* Replaces common plain text characters into formatted entities
*
* As an example,
- * <code>
- * 'cause today's effort makes it worth tomorrow's "holiday"...
- * </code>
+ *
+ * 'cause today's effort makes it worth tomorrow's "holiday" ...
+ *
* Becomes:
- * <code>
- * ’cause today’s effort makes it worth tomorrow’s “holiday”…
- * </code>
+ *
+ * ’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
+ * @param bool $reset Set to true for unit testing. Translated patterns will reset.
* @return string The string replaced with html entities
*/
-function wptexturize($text) {
- global $wp_cockneyreplace;
+function wptexturize($text, $reset = false) {
+ global $wp_cockneyreplace, $shortcode_tags;
static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
- $default_no_texturize_tags, $default_no_texturize_shortcodes;
+ $default_no_texturize_tags, $default_no_texturize_shortcodes, $run_texturize = true;
+
+ // If there's nothing to do, just stop.
+ if ( empty( $text ) || false === $run_texturize ) {
+ return $text;
+ }
+
+ // Set up static variables. Run once only.
+ if ( $reset || ! isset( $static_characters ) ) {
+ /**
+ * Filter whether to skip running wptexturize().
+ *
+ * Passing false to the filter will effectively short-circuit wptexturize().
+ * returning the original text passed to the function instead.
+ *
+ * The filter runs only once, the first time wptexturize() is called.
+ *
+ * @since 4.0.0
+ *
+ * @see wptexturize()
+ *
+ * @param bool $run_texturize Whether to short-circuit wptexturize().
+ */
+ $run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
+ if ( false === $run_texturize ) {
+ return $text;
+ }
- // No need to set up these static variables more than once
- if ( ! isset( $static_characters ) ) {
/* translators: opening curly double quote */
$opening_quote = _x( '“', 'opening curly double quote' );
/* translators: closing curly double quote */
$cockney = $cockneyreplace = array();
}
- $static_characters = array_merge( array( '---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)' ), $cockney );
- $static_replacements = array_merge( array( $em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
+ $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
+ $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
+
+ // Pattern-based replacements of characters.
+ // Sort the remaining patterns into several arrays for performance tuning.
+ $dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
+ $dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
$dynamic = array();
- if ( "'" != $apos ) {
- $dynamic[ '/\'(\d\d(?:’|\')?s)/' ] = $apos . '$1'; // '99's
- $dynamic[ '/\'(\d)/' ] = $apos . '$1'; // '99
+ $spaces = wp_spaces_regexp();
+
+ // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
+ if ( "'" !== $apos || "'" !== $closing_single_quote ) {
+ $dynamic[ '/\'(\d\d)\'(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $apos . '$1' . $closing_single_quote;
+ }
+ if ( "'" !== $apos || '"' !== $closing_quote ) {
+ $dynamic[ '/\'(\d\d)"(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $apos . '$1' . $closing_quote;
+ }
+
+ // '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
+ if ( "'" !== $apos ) {
+ $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos;
+ }
+
+ // Quoted Numbers like '0.42'
+ if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
+ $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $opening_single_quote . '$1' . $closing_single_quote;
+ }
+
+ // Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
+ if ( "'" !== $opening_single_quote ) {
+ $dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $opening_single_quote;
+ }
+
+ // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
+ if ( "'" !== $apos ) {
+ $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos;
+ }
+
+ // 9' (prime)
+ if ( "'" !== $prime ) {
+ $dynamic[ '/(?<=\d)\'/' ] = $prime;
+ }
+
+ // Single quotes followed by spaces or ending punctuation.
+ if ( "'" !== $closing_single_quote ) {
+ $dynamic[ '/\'(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $closing_single_quote;
}
- if ( "'" != $opening_single_quote )
- $dynamic[ '/(\s|\A|[([{<]|")\'/' ] = '$1' . $opening_single_quote; // opening single quote, even after (, {, <, [
- if ( '"' != $double_prime )
- $dynamic[ '/(\d)"/' ] = '$1' . $double_prime; // 9" (double prime)
- if ( "'" != $prime )
- $dynamic[ '/(\d)\'/' ] = '$1' . $prime; // 9' (prime)
- if ( "'" != $apos )
- $dynamic[ '/(\S)\'([^\'\s])/' ] = '$1' . $apos . '$2'; // apostrophe in a word
- if ( '"' != $opening_quote )
- $dynamic[ '/(\s|\A|[([{<])"(?!\s)/' ] = '$1' . $opening_quote . '$2'; // opening double quote, even after (, {, <, [
- if ( '"' != $closing_quote )
- $dynamic[ '/"(\s|\S|\Z)/' ] = $closing_quote . '$1'; // closing double quote
- if ( "'" != $closing_single_quote )
- $dynamic[ '/\'([\s.]|\Z)/' ] = $closing_single_quote . '$1'; // closing single quote
-
- $dynamic[ '/\b(\d+)x(\d+)\b/' ] = '$1×$2'; // 9x9 (times)
-
- $dynamic_characters = array_keys( $dynamic );
- $dynamic_replacements = array_values( $dynamic );
- }
-
- // Transform into regexp sub-expression used in _wptexturize_pushpop_element
+
+ $dynamic_characters['apos'] = array_keys( $dynamic );
+ $dynamic_replacements['apos'] = array_values( $dynamic );
+ $dynamic = array();
+
+ // Quoted Numbers like "42"
+ if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
+ $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $opening_quote . '$1' . $closing_quote;
+ }
+
+ // 9" (double prime)
+ if ( '"' !== $double_prime ) {
+ $dynamic[ '/(?<=\d)"/' ] = $double_prime;
+ }
+
+ // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
+ if ( '"' !== $opening_quote ) {
+ $dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
+ }
+
+ // Any remaining double quotes.
+ if ( '"' !== $closing_quote ) {
+ $dynamic[ '/"/' ] = $closing_quote;
+ }
+
+ $dynamic_characters['quote'] = array_keys( $dynamic );
+ $dynamic_replacements['quote'] = array_values( $dynamic );
+ $dynamic = array();
+
+ // Dashes and spaces
+ $dynamic[ '/---/' ] = $em_dash;
+ $dynamic[ '/(?<=' . $spaces . ')--(?=' . $spaces . ')/' ] = $em_dash;
+ $dynamic[ '/(?<!xn)--/' ] = $en_dash;
+ $dynamic[ '/(?<=' . $spaces . ')-(?=' . $spaces . ')/' ] = $en_dash;
+
+ $dynamic_characters['dash'] = array_keys( $dynamic );
+ $dynamic_replacements['dash'] = array_values( $dynamic );
+ }
+
// Must do this every time in case plugins use these filters in a context sensitive manner
- $no_texturize_tags = '(' . implode('|', apply_filters('no_texturize_tags', $default_no_texturize_tags) ) . ')';
- $no_texturize_shortcodes = '(' . implode('|', apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes) ) . ')';
+ /**
+ * Filter the list of HTML elements not to texturize.
+ *
+ * @since 2.8.0
+ *
+ * @param array $default_no_texturize_tags An array of HTML element names.
+ */
+ $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
+ /**
+ * Filter the list of shortcodes not to texturize.
+ *
+ * @since 2.8.0
+ *
+ * @param array $default_no_texturize_shortcodes An array of shortcode names.
+ */
+ $no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
$no_texturize_tags_stack = array();
$no_texturize_shortcodes_stack = array();
- $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
+ // Look for shortcodes and HTML elements.
+
+ $tagnames = array_keys( $shortcode_tags );
+ $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
+ $tagregexp = "(?:$tagregexp)(?![\\w-])"; // Excerpt of get_shortcode_regex().
+
+ $comment_regex =
+ '!' // 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.
+
+ $shortcode_regex =
+ '\[' // Find start of shortcode.
+ . '[\/\[]?' // Shortcodes may begin with [/ or [[
+ . $tagregexp // Only match registered shortcodes, because performance.
+ . '(?:'
+ . '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
+ . '|'
+ . '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
+ . ')*+' // Possessive critical.
+ . '\]' // Find end of shortcode.
+ . '\]?'; // Shortcodes may end with ]]
+
+ $regex =
+ '/(' // Capture the entire match.
+ . '<' // Find start of element.
+ . '(?(?=!--)' // Is this a comment?
+ . $comment_regex // Find end of comment.
+ . '|'
+ . '[^>]+>' // Find end of element.
+ . ')'
+ . '|'
+ . $shortcode_regex // Find shortcodes.
+ . ')/s';
+
+ $textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
foreach ( $textarr as &$curl ) {
- if ( empty( $curl ) )
+ // Only call _wptexturize_pushpop_element if $curl is a delimiter.
+ $first = $curl[0];
+ if ( '<' === $first && '<!--' === substr( $curl, 0, 4 ) ) {
+ // This is an HTML comment delimeter.
+
continue;
- // Only call _wptexturize_pushpop_element if first char is correct tag opening
- $first = $curl[0];
- if ( '<' === $first ) {
- _wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
- } elseif ( '[' === $first ) {
- _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
- } elseif ( empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack) ) {
- // This is not a tag, nor is the texturization disabled static strings
- $curl = str_replace($static_characters, $static_replacements, $curl);
- // regular expressions
- $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
+ } elseif ( '<' === $first && '>' === substr( $curl, -1 ) ) {
+ // This is an HTML element delimiter.
+
+ _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
+
+ } elseif ( '' === trim( $curl ) ) {
+ // This is a newline between delimiters. Performance improves when we check this.
+
+ continue;
+
+ } elseif ( '[' === $first && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
+ // This is a shortcode delimiter.
+
+ if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
+ // Looks like a normal shortcode.
+ _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
+ } else {
+ // Looks like an escaped shortcode.
+ continue;
+ }
+
+ } elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
+ // This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
+
+ $curl = str_replace( $static_characters, $static_replacements, $curl );
+
+ if ( false !== strpos( $curl, "'" ) ) {
+ $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
+ }
+ if ( false !== strpos( $curl, '"' ) ) {
+ $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
+ }
+ if ( false !== strpos( $curl, '-' ) ) {
+ $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
+ }
+
+ // 9x9 (times), but never 0x9999
+ if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
+ // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
+ $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1×$2', $curl );
+ }
}
- $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
}
- return implode( '', $textarr );
+ $text = implode( '', $textarr );
+
+ // Replace each & with & unless it already looks like an entity.
+ $text = preg_replace('/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $text);
+
+ return $text;
}
/**
* Search for disabled element tags. Push element to stack on tag open and pop
- * on tag close. Assumes first character of $text is tag opening.
+ * on tag close.
+ *
+ * Assumes first char of $text is tag opening and last char is tag closing.
+ * Assumes second char of $text is optionally '/' to indicate closing as in </html>.
*
* @since 2.9.0
* @access private
*
- * @param string $text Text to check. First character is assumed to be $opening
- * @param array $stack Array used as stack of opened tag elements
- * @param string $disabled_elements Tags to match against formatted as regexp sub-expression
- * @param string $opening Tag opening character, assumed to be 1 character long
- * @param string $closing Tag closing character
- */
-function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
- // Check if it is a closing tag -- otherwise assume opening tag
- if (strncmp($opening . '/', $text, 2)) {
- // Opening? Check $text+1 against disabled elements
- if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {
+ * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
+ * @param array $stack List of open tag elements.
+ * @param array $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
+ */
+function _wptexturize_pushpop_element($text, &$stack, $disabled_elements) {
+ // Is it an opening tag or closing tag?
+ if ( '/' !== $text[1] ) {
+ $opening_tag = true;
+ $name_offset = 1;
+ } elseif ( 0 == count( $stack ) ) {
+ // Stack is empty. Just stop.
+ return;
+ } else {
+ $opening_tag = false;
+ $name_offset = 2;
+ }
+
+ // Parse out the tag name.
+ $space = strpos( $text, ' ' );
+ if ( false === $space ) {
+ $space = -1;
+ } else {
+ $space -= $name_offset;
+ }
+ $tag = substr( $text, $name_offset, $space );
+
+ // Handle disabled tags.
+ if ( in_array( $tag, $disabled_elements ) ) {
+ if ( $opening_tag ) {
/*
* This disables texturize until we find a closing tag of our type
* (e.g. <pre>) even if there was invalid nesting before that
* "baba" won't be texturize
*/
- array_push($stack, $matches[1]);
- }
- } else {
- // Closing? Check $text+2 against disabled elements
- $c = preg_quote($closing, '/');
- if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {
- $last = array_pop($stack);
-
- // Make sure it matches the opening tag
- if ($last != $matches[1])
- array_push($stack, $last);
+ array_push( $stack, $tag );
+ } elseif ( end( $stack ) == $tag ) {
+ array_pop( $stack );
}
}
}
$pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
// Space things out a little
- $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|option|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|noscript|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
+ $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|details|menu|summary)';
$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
- if ( strpos($pee, '<object') !== false ) {
- $pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
- $pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
+
+ if ( strpos( $pee, '<option' ) !== false ) {
+ // no P/BR around option
+ $pee = preg_replace( '|\s*<option|', '<option', $pee );
+ $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
+ }
+
+ if ( strpos( $pee, '</object>' ) !== false ) {
+ // no P/BR around param and embed
+ $pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
+ $pee = preg_replace( '|\s*</object>|', '</object>', $pee );
+ $pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
}
+
+ if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
+ // no P/BR around source and track
+ $pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
+ $pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
+ $pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
+ }
+
$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
// make paragraphs, including one at the end
$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
$pee = '';
- foreach ( $pees as $tinkle )
+
+ foreach ( $pees as $tinkle ) {
$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
+ }
+
$pee = preg_replace('|<p>\s*</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
$pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
+
if ( $br ) {
$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
$pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
}
+
$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
$pee = preg_replace( "|\n</p>$|", '</p>', $pee );
/**
* Don't auto-p wrap shortcodes that stand alone
*
- * Ensures that shortcodes are not wrapped in <<p>>...<</p>>.
+ * Ensures that shortcodes are not wrapped in `<p>...</p>`.
*
* @since 2.9.0
*
}
$tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
+ $spaces = wp_spaces_regexp();
$pattern =
'/'
. '<p>' // Opening paragraph
- . '\\s*+' // Optional leading whitespace
+ . '(?:' . $spaces . ')*+' // Optional leading whitespace
. '(' // 1: The shortcode
. '\\[' // Opening bracket
. "($tagregexp)" // 2: Shortcode name
. ')?'
. ')'
. ')'
- . '\\s*+' // optional trailing whitespace
+ . '(?:' . $spaces . ')*+' // optional trailing whitespace
. '<\\/p>' // closing paragraph
. '/s';
* @return bool True if $str fits a UTF-8 model, false otherwise.
*/
function seems_utf8($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
* @access private
*
* @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 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.
* @return string The encoded text with HTML entities.
$num_octets = 1;
$unicode_length = 0;
+ mbstring_binary_safe_encoding();
$string_length = strlen( $utf8_string );
+ reset_mbstring_encoding();
+
for ($i = 0; $i < $string_length; $i++ ) {
$value = ord( $utf8_string[ $i ] );
$chars[ chr(195).chr(156) ] = 'Ue';
$chars[ chr(195).chr(188) ] = 'ue';
$chars[ chr(195).chr(159) ] = 'ss';
+ } elseif ( 'da_DK' === $locale ) {
+ $chars[ chr(195).chr(134) ] = 'Ae';
+ $chars[ chr(195).chr(166) ] = 'ae';
+ $chars[ chr(195).chr(152) ] = 'Oe';
+ $chars[ chr(195).chr(184) ] = 'oe';
+ $chars[ chr(195).chr(133) ] = 'Aa';
+ $chars[ chr(195).chr(165) ] = 'aa';
}
$string = strtr($string, $chars);
function sanitize_file_name( $filename ) {
$filename_raw = $filename;
$special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));
- $special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
- $filename = str_replace($special_chars, '', $filename);
- $filename = preg_replace('/[\s-]+/', '-', $filename);
- $filename = trim($filename, '.-_');
+ /**
+ * Filter the list of characters to remove from a filename.
+ *
+ * @since 2.8.0
+ *
+ * @param array $special_chars Characters to remove.
+ * @param string $filename_raw Filename as it was passed into sanitize_file_name().
+ */
+ $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
+ $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
+ $filename = str_replace( $special_chars, '', $filename );
+ $filename = str_replace( array( '%20', '+' ), '-', $filename );
+ $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
+ $filename = trim( $filename, '.-_' );
// Split the filename into a base and extension[s]
$parts = explode('.', $filename);
// Return if only one extension
- if ( count($parts) <= 2 )
- return apply_filters('sanitize_file_name', $filename, $filename_raw);
+ if ( count( $parts ) <= 2 ) {
+ /**
+ * Filter a sanitized filename string.
+ *
+ * @since 2.8.0
+ *
+ * @param string $filename Sanitized filename.
+ * @param string $filename_raw The filename prior to sanitization.
+ */
+ return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
+ }
// Process multiple extensions
$filename = array_shift($parts);
$extension = array_pop($parts);
$mimes = get_allowed_mime_types();
- // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character
- // long alpha string not in the extension whitelist.
+ /*
+ * Loop over any intermediate extensions. Postfix them with a trailing underscore
+ * if they are a 2 - 5 character long alpha string not in the extension whitelist.
+ */
foreach ( (array) $parts as $part) {
$filename .= '.' . $part;
}
}
$filename .= '.' . $extension;
-
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters('sanitize_file_name', $filename, $filename_raw);
}
* parameters for the 'sanitize_user' 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.
// Consolidate contiguous whitespace
$username = preg_replace( '|\s+|', ' ', $username );
+ /**
+ * Filter a sanitized username string.
+ *
+ * @since 2.0.1
+ *
+ * @param string $username Sanitized username.
+ * @param string $raw_username The username prior to sanitization.
+ * @param bool $strict Whether to limit the sanitization to specific characters. Default false.
+ */
return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
}
$raw_key = $key;
$key = strtolower( $key );
$key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
+
+ /**
+ * Filter a sanitized key string.
+ *
+ * @since 3.0.0
+ *
+ * @param string $key Sanitized key.
+ * @param string $raw_key The key prior to sanitization.
+ */
return apply_filters( 'sanitize_key', $key, $raw_key );
}
if ( 'save' == $context )
$title = remove_accents($title);
- $title = apply_filters('sanitize_title', $title, $raw_title, $context);
+ /**
+ * Filter a sanitized title string.
+ *
+ * @since 1.2.0
+ *
+ * @param string $title Sanitized title.
+ * @param string $raw_title The title prior to sanitization.
+ * @param string $context The context for which the title is being sanitized.
+ */
+ $title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
if ( '' === $title || false === $title )
$title = $fallback_title;
* Used for querying the database for a value from URL.
*
* @since 3.1.0
- * @uses sanitize_title()
*
* @param string $title The string to be sanitized.
* @return string The sanitized string.
}
/**
- * 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 string|bool Returns the order by clause if it is a match, false otherwise.
+ * @param string $orderby Order by clause to be validated.
+ * @return string|bool 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;
}
/**
* @since 2.8.0
*
* @param string $class The classname to be sanitized
- * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string.
+ * @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
*/
if ( '' == $sanitized )
$sanitized = $fallback;
+ /**
+ * Filter a sanitized HTML class string.
+ *
+ * @since 2.8.0
+ *
+ * @param string $sanitized The sanitized HTML class.
+ * @param string $class HTML class before sanitization.
+ * @param string $fallback The fallback string.
+ */
return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
}
/**
* Converts a number of characters from a string.
*
- * Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are
+ * Metadata tags `<title>` and `<category>` are removed, `<br>` and `<hr>` are
* converted into correct XHTML and Unicode characters are converted to the
* valid range.
*
* @return string Balanced text
*/
function balanceTags( $text, $force = false ) {
- if ( $force || get_option('use_balanceTags') == 1 )
+ if ( $force || get_option('use_balanceTags') == 1 ) {
return force_balance_tags( $text );
- else
+ } else {
return $text;
+ }
}
/**
* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
*/
function format_to_edit( $content, $richedit = false ) {
+ /**
+ * Filter the text to be formatted for editing.
+ *
+ * @since 1.2.0
+ *
+ * @param string $content The text, prior to formatting for editing.
+ */
$content = apply_filters( 'format_to_edit', $content );
if ( ! $richedit )
$content = esc_textarea( $content );
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;
-}
-
/**
* Add leading zeros when necessary.
*
/**
* 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.
+ * Will remove trailing forward and backslashes if it exists already before adding
+ * a trailing forward 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) . '/';
+function trailingslashit( $string ) {
+ return untrailingslashit( $string ) . '/';
}
/**
- * Removes trailing slash if it exists.
+ * Removes trailing forward slashes and backslashes if they exist.
*
* 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.
+ * @param string $string What to remove the trailing slashes from.
+ * @return string String without the trailing slashes.
*/
-function untrailingslashit($string) {
- return rtrim($string, '/');
+function untrailingslashit( $string ) {
+ return rtrim( $string, '/\\' );
}
/**
*
* @since 0.71
*
- * @param string $emailaddy Email address.
- * @param int $mailto Optional. Range from 0 to 1. Used for encoding.
+ * @param string $email_address Email address.
+ * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
* @return string Converted email address.
*/
-function antispambot($emailaddy, $mailto=0) {
- $emailNOSPAMaddy = '';
- srand ((float) microtime() * 1000000);
- for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
- $j = floor(rand(0, 1+$mailto));
- if ($j==0) {
- $emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
- } elseif ($j==1) {
- $emailNOSPAMaddy .= substr($emailaddy,$i,1);
- } elseif ($j==2) {
- $emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
+function antispambot( $email_address, $hex_encoding = 0 ) {
+ $email_no_spam_address = '';
+ for ( $i = 0; $i < strlen( $email_address ); $i++ ) {
+ $j = rand( 0, 1 + $hex_encoding );
+ if ( $j == 0 ) {
+ $email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
+ } elseif ( $j == 1 ) {
+ $email_no_spam_address .= $email_address[$i];
+ } elseif ( $j == 2 ) {
+ $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[$i] ) ), 2 );
}
}
- $emailNOSPAMaddy = str_replace('@','@',$emailNOSPAMaddy);
- return $emailNOSPAMaddy;
+
+ $email_no_spam_address = str_replace( '@', '@', $email_no_spam_address );
+
+ return $email_no_spam_address;
}
/**
function make_clickable( $text ) {
$r = '';
$textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
+ $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
foreach ( $textarr as $piece ) {
- if ( empty( $piece ) || ( $piece[0] == '<' && ! preg_match('|^<\s*[\w]{1,20}+://|', $piece) ) ) {
+
+ if ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) )
+ $nested_code_pre++;
+ elseif ( ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) ) && $nested_code_pre )
+ $nested_code_pre--;
+
+ if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
$r .= $piece;
continue;
}
}
// Cleanup of accidental links within links
- $r = preg_replace( '#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
+ $r = preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
return $r;
}
*
* Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
*
- * <code>
- * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
- * array (
- * 0 => '1234 67890 ', // 11 characters: Perfect split
- * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
- * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
- * 3 => '1234 890 ', // 11 characters: Perfect split
- * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
- * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
- * 6 => ' 45678 ', // 11 characters: Perfect split
- * 7 => '1 3 5 7 9', // 9 characters: End of $string
- * );
- * </code>
+ * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
+ * array (
+ * 0 => '1234 67890 ', // 11 characters: Perfect split
+ * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
+ * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
+ * 3 => '1234 890 ', // 11 characters: Perfect split
+ * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
+ * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
+ * 6 => ' 45678 ', // 11 characters: Perfect split
+ * 7 => '1 3 5 7 90 ', // 11 characters: End of $string
+ * );
*
* @since 3.4.0
* @access private
/**
* Convert one smiley code to the icon graphic file equivalent.
*
+ * Callback handler for {@link convert_smilies()}.
* Looks up one smiley code in the $wpsmiliestrans global array and returns an
- * <img> string for that smiley.
+ * `<img>` string for that smiley.
*
* @global array $wpsmiliestrans
* @since 2.8.0
*
- * @param string $smiley Smiley code to convert to image.
+ * @param array $matches Single match. Smiley code to convert to image.
* @return string Image string for smiley.
*/
-function translate_smiley($smiley) {
+function translate_smiley( $matches ) {
global $wpsmiliestrans;
- if (count($smiley) == 0) {
+ if ( count( $matches ) == 0 )
return '';
- }
- $smiley = trim(reset($smiley));
- $img = $wpsmiliestrans[$smiley];
- $smiley_masked = esc_attr($smiley);
-
- $srcurl = apply_filters('smilies_src', includes_url("images/smilies/$img"), $img, site_url());
+ $smiley = trim( reset( $matches ) );
+ $img = $wpsmiliestrans[ $smiley ];
+
+ /**
+ * Filter the Smiley image URL before it's used in the image element.
+ *
+ * @since 2.9.0
+ *
+ * @param string $smiley_url URL for the smiley image.
+ * @param string $img Filename for the smiley image.
+ * @param string $site_url Site URL, as returned by site_url().
+ */
+ $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
- return " <img src='$srcurl' alt='$smiley_masked' class='wp-smiley' /> ";
+ return sprintf( '<img src="%s" alt="%s" class="wp-smiley" />', esc_url( $src_url ), esc_attr( $smiley ) );
}
/**
* @param string $text Content to convert smilies from text.
* @return string Converted content with text smilies replaced with images.
*/
-function convert_smilies($text) {
+function convert_smilies( $text ) {
global $wp_smiliessearch;
$output = '';
- if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
+ 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++) {
+ $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
+ $stop = count( $textarr );// loop stuff
+
+ // Ignore proessing of specific tags
+ $tags_to_ignore = 'code|pre|style|script|textarea';
+ $ignore_block_element = '';
+
+ for ( $i = 0; $i < $stop; $i++ ) {
$content = $textarr[$i];
- if ((strlen($content) > 0) && ('<' != $content[0])) { // If it's not a tag
- $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
+
+ // 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] ) {
+ $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
+ }
+
+ // did we exit ignore block
+ if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
+ $ignore_block_element = '';
}
+
$output .= $content;
}
} else {
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
+ /**
+ * Filter whether an email address is valid.
+ *
+ * This filter is evaluated under several different contexts, such as 'email_too_short',
+ * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
+ * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
+ *
+ * @since 2.8.0
+ *
+ * @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
+ * @param string $email The email address being checked.
+ * @param string $message An explanatory message to the user.
+ * @param string $context Context under which the email was tested.
+ */
return apply_filters( 'is_email', false, $email, 'email_too_short' );
}
// Test for an @ character after the first position
if ( strpos( $email, '@', 1 ) === false ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'email_no_at' );
}
// LOCAL PART
// Test for invalid characters
if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
}
// DOMAIN PART
// Test for sequences of periods
if ( preg_match( '/\.{2,}/', $domain ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
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 ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
}
// Assume the domain will have at least two subs
if ( 2 > count( $subs ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
}
foreach ( $subs as $sub ) {
// Test for leading and trailing hyphens and whitespace
if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
}
// Test for invalid characters
if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
}
}
// Congratulations your email made it!
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', $email, $email, null );
}
* @access private
*
* @param array $match The preg_replace_callback matches array
- * @return array Converted chars
+ * @return string Converted chars
*/
function _wp_iso_convert( $match ) {
return chr( hexdec( strtolower( $match[1] ) ) );
*
* @since 1.2.0
*
- * @uses get_option() to retrieve the value of 'gmt_offset'.
* @param string $string The date to be converted.
* @param string $format The format string for the returned date (default is Y-m-d H:i:s)
* @return string GMT version of the date provided.
function sanitize_email( $email ) {
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
+ /**
+ * Filter a sanitized email address.
+ *
+ * This filter is evaluated under several contexts, including 'email_too_short',
+ * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
+ * 'domain_no_periods', 'domain_no_valid_subs', or no context.
+ *
+ * @since 2.8.0
+ *
+ * @param string $email The sanitized email address.
+ * @param string $email The email address, as provided to sanitize_email().
+ * @param string $message A message to pass to the user.
+ */
return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
}
// Test for an @ character after the first position
if ( strpos( $email, '@', 1 ) === false ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
}
// Test for invalid characters
$local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
if ( '' === $local ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
}
// Test for sequences of periods
$domain = preg_replace( '/\.{2,}/', '', $domain );
if ( '' === $domain ) {
+ /** This filter is documented in wp-includes/formatting.php */
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 ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
}
// Assume the domain will have at least two subs
if ( 2 > count( $subs ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
}
// If there aren't 2 or more valid subs
if ( 2 > count( $new_subs ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
}
$email = $local . '@' . $domain;
// Congratulations your email made it!
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', $email, $email, null );
}
* @return string Human readable time difference.
*/
function human_time_diff( $from, $to = '' ) {
- if ( empty( $to ) )
+ if ( empty( $to ) ) {
$to = time();
+ }
$diff = (int) abs( $to - $from );
$since = sprintf( _n( '%s year', '%s years', $years ), $years );
}
- return $since;
+ /**
+ * Filter the human readable difference between two timestamps.
+ *
+ * @since 4.0.0
+ *
+ * @param string $since The difference in human readable text.
+ * @param int $diff The difference in seconds.
+ * @param int $from Unix timestamp from which the difference begins.
+ * @param int $to Unix timestamp to end the time difference.
+ */
+ return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
}
/**
$text = strip_shortcodes( $text );
- $text = apply_filters('the_content', $text);
+ /** This filter is documented in wp-includes/post-template.php */
+ $text = apply_filters( 'the_content', $text );
$text = str_replace(']]>', ']]>', $text);
- $excerpt_length = apply_filters('excerpt_length', 55);
- $excerpt_more = apply_filters('excerpt_more', ' ' . '[…]');
+
+ /**
+ * Filter the number of words in an excerpt.
+ *
+ * @since 2.7.0
+ *
+ * @param int $number The number of words. Default 55.
+ */
+ $excerpt_length = apply_filters( 'excerpt_length', 55 );
+ /**
+ * Filter the string in the "more" link displayed after a trimmed excerpt.
+ *
+ * @since 2.9.0
+ *
+ * @param string $more_string The string shown within the more link.
+ */
+ $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' );
$text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
}
- return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
+ /**
+ * Filter the trimmed excerpt string.
+ *
+ * @since 2.8.0
+ *
+ * @param string $text The trimmed text.
+ * @param string $raw_excerpt The text prior to trimming.
+ */
+ return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
}
/**
} else {
$text = implode( $sep, $words_array );
}
+ /**
+ * Filter the text content after words have been trimmed.
+ *
+ * @since 3.3.0
+ *
+ * @param string $text The trimmed text.
+ * @param int $num_words The number of words to trim the text to. Default 5.
+ * @param string $more An optional string to append to the end of the trimmed text, e.g. ….
+ * @param string $original_text The text before it was trimmed.
+ */
return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
}
*/
function ent2ncr($text) {
- // Allow a plugin to short-circuit and override the mappings.
+ /**
+ * Filter text before named entities are converted into numbered entities.
+ *
+ * A non-null string must be returned for the filter to be evaluated.
+ *
+ * @since 3.3.0
+ *
+ * @param null $converted_text The text to be converted. Default null.
+ * @param string $text The text prior to entity conversion.
+ */
$filtered = apply_filters( 'pre_ent2ncr', null, $text );
if( null !== $filtered )
return $filtered;
* @return string The formatted text after filter is applied.
*/
function wp_richedit_pre($text) {
- // Filtering a blank results in an annoying <br />\n
- if ( empty($text) ) return apply_filters('richedit_pre', '');
+ 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', '' );
+ }
$output = convert_chars($text);
$output = wpautop($output);
$output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) );
- return apply_filters('richedit_pre', $output);
+ /** This filter is documented in wp-includes/formatting.php */
+ return apply_filters( 'richedit_pre', $output );
}
/**
if ( !empty($output) )
$output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) ); // convert only < > &
- return apply_filters('htmledit_pre', $output);
+ /**
+ * Filter the text before it is formatted for the HTML editor.
+ *
+ * @since 2.5.0
+ *
+ * @param string $output The HTML-formatted text.
+ */
+ return apply_filters( 'htmledit_pre', $output );
}
/**
* @since 2.8.1
* @access private
*
- * @param string|array $search
- * @param string $subject
- * @return string The processed string
+ * @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 ) {
- $found = true;
$subject = (string) $subject;
- while ( $found ) {
- $found = false;
- foreach ( (array) $search as $val ) {
- while ( strpos( $subject, $val ) !== false ) {
- $found = true;
- $subject = str_replace( $val, '', $subject );
- }
- }
+
+ $count = 1;
+ while ( $count ) {
+ $subject = str_replace( $search, '', $subject, $count );
}
return $subject;
* is preparing an array for use in an IN clause.
*
* @since 2.8.0
- * @param string $data Unescaped data
- * @return string Escaped data
+ * @param string|array $data Unescaped data
+ * @return string|array Escaped data
*/
function esc_sql( $data ) {
global $wpdb;
* is applied to the returned cleaned URL.
*
* @since 2.8.0
- * @uses wp_kses_bad_protocol() To only permit protocols in the URL set
- * via $protocols or the common ones set in the function.
*
* @param string $url The URL to be cleaned.
* @param array $protocols Optional. An array of acceptable protocols.
return '';
}
- return apply_filters('clean_url', $good_protocol_url, $original_url, $_context);
+ /**
+ * Filter a string cleaned and escaped for output as a URL.
+ *
+ * @since 2.3.0
+ *
+ * @param string $good_protocol_url The cleaned URL to be returned.
+ * @param string $original_url The URL prior to cleaning.
+ * @param string $_context If 'display', replace ampersands and single quotes only.
+ */
+ return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
}
/**
* Performs esc_url() for database usage.
*
* @since 2.8.0
- * @uses esc_url()
*
* @param string $url The URL to be cleaned.
* @param array $protocols An array of acceptable protocols.
$safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
$safe_text = str_replace( "\r", '', $safe_text );
$safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
+ /**
+ * Filter a string cleaned and escaped for output in JavaScript.
+ *
+ * Text passed to esc_js() is stripped of invalid or special characters,
+ * and properly slashed for output.
+ *
+ * @since 2.0.6
+ *
+ * @param string $safe_text The text after it has been escaped.
+ * @param string $text The text prior to being escaped.
+ */
return apply_filters( 'js_escape', $safe_text, $text );
}
function esc_html( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
+ /**
+ * Filter a string cleaned and escaped for output in HTML.
+ *
+ * Text passed to esc_html() is stripped of invalid or special characters
+ * before output.
+ *
+ * @since 2.8.0
+ *
+ * @param string $safe_text The text after it has been escaped.
+ * @param string $text The text prior to being escaped.
+ */
return apply_filters( 'esc_html', $safe_text, $text );
}
function esc_attr( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
+ /**
+ * Filter a string cleaned and escaped for output in an HTML attribute.
+ *
+ * Text passed to esc_attr() is stripped of invalid or special characters
+ * before output.
+ *
+ * @since 2.0.6
+ *
+ * @param string $safe_text The text after it has been escaped.
+ * @param string $text The text prior to being escaped.
+ */
return apply_filters( 'attribute_escape', $safe_text, $text );
}
*/
function esc_textarea( $text ) {
$safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
+ /**
+ * Filter a string cleaned and escaped for output in a textarea element.
+ *
+ * @since 3.1.0
+ *
+ * @param string $safe_text The text after it has been escaped.
+ * @param string $text The text prior to being escaped.
+ */
return apply_filters( 'esc_textarea', $safe_text, $text );
}
*/
function tag_escape($tag_name) {
$safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
- return apply_filters('tag_escape', $safe_tag, $tag_name);
-}
-
-/**
- * Escapes text for SQL LIKE special characters % and _.
- *
- * @since 2.5.0
- *
- * @param string $text The text to be escaped.
- * @return string text, safe for inclusion in LIKE query.
- */
-function like_escape($text) {
- return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
+ /**
+ * Filter a string cleaned and escaped for output as an HTML tag.
+ *
+ * @since 2.8.0
+ *
+ * @param string $safe_tag The tag name after it has been escaped.
+ * @param string $tag_name The text before it was escaped.
+ */
+ return apply_filters( 'tag_escape', $safe_tag, $tag_name );
}
/**
* beginning, so it isn't a true relative link, but from the web root base.
*
* @since 2.1.0
+ * @since 4.1.0 Support was added for relative URLs.
*
* @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', '$2', $link );
}
/**
case 'WPLANG':
$allowed = get_available_languages();
- if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
+ if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
+ $allowed[] = WPLANG;
+ }
+ if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
$value = get_option( $option );
+ }
break;
case 'illegal_names':
$value = esc_url_raw( $value );
$value = str_replace( 'http://', '', $value );
break;
+
+ case 'default_role' :
+ if ( ! get_role( $value ) && get_role( 'subscriber' ) )
+ $value = 'subscriber';
+ break;
+
+ 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 );
+ break;
}
- $value = apply_filters("sanitize_option_{$option}", $value, $option);
+ /**
+ * Filter an option value following sanitization.
+ *
+ * @since 2.3.0
+ *
+ * @param string $value The sanitized option value.
+ * @param string $option The option name.
+ */
+ $value = apply_filters( "sanitize_option_{$option}", $value, $option );
return $value;
}
* {@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.
parse_str( $string, $array );
if ( get_magic_quotes_gpc() )
$array = stripslashes_deep( $array );
+ /**
+ * Filter the array of variables derived from a parsed string.
+ *
+ * @since 2.3.0
+ *
+ * @param array $array The array populated with variables.
+ */
$array = apply_filters( 'wp_parse_str', $array );
}
*
* 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.
/**
* 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.
$arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
}
- // Apply filters OR sprintf
+ /**
+ * Filter a fragment from the pattern passed to wp_sprintf().
+ *
+ * If the fragment is unchanged, then sprintf() will be run on the fragment.
+ *
+ * @since 2.5.0
+ *
+ * @param string $fragment A fragment from the pattern.
+ * @param string $arg The argument.
+ */
$_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
if ( $_fragment != $fragment )
$fragment = $_fragment;
if ( empty($args) )
return '';
- // Translate and filter the delimiter set (avoid ampersands and entities here)
- $l = apply_filters('wp_sprintf_l', array(
- /* translators: used between list items, there is a space after the comma */
- '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 '),
- ));
+ /**
+ * Filter the translated delimiters used by wp_sprintf_l().
+ * Placeholders (%s) are included to assist translators and then
+ * removed before the array of strings reaches the filter.
+ *
+ * Please note: Ampersands and entities should be avoided here.
+ *
+ * @since 2.5.0
+ *
+ * @param array $delimiters An array of translated delimiters.
+ */
+ $l = apply_filters( 'wp_sprintf_l', array(
+ /* translators: used to join items in a list with more than 2 items */
+ 'between' => sprintf( __('%s, %s'), '', '' ),
+ /* translators: used to join last two items in a list with more than 2 times */
+ 'between_last_two' => sprintf( __('%s, and %s'), '', '' ),
+ /* translators: used to join items in a list with only 2 items */
+ 'between_only_two' => sprintf( __('%s and %s'), '', '' ),
+ ) );
$args = (array) $args;
$result = array_shift($args);
return $m[1] . '=' . $m[2] .
( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
$m[3] :
- path_join( $_links_add_base, $m[3] ) )
+ WP_HTTP::make_absolute_url( $m[3], $_links_add_base )
+ )
. $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
+ * 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 stripped and replaced.
+ * *NOTE:* Any current target attributed will be stripped and replaced.
*
* @since 2.7.0
*
global $_links_add_target;
$_links_add_target = $target;
$tags = implode('|', (array)$tags);
- return preg_replace_callback( "!<($tags)(.+?)>!i", '_links_add_target', $content );
+ return preg_replace_callback( "!<($tags)([^>]*)>!i", '_links_add_target', $content );
}
/**
function _links_add_target( $m ) {
global $_links_add_target;
$tag = $m[1];
- $link = preg_replace('|(target=([\'"])(.*?)\2)|i', '', $m[2]);
+ $link = preg_replace('|( target=([\'"])(.*?)\2)|i', '', $m[2]);
return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
}
/**
* Properly strip all HTML tags including script and style
*
+ * This differs from strip_tags() because it removes the contents of
+ * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
+ * will return 'something'. wp_strip_all_tags will return ''
+ *
* @since 2.9.0
*
* @param string $string String containing HTML tags
$filtered = trim( preg_replace('/ +/', ' ', $filtered) );
}
- return apply_filters('sanitize_text_field', $filtered, $str);
+ /**
+ * Filter a sanitized text field string.
+ *
+ * @since 2.9.0
+ *
+ * @param string $filtered The sanitized string.
+ * @param string $str The string prior to being sanitized.
+ */
+ return apply_filters( 'sanitize_text_field', $filtered, $str );
}
/**
*/
function capital_P_dangit( $text ) {
// Simple replacement for titles
- if ( 'the_title' === current_filter() )
+ $current_filter = current_filter();
+ if ( 'the_title' === $current_filter || 'wp_title' === $current_filter )
return str_replace( 'Wordpress', 'WordPress', $text );
// Still here? Use the more judicious replacement
static $dblq = false;
*/
function sanitize_mime_type( $mime_type ) {
$sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
+ /**
+ * Filter a mime type following sanitization.
+ *
+ * @since 3.1.3
+ *
+ * @param string $sani_mime_type The sanitized mime type.
+ * @param string $mime_type The mime type prior to sanitization.
+ */
return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
}
}
$urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
$urls_to_ping = implode( "\n", $urls_to_ping );
+ /**
+ * Filter a list of trackback URLs following sanitization.
+ *
+ * The string returned here consists of a space or carriage return-delimited list
+ * of trackback URLs.
+ *
+ * @since 3.4.0
+ *
+ * @param string $urls_to_ping Sanitized space or carriage return separated URLs.
+ * @param string $to_ping Space or carriage return separated URLs before sanitization.
+ */
return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
}
* @return string The found URL.
*/
function get_url_in_content( $content ) {
- if ( empty( $content ) )
- return '';
+ if ( empty( $content ) ) {
+ return false;
+ }
- if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) )
+ if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) ) {
return esc_url_raw( $matches[2] );
+ }
return false;
}
+
+/**
+ * Returns the regexp for common whitespace characters.
+ *
+ * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
+ * This is designed to replace the PCRE \s sequence. In ticket #22692, that
+ * sequence was found to be unreliable due to random inclusion of the A0 byte.
+ *
+ * @since 4.0.0
+ *
+ * @return string The spaces regexp.
+ */
+function wp_spaces_regexp() {
+ static $spaces;
+
+ if ( empty( $spaces ) ) {
+ /**
+ * Filter the regexp for common whitespace characters.
+ *
+ * This string is substituted for the \s sequence as needed in regular
+ * expressions. For websites not written in English, different characters
+ * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0
+ * sequence may not be in use.
+ *
+ * @since 4.0.0
+ *
+ * @param string $spaces Regexp pattern for matching common whitespace characters.
+ */
+ $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' );
+ }
+
+ return $spaces;
+}