* 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 */
$opening_quote = _x( '“', 'opening curly double quote' );
/* translators: closing curly double quote */
// if a plugin has provided an autocorrect array, use it
if ( isset($wp_cockneyreplace) ) {
- $cockney = array_keys($wp_cockneyreplace);
- $cockneyreplace = array_values($wp_cockneyreplace);
+ $cockney = array_keys( $wp_cockneyreplace );
+ $cockneyreplace = array_values( $wp_cockneyreplace );
} elseif ( "'" != $apos ) { // Only bother if we're doing a replacement.
- $cockney = array( "'tain't", "'twere", "'twas", "'tis", "'twill", "'til", "'bout", "'nuff", "'round", "'cause" );
- $cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause" );
+ $cockney = array( "'tain't", "'twere", "'twas", "'tis", "'twill", "'til", "'bout", "'nuff", "'round", "'cause", "'em" );
+ $cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause", $apos . "em" );
} else {
$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();
+ $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;
+ }
+ $dynamic_characters['apos'] = array_keys( $dynamic );
+ $dynamic_replacements['apos'] = array_values( $dynamic );
$dynamic = array();
- if ( "'" != $apos ) {
- $dynamic[ '/\'(\d\d(?:’|\')?s)/' ] = $apos . '$1'; // '99's
- $dynamic[ '/\'(\d)/' ] = $apos . '$1'; // '99
+
+ // 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;
}
- 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
+
+ // 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
/**
* 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.
+
+ $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 );
}
}
}
* 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 <<br />> tags, unless $br is set to '0'
- * or 'false'.
+ * replace double line-breaks with HTML paragraph tags. The remaining line-breaks
+ * after conversion become <<br />> tags, unless $br is set to '0' or 'false'.
*
* @since 0.71
*
* @param string $pee The text which has to be formatted.
- * @param bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
+ * @param 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, $br = true) {
if ( trim($pee) === '' )
return '';
- $pee = $pee . "\n"; // just to make things a little easier, pad the end
+ // Just to make things a little easier, pad the end.
+ $pee = $pee . "\n";
+ /*
+ * Pre tags shouldn't be touched by autop.
+ * Replace pre tags with placeholders and bring them back after autop.
+ */
if ( strpos($pee, '<pre') !== false ) {
$pee_parts = explode( '</pre>', $pee );
$last_pee = array_pop($pee_parts);
$pee .= $last_pee;
}
-
+ // Change multiple <br>s into two line breaks, which will turn into paragraphs.
$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|figcaption|details|menu|summary)';
+
+ // Add a single line break above block-level opening tags.
$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
+
+ // Add a double line break below block-level closing tags.
$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);
+
+ // Standardize newline characters to "\n".
+ $pee = str_replace(array("\r\n", "\r"), "\n", $pee);
+
+ // Find newlines in all elements and add placeholders.
+ $pee = wp_replace_in_html_tags( $pee, array( "\n" => " <!-- wpnl --> " ) );
+
+ // Collapse line breaks before and after <option> elements so they don't get autop'd.
+ if ( strpos( $pee, '<option' ) !== false ) {
+ $pee = preg_replace( '|\s*<option|', '<option', $pee );
+ $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
+ }
+
+ /*
+ * Collapse line breaks inside <object> elements, before <param> and <embed> elements
+ * so they don't get autop'd.
+ */
+ if ( strpos( $pee, '</object>' ) !== false ) {
+ $pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
+ $pee = preg_replace( '|\s*</object>|', '</object>', $pee );
+ $pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
+ }
+
+ /*
+ * Collapse line breaks inside <audio> and <video> elements,
+ * before and after <source> and <track> elements.
+ */
+ if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
+ $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
+
+ // Remove more than two contiguous line breaks.
+ $pee = preg_replace("/\n\n+/", "\n\n", $pee);
+
+ // Split up the contents into an array of strings, separated by double line breaks.
$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
+
+ // Reset $pee prior to rebuilding.
$pee = '';
- foreach ( $pees as $tinkle )
+
+ // Rebuild the content as a string, wrapping every bit with a <p>.
+ 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
+ }
+
+ // Under certain strange conditions it could create a P of entirely whitespace.
+ $pee = preg_replace('|<p>\s*</p>|', '', $pee);
+
+ // Add a closing <p> inside <div>, <address>, or <form> tag if missing.
$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 = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
+
+ // If an opening or closing block element tag is wrapped in a <p>, unwrap it.
+ $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
+
+ // In some cases <li> may get wrapped in <p>, fix them.
+ $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee);
+
+ // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
$pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
+
+ // If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
+
+ // If an opening or closing block element tag is followed by a closing <p> tag, remove it.
$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
+
+ // Optionally insert line breaks.
if ( $br ) {
+ // Replace newlines that shouldn't be touched with a placeholder.
$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
+
+ // Replace any new line characters that aren't preceded by a <br /> with a <br />.
+ $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee);
+
+ // Replace newline placeholders with newlines.
$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
}
+
+ // If a <br /> tag is after an opening or closing block tag, remove it.
$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
+
+ // If a <br /> tag is before a subset of opening or closing block tags, remove it.
$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
$pee = preg_replace( "|\n</p>$|", '</p>', $pee );
+ // Replace placeholder <pre> tags with their original content.
if ( !empty($pre_tags) )
$pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
+ // Restore newlines in all elements.
+ $pee = str_replace( " <!-- wpnl --> ", "\n", $pee );
+
return $pee;
}
+/**
+ * Separate HTML elements and comments from the text.
+ *
+ * @since 4.2.4
+ *
+ * @param string $input The text which has to be formatted.
+ * @return array The formatted text.
+ */
+function wp_html_split( $input ) {
+ static $regex;
+
+ if ( ! isset( $regex ) ) {
+ $comments =
+ '!' // Start of comment, after the <.
+ . '(?:' // Unroll the loop: Consume everything until --> is found.
+ . '-(?!->)' // Dash not followed by end of comment.
+ . '[^\-]*+' // Consume non-dashes.
+ . ')*+' // Loop possessively.
+ . '(?:-->)?'; // End of comment. If not found, match all input.
+
+ $cdata =
+ '!\[CDATA\[' // Start of comment, after the <.
+ . '[^\]]*+' // Consume non-].
+ . '(?:' // Unroll the loop: Consume everything until ]]> is found.
+ . '](?!]>)' // One ] not followed by end of comment.
+ . '[^\]]*+' // Consume non-].
+ . ')*+' // Loop possessively.
+ . '(?:]]>)?'; // End of comment. If not found, match all input.
+
+ $regex =
+ '/(' // Capture the entire match.
+ . '<' // Find start of element.
+ . '(?(?=!--)' // Is this a comment?
+ . $comments // Find end of comment.
+ . '|'
+ . '(?(?=!\[CDATA\[)' // Is this a comment?
+ . $cdata // Find end of comment.
+ . '|'
+ . '[^>]*>?' // Find end of element. If not found, match all input.
+ . ')'
+ . ')'
+ . ')/s';
+ }
+
+ return preg_split( $regex, $input, -1, PREG_SPLIT_DELIM_CAPTURE );
+}
+
+/**
+ * Replace characters or phrases within HTML elements only.
+ *
+ * @since 4.2.3
+ *
+ * @param string $haystack The text which has to be formatted.
+ * @param array $replace_pairs In the form array('from' => 'to', ...).
+ * @return string The formatted text.
+ */
+function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
+ // Find all elements.
+ $textarr = wp_html_split( $haystack );
+ $changed = false;
+
+ // Optimize when searching for one item.
+ if ( 1 === count( $replace_pairs ) ) {
+ // Extract $needle and $replace.
+ foreach ( $replace_pairs as $needle => $replace );
+
+ // Loop through delimeters (elements) only.
+ for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
+ if ( false !== strpos( $textarr[$i], $needle ) ) {
+ $textarr[$i] = str_replace( $needle, $replace, $textarr[$i] );
+ $changed = true;
+ }
+ }
+ } else {
+ // Extract all $needles.
+ $needles = array_keys( $replace_pairs );
+
+ // Loop through delimeters (elements) only.
+ for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
+ foreach ( $needles as $needle ) {
+ if ( false !== strpos( $textarr[$i], $needle ) ) {
+ $textarr[$i] = strtr( $textarr[$i], $replace_pairs );
+ $changed = true;
+ // After one strtr() break out of the foreach loop and look at next element.
+ break;
+ }
+ }
+ }
+ }
+
+ if ( $changed ) {
+ $haystack = implode( $textarr );
+ }
+
+ return $haystack;
+}
+
/**
* Newline preservation help function for wpautop
*
/**
* 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) $n = 0; # 0bbbbbbb
- elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
- elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
- elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
- elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
- elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
- else return false; # Does not match any model
- for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
+ if ($c < 0x80) $n = 0; // 0bbbbbbb
+ elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb
+ elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb
+ elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb
+ elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb
+ elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b
+ else return false; // Does not match any model
+ for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ?
if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
return false;
}
* @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.
// Now re-encode everything except &entity;
$string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE );
- for ( $i = 0; $i < count( $string ); $i += 2 )
+ for ( $i = 0, $c = count( $string ); $i < $c; $i += 2 ) {
$string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset );
-
+ }
$string = implode( '', $string );
}
$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 ] );
$unicode .= chr($value);
$unicode_length++;
} else {
- if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
+ if ( count( $values ) == 0 ) {
+ if ( $value < 224 ) {
+ $num_octets = 2;
+ } elseif ( $value < 240 ) {
+ $num_octets = 3;
+ } else {
+ $num_octets = 4;
+ }
+ }
$values[] = $value;
if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
break;
if ( count( $values ) == $num_octets ) {
- if ($num_octets == 3) {
- $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
- $unicode_length += 9;
- } else {
- $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
- $unicode_length += 6;
+ for ( $j = 0; $j < $num_octets; $j++ ) {
+ $unicode .= '%' . dechex( $values[ $j ] );
}
+ $unicode_length += $num_octets * 3;
+
$values = array();
$num_octets = 1;
}
$string = strtr($string, $chars);
} else {
+ $chars = array();
// Assume ISO-8859-1 if not UTF-8
$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
$string = strtr($string, $chars['in'], $chars['out']);
+ $double_chars = array();
$double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
$string = str_replace($double_chars['in'], $double_chars['out'], $string);
* @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 );
- $filename = str_replace($special_chars, '', $filename);
- $filename = preg_replace('/[\s-]+/', '-', $filename);
- $filename = trim($filename, '.-_');
+ $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);
* 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 a sort order (ASC / DESC).
+ * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
*
- * Accepts one or more columns, with or without ASC/DESC, and also accepts
- * RAND().
+ * 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
*/
/**
* 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.
*
// or close to be safe $tag = '/' . $tag;
}
// if stacktop value = tag close value then pop
- else if ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
+ elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
$tag = '</' . $tag . '>'; // Close Tag
// Pop
array_pop( $tagstack );
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) {
- /**
- * Filter the string returned by format_to_post().
- *
- * @since 1.2.0
- *
- * @param string $content The string to format.
- */
- $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, '/\\' );
}
/**
*/
function antispambot( $email_address, $hex_encoding = 0 ) {
$email_no_spam_address = '';
- for ( $i = 0; $i < strlen( $email_address ); $i++ ) {
+ for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
$j = rand( 0, 1 + $hex_encoding );
if ( $j == 0 ) {
$email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
}
// 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
*
* 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
$smiley = trim( reset( $matches ) );
$img = $wpsmiliestrans[ $smiley ];
+ $matches = array();
+ $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
+ $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
+
+ // Don't convert smilies that aren't images - they're probably emoji.
+ if ( ! in_array( $ext, $image_exts ) ) {
+ return $img;
+ }
+
/**
* Filter the Smiley image URL before it's used in the image element.
*
*/
$src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
- return sprintf( ' <img src="%s" alt="%s" class="wp-smiley" /> ', esc_url( $src_url ), esc_attr( $smiley ) );
+ return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
}
/**
* @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.
return gmdate('Y-m-d H:i:s', $timestamp);
- } else if ($timezone == 'user') {
+ } elseif ($timezone == 'user') {
return preg_replace('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', '$1-$2-$3 $4:$5:$6', $date_string);
}
}
* @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 );
}
/**
* 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.
* 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.
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.
*
* 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', $link );
}
/**
* @return string Sanitized value.
*/
function sanitize_option($option, $value) {
+ global $wpdb;
+ $error = '';
switch ( $option ) {
case 'admin_email' :
case 'new_admin_email' :
- $value = sanitize_email( $value );
- if ( ! is_email( $value ) ) {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists( 'add_settings_error' ) )
- add_settings_error( $option, 'invalid_admin_email', __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ) );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = sanitize_email( $value );
+ if ( ! is_email( $value ) ) {
+ $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
+ }
}
break;
case 'blogdescription':
case 'blogname':
- $value = wp_kses_post( $value );
- $value = esc_html( $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = wp_kses_post( $value );
+ $value = esc_html( $value );
+ }
break;
case 'blog_charset':
case 'mailserver_login':
case 'mailserver_pass':
case 'upload_path':
- $value = strip_tags( $value );
- $value = wp_kses_data( $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = strip_tags( $value );
+ $value = wp_kses_data( $value );
+ }
break;
case 'ping_sites':
break;
case 'siteurl':
- if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
- $value = esc_url_raw($value);
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
} else {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.'));
+ if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
+ $value = esc_url_raw( $value );
+ } else {
+ $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
+ }
}
break;
case 'home':
- if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
- $value = esc_url_raw($value);
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
} else {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.'));
+ if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
+ $value = esc_url_raw( $value );
+ } else {
+ $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
+ }
}
break;
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 ( ! is_array( $value ) )
- $value = explode( ' ', $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ if ( ! is_array( $value ) )
+ $value = explode( ' ', $value );
- $value = array_values( array_filter( array_map( 'trim', $value ) ) );
+ $value = array_values( array_filter( array_map( 'trim', $value ) ) );
- if ( ! $value )
- $value = '';
+ if ( ! $value )
+ $value = '';
+ }
break;
case 'limited_email_domains':
case 'banned_email_domains':
- if ( ! is_array( $value ) )
- $value = explode( "\n", $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ if ( ! is_array( $value ) )
+ $value = explode( "\n", $value );
- $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
- $value = array();
+ $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
+ $value = array();
- foreach ( $domains as $domain ) {
- if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) )
- $value[] = $domain;
+ foreach ( $domains as $domain ) {
+ if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
+ $value[] = $domain;
+ }
+ }
+ if ( ! $value )
+ $value = '';
}
- if ( ! $value )
- $value = '';
break;
case 'timezone_string':
$allowed_zones = timezone_identifiers_list();
if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('timezone_string', 'invalid_timezone_string', __('The timezone you have entered is not valid. Please select a valid timezone.') );
+ $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
}
break;
case 'permalink_structure':
case 'category_base':
case 'tag_base':
- $value = esc_url_raw( $value );
- $value = str_replace( 'http://', '', $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = esc_url_raw( $value );
+ $value = str_replace( 'http://', '', $value );
+ }
break;
case 'default_role' :
if ( ! get_role( $value ) && get_role( 'subscriber' ) )
$value = 'subscriber';
break;
+
+ case 'moderation_keys':
+ case 'blacklist_keys':
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = explode( "\n", $value );
+ $value = array_filter( array_map( 'trim', $value ) );
+ $value = array_unique( $value );
+ $value = implode( "\n", $value );
+ }
+ break;
+ }
+
+ if ( ! empty( $error ) ) {
+ $value = get_option( $option );
+ if ( function_exists( 'add_settings_error' ) ) {
+ add_settings_error( $option, "invalid_{$option}", $error );
+ }
}
/**
*
* 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.
* @link http://www.php.net/sprintf
*
* @param string $pattern The string which formatted args are inserted.
- * @param mixed $args,... Arguments to be formatted into the $pattern string.
+ * @param mixed $args ,... Arguments to be formatted into the $pattern string.
* @return string The formatted string.
*/
function wp_sprintf( $pattern ) {
/**
* 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.
*
* @param array $delimiters An array of translated delimiters.
*/
$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 '),
+ /* 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;
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
*
/**
* 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
* @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;
+}
+
+/**
+ * Print the important emoji-related styles.
+ *
+ * @since 4.2.0
+ */
+function print_emoji_styles() {
+ static $printed = false;
+
+ if ( $printed ) {
+ return;
+ }
+
+ $printed = true;
+?>
+<style type="text/css">
+img.wp-smiley,
+img.emoji {
+ display: inline !important;
+ border: none !important;
+ box-shadow: none !important;
+ height: 1em !important;
+ width: 1em !important;
+ margin: 0 .07em !important;
+ vertical-align: -0.1em !important;
+ background: none !important;
+ padding: 0 !important;
+}
+</style>
+<?php
+}
+
+function print_emoji_detection_script() {
+ global $wp_version;
+ static $printed = false;
+
+ if ( $printed ) {
+ return;
+ }
+
+ $printed = true;
+
+ $settings = array(
+ /**
+ * Filter the URL where emoji images are hosted.
+ *
+ * @since 4.2.0
+ *
+ * @param string The emoji base URL.
+ */
+ 'baseUrl' => apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) ),
+
+ /**
+ * Filter the extension of the emoji files.
+ *
+ * @since 4.2.0
+ *
+ * @param string The emoji extension. Default .png.
+ */
+ 'ext' => apply_filters( 'emoji_ext', '.png' ),
+ );
+
+ $version = 'ver=' . $wp_version;
+ $develop_src = false !== strpos( $wp_version, '-src' );
+
+ if ( $develop_src || ( defined( 'SCRIPT_DEBUG' ) && SCRIPT_DEBUG ) ) {
+ $settings['source'] = array(
+ /** This filter is documented in wp-includes/class.wp-scripts.php */
+ 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ),
+ /** This filter is documented in wp-includes/class.wp-scripts.php */
+ 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ),
+ );
+
+ ?>
+ <script type="text/javascript">
+ window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
+ <?php readfile( ABSPATH . WPINC . "/js/wp-emoji-loader.js" ); ?>
+ </script>
+ <?php
+ } else {
+ $settings['source'] = array(
+ /** This filter is documented in wp-includes/class.wp-scripts.php */
+ 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ),
+ );
+
+ /*
+ * If you're looking at a src version of this file, you'll see an "include"
+ * statement below. This is used by the `grunt build` process to directly
+ * include a minified version of wp-emoji-loader.js, instead of using the
+ * readfile() method from above.
+ *
+ * If you're looking at a build version of this file, you'll see a string of
+ * minified JavaScript. If you need to debug it, please turn on SCRIPT_DEBUG
+ * and edit wp-emoji-loader.js directly.
+ */
+ ?>
+ <script type="text/javascript">
+ window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
+ !function(a,b,c){function d(a){var c=b.createElement("canvas"),d=c.getContext&&c.getContext("2d");return d&&d.fillText?(d.textBaseline="top",d.font="600 32px Arial","flag"===a?(d.fillText(String.fromCharCode(55356,56812,55356,56807),0,0),c.toDataURL().length>3e3):(d.fillText(String.fromCharCode(55357,56835),0,0),0!==d.getImageData(16,16,1,1).data[0])):!1}function e(a){var c=b.createElement("script");c.src=a,c.type="text/javascript",b.getElementsByTagName("head")[0].appendChild(c)}var f,g;c.supports={simple:d("simple"),flag:d("flag")},c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.simple&&c.supports.flag||(g=function(){c.readyCallback()},b.addEventListener?(b.addEventListener("DOMContentLoaded",g,!1),a.addEventListener("load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onreadystatechange",function(){"complete"===b.readyState&&c.readyCallback()})),f=c.source||{},f.concatemoji?e(f.concatemoji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(window,document,window._wpemojiSettings);
+ </script>
+ <?php
+ }
+}
+
+/**
+ * Convert any 4 byte emoji in a string to their equivalent HTML entity.
+ *
+ * Currently, only Unicode 7 emoji are supported. Skin tone modifiers are allowed,
+ * all other Unicode 8 emoji will be added when the spec is finalised.
+ *
+ * This allows us to store emoji in a DB using the utf8 character set.
+ *
+ * @since 4.2.0
+ *
+ * @param string $content The content to encode.
+ * @return string The encoded content.
+ */
+function wp_encode_emoji( $content ) {
+ if ( function_exists( 'mb_convert_encoding' ) ) {
+ $regex = '/(
+ \x23\xE2\x83\xA3 # Digits
+ [\x30-\x39]\xE2\x83\xA3
+ | \xF0\x9F[\x85-\x88][\xA6-\xBF] # Enclosed characters
+ | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc
+ | \xF0\x9F\x98[\x80-\xBF] # Smilies
+ | \xF0\x9F\x99[\x80-\x8F]
+ | \xF0\x9F\x9A[\x80-\xBF] # Transport and map symbols
+ )/x';
+
+ $matches = array();
+ if ( preg_match_all( $regex, $content, $matches ) ) {
+ if ( ! empty( $matches[1] ) ) {
+ foreach( $matches[1] as $emoji ) {
+ /*
+ * UTF-32's hex encoding is the same as HTML's hex encoding.
+ * So, by converting the emoji from UTF-8 to UTF-32, we magically
+ * get the correct hex encoding.
+ */
+ $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) );
+ if ( isset( $unpacked[1] ) ) {
+ $entity = '&#x' . ltrim( $unpacked[1], '0' ) . ';';
+ $content = str_replace( $emoji, $entity, $content );
+ }
+ }
+ }
+ }
+ }
+
+ return $content;
+}
+
+/**
+ * Convert emoji to a static img element.
+ *
+ * @since 4.2.0
+ *
+ * @param string $text The content to encode.
+ * @return string The encoded content.
+ */
+function wp_staticize_emoji( $text ) {
+ $text = wp_encode_emoji( $text );
+
+ /** This filter is documented in wp-includes/formatting.php */
+ $cdn_url = apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) );
+
+ /** This filter is documented in wp-includes/formatting.php */
+ $ext = apply_filters( 'emoji_ext', '.png' );
+
+ $output = '';
+ /*
+ * HTML loop taken from smiley function, which was taken from texturize function.
+ * It'll never be consolidated.
+ *
+ * First, capture the tags as well as in between.
+ */
+ $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
+ $stop = count( $textarr );
+
+ // Ignore processing of specific tags.
+ $tags_to_ignore = 'code|pre|style|script|textarea';
+ $ignore_block_element = '';
+
+ for ( $i = 0; $i < $stop; $i++ ) {
+ $content = $textarr[$i];
+
+ // If we're in an ignore block, wait until we find its closing tag.
+ if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
+ $ignore_block_element = $matches[1];
+ }
+
+ // If it's not a tag and not in ignore block.
+ if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
+ $matches = array();
+ if ( preg_match_all( '/(DZ(e[6-9a-f]|f[0-9a-f]);){2}/', $content, $matches ) ) {
+ if ( ! empty( $matches[0] ) ) {
+ foreach ( $matches[0] as $flag ) {
+ $chars = str_replace( array( '&#x', ';'), '', $flag );
+
+ list( $char1, $char2 ) = str_split( $chars, 5 );
+ $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char1 . '-' . $char2 . $ext, html_entity_decode( $flag ) );
+
+ $content = str_replace( $flag, $entity, $content );
+ }
+ }
+ }
+
+ // Loosely match the Emoji Unicode range.
+ $regex = '/(&#x[2-3][0-9a-f]{3};|[1-6][0-9a-f]{2};)/';
+
+ $matches = array();
+ if ( preg_match_all( $regex, $content, $matches ) ) {
+ if ( ! empty( $matches[1] ) ) {
+ foreach ( $matches[1] as $emoji ) {
+ $char = str_replace( array( '&#x', ';'), '', $emoji );
+ $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char . $ext, html_entity_decode( $emoji ) );
+
+ $content = str_replace( $emoji, $entity, $content );
+ }
+ }
+ }
+ }
+
+ // Did we exit ignore block.
+ if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
+ $ignore_block_element = '';
+ }
+
+ $output .= $content;
+ }
+
+ return $output;
+}
+
+/**
+ * Convert emoji in emails into static images.
+ *
+ * @since 4.2.0
+ *
+ * @param array $mail The email data array.
+ * @return array The email data array, with emoji in the message staticized.
+ */
+function wp_staticize_emoji_for_email( $mail ) {
+ if ( ! isset( $mail['message'] ) ) {
+ return $mail;
+ }
+
+ /*
+ * We can only transform the emoji into images if it's a text/html email.
+ * To do that, here's a cut down version of the same process that happens
+ * in wp_mail() - get the Content-Type from the headers, if there is one,
+ * then pass it through the wp_mail_content_type filter, in case a plugin
+ * is handling changing the Content-Type.
+ */
+ $headers = array();
+ if ( isset( $mail['headers'] ) ) {
+ if ( is_array( $mail['headers'] ) ) {
+ $headers = $mail['headers'];
+ } else {
+ $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) );
+ }
+ }
+
+ foreach ( $headers as $header ) {
+ if ( strpos($header, ':') === false ) {
+ continue;
+ }
+
+ // Explode them out.
+ list( $name, $content ) = explode( ':', trim( $header ), 2 );
+
+ // Cleanup crew.
+ $name = trim( $name );
+ $content = trim( $content );
+
+ if ( 'content-type' === strtolower( $name ) ) {
+ if ( strpos( $content, ';' ) !== false ) {
+ list( $type, $charset ) = explode( ';', $content );
+ $content_type = trim( $type );
+ } else {
+ $content_type = trim( $content );
+ }
+ break;
+ }
+ }
+
+ // Set Content-Type if we don't have a content-type from the input headers.
+ if ( ! isset( $content_type ) ) {
+ $content_type = 'text/plain';
+ }
+
+ /** This filter is documented in wp-includes/pluggable.php */
+ $content_type = apply_filters( 'wp_mail_content_type', $content_type );
+
+ if ( 'text/html' === $content_type ) {
+ $mail['message'] = wp_staticize_emoji( $mail['message'] );
+ }
+
+ return $mail;
+}