintf * - * @param string $pattern The string which formatted args are inserted. - * @param mixed $args,... Arguments to be formatted into the $pattern string. + * @param string $pattern The string which formatted args are inserted. + * @param mixed $args ,... Arguments to be formatted into the $pattern string. * @return string The formatted string. */ function wp_sprintf( $pattern ) { @@ -3584,10 +3871,10 @@ function wp_sprintf( $pattern ) { * @since 2.5.0 * * @param string $pattern Content containing '%l' at the beginning. - * @param array $args List items to prepend to the content and replace '%l'. + * @param array $args List items to prepend to the content and replace '%l'. * @return string Localized list items and rest of the content. */ -function wp_sprintf_l($pattern, $args) { +function wp_sprintf_l( $pattern, $args ) { // Not a match if ( substr($pattern, 0, 2) != '%l' ) return $pattern; @@ -3642,9 +3929,9 @@ function wp_sprintf_l($pattern, $args) { * * @since 2.5.0 * - * @param string $str String to get the excerpt from. - * @param integer $count Maximum number of characters to take. - * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string. + * @param string $str String to get the excerpt from. + * @param int $count Maximum number of characters to take. + * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string. * @return string The excerpt. */ function wp_html_excerpt( $str, $count, $more = null ) { @@ -3667,9 +3954,11 @@ function wp_html_excerpt( $str, $count, $more = null ) { * * @since 2.7.0 * + * @global string $_links_add_base + * * @param string $content String to search for links in. - * @param string $base The base URL to prefix to links. - * @param array $attrs The attributes which should be processed. + * @param string $base The base URL to prefix to links. + * @param array $attrs The attributes which should be processed. * @return string The processed content. */ function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) { @@ -3685,10 +3974,12 @@ function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) { * @since 2.7.0 * @access private * + * @global string $_links_add_base + * * @param string $m The matched link. * @return string The processed link. */ -function _links_add_base($m) { +function _links_add_base( $m ) { global $_links_add_base; //1 = attribute name 2 = quotation mark 3 = URL return $m[1] . '=' . $m[2] . @@ -3709,9 +4000,11 @@ function _links_add_base($m) { * * @since 2.7.0 * + * @global string $_links_add_target + * * @param string $content String to search for links in. - * @param string $target The Target to add to the links. - * @param array $tags An array of tags to apply to. + * @param string $target The Target to add to the links. + * @param array $tags An array of tags to apply to. * @return string The processed content. */ function links_add_target( $content, $target = '_blank', $tags = array('a') ) { @@ -3727,6 +4020,8 @@ function links_add_target( $content, $target = '_blank', $tags = array('a') ) { * @since 2.7.0 * @access private * + * @global string $_links_add_target + * * @param string $m The matched link. * @return string The processed link. */ @@ -3761,8 +4056,8 @@ function normalize_whitespace( $str ) { * * @since 2.9.0 * - * @param string $string String containing HTML tags - * @param bool $remove_breaks optional Whether to remove left over line breaks and white space chars + * @param string $string String containing HTML tags + * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars * @return string The processed string. */ function wp_strip_all_tags($string, $remove_breaks = false) { @@ -3789,7 +4084,7 @@ function wp_strip_all_tags($string, $remove_breaks = false) { * @param string $str * @return string */ -function sanitize_text_field($str) { +function sanitize_text_field( $str ) { $filtered = wp_check_invalid_utf8( $str ); if ( strpos($filtered, '<') !== false ) { @@ -3827,7 +4122,7 @@ function sanitize_text_field($str) { * * @since 3.1.0 * - * @param string $path A path. + * @param string $path A path. * @param string $suffix If the filename ends in suffix this will also be cut off. * @return string */ @@ -3841,6 +4136,8 @@ function wp_basename( $path, $suffix = '' ) { * Violating our coding standards for a good function name. * * @since 3.0.0 + * + * @staticvar string|false $dblq */ function capital_P_dangit( $text ) { // Simple replacement for titles @@ -3849,13 +4146,13 @@ function capital_P_dangit( $text ) { return str_replace( 'Wordpress', 'WordPress', $text ); // Still here? Use the more judicious replacement static $dblq = false; - if ( false === $dblq ) + if ( false === $dblq ) { $dblq = _x( '“', 'opening curly double quote' ); + } return str_replace( array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ), array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ), $text ); - } /** @@ -3957,7 +4254,7 @@ function wp_unslash( $value ) { * @since 3.6.0 * * @param string $content A string which might contain a URL. - * @return string The found URL. + * @return string|false The found URL. */ function get_url_in_content( $content ) { if ( empty( $content ) ) { @@ -3980,10 +4277,12 @@ function get_url_in_content( $content ) { * * @since 4.0.0 * + * @staticvar string $spaces + * * @return string The spaces regexp. */ function wp_spaces_regexp() { - static $spaces; + static $spaces = ''; if ( empty( $spaces ) ) { /** @@ -4003,3 +4302,308 @@ function wp_spaces_regexp() { return $spaces; } + +/** + * Print the important emoji-related styles. + * + * @since 4.2.0 + * + * @staticvar bool $printed + */ +function print_emoji_styles() { + static $printed = false; + + if ( $printed ) { + return; + } + + $printed = true; +?> +<style type="text/css"> +img.wp-smiley, +img.emoji { + display: inline !important; + border: none !important; + box-shadow: none !important; + height: 1em !important; + width: 1em !important; + margin: 0 .07em !important; + vertical-align: -0.1em !important; + background: none !important; + padding: 0 !important; +} +</style> +<?php +} + +/** + * + * @global string $wp_version + * @staticvar bool $printed + */ +function print_emoji_detection_script() { + global $wp_version; + static $printed = false; + + if ( $printed ) { + return; + } + + $printed = true; + + $settings = array( + /** + * Filter the URL where emoji images are hosted. + * + * @since 4.2.0 + * + * @param string The emoji base URL. + */ + 'baseUrl' => apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) ), + + /** + * Filter the extension of the emoji files. + * + * @since 4.2.0 + * + * @param string The emoji extension. Default .png. + */ + 'ext' => apply_filters( 'emoji_ext', '.png' ), + ); + + $version = 'ver=' . $wp_version; + + if ( SCRIPT_DEBUG ) { + $settings['source'] = array( + /** This filter is documented in wp-includes/class.wp-scripts.php */ + 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ), + /** This filter is documented in wp-includes/class.wp-scripts.php */ + 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ), + ); + + ?> + <script type="text/javascript"> + window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>; + <?php readfile( ABSPATH . WPINC . "/js/wp-emoji-loader.js" ); ?> + </script> + <?php + } else { + $settings['source'] = array( + /** This filter is documented in wp-includes/class.wp-scripts.php */ + 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ), + ); + + /* + * If you're looking at a src version of this file, you'll see an "include" + * statement below. This is used by the `grunt build` process to directly + * include a minified version of wp-emoji-loader.js, instead of using the + * readfile() method from above. + * + * If you're looking at a build version of this file, you'll see a string of + * minified JavaScript. If you need to debug it, please turn on SCRIPT_DEBUG + * and edit wp-emoji-loader.js directly. + */ + ?> + <script type="text/javascript"> + window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>; + !function(a,b,c){function d(a){var c=b.createElement("canvas"),d=c.getContext&&c.getContext("2d");return d&&d.fillText?(d.textBaseline="top",d.font="600 32px Arial","flag"===a?(d.fillText(String.fromCharCode(55356,56812,55356,56807),0,0),c.toDataURL().length>3e3):(d.fillText(String.fromCharCode(55357,56835),0,0),0!==d.getImageData(16,16,1,1).data[0])):!1}function e(a){var c=b.createElement("script");c.src=a,c.type="text/javascript",b.getElementsByTagName("head")[0].appendChild(c)}var f,g;c.supports={simple:d("simple"),flag:d("flag")},c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.simple&&c.supports.flag||(g=function(){c.readyCallback()},b.addEventListener?(b.addEventListener("DOMContentLoaded",g,!1),a.addEventListener("load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onreadystatechange",function(){"complete"===b.readyState&&c.readyCallback()})),f=c.source||{},f.concatemoji?e(f.concatemoji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(window,document,window._wpemojiSettings); + </script> + <?php + } +} + +/** + * Convert any 4 byte emoji in a string to their equivalent HTML entity. + * + * Currently, only Unicode 7 emoji are supported. Skin tone modifiers are allowed, + * all other Unicode 8 emoji will be added when the spec is finalised. + * + * This allows us to store emoji in a DB using the utf8 character set. + * + * @since 4.2.0 + * + * @param string $content The content to encode. + * @return string The encoded content. + */ +function wp_encode_emoji( $content ) { + if ( function_exists( 'mb_convert_encoding' ) ) { + $regex = '/( + \x23\xE2\x83\xA3 # Digits + [\x30-\x39]\xE2\x83\xA3 + | \xF0\x9F[\x85-\x88][\xA6-\xBF] # Enclosed characters + | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc + | \xF0\x9F\x98[\x80-\xBF] # Smilies + | \xF0\x9F\x99[\x80-\x8F] + | \xF0\x9F\x9A[\x80-\xBF] # Transport and map symbols + )/x'; + + $matches = array(); + if ( preg_match_all( $regex, $content, $matches ) ) { + if ( ! empty( $matches[1] ) ) { + foreach( $matches[1] as $emoji ) { + /* + * UTF-32's hex encoding is the same as HTML's hex encoding. + * So, by converting the emoji from UTF-8 to UTF-32, we magically + * get the correct hex encoding. + */ + $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) ); + if ( isset( $unpacked[1] ) ) { + $entity = '&#x' . ltrim( $unpacked[1], '0' ) . ';'; + $content = str_replace( $emoji, $entity, $content ); + } + } + } + } + } + + return $content; +} + +/** + * Convert emoji to a static img element. + * + * @since 4.2.0 + * + * @param string $text The content to encode. + * @return string The encoded content. + */ +function wp_staticize_emoji( $text ) { + $text = wp_encode_emoji( $text ); + + /** This filter is documented in wp-includes/formatting.php */ + $cdn_url = apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) ); + + /** This filter is documented in wp-includes/formatting.php */ + $ext = apply_filters( 'emoji_ext', '.png' ); + + $output = ''; + /* + * HTML loop taken from smiley function, which was taken from texturize function. + * It'll never be consolidated. + * + * First, capture the tags as well as in between. + */ + $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); + $stop = count( $textarr ); + + // Ignore processing of specific tags. + $tags_to_ignore = 'code|pre|style|script|textarea'; + $ignore_block_element = ''; + + for ( $i = 0; $i < $stop; $i++ ) { + $content = $textarr[$i]; + + // If we're in an ignore block, wait until we find its closing tag. + if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) { + $ignore_block_element = $matches[1]; + } + + // If it's not a tag and not in ignore block. + if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) { + $matches = array(); + if ( preg_match_all( '/(DZ(e[6-9a-f]|f[0-9a-f]);){2}/', $content, $matches ) ) { + if ( ! empty( $matches[0] ) ) { + foreach ( $matches[0] as $flag ) { + $chars = str_replace( array( '&#x', ';'), '', $flag ); + + list( $char1, $char2 ) = str_split( $chars, 5 ); + $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char1 . '-' . $char2 . $ext, html_entity_decode( $flag ) ); + + $content = str_replace( $flag, $entity, $content ); + } + } + } + + // Loosely match the Emoji Unicode range. + $regex = '/(&#x[2-3][0-9a-f]{3};| [1-6][0-9a-f]{2};)/'; + + $matches = array(); + if ( preg_match_all( $regex, $content, $matches ) ) { + if ( ! empty( $matches[1] ) ) { + foreach ( $matches[1] as $emoji ) { + $char = str_replace( array( '&#x', ';'), '', $emoji ); + $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char . $ext, html_entity_decode( $emoji ) ); + + $content = str_replace( $emoji, $entity, $content ); + } + } + } + } + + // Did we exit ignore block. + if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) { + $ignore_block_element = ''; + } + + $output .= $content; + } + + return $output; +} + +/** + * Convert emoji in emails into static images. + * + * @since 4.2.0 + * + * @param array $mail The email data array. + * @return array The email data array, with emoji in the message staticized. + */ +function wp_staticize_emoji_for_email( $mail ) { + if ( ! isset( $mail['message'] ) ) { + return $mail; + } + + /* + * We can only transform the emoji into images if it's a text/html email. + * To do that, here's a cut down version of the same process that happens + * in wp_mail() - get the Content-Type from the headers, if there is one, + * then pass it through the wp_mail_content_type filter, in case a plugin + * is handling changing the Content-Type. + */ + $headers = array(); + if ( isset( $mail['headers'] ) ) { + if ( is_array( $mail['headers'] ) ) { + $headers = $mail['headers']; + } else { + $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) ); + } + } + + foreach ( $headers as $header ) { + if ( strpos($header, ':') === false ) { + continue; + } + + // Explode them out. + list( $name, $content ) = explode( ':', trim( $header ), 2 ); + + // Cleanup crew. + $name = trim( $name ); + $content = trim( $content ); + + if ( 'content-type' === strtolower( $name ) ) { + if ( strpos( $content, ';' ) !== false ) { + list( $type, $charset ) = explode( ';', $content ); + $content_type = trim( $type ); + } else { + $content_type = trim( $content ); + } + break; + } + } + + // Set Content-Type if we don't have a content-type from the input headers. + if ( ! isset( $content_type ) ) { + $content_type = 'text/plain'; + } + + /** This filter is documented in wp-includes/pluggable.php */ + $content_type = apply_filters( 'wp_mail_content_type', $content_type ); + + if ( 'text/html' === $content_type ) { + $mail['message'] = wp_staticize_emoji( $mail['message'] ); + } + + return $mail; +}