X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/959f97d8ecd5c1668103a3e41c795486b944bc68..refs/tags/wordpress-2.8-scripts:/wp-includes/formatting.php diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php index 052445d1..26bfc694 100644 --- a/wp-includes/formatting.php +++ b/wp-includes/formatting.php @@ -1,12 +1,47 @@ + * 'cause today's effort makes it worth tomorrow's "holiday"... + * + * Becomes: + * + * ’cause today’s effort makes it worth tomorrow’s “holiday”… + * + * Code within certain html blocks are skipped. + * + * @since 0.71 + * @uses $wp_cockneyreplace Array of formatted entities for certain common phrases + * + * @param string $text The text to be formatted + * @return string The string replaced with html entities + */ function wptexturize($text) { global $wp_cockneyreplace; - $next = true; $output = ''; $curl = ''; $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE); $stop = count($textarr); + + /* translators: opening curly quote */ + $opening_quote = _x('“', 'opening curly quote'); + /* translators: closing curly quote */ + $closing_quote = _x('”', 'closing curly quote'); + + $no_texturize_tags = apply_filters('no_texturize_tags', array('pre', 'code', 'kbd', 'style', 'script', 'tt')); + $no_texturize_shortcodes = apply_filters('no_texturize_shortcodes', array('code')); + $no_texturize_tags_stack = array(); + $no_texturize_shortcodes_stack = array(); // if a plugin has provided an autocorrect array, use it if ( isset($wp_cockneyreplace) ) { @@ -17,35 +52,59 @@ function wptexturize($text) { $cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause"); } - $static_characters = array_merge(array('---', ' -- ', '--', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney); - $static_replacements = array_merge(array('—', ' — ', '–', 'xn--', '…', '“', '’s', '”', ' ™'), $cockneyreplace); + $static_characters = array_merge(array('---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney); + $static_replacements = array_merge(array('—', ' — ', '–', ' – ', 'xn--', '…', $opening_quote, '’s', $closing_quote, ' ™'), $cockneyreplace); $dynamic_characters = array('/\'(\d\d(?:’|\')?s)/', '/(\s|\A|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A)"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/'); - $dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1“$2', '”$1', '’$1', '$1×$2'); + $dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '’$1', '$1×$2'); for ( $i = 0; $i < $stop; $i++ ) { - $curl = $textarr[$i]; + $curl = $textarr[$i]; - if (isset($curl{0}) && '<' != $curl{0} && '[' != $curl{0} && $next) { // If it's not a tag + if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0} + && empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) { // If it's not a tag // static strings $curl = str_replace($static_characters, $static_replacements, $curl); // regular expressions $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl); - } elseif (strpos($curl, ''); + wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']'); } $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl); $output .= $curl; } - return $output; + return $output; +} + +function wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') { + $o = preg_quote($opening); + $c = preg_quote($closing); + foreach($disabled_elements as $element) { + if (preg_match('/^'.$o.$element.'\b/', $text)) array_push($stack, $element); + if (preg_match('/^'.$o.'\/'.$element.$c.'/', $text)) { + $last = array_pop($stack); + // disable texturize until we find a closing tag of our type (e.g.
)
+			// even if there was invalid nesting before that
+			// Example: in the case 
sadsadasd"baba"
"baba" won't be texturized + if ($last != $element) array_push($stack, $last); + } + } } -// Accepts matches array from preg_replace_callback in wpautop() -// or a string +/** + * Accepts matches array from preg_replace_callback in wpautop() or a string. + * + * Ensures that the contents of a <
>...<
> HTML block are not + * converted into paragraphs or line-breaks. + * + * @since 1.2.0 + * + * @param array|string $matches The array or string + * @return string The pre block without paragraph/line-break conversion. + */ function clean_pre($matches) { if ( is_array($matches) ) $text = $matches[1] . $matches[2] . "
"; @@ -59,11 +118,27 @@ function clean_pre($matches) { return $text; } +/** + * Replaces double line-breaks with paragraph elements. + * + * A group of regex replaces used to identify text formatted with newlines and + * replace double line-breaks with HTML paragraph tags. The remaining + * line-breaks after conversion become <
> tags, unless $br is set to '0' + * or 'false'. + * + * @since 0.71 + * + * @param string $pee The text which has to be formatted. + * @param int|bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true. + * @return string Text which has been converted into correct paragraph tags. + */ function wpautop($pee, $br = 1) { + if ( trim($pee) === '' ) + return ''; $pee = $pee . "\n"; // just to make things a little easier, pad the end $pee = preg_replace('|
\s*
|', "\n\n", $pee); // Space things out a little - $allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)'; + $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)'; $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee); $pee = preg_replace('!()!', "$1\n\n", $pee); $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines @@ -72,10 +147,13 @@ function wpautop($pee, $br = 1) { $pee = preg_replace('|\s*\s*|', '', $pee); } $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates - $pee = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "

$1

\n", $pee); // make paragraphs, including one at the end - $pee = preg_replace('|

\s*?

|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace - $pee = preg_replace('!

([^<]+)\s*?(]*>)!', "

$1

$2", $pee); - $pee = preg_replace( '|

|', "$1

", $pee ); + // make paragraphs, including one at the end + $pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY); + $pee = ''; + foreach ( $pees as $tinkle ) + $pee .= '

' . trim($tinkle, "\n") . "

\n"; + $pee = preg_replace('|

\s*

|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace + $pee = preg_replace('!

([^<]+)!', "

$1

", $pee); $pee = preg_replace('!

\s*(]*>)\s*

!', "$1", $pee); // don't pee all over a tag $pee = preg_replace("|

(|", "$1", $pee); // problem with nested lists $pee = preg_replace('|

]*)>|i', "

", $pee); @@ -90,50 +168,241 @@ function wpautop($pee, $br = 1) { $pee = preg_replace('!(]*>)\s*
!', "$1", $pee); $pee = preg_replace('!
(\s*]*>)!', '$1', $pee); if (strpos($pee, ')(.*?)!is', 'clean_pre', $pee ); + $pee = preg_replace_callback('!(]*>)(.*?)!is', 'clean_pre', $pee ); $pee = preg_replace( "|\n

$|", '

', $pee ); $pee = preg_replace('/

\s*?(' . get_shortcode_regex() . ')\s*<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone return $pee; } - -function seems_utf8($Str) { # by bmorel at ssi dot fr - $length = strlen($Str); +/** + * Checks to see if a string is utf8 encoded. + * + * NOTE: This function checks for 5-Byte sequences, UTF8 + * has Bytes Sequences with a maximum length of 4. + * + * @author bmorel at ssi dot fr (modified) + * @since 1.2.1 + * + * @param string $str The string to be checked + * @return bool True if $str fits a UTF-8 model, false otherwise. + */ +function seems_utf8($str) { + $length = strlen($str); for ($i=0; $i < $length; $i++) { - if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb - elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb - elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb - elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb - elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb - elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b + $c = ord($str[$i]); + if ($c < 0x80) $n = 0; # 0bbbbbbb + elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb + elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb + elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb + elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb + elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b else return false; # Does not match any model for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? - if ((++$i == $length) || ((ord($Str[$i]) & 0xC0) != 0x80)) - return false; + if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) + return false; } } return true; } -function wp_specialchars( $text, $quotes = 0 ) { - // Like htmlspecialchars except don't double-encode HTML entities - $text = str_replace('&&', '&&', $text); - $text = str_replace('&&', '&&', $text); - $text = preg_replace('/&(?:$|([^#])(?![a-z1-4]{1,8};))/', '&$1', $text); - $text = str_replace('<', '<', $text); - $text = str_replace('>', '>', $text); - if ( 'double' === $quotes ) { - $text = str_replace('"', '"', $text); - } elseif ( 'single' === $quotes ) { - $text = str_replace("'", ''', $text); - } elseif ( $quotes ) { - $text = str_replace('"', '"', $text); - $text = str_replace("'", ''', $text); +/** + * Converts a number of special characters into their HTML entities. + * + * Specifically deals with: &, <, >, ", and '. + * + * $quote_style can be set to ENT_COMPAT to encode " to + * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded. + * + * @since 1.2.2 + * + * @param string $string The text which is to be encoded. + * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. + * @param string $charset Optional. The character encoding of the string. Default is false. + * @param boolean $double_encode Optional. Whether or not to encode existing html entities. Default is false. + * @return string The encoded text with HTML entities. + */ +function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) { + $string = (string) $string; + + if ( 0 === strlen( $string ) ) { + return ''; } - return $text; + + // Don't bother if there are no specialchars - saves some processing + if ( !preg_match( '/[&<>"\']/', $string ) ) { + return $string; + } + + // Account for the previous behaviour of the function when the $quote_style is not an accepted value + if ( empty( $quote_style ) ) { + $quote_style = ENT_NOQUOTES; + } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) { + $quote_style = ENT_QUOTES; + } + + // Store the site charset as a static to avoid multiple calls to wp_load_alloptions() + if ( !$charset ) { + static $_charset; + if ( !isset( $_charset ) ) { + $alloptions = wp_load_alloptions(); + $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : ''; + } + $charset = $_charset; + } + if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) { + $charset = 'UTF-8'; + } + + $_quote_style = $quote_style; + + if ( $quote_style === 'double' ) { + $quote_style = ENT_COMPAT; + $_quote_style = ENT_COMPAT; + } elseif ( $quote_style === 'single' ) { + $quote_style = ENT_NOQUOTES; + } + + // Handle double encoding ourselves + if ( !$double_encode ) { + $string = wp_specialchars_decode( $string, $_quote_style ); + $string = preg_replace( '/&(#?x?[0-9a-z]+);/i', '|wp_entity|$1|/wp_entity|', $string ); + } + + $string = @htmlspecialchars( $string, $quote_style, $charset ); + + // Handle double encoding ourselves + if ( !$double_encode ) { + $string = str_replace( array( '|wp_entity|', '|/wp_entity|' ), array( '&', ';' ), $string ); + } + + // Backwards compatibility + if ( 'single' === $_quote_style ) { + $string = str_replace( "'", ''', $string ); + } + + return $string; +} + +/** + * Converts a number of HTML entities into their special characters. + * + * Specifically deals with: &, <, >, ", and '. + * + * $quote_style can be set to ENT_COMPAT to decode " entities, + * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded. + * + * @since 2.8 + * + * @param string $string The text which is to be decoded. + * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. + * @return string The decoded text without HTML entities. + */ +function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) { + $string = (string) $string; + + if ( 0 === strlen( $string ) ) { + return ''; + } + + // Don't bother if there are no entities - saves a lot of processing + if ( strpos( $string, '&' ) === false ) { + return $string; + } + + // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value + if ( empty( $quote_style ) ) { + $quote_style = ENT_NOQUOTES; + } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) { + $quote_style = ENT_QUOTES; + } + + // More complete than get_html_translation_table( HTML_SPECIALCHARS ) + $single = array( ''' => '\'', ''' => '\'' ); + $single_preg = array( '/�*39;/' => ''', '/�*27;/i' => ''' ); + $double = array( '"' => '"', '"' => '"', '"' => '"' ); + $double_preg = array( '/�*34;/' => '"', '/�*22;/i' => '"' ); + $others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' ); + $others_preg = array( '/�*60;/' => '<', '/�*62;/' => '>', '/�*38;/' => '&', '/�*26;/i' => '&' ); + + if ( $quote_style === ENT_QUOTES ) { + $translation = array_merge( $single, $double, $others ); + $translation_preg = array_merge( $single_preg, $double_preg, $others_preg ); + } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) { + $translation = array_merge( $double, $others ); + $translation_preg = array_merge( $double_preg, $others_preg ); + } elseif ( $quote_style === 'single' ) { + $translation = array_merge( $single, $others ); + $translation_preg = array_merge( $single_preg, $others_preg ); + } elseif ( $quote_style === ENT_NOQUOTES ) { + $translation = $others; + $translation_preg = $others_preg; + } + + // Remove zero padding on numeric entities + $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string ); + + // Replace characters according to translation table + return strtr( $string, $translation ); +} + +/** + * Checks for invalid UTF8 in a string. + * + * @since 2.8 + * + * @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. + * @return string The checked text. + */ +function wp_check_invalid_utf8( $string, $strip = false ) { + $string = (string) $string; + + if ( 0 === strlen( $string ) ) { + return ''; + } + + // Store the site charset as a static to avoid multiple calls to get_option() + static $is_utf8; + if ( !isset( $is_utf8 ) ) { + $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ); + } + if ( !$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 ) ) { + $utf8_pcre = @preg_match( '/^./u', 'a' ); + } + // We can't demand utf8 in the PCRE installation, so just return the string in those cases + if ( !$utf8_pcre ) { + return $string; + } + + // preg_match fails when it encounters invalid UTF8 in $string + if ( 1 === @preg_match( '/^./us', $string ) ) { + return $string; + } + + // Attempt to strip the bad chars if requested (not recommended) + if ( $strip && function_exists( 'iconv' ) ) { + return iconv( 'utf-8', 'utf-8', $string ); + } + + return ''; } +/** + * Encode the Unicode values to be used in the URI. + * + * @since 1.5.0 + * + * @param string $utf8_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 ) { $unicode = ''; $values = array(); @@ -175,6 +444,16 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) { return $unicode; } +/** + * Converts all accent characters to ASCII characters. + * + * If there are no accent characters, then the string given is just returned. + * + * @since 1.2.1 + * + * @param string $string Text that might have accent characters + * @return string Filtered string with replaced "nice" characters. + */ function remove_accents($string) { if ( !preg_match('/[\x80-\xff]/', $string) ) return $string; @@ -305,17 +584,48 @@ function remove_accents($string) { return $string; } -function sanitize_file_name( $name ) { // Like sanitize_title, but with periods - $name = strtolower( $name ); - $name = preg_replace('/&.+?;/', '', $name); // kill entities - $name = str_replace( '_', '-', $name ); - $name = preg_replace('/[^a-z0-9\s-.]/', '', $name); - $name = preg_replace('/\s+/', '-', $name); - $name = preg_replace('|-+|', '-', $name); - $name = trim($name, '-'); - return $name; +/** + * Sanitizes a filename replacing whitespace with dashes + * + * Removes special characters that are illegal in filenames on certain + * operating systems and special characters requiring special escaping + * to manipulate at the command line. Replaces spaces and consecutive + * dashes with a single dash. Trim period, dash and underscore from beginning + * and end of filename. + * + * @since 2.1.0 + * + * @param string $filename The filename to be sanitized + * @return string The sanitized filename + */ +function sanitize_file_name( $filename ) { + $filename_raw = $filename; + $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}"); + $special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw); + $filename = str_replace($special_chars, '', $filename); + $filename = preg_replace('/[\s-]+/', '-', $filename); + $filename = trim($filename, '.-_'); + return apply_filters('sanitize_file_name', $filename, $filename_raw); } +/** + * Sanitize username stripping out unsafe characters. + * + * If $strict is true, only alphanumeric characters (as well as _, space, ., -, + * @) are returned. + * Removes tags, octets, entities, and if strict is enabled, will remove all + * non-ASCII characters. After sanitizing, it passes the username, raw username + * (the username in the parameter), and the strict parameter as parameters for + * the filter. + * + * @since 2.0.0 + * @uses apply_filters() Calls 'sanitize_user' hook on username, raw username, + * and $strict parameter. + * + * @param string $username The username to be sanitized. + * @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 ) { $raw_username = $username; $username = strip_tags($username); @@ -327,12 +637,29 @@ function sanitize_user( $username, $strict = false ) { if ( $strict ) $username = preg_replace('|[^a-z0-9 _.\-@]|i', '', $username); + // Consolidate contiguous whitespace + $username = preg_replace('|\s+|', ' ', $username); + return apply_filters('sanitize_user', $username, $raw_username, $strict); } +/** + * Sanitizes title or use fallback title. + * + * Specifically, HTML and PHP tags are stripped. Further actions can be added + * via the plugin API. If $title is empty and $fallback_title is set, the latter + * will be used. + * + * @since 1.0.0 + * + * @param string $title The string to be sanitized. + * @param string $fallback_title Optional. A title to use if $title is empty. + * @return string The sanitized string. + */ function sanitize_title($title, $fallback_title = '') { + $raw_title = $title; $title = strip_tags($title); - $title = apply_filters('sanitize_title', $title); + $title = apply_filters('sanitize_title', $title, $raw_title); if ( '' === $title || false === $title ) $title = $fallback_title; @@ -340,6 +667,17 @@ function sanitize_title($title, $fallback_title = '') { return $title; } +/** + * Sanitizes title, replacing whitespace with dashes. + * + * Limits the output to alphanumeric characters, underscore (_) and dash (-). + * Whitespace becomes a dash. + * + * @since 1.2.0 + * + * @param string $title The title to be sanitized. + * @return string The sanitized title. + */ function sanitize_title_with_dashes($title) { $title = strip_tags($title); // Preserve escaped octets. @@ -359,6 +697,7 @@ function sanitize_title_with_dashes($title) { $title = strtolower($title); $title = preg_replace('/&.+?;/', '', $title); // kill entities + $title = str_replace('.', '-', $title); $title = preg_replace('/[^%a-z0-9 _-]/', '', $title); $title = preg_replace('/\s+/', '-', $title); $title = preg_replace('|-+|', '-', $title); @@ -367,8 +706,17 @@ function sanitize_title_with_dashes($title) { return $title; } -// ensures a string is a valid SQL order by clause like: post_name ASC, ID DESC -// accepts one or more columns, with or without ASC/DESC, and also accepts RAND() +/** + * Ensures a string is a valid SQL order by clause. + * + * Accepts one or more columns, with or without ASC/DESC, and also accepts + * RAND(). + * + * @since 2.5.1 + * + * @param string $orderby Order by string to be checked. + * @return string|false Returns the order by clause if it is a match, false otherwise. + */ 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 ) @@ -376,6 +724,46 @@ function sanitize_sql_orderby( $orderby ){ return $orderby; } +/** + * Santizes a html classname to ensure it only contains valid characters + * + * Strips the string down to A-Z,a-z,0-9,'-' if this results in an empty + * string then it will return the alternative value supplied. + * + * @todo Expand to support the full range of CDATA that a class attribute can contain. + * + * @since 2.8.0 + * + * @param string $class The classname to be sanitized + * @param string $fallback The value to return if the sanitization end's up as an empty string. + * @return string The sanitized value + */ +function sanitize_html_class($class, $fallback){ + //Strip out any % encoded octets + $sanitized = preg_replace('|%[a-fA-F0-9][a-fA-F0-9]|', '', $class); + + //Limit to A-Z,a-z,0-9,'-' + $sanitized = preg_replace('/[^A-Za-z0-9-]/', '', $sanitized); + + if ('' == $sanitized) + $sanitized = $fallback; + + return apply_filters('sanitize_html_class',$sanitized, $class, $fallback); +} + +/** + * Converts a number of characters from a string. + * + * Metadata tags <> and <<category>> are removed, <<br>> and <<hr>> are + * converted into correct XHTML and Unicode characters are converted to the + * valid range. + * + * @since 0.71 + * + * @param string $content String of characters to be converted. + * @param string $deprecated Not used. + * @return string Converted string. + */ function convert_chars($content, $deprecated = '') { // Translation of invalid Unicode references range to valid range $wp_htmltranswinuni = array( @@ -430,42 +818,79 @@ function convert_chars($content, $deprecated = '') { return $content; } +/** + * Callback used to change %uXXXX to &#YYY; syntax + * + * @since 2.8? + * + * @param array $matches Single Match + * @return string An HTML entity + */ +function funky_javascript_callback($matches) { + return "&#".base_convert($matches[1],16,10).";"; +} + +/** + * Fixes javascript bugs in browsers. + * + * Converts unicode characters to HTML numbered entities. + * + * @since 1.5.0 + * @uses $is_macIE + * @uses $is_winIE + * + * @param string $text Text to be made safe. + * @return string Fixed text. + */ function funky_javascript_fix($text) { // Fixes for browsers' javascript bugs global $is_macIE, $is_winIE; if ( $is_winIE || $is_macIE ) - $text = preg_replace("/\%u([0-9A-F]{4,4})/e", "'&#'.base_convert('\\1',16,10).';'", $text); + $text = preg_replace_callback("/\%u([0-9A-F]{4,4})/", + "funky_javascript_callback", + $text); return $text; } +/** + * Will only balance the tags if forced to and the option is set to balance tags. + * + * The option 'use_balanceTags' is used for whether the tags will be balanced. + * Both the $force parameter and 'use_balanceTags' option will have to be true + * before the tags will be balanced. + * + * @since 0.71 + * + * @param string $text Text to be balanced + * @param bool $force Forces balancing, ignoring the value of the option. Default false. + * @return string Balanced text + */ function balanceTags( $text, $force = false ) { if ( !$force && get_option('use_balanceTags') == 0 ) return $text; return force_balance_tags( $text ); } -/* - force_balance_tags - - Balances Tags of string using a modified stack. - - @param text Text to be balanced - @param force Forces balancing, ignoring the value of the option - @return Returns balanced text - @author Leonard Lin (leonard@acm.org) - @version v1.1 - @date November 4, 2001 - @license GPL v2.0 - @notes - @changelog - --- Modified by Scott Reilly (coffee2code) 02 Aug 2004 - 1.2 ***TODO*** Make better - change loop condition to $text - 1.1 Fixed handling of append/stack pop order of end text - Added Cleaning Hooks - 1.0 First Version -*/ +/** + * Balances tags of string using a modified stack. + * + * @since 2.0.4 + * + * @author Leonard Lin <leonard@acm.org> + * @license GPL v2.0 + * @copyright November 4, 2001 + * @version 1.1 + * @todo Make better - change loop condition to $text in 1.2 + * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004 + * 1.1 Fixed handling of append/stack pop order of end text + * Added Cleaning Hooks + * 1.0 First Version + * + * @param string $text Text to be balanced. + * @return string Balanced text. + */ function force_balance_tags( $text ) { $tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = ''; $single_tags = array('br', 'hr', 'img', 'input'); //Known single-entity/self-closing tags @@ -485,7 +910,7 @@ function force_balance_tags( $text ) { // clear the shifter $tagqueue = ''; // Pop or Push - if ($regex[1][0] == "/") { // End Tag + if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag $tag = strtolower(substr($regex[1],1)); // if too many closing tags if($stacksize <= 0) { @@ -565,6 +990,19 @@ function force_balance_tags( $text ) { return $newtext; } +/** + * Acts on text which is about to be edited. + * + * Unless $richedit is set, it is simply a holder for the 'format_to_edit' + * filter. If $richedit is set true htmlspecialchars() will be run on the + * content, converting special characters to HTMl entities. + * + * @since 0.71 + * + * @param string $content The text about to be edited. + * @param bool $richedit Whether or not the $content should pass through htmlspecialchars(). Default false. + * @return string The text after the filter (and possibly htmlspecialchars()) has been run. + */ function format_to_edit($content, $richedit = false) { $content = apply_filters('format_to_edit', $content); if (! $richedit ) @@ -572,30 +1010,99 @@ function format_to_edit($content, $richedit = false) { return $content; } +/** + * Holder for the 'format_to_post' filter. + * + * @since 0.71 + * + * @param string $content The text to pass through the filter. + * @return string Text returned from the 'format_to_post' filter. + */ function format_to_post($content) { $content = apply_filters('format_to_post', $content); return $content; } -function zeroise($number,$threshold) { // function to add leading zeros when necessary +/** + * Add leading zeros when necessary. + * + * If you set the threshold to '4' and the number is '10', then you will get + * back '0010'. If you set the number to '4' and the number is '5000', then you + * will get back '5000'. + * + * Uses sprintf to append the amount of zeros based on the $threshold parameter + * and the size of the number. If the number is large enough, then no zeros will + * be appended. + * + * @since 0.71 + * + * @param mixed $number Number to append zeros to if not greater than threshold. + * @param int $threshold Digit places number needs to be to not have zeros added. + * @return string Adds leading zeros to number if needed. + */ +function zeroise($number, $threshold) { return sprintf('%0'.$threshold.'s', $number); } - +/** + * Adds backslashes before letters and before a number at the start of a string. + * + * @since 0.71 + * + * @param string $string Value to which backslashes will be added. + * @return string String with backslashes inserted. + */ function backslashit($string) { $string = preg_replace('/^([0-9])/', '\\\\\\\\\1', $string); $string = preg_replace('/([a-z])/i', '\\\\\1', $string); return $string; } +/** + * Appends a trailing slash. + * + * Will remove trailing slash if it exists already before adding a trailing + * slash. This prevents double slashing a string or path. + * + * The primary use of this is for paths and thus should be used for paths. It is + * not restricted to paths and offers no specific path support. + * + * @since 1.2.0 + * @uses untrailingslashit() Unslashes string if it was slashed already. + * + * @param string $string What to add the trailing slash to. + * @return string String with trailing slash added. + */ function trailingslashit($string) { return untrailingslashit($string) . '/'; } +/** + * Removes trailing slash if it exists. + * + * The primary use of this is for paths and thus should be used for paths. It is + * not restricted to paths and offers no specific path support. + * + * @since 2.2.0 + * + * @param string $string What to remove the trailing slash from. + * @return string String without the trailing slash. + */ function untrailingslashit($string) { return rtrim($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. + * + * @since 0.71 + * + * @param string $gpc The string returned from HTTP request data. + * @return string Returns a string escaped with slashes. + */ function addslashes_gpc($gpc) { global $wpdb; @@ -606,23 +1113,47 @@ function addslashes_gpc($gpc) { return $wpdb->escape($gpc); } - +/** + * Navigates through an array and removes slashes from the values. + * + * If an array is passed, the array_map() function causes a callback to pass the + * value back to the function. The slashes from this value will removed. + * + * @since 2.0.0 + * + * @param array|string $value The array or string to be striped. + * @return array|string Stripped array (or string in the callback). + */ function stripslashes_deep($value) { - $value = is_array($value) ? - array_map('stripslashes_deep', $value) : - stripslashes($value); - - return $value; + $value = is_array($value) ? array_map('stripslashes_deep', $value) : stripslashes($value); + return $value; } +/** + * Navigates through an array and encodes the values to be used in a URL. + * + * Uses a callback to pass the value of the array back to the function as a + * string. + * + * @since 2.2.0 + * + * @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; + $value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value); + return $value; } +/** + * Converts email addresses characters to HTML entities to block spam bots. + * + * @since 0.71 + * + * @param string $emailaddy Email address. + * @param int $mailto Optional. Range from 0 to 1. Used for encoding. + * @return string Converted email address. + */ function antispambot($emailaddy, $mailto=0) { $emailNOSPAMaddy = ''; srand ((float) microtime() * 1000000); @@ -640,25 +1171,43 @@ function antispambot($emailaddy, $mailto=0) { return $emailNOSPAMaddy; } +/** + * 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()}. + * + * @since 2.3.2 + * @access private + * + * @param array $matches Single Regex Match. + * @return string HTML A element with URI address. + */ function _make_url_clickable_cb($matches) { - $ret = ''; $url = $matches[2]; - $url = clean_url($url); + $url = esc_url($url); if ( empty($url) ) return $matches[0]; - // removed trailing [.,;:] from URL - if ( in_array(substr($url, -1), array('.', ',', ';', ':')) === true ) { - $ret = substr($url, -1); - $url = substr($url, 0, strlen($url)-1); - } - return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $ret; + return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>"; } +/** + * 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()}. + * + * @since 2.3.2 + * @access private + * + * @param array $matches Single Regex Match. + * @return string HTML A element with URL address. + */ function _make_web_ftp_clickable_cb($matches) { $ret = ''; $dest = $matches[2]; $dest = 'http://' . $dest; - $dest = clean_url($dest); + $dest = esc_url($dest); if ( empty($dest) ) return $matches[0]; // removed trailing [,;:] from URL @@ -669,16 +1218,39 @@ function _make_web_ftp_clickable_cb($matches) { return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>" . $ret; } +/** + * 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()}. + * + * @since 2.3.2 + * @access private + * + * @param array $matches Single Regex Match. + * @return string HTML A element with email address. + */ function _make_email_clickable_cb($matches) { $email = $matches[2] . '@' . $matches[3]; return $matches[1] . "<a href=\"mailto:$email\">$email</a>"; } +/** + * Convert plaintext URI to HTML links. + * + * Converts URI, www and ftp, and email addresses. Finishes by fixing links + * within links. + * + * @since 0.71 + * + * @param string $ret Content to convert URIs. + * @return string Content with converted URIs. + */ function make_clickable($ret) { $ret = ' ' . $ret; // in testing, using arrays here was found to be faster - $ret = preg_replace_callback('#([\s>])([\w]+?://[\w\#$%&~/.\-;:=,?@\[\]+]*)#is', '_make_url_clickable_cb', $ret); - $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\#$%&~/.\-;:=,?@\[\]+]*)#is', '_make_web_ftp_clickable_cb', $ret); + $ret = preg_replace_callback('#(?<=[\s>])(\()?([\w]+?://(?:[\w\\x80-\\xff\#$%&~/\-=?@\[\](+]|[.,;:](?![\s<])|(?(1)\)(?![\s<])|\)))+)#is', '_make_url_clickable_cb', $ret); + $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret); $ret = preg_replace_callback('#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret); // this one is not in an array because we need it to run last, for cleanup of accidental links within links $ret = preg_replace("#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i", "$1$3</a>", $ret); @@ -686,6 +1258,14 @@ function make_clickable($ret) { return $ret; } +/** + * Adds rel nofollow string to all HTML A elements in content. + * + * @since 1.5.0 + * + * @param string $text Content that may contain HTML A elements. + * @return string Converted content. + */ function wp_rel_nofollow( $text ) { global $wpdb; // This is a pre save filter, so text is already escaped. @@ -695,23 +1275,76 @@ function wp_rel_nofollow( $text ) { return $text; } +/** + * Callback to used to add rel=nofollow string to HTML A element. + * + * Will remove already existing rel="nofollow" and rel='nofollow' from the + * string to prevent from invalidating (X)HTML. + * + * @since 2.3.0 + * + * @param array $matches Single Match + * @return string HTML A Element with rel nofollow. + */ function wp_rel_nofollow_callback( $matches ) { $text = $matches[1]; $text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text); return "<a $text rel=\"nofollow\">"; } + +/** + * Convert one smiley code to the icon graphic file equivalent. + * + * Looks up one smiley code in the $wpsmiliestrans global array and returns an + * <img> string for that smiley. + * + * @global array $wpsmiliestrans + * @since 2.8.0 + * + * @param string $smiley Smiley code to convert to image. + * @return string Image string for smiley. + */ +function translate_smiley($smiley) { + global $wpsmiliestrans; + + if (count($smiley) == 0) { + return ''; + } + + $siteurl = get_option( 'siteurl' ); + + $smiley = trim(reset($smiley)); + $img = $wpsmiliestrans[$smiley]; + $smiley_masked = esc_attr($smiley); + + return " <img src='$siteurl/wp-includes/images/smilies/$img' alt='$smiley_masked' class='wp-smiley' /> "; +} + + +/** + * Convert text equivalent of smilies to images. + * + * Will only convert smilies if the option 'use_smilies' is true and the global + * used in the function isn't empty. + * + * @since 0.71 + * @uses $wp_smiliessearch + * + * @param string $text Content to convert smilies from text. + * @return string Converted content with text smilies replaced with images. + */ function convert_smilies($text) { - global $wp_smiliessearch, $wp_smiliesreplace; - $output = ''; - if ( get_option('use_smilies') && !empty($wp_smiliessearch) && !empty($wp_smiliesreplace) ) { + global $wp_smiliessearch; + $output = ''; + if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) { // HTML loop taken from texturize function, could possible be consolidated $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between $stop = count($textarr);// loop stuff for ($i = 0; $i < $stop; $i++) { $content = $textarr[$i]; if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag - $content = preg_replace($wp_smiliessearch, $wp_smiliesreplace, $content); + $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content); } $output .= $content; } @@ -722,94 +1355,300 @@ function convert_smilies($text) { return $output; } +/** + * Verifies that an email is valid. + * + * Does not grok i18n domains. Not RFC compliant. + * + * @since 0.71 + * + * @param string $email Email address to verify. + * @param boolean $check_dns Whether to check the DNS for the domain using checkdnsrr(). + * @return string|bool Either false or the valid email address. + */ +function is_email( $email, $check_dns = false ) { + // Test for the minimum length the email can be + if ( strlen( $email ) < 3 ) { + return apply_filters( 'is_email', false, $email, 'email_too_short' ); + } + + // Test for an @ character after the first position + if ( strpos( $email, '@', 1 ) === false ) { + return apply_filters( 'is_email', false, $email, 'email_no_at' ); + } -function is_email($user_email) { - $chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i"; - if (strpos($user_email, '@') !== false && strpos($user_email, '.') !== false) { - if (preg_match($chars, $user_email)) { - return true; - } else { - return false; + // Split out the local and domain parts + list( $local, $domain ) = explode( '@', $email, 2 ); + + // LOCAL PART + // Test for invalid characters + if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) { + return apply_filters( 'is_email', false, $email, 'local_invalid_chars' ); + } + + // DOMAIN PART + // Test for sequences of periods + if ( preg_match( '/\.{2,}/', $domain ) ) { + return apply_filters( 'is_email', false, $email, 'domain_period_sequence' ); + } + + // Test for leading and trailing periods and whitespace + if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) { + return apply_filters( 'is_email', false, $email, 'domain_period_limits' ); + } + + // Split the domain into subs + $subs = explode( '.', $domain ); + + // Assume the domain will have at least two subs + if ( 2 > count( $subs ) ) { + return apply_filters( 'is_email', false, $email, 'domain_no_periods' ); + } + + // Loop through each sub + foreach ( $subs as $sub ) { + // Test for leading and trailing hyphens and whitespace + if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) { + return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' ); } - } else { - return false; + + // Test for invalid characters + if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) { + return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' ); + } + } + + // DNS + // Check the domain has a valid MX and A resource record + if ( $check_dns && function_exists( 'checkdnsrr' ) && !( checkdnsrr( $domain . '.', 'MX' ) || checkdnsrr( $domain . '.', 'A' ) ) ) { + return apply_filters( 'is_email', false, $email, 'dns_no_rr' ); } + + // Congratulations your email made it! + return apply_filters( 'is_email', $email, $email, null ); } -// used by wp-mail to handle charsets in email subjects +/** + * Convert to ASCII from email subjects. + * + * @since 1.2.0 + * @usedby wp_mail() handles charsets in email subjects + * + * @param string $string Subject line + * @return string Converted string to ASCII + */ function wp_iso_descrambler($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('#\=([0-9a-f]{2})#ei', "chr(hexdec(strtolower('$1')))", $subject); - return $subject; - } + /* 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]); + $subject = preg_replace_callback('#\=([0-9a-f]{2})#i', create_function('$match', 'return chr(hexdec(strtolower($match[1])));'), $subject); + return $subject; + } } - -// give it a date, it will give you the same date as GMT +/** + * Returns a date in the GMT equivalent. + * + * Requires and returns a date in the Y-m-d H:i:s format. Simply subtracts the + * value of the 'gmt_offset' option. + * + * @since 1.2.0 + * + * @uses get_option() to retrieve the the value of 'gmt_offset'. + * @param string $string The date to be converted. + * @return string GMT version of the date provided. + */ function get_gmt_from_date($string) { - // note: this only substracts $time_difference from the given date - preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches); - $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]); - $string_gmt = gmdate('Y-m-d H:i:s', $string_time - get_option('gmt_offset') * 3600); - return $string_gmt; + preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches); + $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]); + $string_gmt = gmdate('Y-m-d H:i:s', $string_time - get_option('gmt_offset') * 3600); + return $string_gmt; } -// give it a GMT date, it will give you the same date with $time_difference added +/** + * Converts a GMT date into the correct format for the blog. + * + * Requires and returns in the Y-m-d H:i:s format. Simply adds the value of + * gmt_offset. + * + * @since 1.2.0 + * + * @param string $string The date to be converted. + * @return string Formatted date relative to the GMT offset. + */ function get_date_from_gmt($string) { - // note: this only adds $time_difference to the given date - preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches); - $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]); - $string_localtime = gmdate('Y-m-d H:i:s', $string_time + get_option('gmt_offset')*3600); - return $string_localtime; + preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches); + $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]); + $string_localtime = gmdate('Y-m-d H:i:s', $string_time + get_option('gmt_offset')*3600); + return $string_localtime; } -// computes an offset in seconds from an iso8601 timezone +/** + * Computes an offset in seconds from an iso8601 timezone. + * + * @since 1.5.0 + * + * @param string $timezone Either 'Z' for 0 offset or '±hhmm'. + * @return int|float The offset in seconds. + */ function iso8601_timezone_to_offset($timezone) { - // $timezone is either 'Z' or '[+|-]hhmm' - if ($timezone == 'Z') { - $offset = 0; - } else { - $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1; - $hours = intval(substr($timezone, 1, 2)); - $minutes = intval(substr($timezone, 3, 4)) / 60; - $offset = $sign * 3600 * ($hours + $minutes); - } - return $offset; -} - -// converts an iso8601 date to MySQL DateTime format used by post_date[_gmt] -function iso8601_to_datetime($date_string, $timezone = USER) { - if ($timezone == GMT) { - preg_match('#([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}#', $date_string, $date_bits); - if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset - $offset = iso8601_timezone_to_offset($date_bits[7]); - } else { // we don't have a timezone, so we assume user local timezone (not server's!) - $offset = 3600 * get_option('gmt_offset'); - } - $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]); - $timestamp -= $offset; - return gmdate('Y-m-d H:i:s', $timestamp); - } elseif ($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); - } + // $timezone is either 'Z' or '[+|-]hhmm' + if ($timezone == 'Z') { + $offset = 0; + } else { + $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1; + $hours = intval(substr($timezone, 1, 2)); + $minutes = intval(substr($timezone, 3, 4)) / 60; + $offset = $sign * 3600 * ($hours + $minutes); + } + return $offset; +} + +/** + * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt]. + * + * @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 $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'. + * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s. + */ +function iso8601_to_datetime($date_string, $timezone = 'user') { + $timezone = strtolower($timezone); + + if ($timezone == 'gmt') { + + preg_match('#([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}#', $date_string, $date_bits); + + if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset + $offset = iso8601_timezone_to_offset($date_bits[7]); + } else { // we don't have a timezone, so we assume user local timezone (not server's!) + $offset = 3600 * get_option('gmt_offset'); + } + + $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]); + $timestamp -= $offset; + + return gmdate('Y-m-d H:i:s', $timestamp); + + } else if ($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); + } } +/** + * 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) { - // 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. $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text); return $text; } -function sanitize_email($email) { - return preg_replace('/[^a-z0-9+_.@-]/i', '', $email); +/** + * Strips out all characters that are not allowable in an email. + * + * @since 1.5.0 + * + * @param string $email Email address to filter. + * @return string Filtered email address. + */ +function sanitize_email( $email ) { + // Test for the minimum length the email can be + if ( strlen( $email ) < 3 ) { + return apply_filters( 'sanitize_email', '', $email, 'email_too_short' ); + } + + // Test for an @ character after the first position + if ( strpos( $email, '@', 1 ) === false ) { + return apply_filters( 'sanitize_email', '', $email, 'email_no_at' ); + } + + // Split out the local and domain parts + list( $local, $domain ) = explode( '@', $email, 2 ); + + // LOCAL PART + // Test for invalid characters + $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local ); + if ( '' === $local ) { + return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' ); + } + + // DOMAIN PART + // Test for sequences of periods + $domain = preg_replace( '/\.{2,}/', '', $domain ); + if ( '' === $domain ) { + return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' ); + } + + // Test for leading and trailing periods and whitespace + $domain = trim( $domain, " \t\n\r\0\x0B." ); + if ( '' === $domain ) { + return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' ); + } + + // Split the domain into subs + $subs = explode( '.', $domain ); + + // Assume the domain will have at least two subs + if ( 2 > count( $subs ) ) { + return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' ); + } + + // Create an array that will contain valid subs + $new_subs = array(); + + // Loop through each sub + foreach ( $subs as $sub ) { + // Test for leading and trailing hyphens + $sub = trim( $sub, " \t\n\r\0\x0B-" ); + + // Test for invalid characters + $sub = preg_replace( '/^[^a-z0-9-]+$/i', '', $sub ); + + // If there's anything left, add it to the valid subs + if ( '' !== $sub ) { + $new_subs[] = $sub; + } + } + + // If there aren't 2 or more valid subs + if ( 2 > count( $new_subs ) ) { + return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' ); + } + + // Join valid subs into the new domain + $domain = join( '.', $new_subs ); + + // Put the email back together + $email = $local . '@' . $domain; + + // Congratulations your email made it! + return apply_filters( 'sanitize_email', $email, $email, null ); } +/** + * Determines the difference between two timestamps. + * + * The difference is returned in a human readable format such as "1 hour", + * "5 mins", "2 days". + * + * @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. + * @return string Human readable time difference. + */ function human_time_diff( $from, $to = '' ) { if ( empty($to) ) $to = time(); @@ -819,30 +1658,46 @@ function human_time_diff( $from, $to = '' ) { if ($mins <= 1) { $mins = 1; } - $since = sprintf(__ngettext('%s min', '%s mins', $mins), $mins); + $since = sprintf(_n('%s min', '%s mins', $mins), $mins); } else if (($diff <= 86400) && ($diff > 3600)) { $hours = round($diff / 3600); if ($hours <= 1) { $hours = 1; } - $since = sprintf(__ngettext('%s hour', '%s hours', $hours), $hours); + $since = sprintf(_n('%s hour', '%s hours', $hours), $hours); } elseif ($diff >= 86400) { $days = round($diff / 86400); if ($days <= 1) { $days = 1; } - $since = sprintf(__ngettext('%s day', '%s days', $days), $days); + $since = sprintf(_n('%s day', '%s days', $days), $days); } return $since; } -function wp_trim_excerpt($text) { // Fakes an excerpt if needed +/** + * Generates an excerpt from the content, if needed. + * + * The excerpt word amount will be 55 words and if the amount is greater than + * that, then the string '[...]' will be appended to the excerpt. If the string + * is less than 55 words, then the content will be returned as is. + * + * @since 1.5.0 + * + * @param string $text The exerpt. If set to empty an excerpt is generated. + * @return string The excerpt. + */ +function wp_trim_excerpt($text) { + $raw_excerpt = $text; if ( '' == $text ) { $text = get_the_content(''); + + $text = strip_shortcodes( $text ); + $text = apply_filters('the_content', $text); $text = str_replace(']]>', ']]>', $text); $text = strip_tags($text); - $excerpt_length = 55; + $excerpt_length = apply_filters('excerpt_length', 55); $words = explode(' ', $text, $excerpt_length + 1); if (count($words) > $excerpt_length) { array_pop($words); @@ -850,9 +1705,17 @@ function wp_trim_excerpt($text) { // Fakes an excerpt if needed $text = implode(' ', $words); } } - return $text; + return apply_filters('wp_trim_excerpt', $text, $raw_excerpt); } +/** + * Converts named entities into numbered entities. + * + * @since 1.5.1 + * + * @param string $text The text within which entities will be converted. + * @return string Text with converted entities. + */ function ent2ncr($text) { $to_ncr = array( '"' => '"', @@ -1117,21 +1980,39 @@ function ent2ncr($text) { return str_replace( array_keys($to_ncr), array_values($to_ncr), $text ); } +/** + * Formats text for the rich text editor. + * + * The filter 'richedit_pre' is applied here. If $text is empty the filter will + * be applied to an empty string. + * + * @since 2.0.0 + * + * @param string $text The text to be formatted. + * @return string The formatted text after filter is applied. + */ function wp_richedit_pre($text) { // Filtering a blank results in an annoying <br />\n if ( empty($text) ) return apply_filters('richedit_pre', ''); - $output = $text; - $output = convert_chars($output); + $output = convert_chars($text); $output = wpautop($output); - - // These must be double-escaped or planets will collide. - $output = str_replace('<', '&lt;', $output); - $output = str_replace('>', '&gt;', $output); + $output = htmlspecialchars($output, ENT_NOQUOTES); 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); // convert only < > & @@ -1139,25 +2020,44 @@ function wp_htmledit_pre($output) { return apply_filters('htmledit_pre', $output); } +/** + * Checks and cleans a URL. + * + * A number of characters are removed from the URL. If the URL is for displaying + * (the default behaviour) amperstands are also replaced. The 'esc_url' filter + * is applied to the returned cleaned URL. + * + * @since 1.2.0 + * @uses wp_kses_bad_protocol() To only permit protocols in the URL set + * via $protocols or the common ones set in the function. + * + * @param string $url The URL to be cleaned. + * @param array $protocols Optional. An array of acceptable protocols. + * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet' if not set. + * @param string $context Optional. How the URL will be used. Default is 'display'. + * @return string The cleaned $url after the 'cleaned_url' filter is applied. + */ function clean_url( $url, $protocols = null, $context = 'display' ) { $original_url = $url; if ('' == $url) return $url; - $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@()]|i', '', $url); + $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url); $strip = array('%0d', '%0a'); $url = str_replace($strip, '', $url); $url = str_replace(';//', '://', $url); /* If the URL doesn't appear to contain a scheme, we * presume it needs http:// appended (unless a relative * link starting with / or a php file). - */ + */ if ( strpos($url, ':') === false && - substr( $url, 0, 1 ) != '/' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) ) + substr( $url, 0, 1 ) != '/' && substr( $url, 0, 1 ) != '#' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) ) $url = 'http://' . $url; - // Replace ampersands ony when displaying. - if ( 'display' == $context ) + // Replace ampersands and single quotes only when displaying. + if ( 'display' == $context ) { $url = preg_replace('/&([^#])(?![a-z]{2,8};)/', '&$1', $url); + $url = str_replace( "'", ''', $url ); + } if ( !is_array($protocols) ) $protocols = array('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet'); @@ -1167,59 +2067,248 @@ function clean_url( $url, $protocols = null, $context = 'display' ) { return apply_filters('clean_url', $url, $original_url, $context); } +/** + * Escapes data for use in a MySQL query + * + * This is just a handy shortcut for $wpdb->escape(), for completeness' sake + * + * @since 2.8.0 + * @param string $sql Unescaped SQL data + * @return string The cleaned $sql + */ +function esc_sql( $sql ) { + global $wpdb; + return $wpdb->escape( $sql ); +} + + +/** + * Checks and cleans a URL. + * + * A number of characters are removed from the URL. If the URL is for displaying + * (the default behaviour) amperstands are also replaced. The 'esc_url' filter + * is applied to the returned cleaned URL. + * + * @since 2.8.0 + * @uses esc_url() + * @uses wp_kses_bad_protocol() To only permit protocols in the URL set + * via $protocols or the common ones set in the function. + * + * @param string $url The URL to be cleaned. + * @param array $protocols Optional. An array of acceptable protocols. + * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet' if not set. + * @return string The cleaned $url after the 'cleaned_url' filter is applied. + */ +function esc_url( $url, $protocols = null ) { + return clean_url( $url, $protocols, 'display' ); +} + +/** + * Performs esc_url() for database usage. + * + * @see esc_url() + * @see esc_url() + * + * @since 2.8.0 + * + * @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 ) { + return clean_url( $url, $protocols, 'db' ); +} + +/** + * Performs esc_url() for database or redirect usage. + * + * @see esc_url() + * @deprecated 2.8.0 + * + * @since 2.3.1 + * + * @param string $url The URL to be cleaned. + * @param array $protocols An array of acceptable protocols. + * @return string The cleaned URL. + */ function sanitize_url( $url, $protocols = null ) { - return clean_url( $url, $protocols, 'db'); + return clean_url( $url, $protocols, 'db' ); } -// Borrowed from the PHP Manual user notes. Convert entities, while -// preserving already-encoded entities: +/** + * Convert entities, while preserving already-encoded entities. + * + * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes. + * + * @since 1.2.2 + * + * @param string $myHTML The text to be converted. + * @return string Converted text. + */ function htmlentities2($myHTML) { - $translation_table=get_html_translation_table (HTML_ENTITIES,ENT_QUOTES); + $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, $translation_table)); + return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) ); +} + +/** + * Escape single quotes, specialchar double quotes, and fix line endings. + * + * The filter 'js_escape' is also applied here. + * + * @since 2.8.0 + * + * @param string $text The text to be escaped. + * @return string Escaped text. + */ +function esc_js( $text ) { + $safe_text = wp_check_invalid_utf8( $text ); + $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT ); + $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) ); + $safe_text = preg_replace( "/\r?\n/", "\\n", addslashes( $safe_text ) ); + return apply_filters( 'js_escape', $safe_text, $text ); +} + +/** + * Escape single quotes, specialchar double quotes, and fix line endings. + * + * The filter 'js_escape' is also applied by esc_js() + * + * @since 2.0.4 + * + * @deprecated 2.8.0 + * @see esc_js() + * + * @param string $text The text to be escaped. + * @return string Escaped text. + */ +function js_escape( $text ) { + return esc_js( $text ); +} + +/** + * Escaping for HTML blocks. + * + * @since 2.8.0 + * + * @param string $text + * @return string + */ +function esc_html( $text ) { + $safe_text = wp_check_invalid_utf8( $text ); + $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES ); + return apply_filters( 'esc_html', $safe_text, $text ); + return $text; +} + +/** + * Escaping for HTML blocks + * @deprecated 2.8.0 + * @see esc_html() + */ +function wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) { + if ( func_num_args() > 1 ) { // Maintain backwards compat for people passing additional args + $args = func_get_args(); + return call_user_func_array( '_wp_specialchars', $args ); + } else { + return esc_html( $string ); + } } -// Escape single quotes, specialchar double quotes, and fix line endings. -function js_escape($text) { - $safe_text = wp_specialchars($text, 'double'); - $safe_text = preg_replace('/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes($safe_text)); - $safe_text = preg_replace("/\r?\n/", "\\n", addslashes($safe_text)); - return apply_filters('js_escape', $safe_text, $text); +/** + * Escaping for HTML attributes. + * + * @since 2.8.0 + * + * @param string $text + * @return string + */ +function esc_attr( $text ) { + $safe_text = wp_check_invalid_utf8( $text ); + $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES ); + return apply_filters( 'attribute_escape', $safe_text, $text ); } -// Escaping for HTML attributes -function attribute_escape($text) { - $safe_text = wp_specialchars($text, true); - return apply_filters('attribute_escape', $safe_text, $text); +/** + * Escaping for HTML attributes. + * + * @since 2.0.6 + * + * @deprecated 2.8.0 + * @see esc_attr() + * + * @param string $text + * @return string + */ +function attribute_escape( $text ) { + return esc_attr( $text ); } -// Escape a HTML tag name +/** + * Escape a HTML tag name. + * + * @since 2.5.0 + * + * @param string $tag_name + * @return string + */ function tag_escape($tag_name) { - $safe_tag = strtolower( preg_replace('[^a-zA-Z_:]', '', $tag_name) ); + $safe_tag = strtolower( preg_replace('/[^a-zA-Z_:]/', '', $tag_name) ); return apply_filters('tag_escape', $safe_tag, $tag_name); } /** - * Escapes text for SQL LIKE special characters % and _ + * Escapes text for SQL LIKE special characters % and _. + * + * @since 2.5.0 * - * @param string text the text to be escaped - * @return string text, safe for inclusion in LIKE query + * @param string $text The text to be escaped. + * @return string text, safe for inclusion in LIKE query. */ function like_escape($text) { return str_replace(array("%", "_"), array("\\%", "\\_"), $text); } +/** + * Convert full URL paths to absolute paths. + * + * Removes the http or https protocols and the domain. Keeps the path '/' at the + * beginning, so it isn't a true relative link, but from the web root base. + * + * @since 2.1.0 + * + * @param string $link Full URL path. + * @return string Absolute path. + */ function wp_make_link_relative( $link ) { - return preg_replace('|https?://[^/]+(/.*)|i', '$1', $link ); + return preg_replace( '|https?://[^/]+(/.*)|i', '$1', $link ); } -function sanitize_option($option, $value) { // Remember to call stripslashes! +/** + * Sanitises various option values based on the nature of the option. + * + * This is basically a switch statement which will pass $value through a number + * of functions depending on the $option. + * + * @since 2.0.5 + * + * @param string $option The name of the option. + * @param string $value The unsanitised value. + * @return string Sanitized value. + */ +function sanitize_option($option, $value) { switch ($option) { case 'admin_email': $value = sanitize_email($value); break; + case 'thumbnail_size_w': + case 'thumbnail_size_h': + case 'medium_size_w': + case 'medium_size_h': + case 'large_size_w': + case 'large_size_h': case 'default_post_edit_rows': case 'mailserver_port': case 'comment_max_links': @@ -1228,6 +2317,9 @@ function sanitize_option($option, $value) { // Remember to call stripslashes! case 'default_category': case 'default_email_category': case 'default_link_category': + case 'close_comments_days_old': + case 'comments_per_page': + case 'thread_comments_depth': $value = abs((int) $value); break; @@ -1250,7 +2342,7 @@ function sanitize_option($option, $value) { // Remember to call stripslashes! $value = addslashes($value); $value = wp_filter_post_kses( $value ); // calls stripslashes then addslashes $value = stripslashes($value); - $value = wp_specialchars( $value ); + $value = esc_html( $value ); break; case 'blog_charset': @@ -1277,7 +2369,7 @@ function sanitize_option($option, $value) { // Remember to call stripslashes! case 'siteurl': case 'home': $value = stripslashes($value); - $value = clean_url($value); + $value = esc_url($value); break; default : $value = apply_filters("sanitize_option_{$option}", $value, $option); @@ -1287,26 +2379,64 @@ function sanitize_option($option, $value) { // Remember to call stripslashes! 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. + * + * @since 2.2.1 + * @uses apply_filters() for the 'wp_parse_str' filter. + * + * @param string $string The string to be parsed. + * @param array $array Variables will be stored in this array. + */ function wp_parse_str( $string, &$array ) { parse_str( $string, $array ); if ( get_magic_quotes_gpc() ) - $array = stripslashes_deep( $array ); // parse_str() adds slashes if magicquotes is on. See: http://php.net/parse_str + $array = stripslashes_deep( $array ); $array = apply_filters( 'wp_parse_str', $array ); } -// Convert lone less than signs. KSES already converts lone greater than signs. +/** + * Convert lone less than signs. + * + * KSES already converts lone greater than signs. + * + * @uses wp_pre_kses_less_than_callback in the callback function. + * @since 2.3.0 + * + * @param string $text Text to be converted. + * @return string Converted text. + */ function wp_pre_kses_less_than( $text ) { return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text); } +/** + * Callback function used by preg_replace. + * + * @uses esc_html to format the $matches text. + * @since 2.3.0 + * + * @param array $matches Populated by matches to preg_replace. + * @return string The text returned after esc_html if needed. + */ function wp_pre_kses_less_than_callback( $matches ) { if ( false === strpos($matches[0], '>') ) - return wp_specialchars($matches[0]); + return esc_html($matches[0]); return $matches[0]; } /** - * wp_sprintf() - sprintf() with filters + * WordPress implementation of PHP sprintf() with filters. + * + * @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. + * @return string The formatted string. */ function wp_sprintf( $pattern ) { $args = func_get_args( ); @@ -1361,11 +2491,17 @@ function wp_sprintf( $pattern ) { } /** - * wp_sprintf_l - List specifier %l for wp_sprintf + * Localize list items before the rest of the content. + * + * The '%l' must be at the first characters can then contain the rest of the + * content. The list items will have ', ', ', and', and ' and ' added depending + * on the amount of list items in the $args parameter. * - * @param unknown_type $pattern - * @param unknown_type $args - * @return unknown + * @since 2.5.0 + * + * @param string $pattern Content containing '%l' at the beginning. + * @param array $args List items to prepend to the content and replace '%l'. + * @return string Localized list items and rest of the content. */ function wp_sprintf_l($pattern, $args) { // Not a match @@ -1378,9 +2514,12 @@ function wp_sprintf_l($pattern, $args) { // Translate and filter the delimiter set (avoid ampersands and entities here) $l = apply_filters('wp_sprintf_l', array( - 'between' => _c(', |between list items'), - 'between_last_two' => _c(', and |between last two list items'), - 'between_only_two' => _c(' and |between only two list items'), + /* translators: used between list items, there is a space after the coma */ + 'between' => __(', '), + /* translators: used between list items, there is a space after the and */ + 'between_last_two' => __(', and '), + /* translators: used between only two list items, there is a space after the and */ + 'between_only_two' => __(' and '), )); $args = (array) $args; @@ -1388,9 +2527,11 @@ function wp_sprintf_l($pattern, $args) { if ( count($args) == 1 ) $result .= $l['between_only_two'] . array_shift($args); // Loop when more than two args - while ( count($args) ) { + $i = count($args); + while ( $i ) { $arg = array_shift($args); - if ( $i == 1 ) + $i--; + if ( 0 == $i ) $result .= $l['between_last_two'] . $arg; else $result .= $l['between'] . $arg; @@ -1399,21 +2540,108 @@ function wp_sprintf_l($pattern, $args) { } /** - * Safely extracts not more than the first $count characters from html string + * Safely extracts not more than the first $count characters from html string. + * + * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT* + * be counted as one character. For example & will be counted as 4, < as + * 3, etc. * - * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT* be - * counted as one character. For example & will be counted as 4, < as 3, etc. + * @since 2.5.0 * - * @param integer $str String to get the excerpt from - * @param integer $count Maximum number of characters to take - * @eaturn string the excerpt + * @param integer $str String to get the excerpt from. + * @param integer $count Maximum number of characters to take. + * @return string The excerpt. */ function wp_html_excerpt( $str, $count ) { $str = strip_tags( $str ); - $str = mb_strcut( $str, 0, $count ); + $str = mb_substr( $str, 0, $count ); // remove part of an entity at the end $str = preg_replace( '/&[^;\s]{0,6}$/', '', $str ); return $str; } +/** + * Add a Base url to relative links in passed content. + * + * By default it supports the 'src' and 'href' attributes. However this can be + * changed via the 3rd param. + * + * @since 2.7.0 + * + * @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. + * @return string The processed content. + */ +function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) { + $attrs = implode('|', (array)$attrs); + return preg_replace_callback("!($attrs)=(['\"])(.+?)\\2!i", + create_function('$m', 'return _links_add_base($m, "' . $base . '");'), + $content); +} + +/** + * Callback to add a base url to relative links in passed content. + * + * @since 2.7.0 + * @access private + * + * @param string $m The matched link. + * @param string $base The base URL to prefix to links. + * @return string The processed link. + */ +function _links_add_base($m, $base) { + //1 = attribute name 2 = quotation mark 3 = URL + return $m[1] . '=' . $m[2] . + (strpos($m[3], 'http://') === false ? + path_join($base, $m[3]) : + $m[3]) + . $m[2]; +} + +/** + * Adds a Target attribute to all links in passed content. + * + * This function by default only applies to <a> tags, however this can be + * modified by the 3rd param. + * + * <b>NOTE:</b> Any current target attributed will be striped and replaced. + * + * @since 2.7.0 + * + * @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. + * @return string The processed content. + */ +function links_add_target( $content, $target = '_blank', $tags = array('a') ) { + $tags = implode('|', (array)$tags); + return preg_replace_callback("!<($tags)(.+?)>!i", + create_function('$m', 'return _links_add_target($m, "' . $target . '");'), + $content); +} +/** + * Callback to add a target attribute to all links in passed content. + * + * @since 2.7.0 + * @access private + * + * @param string $m The matched link. + * @param string $target The Target to add to the links. + * @return string The processed link. + */ +function _links_add_target( $m, $target ) { + $tag = $m[1]; + $link = preg_replace('|(target=[\'"](.*?)[\'"])|i', '', $m[2]); + return '<' . $tag . $link . ' target="' . $target . '">'; +} + +// normalize EOL characters and strip duplicate whitespace +function normalize_whitespace( $str ) { + $str = trim($str); + $str = str_replace("\r", "\n", $str); + $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str ); + return $str; +} + ?>