* @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) {
+function wptexturize($text, $reset = false) {
global $wp_cockneyreplace;
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 );
-
- /*
- * Regex 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 #WP22692, that sequence
- * was found to be unreliable due to random inclusion of the A0 byte.
- */
- $spaces = '[\r\n\t ]|\xC2\xA0| ';
+ $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();
+ $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)
+ // '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
if ( "'" !== $apos ) {
- $dynamic[ '/\'(?=\d)/' ] = $apos;
+ $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos;
}
- // Single quote at start, or preceded by (, {, <, [, ", or spaces.
+ // 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;
+ $dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $opening_single_quote;
}
- // 9" (double prime)
- if ( '"' !== $double_prime ) {
- $dynamic[ '/(?<=\d)"/' ] = $double_prime;
+ // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
+ if ( "'" !== $apos ) {
+ $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos;
}
// 9' (prime)
$dynamic[ '/(?<=\d)\'/' ] = $prime;
}
- // Apostrophe in a word. No spaces or double primes.
- if ( "'" !== $apos ) {
- $dynamic[ '/(?<!' . $spaces . ')\'(?!\'|' . $spaces . ')/' ] = $apos;
+ // Single quotes followed by spaces or ending punctuation.
+ if ( "'" !== $closing_single_quote ) {
+ $dynamic[ '/\'(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $closing_single_quote;
+ }
+
+ $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.
+ // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
if ( '"' !== $opening_quote ) {
- $dynamic[ '/(?<=\A|[([{<]|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
+ $dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
}
// Any remaining double quotes.
$dynamic[ '/"/' ] = $closing_quote;
}
- // Single quotes followed by spaces or a period.
- if ( "'" !== $closing_single_quote ) {
- $dynamic[ '/\'(?=\Z|\.|' . $spaces . ')/' ] = $closing_single_quote;
- }
+ $dynamic_characters['quote'] = array_keys( $dynamic );
+ $dynamic_replacements['quote'] = array_values( $dynamic );
+ $dynamic = array();
- $dynamic_characters = array_keys( $dynamic );
- $dynamic_replacements = array_values( $dynamic );
+ // 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 );
}
- // Transform into regexp sub-expression used in _wptexturize_pushpop_element
// Must do this every time in case plugins use these filters in a context sensitive manner
/**
* Filter the list of HTML elements not to texturize.
*
* @param array $default_no_texturize_tags An array of HTML element names.
*/
- $no_texturize_tags = '(' . implode( '|', apply_filters( 'no_texturize_tags', $default_no_texturize_tags ) ) . ')';
+ $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
/**
* Filter the list of shortcodes not to texturize.
*
*
* @param array $default_no_texturize_shortcodes An array of shortcode names.
*/
- $no_texturize_shortcodes = '(' . implode( '|', apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes ) ) . ')';
+ $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.
+
+ $regex = '/(' // Capture the entire match.
+ . '<' // Find start of element.
+ . '(?(?=!--)' // Is this a comment?
+ . '.+?--\s*>' // Find end of comment
+ . '|'
+ . '[^>]+>' // Find end of element
+ . ')'
+ . '|'
+ . '\[' // Find start of shortcode.
+ . '\[?' // Shortcodes may begin with [[
+ . '(?:'
+ . '[^\[\]<>]' // Shortcodes do not contain other shortcodes.
+ . '|'
+ . '<[^>]+>' // HTML elements permitted. Prevents matching ] before >.
+ . ')++'
+ . '\]' // Find end of shortcode.
+ . '\]?' // Shortcodes may end with ]]
+ . ')/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, -1 ) ) {
+ // This is an HTML delimiter.
+
+ if ( '<!--' !== substr( $curl, 0, 4 ) ) {
+ _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;
- }
- // 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) ) {
+ } elseif ( '[' === $first && 1 === preg_match( '/^\[(?:[^\[\]<>]|<[^>]+>)++\]$/', $curl ) ) {
+ // This is a shortcode delimiter.
+
+ _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
- // This is not a tag, nor is the texturization disabled static strings
- $curl = str_replace($static_characters, $static_replacements, $curl);
+ } elseif ( '[' === $first && 1 === preg_match( '/^\[\[?(?:[^\[\]<>]|<[^>]+>)++\]\]?$/', $curl ) ) {
+ // This is an escaped shortcode delimiter.
- // regular expressions
- $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
+ // Do not texturize.
+ // Do not push to the shortcodes stack.
- // 9x9 (times)
- if ( 1 === preg_match( '/(?<=\d)x\d/', $text ) ) {
+ 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+)x(\d+)\b/', '$1×$2', $curl );
+ $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(-?\d[\d\.,]*)\b/', '$1×$2', $curl );
}
}
-
- // Replace each & with & unless it already looks like an entity.
- $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|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|noscript|legend|section|article|aside|hgroup|header|footer|nav|figure|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, '<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 );
}
$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
$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 ] );
$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('/[\s-]+/', '-', $filename);
$filename = trim($filename, '.-_');
* @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
*/
*/
$src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
- return sprintf( ' <img src="%s" alt="%s" class="wp-smiley" /> ', esc_url( $src_url ), esc_attr( $smiley ) );
+ return sprintf( '<img src="%s" alt="%s" class="wp-smiley" />', esc_url( $src_url ), esc_attr( $smiley ) );
}
/**
* @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 );
}
/**
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);
-}
-
/**
* Convert full URL paths to absolute paths.
*
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':
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;
}
/**
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;
+}