Skip to content
Permalink
master
Go to file
 
 
Cannot retrieve contributors at this time
6062 lines (5503 sloc) 303 KB
<?php
/**
* Main WordPress Formatting API.
*
* Handles many functions for formatting output.
*
* @package WordPress
*/
/**
* Replaces common plain text characters with formatted entities.
*
* Returns given text with transformations of quotes into smart quotes, apostrophes,
* dashes, ellipses, the trademark symbol, and the multiplication symbol.
*
* As an example,
*
* 'cause today's effort makes it worth tomorrow's "holiday" ...
*
* Becomes:
*
* &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221; &#8230;
*
* Code within certain HTML blocks are skipped.
*
* Do not use this function before the {@see 'init'} action hook; everything will break.
*
* @since 0.71
*
* @global array $wp_cockneyreplace Array of formatted entities for certain common phrases.
* @global array $shortcode_tags
*
* @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, $reset = false ) {
global $wp_cockneyreplace, $shortcode_tags;
static $static_characters = null,
$static_replacements = null,
$dynamic_characters = null,
$dynamic_replacements = null,
$default_no_texturize_tags = null,
$default_no_texturize_shortcodes = null,
$run_texturize = true,
$apos = null,
$prime = null,
$double_prime = null,
$opening_quote = null,
$closing_quote = null,
$opening_single_quote = null,
$closing_single_quote = null,
$open_q_flag = '<!--oq-->',
$open_sq_flag = '<!--osq-->',
$apos_flag = '<!--apos-->';
// 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 ) ) {
/**
* Filters whether to skip running wptexturize().
*
* Returning false from the filter will effectively short-circuit wptexturize()
* and return 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;
}
/* translators: Opening curly double quote. */
$opening_quote = _x( '&#8220;', 'opening curly double quote' );
/* translators: Closing curly double quote. */
$closing_quote = _x( '&#8221;', 'closing curly double quote' );
/* translators: Apostrophe, for example in 'cause or can't. */
$apos = _x( '&#8217;', 'apostrophe' );
/* translators: Prime, for example in 9' (nine feet). */
$prime = _x( '&#8242;', 'prime' );
/* translators: Double prime, for example in 9" (nine inches). */
$double_prime = _x( '&#8243;', 'double prime' );
/* translators: Opening curly single quote. */
$opening_single_quote = _x( '&#8216;', 'opening curly single quote' );
/* translators: Closing curly single quote. */
$closing_single_quote = _x( '&#8217;', 'closing curly single quote' );
/* translators: En dash. */
$en_dash = _x( '&#8211;', 'en dash' );
/* translators: Em dash. */
$em_dash = _x( '&#8212;', 'em dash' );
$default_no_texturize_tags = array( 'pre', 'code', 'kbd', 'style', 'script', 'tt' );
$default_no_texturize_shortcodes = array( 'code' );
// If a plugin has provided an autocorrect array, use it.
if ( isset( $wp_cockneyreplace ) ) {
$cockney = array_keys( $wp_cockneyreplace );
$cockneyreplace = array_values( $wp_cockneyreplace );
} else {
/*
* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
* for example... 'We do not have enough words yet'... is a typical quoted phrase. But when we write
* lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
*/
$cockney = explode(
',',
_x(
"'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
'Comma-separated list of words to texturize in your language'
)
);
$cockneyreplace = explode(
',',
_x(
'&#8217;tain&#8217;t,&#8217;twere,&#8217;twas,&#8217;tis,&#8217;twill,&#8217;til,&#8217;bout,&#8217;nuff,&#8217;round,&#8217;cause,&#8217;em',
'Comma-separated list of replacement words in your language'
)
);
}
$static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
$static_replacements = array_merge( array( '&#8230;', $opening_quote, $closing_quote, ' &#8482;' ), $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|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
}
if ( "'" !== $apos || '"' !== $closing_quote ) {
$dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$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_flag;
}
// Quoted numbers like '0.42'.
if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
$dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
}
// Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
if ( "'" !== $opening_single_quote ) {
$dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $open_sq_flag;
}
// Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
if ( "'" !== $apos ) {
$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
}
$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]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
}
// Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
if ( '"' !== $opening_quote ) {
$dynamic[ '/(?<=\A|[([{\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
}
$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.
/**
* Filters the list of HTML elements not to texturize.
*
* @since 2.8.0
*
* @param string[] $default_no_texturize_tags An array of HTML element names.
*/
$no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
/**
* Filters the list of shortcodes not to texturize.
*
* @since 2.8.0
*
* @param string[] $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();
// Look for shortcodes and HTML elements.
preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
$tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
$found_shortcodes = ! empty( $tagnames );
$shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
$regex = _get_wptexturize_split_regex( $shortcode_regex );
$textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
foreach ( $textarr as &$curl ) {
// Only call _wptexturize_pushpop_element if $curl is a delimiter.
$first = $curl[0];
if ( '<' === $first ) {
if ( '<!--' === substr( $curl, 0, 4 ) ) {
// This is an HTML comment delimiter.
continue;
} else {
// This is an HTML element delimiter.
// Replace each & with &#038; unless it already looks like an entity.
$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );
_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 && $found_shortcodes && 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 );
$curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
$curl = str_replace( $apos_flag, $apos, $curl );
$curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
}
if ( false !== strpos( $curl, '"' ) ) {
$curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
$curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
$curl = str_replace( $open_q_flag, $opening_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&#215;$2', $curl );
}
// Replace each & with &#038; unless it already looks like an entity.
$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );
}
}
return implode( '', $textarr );
}
/**
* Implements a logic tree to determine whether or not "7'." represents seven feet,
* then converts the special char into either a prime char or a closing quote char.
*
* @since 4.3.0
*
* @param string $haystack The plain text to be searched.
* @param string $needle The character to search for such as ' or ".
* @param string $prime The prime char to use for replacement.
* @param string $open_quote The opening quote char. Opening quote replacement must be
* accomplished already.
* @param string $close_quote The closing quote char to use for replacement.
* @return string The $haystack value after primes and quotes replacements.
*/
function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
$spaces = wp_spaces_regexp();
$flag = '<!--wp-prime-or-quote-->';
$quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|&gt;|" . $spaces . ')/';
$prime_pattern = "/(?<=\\d)$needle/";
$flag_after_digit = "/(?<=\\d)$flag/";
$flag_no_digit = "/(?<!\\d)$flag/";
$sentences = explode( $open_quote, $haystack );
foreach ( $sentences as $key => &$sentence ) {
if ( false === strpos( $sentence, $needle ) ) {
continue;
} elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
$sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
if ( $count > 1 ) {
// This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
$sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
if ( 0 === $count2 ) {
// Try looking for a quote followed by a period.
$count2 = substr_count( $sentence, "$flag." );
if ( $count2 > 0 ) {
// Assume the rightmost quote-period match is the end of quotation.
$pos = strrpos( $sentence, "$flag." );
} else {
// When all else fails, make the rightmost candidate a closing quote.
// This is most likely to be problematic in the context of bug #18549.
$pos = strrpos( $sentence, $flag );
}
$sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
}
// Use conventional replacement on any remaining primes and quotes.
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
$sentence = preg_replace( $flag_after_digit, $prime, $sentence );
$sentence = str_replace( $flag, $close_quote, $sentence );
} elseif ( 1 == $count ) {
// Found only one closing quote candidate, so give it priority over primes.
$sentence = str_replace( $flag, $close_quote, $sentence );
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
} else {
// No closing quotes found. Just run primes pattern.
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
}
} else {
$sentence = preg_replace( $prime_pattern, $prime, $sentence );
$sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
}
if ( '"' === $needle && false !== strpos( $sentence, '"' ) ) {
$sentence = str_replace( '"', $close_quote, $sentence );
}
}
return implode( $open_quote, $sentences );
}
/**
* Search for disabled element tags. Push element to stack on tag open and pop
* 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. Must be a tag like `<html>` or `[shortcode]`.
* @param string[] $stack Array of open tag elements.
* @param string[] $disabled_elements Array of 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 ( isset( $text[1] ) && '/' !== $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, true ) ) {
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.
*
* Example: in the case <pre>sadsadasd</code>"baba"</pre>
* "baba" won't be texturized.
*/
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'.
*
* @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. Line breaks within `<script>`, `<style>`,
* and `<svg>` tags are not affected. Default true.
* @return string Text which has been converted into correct paragraph tags.
*/
function wpautop( $pee, $br = true ) {
$pre_tags = array();
if ( trim( $pee ) === '' ) {
return '';
}
// 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 = '';
$i = 0;
foreach ( $pee_parts as $pee_part ) {
$start = strpos( $pee_part, '<pre' );
// Malformed HTML?
if ( false === $start ) {
$pee .= $pee_part;
continue;
}
$name = "<pre wp-pre-tag-$i></pre>";
$pre_tags[ $name ] = substr( $pee_part, $start ) . '</pre>';
$pee .= substr( $pee_part, 0, $start ) . $name;
$i++;
}
$pee .= $last_pee;
}
// Change multiple <br>'s into two line breaks, which will turn into paragraphs.
$pee = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee );
$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 double line break above block-level opening tags.
$pee = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $pee );
// Add a double line break below block-level closing tags.
$pee = preg_replace( '!(</' . $allblocks . '>)!', "$1\n\n", $pee );
// Add a double line break after hr tags, which are self closing.
$pee = preg_replace( '!(<hr\s*?/?>)!', "$1\n\n", $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 );
}
// Collapse line breaks before and after <figcaption> elements.
if ( strpos( $pee, '<figcaption' ) !== false ) {
$pee = preg_replace( '|\s*(<figcaption[^>]*>)|', '$1', $pee );
$pee = preg_replace( '|</figcaption>\s*|', '</figcaption>', $pee );
}
// 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 = '';
// Rebuild the content as a string, wrapping every bit with a <p>.
foreach ( $pees as $tinkle ) {
$pee .= '<p>' . trim( $tinkle, "\n" ) . "</p>\n";
}
// 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 );
// 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|svg).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee );
// Normalize <br>
$pee = str_replace( array( '<br>', '<br/>' ), '<br />', $pee );
// 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.
if ( false !== strpos( $pee, '<!-- wpnl -->' ) ) {
$pee = str_replace( array( ' <!-- wpnl --> ', '<!-- 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 string[] Array of the formatted text.
*/
function wp_html_split( $input ) {
return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
}
/**
* Retrieve the regular expression for an HTML element.
*
* @since 4.4.0
*
* @return string The regular expression
*/
function get_html_split_regex() {
static $regex;
if ( ! isset( $regex ) ) {
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
$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.
$escaped =
'(?=' // Is the element escaped?
. '!--'
. '|'
. '!\[CDATA\['
. ')'
. '(?(?=!-)' // If yes, which type?
. $comments
. '|'
. $cdata
. ')';
$regex =
'/(' // Capture the entire match.
. '<' // Find start of element.
. '(?' // Conditional expression follows.
. $escaped // Find end of escaped element.
. '|' // ...else...
. '[^>]*>?' // Find end of normal element.
. ')'
. ')/';
// phpcs:enable
}
return $regex;
}
/**
* Retrieve the combined regular expression for HTML and shortcodes.
*
* @access private
* @ignore
* @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
* @since 4.4.0
*
* @param string $shortcode_regex The result from _get_wptexturize_shortcode_regex(). Optional.
* @return string The regular expression
*/
function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
static $html_regex;
if ( ! isset( $html_regex ) ) {
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
$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.
$html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
'<' // Find start of element.
. '(?(?=!--)' // Is this a comment?
. $comment_regex // Find end of comment.
. '|'
. '[^>]*>?' // Find end of element. If not found, match all input.
. ')';
// phpcs:enable
}
if ( empty( $shortcode_regex ) ) {
$regex = '/(' . $html_regex . ')/';
} else {
$regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
}
return $regex;
}
/**
* Retrieve the regular expression for shortcodes.
*
* @access private
* @ignore
* @since 4.4.0
*
* @param string[] $tagnames Array of shortcodes to find.
* @return string The regular expression
*/
function _get_wptexturize_shortcode_regex( $tagnames ) {
$tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
$tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
$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 ]].
// phpcs:enable
return $regex;
}
/**
* 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 delimiters (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 delimiters (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
*
* @since 3.1.0
* @access private
*
* @param array $matches preg_replace_callback matches array
* @return string
*/
function _autop_newline_preservation_helper( $matches ) {
return str_replace( "\n", '<WPPreserveNewline />', $matches[0] );
}
/**
* Don't auto-p wrap shortcodes that stand alone
*
* Ensures that shortcodes are not wrapped in `<p>...</p>`.
*
* @since 2.9.0
*
* @global array $shortcode_tags
*
* @param string $pee The content.
* @return string The filtered content.
*/
function shortcode_unautop( $pee ) {
global $shortcode_tags;
if ( empty( $shortcode_tags ) || ! is_array( $shortcode_tags ) ) {
return $pee;
}
$tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
$spaces = wp_spaces_regexp();
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound,WordPress.WhiteSpace.PrecisionAlignment.Found -- don't remove regex indentation
$pattern =
'/'
. '<p>' // Opening paragraph.
. '(?:' . $spaces . ')*+' // Optional leading whitespace.
. '(' // 1: The shortcode.
. '\\[' // Opening bracket.
. "($tagregexp)" // 2: Shortcode name.
. '(?![\\w-])' // Not followed by word character or hyphen.
// Unroll the loop: Inside the opening shortcode tag.
. '[^\\]\\/]*' // Not a closing bracket or forward slash.
. '(?:'
. '\\/(?!\\])' // A forward slash not followed by a closing bracket.
. '[^\\]\\/]*' // Not a closing bracket or forward slash.
. ')*?'
. '(?:'
. '\\/\\]' // Self closing tag and closing bracket.
. '|'
. '\\]' // Closing bracket.
. '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags.
. '[^\\[]*+' // Not an opening bracket.
. '(?:'
. '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag.
. '[^\\[]*+' // Not an opening bracket.
. ')*+'
. '\\[\\/\\2\\]' // Closing shortcode tag.
. ')?'
. ')'
. ')'
. '(?:' . $spaces . ')*+' // Optional trailing whitespace.
. '<\\/p>' // Closing paragraph.
. '/';
// phpcs:enable
return preg_replace( $pattern, '$1', $pee );
}
/**
* Checks to see if a string is utf8 encoded.
*
* NOTE: This function checks for 5-Byte sequences, UTF8
* has Bytes Sequences with a maximum length of 4.
*
* @author bmorel at ssi dot fr (modified)
* @since 1.2.1
*
* @param string $str The string to be checked
* @return bool True if $str fits a UTF-8 model, false otherwise.
*/
function seems_utf8( $str ) {
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; $j++ ) { // n bytes matching 10bbbbbb follow ?
if ( ( ++$i == $length ) || ( ( ord( $str[ $i ] ) & 0xC0 ) != 0x80 ) ) {
return false;
}
}
}
return true;
}
/**
* Converts a number of special characters into their HTML entities.
*
* Specifically deals with: &, <, >, ", and '.
*
* $quote_style can be set to ENT_COMPAT to encode " to
* &quot;, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
*
* @since 1.2.2
* @since 5.5.0 `$quote_style` also accepts `ENT_XML1`.
* @access private
*
* @param string $string The text which is to be encoded.
* @param int|string $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.
* Converts single and double quotes, as well as converting HTML
* named entities (that are not also XML named entities) to their
* code points if set to ENT_XML1. 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 false|string $charset Optional. The character encoding of the string. Default false.
* @param bool $double_encode Optional. Whether to encode existing HTML entities. Default false.
* @return string The encoded text with HTML entities.
*/
function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Don't bother if there are no specialchars - saves some processing.
if ( ! preg_match( '/[&<>"\']/', $string ) ) {
return $string;
}
// Account for the previous behaviour of the function when the $quote_style is not an accepted value.
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( ENT_XML1 === $quote_style ) {
$quote_style = ENT_QUOTES | ENT_XML1;
} elseif ( ! in_array( $quote_style, array( ENT_NOQUOTES, ENT_COMPAT, ENT_QUOTES, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
// Store the site charset as a static to avoid multiple calls to wp_load_alloptions().
if ( ! $charset ) {
static $_charset = null;
if ( ! isset( $_charset ) ) {
$alloptions = wp_load_alloptions();
$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
}
$charset = $_charset;
}
if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ), true ) ) {
$charset = 'UTF-8';
}
$_quote_style = $quote_style;
if ( 'double' === $quote_style ) {
$quote_style = ENT_COMPAT;
$_quote_style = ENT_COMPAT;
} elseif ( 'single' === $quote_style ) {
$quote_style = ENT_NOQUOTES;
}
if ( ! $double_encode ) {
// Guarantee every &entity; is valid, convert &garbage; into &amp;garbage;
// This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
$string = wp_kses_normalize_entities( $string, ( $quote_style & ENT_XML1 ) ? 'xml' : 'html' );
}
$string = htmlspecialchars( $string, $quote_style, $charset, $double_encode );
// Back-compat.
if ( 'single' === $_quote_style ) {
$string = str_replace( "'", '&#039;', $string );
}
return $string;
}
/**
* Converts a number of HTML entities into their special characters.
*
* Specifically deals with: &, <, >, ", and '.
*
* $quote_style can be set to ENT_COMPAT to decode " entities,
* or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
*
* @since 2.8.0
*
* @param string $string The text which is to be decoded.
* @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
* both single and double if set to ENT_QUOTES or
* none if set to ENT_NOQUOTES.
* Also compatible with old _wp_specialchars() values;
* converting single quotes if set to 'single',
* double if set to 'double' or both if otherwise set.
* Default is ENT_NOQUOTES.
* @return string The decoded text without HTML entities.
*/
function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Don't bother if there are no entities - saves a lot of processing.
if ( strpos( $string, '&' ) === false ) {
return $string;
}
// Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value.
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
// More complete than get_html_translation_table( HTML_SPECIALCHARS ).
$single = array(
'&#039;' => '\'',
'&#x27;' => '\'',
);
$single_preg = array(
'/&#0*39;/' => '&#039;',
'/&#x0*27;/i' => '&#x27;',
);
$double = array(
'&quot;' => '"',
'&#034;' => '"',
'&#x22;' => '"',
);
$double_preg = array(
'/&#0*34;/' => '&#034;',
'/&#x0*22;/i' => '&#x22;',
);
$others = array(
'&lt;' => '<',
'&#060;' => '<',
'&gt;' => '>',
'&#062;' => '>',
'&amp;' => '&',
'&#038;' => '&',
'&#x26;' => '&',
);
$others_preg = array(
'/&#0*60;/' => '&#060;',
'/&#0*62;/' => '&#062;',
'/&#0*38;/' => '&#038;',
'/&#x0*26;/i' => '&#x26;',
);
if ( ENT_QUOTES === $quote_style ) {
$translation = array_merge( $single, $double, $others );
$translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
} elseif ( ENT_COMPAT === $quote_style || 'double' === $quote_style ) {
$translation = array_merge( $double, $others );
$translation_preg = array_merge( $double_preg, $others_preg );
} elseif ( 'single' === $quote_style ) {
$translation = array_merge( $single, $others );
$translation_preg = array_merge( $single_preg, $others_preg );
} elseif ( ENT_NOQUOTES === $quote_style ) {
$translation = $others;
$translation_preg = $others_preg;
}
// Remove zero padding on numeric entities.
$string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
// Replace characters according to translation table.
return strtr( $string, $translation );
}
/**
* Checks for invalid UTF8 in a string.
*
* @since 2.8.0
*
* @param string $string The text which is to be checked.
* @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default false.
* @return string The checked text.
*/
function wp_check_invalid_utf8( $string, $strip = false ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Store the site charset as a static to avoid multiple calls to get_option().
static $is_utf8 = null;
if ( ! isset( $is_utf8 ) ) {
$is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ), true );
}
if ( ! $is_utf8 ) {
return $string;
}
// Check for support for utf8 in the installed PCRE library once and store the result in a static.
static $utf8_pcre = null;
if ( ! isset( $utf8_pcre ) ) {
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged
$utf8_pcre = @preg_match( '/^./u', 'a' );
}
// We can't demand utf8 in the PCRE installation, so just return the string in those cases.
if ( ! $utf8_pcre ) {
return $string;
}
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged -- preg_match fails when it encounters invalid UTF8 in $string.
if ( 1 === @preg_match( '/^./us', $string ) ) {
return $string;
}
// Attempt to strip the bad chars if requested (not recommended).
if ( $strip && function_exists( 'iconv' ) ) {
return iconv( 'utf-8', 'utf-8', $string );
}
return '';
}
/**
* Encode the Unicode values to be used in the URI.
*
* @since 1.5.0
*
* @param string $utf8_string
* @param int $length Max length of the string
* @return string String with Unicode encoded for URI.
*/
function utf8_uri_encode( $utf8_string, $length = 0 ) {
$unicode = '';
$values = array();
$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 ] );
if ( $value < 128 ) {
if ( $length && ( $unicode_length >= $length ) ) {
break;
}
$unicode .= chr( $value );
$unicode_length++;
} else {
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 ) {
for ( $j = 0; $j < $num_octets; $j++ ) {
$unicode .= '%' . dechex( $values[ $j ] );
}
$unicode_length += $num_octets * 3;
$values = array();
$num_octets = 1;
}
}
}
return $unicode;
}
/**
* Converts all accent characters to ASCII characters.
*
* If there are no accent characters, then the string given is just returned.
*
* **Accent characters converted:**
*
* Currency signs:
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | ------------------- |
* | U+00A3 | £ | (empty) | British Pound sign |
* | U+20AC | € | E | Euro sign |
*
* Decompositions for Latin-1 Supplement:
*
* | Code | Glyph | Replacement | Description |
* | ------- | ----- | ----------- | -------------------------------------- |
* | U+00AA | ª | a | Feminine ordinal indicator |
* | U+00BA | º | o | Masculine ordinal indicator |
* | U+00C0 | À | A | Latin capital letter A with grave |
* | U+00C1 | Á | A | Latin capital letter A with acute |
* | U+00C2 | Â | A | Latin capital letter A with circumflex |
* | U+00C3 | Ã | A | Latin capital letter A with tilde |
* | U+00C4 | Ä | A | Latin capital letter A with diaeresis |
* | U+00C5 | Å | A | Latin capital letter A with ring above |
* | U+00C6 | Æ | AE | Latin capital letter AE |
* | U+00C7 | Ç | C | Latin capital letter C with cedilla |
* | U+00C8 | È | E | Latin capital letter E with grave |
* | U+00C9 | É | E | Latin capital letter E with acute |
* | U+00CA | Ê | E | Latin capital letter E with circumflex |
* | U+00CB | Ë | E | Latin capital letter E with diaeresis |
* | U+00CC | Ì | I | Latin capital letter I with grave |
* | U+00CD | Í | I | Latin capital letter I with acute |
* | U+00CE | Î | I | Latin capital letter I with circumflex |
* | U+00CF | Ï | I | Latin capital letter I with diaeresis |
* | U+00D0 | Ð | D | Latin capital letter Eth |
* | U+00D1 | Ñ | N | Latin capital letter N with tilde |
* | U+00D2 | Ò | O | Latin capital letter O with grave |
* | U+00D3 | Ó | O | Latin capital letter O with acute |
* | U+00D4 | Ô | O | Latin capital letter O with circumflex |
* | U+00D5 | Õ | O | Latin capital letter O with tilde |
* | U+00D6 | Ö | O | Latin capital letter O with diaeresis |
* | U+00D8 | Ø | O | Latin capital letter O with stroke |
* | U+00D9 | Ù | U | Latin capital letter U with grave |
* | U+00DA | Ú | U | Latin capital letter U with acute |
* | U+00DB | Û | U | Latin capital letter U with circumflex |
* | U+00DC | Ü | U | Latin capital letter U with diaeresis |
* | U+00DD | Ý | Y | Latin capital letter Y with acute |
* | U+00DE | Þ | TH | Latin capital letter Thorn |
* | U+00DF | ß | s | Latin small letter sharp s |
* | U+00E0 | à | a | Latin small letter a with grave |
* | U+00E1 | á | a | Latin small letter a with acute |
* | U+00E2 | â | a | Latin small letter a with circumflex |
* | U+00E3 | ã | a | Latin small letter a with tilde |
* | U+00E4 | ä | a | Latin small letter a with diaeresis |
* | U+00E5 | å | a | Latin small letter a with ring above |
* | U+00E6 | æ | ae | Latin small letter ae |
* | U+00E7 | ç | c | Latin small letter c with cedilla |
* | U+00E8 | è | e | Latin small letter e with grave |
* | U+00E9 | é | e | Latin small letter e with acute |
* | U+00EA | ê | e | Latin small letter e with circumflex |
* | U+00EB | ë | e | Latin small letter e with diaeresis |
* | U+00EC | ì | i | Latin small letter i with grave |
* | U+00ED | í | i | Latin small letter i with acute |
* | U+00EE | î | i | Latin small letter i with circumflex |
* | U+00EF | ï | i | Latin small letter i with diaeresis |
* | U+00F0 | ð | d | Latin small letter Eth |
* | U+00F1 | ñ | n | Latin small letter n with tilde |
* | U+00F2 | ò | o | Latin small letter o with grave |
* | U+00F3 | ó | o | Latin small letter o with acute |
* | U+00F4 | ô | o | Latin small letter o with circumflex |
* | U+00F5 | õ | o | Latin small letter o with tilde |
* | U+00F6 | ö | o | Latin small letter o with diaeresis |
* | U+00F8 | ø | o | Latin small letter o with stroke |
* | U+00F9 | ù | u | Latin small letter u with grave |
* | U+00FA | ú | u | Latin small letter u with acute |
* | U+00FB | û | u | Latin small letter u with circumflex |
* | U+00FC | ü | u | Latin small letter u with diaeresis |
* | U+00FD | ý | y | Latin small letter y with acute |
* | U+00FE | þ | th | Latin small letter Thorn |
* | U+00FF | ÿ | y | Latin small letter y with diaeresis |
*
* Decompositions for Latin Extended-A:
*
* | Code | Glyph | Replacement | Description |
* | ------- | ----- | ----------- | ------------------------------------------------- |
* | U+0100 | Ā | A | Latin capital letter A with macron |
* | U+0101 | ā | a | Latin small letter a with macron |
* | U+0102 | Ă | A | Latin capital letter A with breve |
* | U+0103 | ă | a | Latin small letter a with breve |
* | U+0104 | Ą | A | Latin capital letter A with ogonek |
* | U+0105 | ą | a | Latin small letter a with ogonek |
* | U+01006 | Ć | C | Latin capital letter C with acute |
* | U+0107 | ć | c | Latin small letter c with acute |
* | U+0108 | Ĉ | C | Latin capital letter C with circumflex |
* | U+0109 | ĉ | c | Latin small letter c with circumflex |
* | U+010A | Ċ | C | Latin capital letter C with dot above |
* | U+010B | ċ | c | Latin small letter c with dot above |
* | U+010C | Č | C | Latin capital letter C with caron |
* | U+010D | č | c | Latin small letter c with caron |
* | U+010E | Ď | D | Latin capital letter D with caron |
* | U+010F | ď | d | Latin small letter d with caron |
* | U+0110 | Đ | D | Latin capital letter D with stroke |
* | U+0111 | đ | d | Latin small letter d with stroke |
* | U+0112 | Ē | E | Latin capital letter E with macron |
* | U+0113 | ē | e | Latin small letter e with macron |
* | U+0114 | Ĕ | E | Latin capital letter E with breve |
* | U+0115 | ĕ | e | Latin small letter e with breve |
* | U+0116 | Ė | E | Latin capital letter E with dot above |
* | U+0117 | ė | e | Latin small letter e with dot above |
* | U+0118 | Ę | E | Latin capital letter E with ogonek |
* | U+0119 | ę | e | Latin small letter e with ogonek |
* | U+011A | Ě | E | Latin capital letter E with caron |
* | U+011B | ě | e | Latin small letter e with caron |
* | U+011C | Ĝ | G | Latin capital letter G with circumflex |
* | U+011D | ĝ | g | Latin small letter g with circumflex |
* | U+011E | Ğ | G | Latin capital letter G with breve |
* | U+011F | ğ | g | Latin small letter g with breve |
* | U+0120 | Ġ | G | Latin capital letter G with dot above |
* | U+0121 | ġ | g | Latin small letter g with dot above |
* | U+0122 | Ģ | G | Latin capital letter G with cedilla |
* | U+0123 | ģ | g | Latin small letter g with cedilla |
* | U+0124 | Ĥ | H | Latin capital letter H with circumflex |
* | U+0125 | ĥ | h | Latin small letter h with circumflex |
* | U+0126 | Ħ | H | Latin capital letter H with stroke |
* | U+0127 | ħ | h | Latin small letter h with stroke |
* | U+0128 | Ĩ | I | Latin capital letter I with tilde |
* | U+0129 | ĩ | i | Latin small letter i with tilde |
* | U+012A | Ī | I | Latin capital letter I with macron |
* | U+012B | ī | i | Latin small letter i with macron |
* | U+012C | Ĭ | I | Latin capital letter I with breve |
* | U+012D | ĭ | i | Latin small letter i with breve |
* | U+012E | Į | I | Latin capital letter I with ogonek |
* | U+012F | į | i | Latin small letter i with ogonek |
* | U+0130 | İ | I | Latin capital letter I with dot above |
* | U+0131 | ı | i | Latin small letter dotless i |
* | U+0132 | IJ | IJ | Latin capital ligature IJ |
* | U+0133 | ij | ij | Latin small ligature ij |
* | U+0134 | Ĵ | J | Latin capital letter J with circumflex |
* | U+0135 | ĵ | j | Latin small letter j with circumflex |
* | U+0136 | Ķ | K | Latin capital letter K with cedilla |
* | U+0137 | ķ | k | Latin small letter k with cedilla |
* | U+0138 | ĸ | k | Latin small letter Kra |
* | U+0139 | Ĺ | L | Latin capital letter L with acute |
* | U+013A | ĺ | l | Latin small letter l with acute |
* | U+013B | Ļ | L | Latin capital letter L with cedilla |
* | U+013C | ļ | l | Latin small letter l with cedilla |
* | U+013D | Ľ | L | Latin capital letter L with caron |
* | U+013E | ľ | l | Latin small letter l with caron |
* | U+013F | Ŀ | L | Latin capital letter L with middle dot |
* | U+0140 | ŀ | l | Latin small letter l with middle dot |
* | U+0141 | Ł | L | Latin capital letter L with stroke |
* | U+0142 | ł | l | Latin small letter l with stroke |
* | U+0143 | Ń | N | Latin capital letter N with acute |
* | U+0144 | ń | n | Latin small letter N with acute |
* | U+0145 | Ņ | N | Latin capital letter N with cedilla |
* | U+0146 | ņ | n | Latin small letter n with cedilla |
* | U+0147 | Ň | N | Latin capital letter N with caron |
* | U+0148 | ň | n | Latin small letter n with caron |
* | U+0149 | ʼn | n | Latin small letter n preceded by apostrophe |
* | U+014A | Ŋ | N | Latin capital letter Eng |
* | U+014B | ŋ | n | Latin small letter Eng |
* | U+014C | Ō | O | Latin capital letter O with macron |
* | U+014D | ō | o | Latin small letter o with macron |
* | U+014E | Ŏ | O | Latin capital letter O with breve |
* | U+014F | ŏ | o | Latin small letter o with breve |
* | U+0150 | Ő | O | Latin capital letter O with double acute |
* | U+0151 | ő | o | Latin small letter o with double acute |
* | U+0152 | Π| OE | Latin capital ligature OE |
* | U+0153 | œ | oe | Latin small ligature oe |
* | U+0154 | Ŕ | R | Latin capital letter R with acute |
* | U+0155 | ŕ | r | Latin small letter r with acute |
* | U+0156 | Ŗ | R | Latin capital letter R with cedilla |
* | U+0157 | ŗ | r | Latin small letter r with cedilla |
* | U+0158 | Ř | R | Latin capital letter R with caron |
* | U+0159 | ř | r | Latin small letter r with caron |
* | U+015A | Ś | S | Latin capital letter S with acute |
* | U+015B | ś | s | Latin small letter s with acute |
* | U+015C | Ŝ | S | Latin capital letter S with circumflex |
* | U+015D | ŝ | s | Latin small letter s with circumflex |
* | U+015E | Ş | S | Latin capital letter S with cedilla |
* | U+015F | ş | s | Latin small letter s with cedilla |
* | U+0160 | Š | S | Latin capital letter S with caron |
* | U+0161 | š | s | Latin small letter s with caron |
* | U+0162 | Ţ | T | Latin capital letter T with cedilla |
* | U+0163 | ţ | t | Latin small letter t with cedilla |
* | U+0164 | Ť | T | Latin capital letter T with caron |
* | U+0165 | ť | t | Latin small letter t with caron |
* | U+0166 | Ŧ | T | Latin capital letter T with stroke |
* | U+0167 | ŧ | t | Latin small letter t with stroke |
* | U+0168 | Ũ | U | Latin capital letter U with tilde |
* | U+0169 | ũ | u | Latin small letter u with tilde |
* | U+016A | Ū | U | Latin capital letter U with macron |
* | U+016B | ū | u | Latin small letter u with macron |
* | U+016C | Ŭ | U | Latin capital letter U with breve |
* | U+016D | ŭ | u | Latin small letter u with breve |
* | U+016E | Ů | U | Latin capital letter U with ring above |
* | U+016F | ů | u | Latin small letter u with ring above |
* | U+0170 | Ű | U | Latin capital letter U with double acute |
* | U+0171 | ű | u | Latin small letter u with double acute |
* | U+0172 | Ų | U | Latin capital letter U with ogonek |
* | U+0173 | ų | u | Latin small letter u with ogonek |
* | U+0174 | Ŵ | W | Latin capital letter W with circumflex |
* | U+0175 | ŵ | w | Latin small letter w with circumflex |
* | U+0176 | Ŷ | Y | Latin capital letter Y with circumflex |
* | U+0177 | ŷ | y | Latin small letter y with circumflex |
* | U+0178 | Ÿ | Y | Latin capital letter Y with diaeresis |
* | U+0179 | Ź | Z | Latin capital letter Z with acute |
* | U+017A | ź | z | Latin small letter z with acute |
* | U+017B | Ż | Z | Latin capital letter Z with dot above |
* | U+017C | ż | z | Latin small letter z with dot above |
* | U+017D | Ž | Z | Latin capital letter Z with caron |
* | U+017E | ž | z | Latin small letter z with caron |
* | U+017F | ſ | s | Latin small letter long s |
* | U+01A0 | Ơ | O | Latin capital letter O with horn |
* | U+01A1 | ơ | o | Latin small letter o with horn |
* | U+01AF | Ư | U | Latin capital letter U with horn |
* | U+01B0 | ư | u | Latin small letter u with horn |
* | U+01CD | Ǎ | A | Latin capital letter A with caron |
* | U+01CE | ǎ | a | Latin small letter a with caron |
* | U+01CF | Ǐ | I | Latin capital letter I with caron |
* | U+01D0 | ǐ | i | Latin small letter i with caron |
* | U+01D1 | Ǒ | O | Latin capital letter O with caron |
* | U+01D2 | ǒ | o | Latin small letter o with caron |
* | U+01D3 | Ǔ | U | Latin capital letter U with caron |
* | U+01D4 | ǔ | u | Latin small letter u with caron |
* | U+01D5 | Ǖ | U | Latin capital letter U with diaeresis and macron |
* | U+01D6 | ǖ | u | Latin small letter u with diaeresis and macron |
* | U+01D7 | Ǘ | U | Latin capital letter U with diaeresis and acute |
* | U+01D8 | ǘ | u | Latin small letter u with diaeresis and acute |
* | U+01D9 | Ǚ | U | Latin capital letter U with diaeresis and caron |
* | U+01DA | ǚ | u | Latin small letter u with diaeresis and caron |
* | U+01DB | Ǜ | U | Latin capital letter U with diaeresis and grave |
* | U+01DC | ǜ | u | Latin small letter u with diaeresis and grave |
*
* Decompositions for Latin Extended-B:
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | ----------------------------------------- |
* | U+0218 | Ș | S | Latin capital letter S with comma below |
* | U+0219 | ș | s | Latin small letter s with comma below |
* | U+021A | Ț | T | Latin capital letter T with comma below |
* | U+021B | ț | t | Latin small letter t with comma below |
*
* Vowels with diacritic (Chinese, Hanyu Pinyin):
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | ----------------------------------------------------- |
* | U+0251 | ɑ | a | Latin small letter alpha |
* | U+1EA0 | Ạ | A | Latin capital letter A with dot below |
* | U+1EA1 | ạ | a | Latin small letter a with dot below |
* | U+1EA2 | Ả | A | Latin capital letter A with hook above |
* | U+1EA3 | ả | a | Latin small letter a with hook above |
* | U+1EA4 | Ấ | A | Latin capital letter A with circumflex and acute |
* | U+1EA5 | ấ | a | Latin small letter a with circumflex and acute |
* | U+1EA6 | Ầ | A | Latin capital letter A with circumflex and grave |
* | U+1EA7 | ầ | a | Latin small letter a with circumflex and grave |
* | U+1EA8 | Ẩ | A | Latin capital letter A with circumflex and hook above |
* | U+1EA9 | ẩ | a | Latin small letter a with circumflex and hook above |
* | U+1EAA | Ẫ | A | Latin capital letter A with circumflex and tilde |
* | U+1EAB | ẫ | a | Latin small letter a with circumflex and tilde |
* | U+1EA6 | Ậ | A | Latin capital letter A with circumflex and dot below |
* | U+1EAD | ậ | a | Latin small letter a with circumflex and dot below |
* | U+1EAE | Ắ | A | Latin capital letter A with breve and acute |
* | U+1EAF | ắ | a | Latin small letter a with breve and acute |
* | U+1EB0 | Ằ | A | Latin capital letter A with breve and grave |
* | U+1EB1 | ằ | a | Latin small letter a with breve and grave |
* | U+1EB2 | Ẳ | A | Latin capital letter A with breve and hook above |
* | U+1EB3 | ẳ | a | Latin small letter a with breve and hook above |
* | U+1EB4 | Ẵ | A | Latin capital letter A with breve and tilde |
* | U+1EB5 | ẵ | a | Latin small letter a with breve and tilde |
* | U+1EB6 | Ặ | A | Latin capital letter A with breve and dot below |
* | U+1EB7 | ặ | a | Latin small letter a with breve and dot below |
* | U+1EB8 | Ẹ | E | Latin capital letter E with dot below |
* | U+1EB9 | ẹ | e | Latin small letter e with dot below |
* | U+1EBA | Ẻ | E | Latin capital letter E with hook above |
* | U+1EBB | ẻ | e | Latin small letter e with hook above |
* | U+1EBC | Ẽ | E | Latin capital letter E with tilde |
* | U+1EBD | ẽ | e | Latin small letter e with tilde |
* | U+1EBE | Ế | E | Latin capital letter E with circumflex and acute |
* | U+1EBF | ế | e | Latin small letter e with circumflex and acute |
* | U+1EC0 | Ề | E | Latin capital letter E with circumflex and grave |
* | U+1EC1 | ề | e | Latin small letter e with circumflex and grave |
* | U+1EC2 | Ể | E | Latin capital letter E with circumflex and hook above |
* | U+1EC3 | ể | e | Latin small letter e with circumflex and hook above |
* | U+1EC4 | Ễ | E | Latin capital letter E with circumflex and tilde |
* | U+1EC5 | ễ | e | Latin small letter e with circumflex and tilde |
* | U+1EC6 | Ệ | E | Latin capital letter E with circumflex and dot below |
* | U+1EC7 | ệ | e | Latin small letter e with circumflex and dot below |
* | U+1EC8 | Ỉ | I | Latin capital letter I with hook above |
* | U+1EC9 | ỉ | i | Latin small letter i with hook above |
* | U+1ECA | Ị | I | Latin capital letter I with dot below |
* | U+1ECB | ị | i | Latin small letter i with dot below |
* | U+1ECC | Ọ | O | Latin capital letter O with dot below |
* | U+1ECD | ọ | o | Latin small letter o with dot below |
* | U+1ECE | Ỏ | O | Latin capital letter O with hook above |
* | U+1ECF | ỏ | o | Latin small letter o with hook above |
* | U+1ED0 | Ố | O | Latin capital letter O with circumflex and acute |
* | U+1ED1 | ố | o | Latin small letter o with circumflex and acute |
* | U+1ED2 | Ồ | O | Latin capital letter O with circumflex and grave |
* | U+1ED3 | ồ | o | Latin small letter o with circumflex and grave |
* | U+1ED4 | Ổ | O | Latin capital letter O with circumflex and hook above |
* | U+1ED5 | ổ | o | Latin small letter o with circumflex and hook above |
* | U+1ED6 | Ỗ | O | Latin capital letter O with circumflex and tilde |
* | U+1ED7 | ỗ | o | Latin small letter o with circumflex and tilde |
* | U+1ED8 | Ộ | O | Latin capital letter O with circumflex and dot below |
* | U+1ED9 | ộ | o | Latin small letter o with circumflex and dot below |
* | U+1EDA | Ớ | O | Latin capital letter O with horn and acute |
* | U+1EDB | ớ | o | Latin small letter o with horn and acute |
* | U+1EDC | Ờ | O | Latin capital letter O with horn and grave |
* | U+1EDD | ờ | o | Latin small letter o with horn and grave |
* | U+1EDE | Ở | O | Latin capital letter O with horn and hook above |
* | U+1EDF | ở | o | Latin small letter o with horn and hook above |
* | U+1EE0 | Ỡ | O | Latin capital letter O with horn and tilde |
* | U+1EE1 | ỡ | o | Latin small letter o with horn and tilde |
* | U+1EE2 | Ợ | O | Latin capital letter O with horn and dot below |
* | U+1EE3 | ợ | o | Latin small letter o with horn and dot below |
* | U+1EE4 | Ụ | U | Latin capital letter U with dot below |
* | U+1EE5 | ụ | u | Latin small letter u with dot below |
* | U+1EE6 | Ủ | U | Latin capital letter U with hook above |
* | U+1EE7 | ủ | u | Latin small letter u with hook above |
* | U+1EE8 | Ứ | U | Latin capital letter U with horn and acute |
* | U+1EE9 | ứ | u | Latin small letter u with horn and acute |
* | U+1EEA | Ừ | U | Latin capital letter U with horn and grave |
* | U+1EEB | ừ | u | Latin small letter u with horn and grave |
* | U+1EEC | Ử | U | Latin capital letter U with horn and hook above |
* | U+1EED | ử | u | Latin small letter u with horn and hook above |
* | U+1EEE | Ữ | U | Latin capital letter U with horn and tilde |
* | U+1EEF | ữ | u | Latin small letter u with horn and tilde |
* | U+1EF0 | Ự | U | Latin capital letter U with horn and dot below |
* | U+1EF1 | ự | u | Latin small letter u with horn and dot below |
* | U+1EF2 | Ỳ | Y | Latin capital letter Y with grave |
* | U+1EF3 | ỳ | y | Latin small letter y with grave |
* | U+1EF4 | Ỵ | Y | Latin capital letter Y with dot below |
* | U+1EF5 | ỵ | y | Latin small letter y with dot below |
* | U+1EF6 | Ỷ | Y | Latin capital letter Y with hook above |
* | U+1EF7 | ỷ | y | Latin small letter y with hook above |
* | U+1EF8 | Ỹ | Y | Latin capital letter Y with tilde |
* | U+1EF9 | ỹ | y | Latin small letter y with tilde |
*
* German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`),
* and German (Switzerland) informal (`de_CH_informal`) locales:
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | --------------------------------------- |
* | U+00C4 | Ä | Ae | Latin capital letter A with diaeresis |
* | U+00E4 | ä | ae | Latin small letter a with diaeresis |
* | U+00D6 | Ö | Oe | Latin capital letter O with diaeresis |
* | U+00F6 | ö | oe | Latin small letter o with diaeresis |
* | U+00DC | Ü | Ue | Latin capital letter U with diaeresis |
* | U+00FC | ü | ue | Latin small letter u with diaeresis |
* | U+00DF | ß | ss | Latin small letter sharp s |
*
* Danish (`da_DK`) locale:
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | --------------------------------------- |
* | U+00C6 | Æ | Ae | Latin capital letter AE |
* | U+00E6 | æ | ae | Latin small letter ae |
* | U+00D8 | Ø | Oe | Latin capital letter O with stroke |
* | U+00F8 | ø | oe | Latin small letter o with stroke |
* | U+00C5 | Å | Aa | Latin capital letter A with ring above |
* | U+00E5 | å | aa | Latin small letter a with ring above |
*
* Catalan (`ca`) locale:
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | --------------------------------------- |
* | U+00B7 | l·l | ll | Flown dot (between two Ls) |
*
* Serbian (`sr_RS`) and Bosnian (`bs_BA`) locales:
*
* | Code | Glyph | Replacement | Description |
* | -------- | ----- | ----------- | --------------------------------------- |
* | U+0110 | Đ | DJ | Latin capital letter D with stroke |
* | U+0111 | đ | dj | Latin small letter d with stroke |
*
* @since 1.2.1
* @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`.
* @since 4.7.0 Added locale support for `sr_RS`.
* @since 4.8.0 Added locale support for `bs_BA`.
*
* @param string $string Text that might have accent characters
* @return string Filtered string with replaced "nice" characters.
*/
function remove_accents( $string ) {
if ( ! preg_match( '/[\x80-\xff]/', $string ) ) {
return $string;
}
if ( seems_utf8( $string ) ) {
$chars = array(
// Decompositions for Latin-1 Supplement.
'ª' => 'a',
'º' => 'o',
'À' => 'A',
'Á' => 'A',
'Â' => 'A',
'Ã' => 'A',
'Ä' => 'A',
'Å' => 'A',
'Æ' => 'AE',
'Ç' => 'C',
'È' => 'E',
'É' => 'E',
'Ê' => 'E',
'Ë' => 'E',
'Ì' => 'I',
'Í' => 'I',
'Î' => 'I',
'Ï' => 'I',
'Ð' => 'D',
'Ñ' => 'N',
'Ò' => 'O',
'Ó' => 'O',
'Ô' => 'O',
'Õ' => 'O',
'Ö' => 'O',
'Ù' => 'U',
'Ú' => 'U',
'Û' => 'U',
'Ü' => 'U',
'Ý' => 'Y',
'Þ' => 'TH',
'ß' => 's',
'à' => 'a',
'á' => 'a',
'â' => 'a',
'ã' => 'a',
'ä' => 'a',
'å' => 'a',
'æ' => 'ae',
'ç' => 'c',
'è' => 'e',
'é' => 'e',
'ê' => 'e',
'ë' => 'e',
'ì' => 'i',
'í' => 'i',
'î' => 'i',
'ï' => 'i',
'ð' => 'd',
'ñ' => 'n',
'ò' => 'o',
'ó' => 'o',
'ô' => 'o',
'õ' => 'o',
'ö' => 'o',
'ø' => 'o',
'ù' => 'u',
'ú' => 'u',
'û' => 'u',
'ü' => 'u',
'ý' => 'y',
'þ' => 'th',
'ÿ' => 'y',
'Ø' => 'O',
// Decompositions for Latin Extended-A.
'Ā' => 'A',
'ā' => 'a',
'Ă' => 'A',
'ă' => 'a',
'Ą' => 'A',
'ą' => 'a',
'Ć' => 'C',
'ć' => 'c',
'Ĉ' => 'C',
'ĉ' => 'c',
'Ċ' => 'C',
'ċ' => 'c',
'Č' => 'C',
'č' => 'c',
'Ď' => 'D',
'ď' => 'd',
'Đ' => 'D',
'đ' => 'd',
'Ē' => 'E',
'ē' => 'e',
'Ĕ' => 'E',
'ĕ' => 'e',
'Ė' => 'E',
'ė' => 'e',
'Ę' => 'E',
'ę' => 'e',
'Ě' => 'E',
'ě' => 'e',
'Ĝ' => 'G',
'ĝ' => 'g',
'Ğ' => 'G',
'ğ' => 'g',
'Ġ' => 'G',
'ġ' => 'g',
'Ģ' => 'G',
'ģ' => 'g',
'Ĥ' => 'H',
'ĥ' => 'h',
'Ħ' => 'H',
'ħ' => 'h',
'Ĩ' => 'I',
'ĩ' => 'i',
'Ī' => 'I',
'ī' => 'i',
'Ĭ' => 'I',
'ĭ' => 'i',
'Į' => 'I',
'į' => 'i',
'İ' => 'I',
'ı' => 'i',
'IJ' => 'IJ',
'ij' => 'ij',
'Ĵ' => 'J',
'ĵ' => 'j',
'Ķ' => 'K',
'ķ' => 'k',
'ĸ' => 'k',
'Ĺ' => 'L',
'ĺ' => 'l',
'Ļ' => 'L',
'ļ' => 'l',
'Ľ' => 'L',
'ľ' => 'l',
'Ŀ' => 'L',
'ŀ' => 'l',
'Ł' => 'L',
'ł' => 'l',
'Ń' => 'N',
'ń' => 'n',
'Ņ' => 'N',
'ņ' => 'n',
'Ň' => 'N',
'ň' => 'n',
'ʼn' => 'n',
'Ŋ' => 'N',
'ŋ' => 'n',
'Ō' => 'O',
'ō' => 'o',
'Ŏ' => 'O',
'ŏ' => 'o',
'Ő' => 'O',
'ő' => 'o',
'Œ' => 'OE',
'œ' => 'oe',
'Ŕ' => 'R',
'ŕ' => 'r',
'Ŗ' => 'R',
'ŗ' => 'r',
'Ř' => 'R',
'ř' => 'r',
'Ś' => 'S',
'ś' => 's',
'Ŝ' => 'S',
'ŝ' => 's',
'Ş' => 'S',
'ş' => 's',
'Š' => 'S',
'š' => 's',
'Ţ' => 'T',
'ţ' => 't',
'Ť' => 'T',
'ť' => 't',
'Ŧ' => 'T',
'ŧ' => 't',
'Ũ' => 'U',
'ũ' => 'u',
'Ū' => 'U',
'ū' => 'u',
'Ŭ' => 'U',
'ŭ' => 'u',
'Ů' => 'U',
'ů' => 'u',
'Ű' => 'U',
'ű' => 'u',
'Ų' => 'U',
'ų' => 'u',
'Ŵ' => 'W',
'ŵ' => 'w',
'Ŷ' => 'Y',
'ŷ' => 'y',
'Ÿ' => 'Y',
'Ź' => 'Z',
'ź' => 'z',
'Ż' => 'Z',
'ż' => 'z',
'Ž' => 'Z',
'ž' => 'z',
'ſ' => 's',
// Decompositions for Latin Extended-B.
'Ș' => 'S',
'ș' => 's',
'Ț' => 'T',
'ț' => 't',
// Euro sign.
'€' => 'E',
// GBP (Pound) sign.
'£' => '',
// Vowels with diacritic (Vietnamese).
// Unmarked.
'Ơ' => 'O',
'ơ' => 'o',
'Ư' => 'U',
'ư' => 'u',
// Grave accent.
'Ầ' => 'A',
'ầ' => 'a',
'Ằ' => 'A',
'ằ' => 'a',
'Ề' => 'E',
'ề' => 'e',
'Ồ' => 'O',
'ồ' => 'o',
'Ờ' => 'O',
'ờ' => 'o',
'Ừ' => 'U',
'ừ' => 'u',
'Ỳ' => 'Y',
'ỳ' => 'y',
// Hook.
'Ả' => 'A',
'ả' => 'a',
'Ẩ' => 'A',
'ẩ' => 'a',
'Ẳ' => 'A',
'ẳ' => 'a',
'Ẻ' => 'E',
'ẻ' => 'e',
'Ể' => 'E',
'ể' => 'e',
'Ỉ' => 'I',
'ỉ' => 'i',
'Ỏ' => 'O',
'ỏ' => 'o',
'Ổ' => 'O',
'ổ' => 'o',
'Ở' => 'O',
'ở' => 'o',
'Ủ' => 'U',
'ủ' => 'u',
'Ử' => 'U',
'ử' => 'u',
'Ỷ' => 'Y',
'ỷ' => 'y',
// Tilde.
'Ẫ' => 'A',
'ẫ' => 'a',
'Ẵ' => 'A',
'ẵ' => 'a',
'Ẽ' => 'E',
'ẽ' => 'e',
'Ễ' => 'E',
'ễ' => 'e',
'Ỗ' => 'O',
'ỗ' => 'o',
'Ỡ' => 'O',
'ỡ' => 'o',
'Ữ' => 'U',
'ữ' => 'u',
'Ỹ' => 'Y',
'ỹ' => 'y',
// Acute accent.
'Ấ' => 'A',
'ấ' => 'a',
'Ắ' => 'A',
'ắ' => 'a',
'Ế' => 'E',
'ế' => 'e',
'Ố' => 'O',
'ố' => 'o',
'Ớ' => 'O',
'ớ' => 'o',
'Ứ' => 'U',
'ứ' => 'u',
// Dot below.
'Ạ' => 'A',
'ạ' => 'a',
'Ậ' => 'A',
'ậ' => 'a',
'Ặ' => 'A',
'ặ' => 'a',
'Ẹ' => 'E',
'ẹ' => 'e',
'Ệ' => 'E',
'ệ' => 'e',
'Ị' => 'I',
'ị' => 'i',
'Ọ' => 'O',
'ọ' => 'o',
'Ộ' => 'O',
'ộ' => 'o',
'Ợ' => 'O',
'ợ' => 'o',
'Ụ' => 'U',
'ụ' => 'u',
'Ự' => 'U',
'ự' => 'u',
'Ỵ' => 'Y',
'ỵ' => 'y',
// Vowels with diacritic (Chinese, Hanyu Pinyin).
'ɑ' => 'a',
// Macron.
'Ǖ' => 'U',
'ǖ' => 'u',
// Acute accent.
'Ǘ' => 'U',
'ǘ' => 'u',
// Caron.
'Ǎ' => 'A',
'ǎ' => 'a',
'Ǐ' => 'I',
'ǐ' => 'i',
'Ǒ' => 'O',
'ǒ' => 'o',
'Ǔ' => 'U',
'ǔ' => 'u',
'Ǚ' => 'U',
'ǚ' => 'u',
// Grave accent.
'Ǜ' => 'U',
'ǜ' => 'u',
);
// Used for locale-specific rules.
$locale = get_locale();
if ( in_array( $locale, array( 'de_DE', 'de_DE_formal', 'de_CH', 'de_CH_informal' ), true ) ) {
$chars['Ä'] = 'Ae';
$chars['ä'] = 'ae';
$chars['Ö'] = 'Oe';
$chars['ö'] = 'oe';
$chars['Ü'] = 'Ue';
$chars['ü'] = 'ue';
$chars['ß'] = 'ss';
} elseif ( 'da_DK' === $locale ) {
$chars['Æ'] = 'Ae';
$chars['æ'] = 'ae';
$chars['Ø'] = 'Oe';
$chars['ø'] = 'oe';
$chars['Å'] = 'Aa';
$chars['å'] = 'aa';
} elseif ( 'ca' === $locale ) {
$chars['l·l'] = 'll';
} elseif ( 'sr_RS' === $locale || 'bs_BA' === $locale ) {
$chars['Đ'] = 'DJ';
$chars['đ'] = 'dj';
}
$string = strtr( $string, $chars );
} else {
$chars = array();
// Assume ISO-8859-1 if not UTF-8.
$chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e"
. "\x9f\xa2\xa5\xb5\xc0\xc1\xc2"
. "\xc3\xc4\xc5\xc7\xc8\xc9\xca"
. "\xcb\xcc\xcd\xce\xcf\xd1\xd2"
. "\xd3\xd4\xd5\xd6\xd8\xd9\xda"
. "\xdb\xdc\xdd\xe0\xe1\xe2\xe3"
. "\xe4\xe5\xe7\xe8\xe9\xea\xeb"
. "\xec\xed\xee\xef\xf1\xf2\xf3"
. "\xf4\xf5\xf6\xf8\xf9\xfa\xfb"
. "\xfc\xfd\xff";
$chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy';
$string = strtr( $string, $chars['in'], $chars['out'] );
$double_chars = array();
$double_chars['in'] = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" );
$double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' );
$string = str_replace( $double_chars['in'], $double_chars['out'], $string );
}
return $string;
}
/**
* Sanitizes a filename, replacing whitespace with dashes.
*
* Removes special characters that are illegal in filenames on certain
* operating systems and special characters requiring special escaping
* to manipulate at the command line. Replaces spaces and consecutive
* dashes with a single dash. Trims period, dash and underscore from beginning
* and end of filename. It is not guaranteed that this function will return a
* filename that is allowed to be uploaded.
*
* @since 2.1.0
*
* @param string $filename The filename to be sanitized.
* @return string The sanitized filename.
*/
function sanitize_file_name( $filename ) {
$filename_raw = $filename;
$filename = remove_accents( $filename );
$special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '|', '~', '`', '!', '{', '}', '%', '+', '’', '«', '»', '”', '“', chr( 0 ) );
// Check for support for utf8 in the installed PCRE library once and store the result in a static.
static $utf8_pcre = null;
if ( ! isset( $utf8_pcre ) ) {
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged
$utf8_pcre = @preg_match( '/^./u', 'a' );
}
if ( ! seems_utf8( $filename ) ) {
$_ext = pathinfo( $filename, PATHINFO_EXTENSION );
$_name = pathinfo( $filename, PATHINFO_FILENAME );
$filename = sanitize_title_with_dashes( $_name ) . '.' . $_ext;
}
if ( $utf8_pcre ) {
$filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
}
/**
* Filters the list of characters to remove from a filename.
*
* @since 2.8.0
*
* @param string[] $special_chars Array of characters to remove.
* @param string $filename_raw The original filename to be sanitized.
*/
$special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
$filename = str_replace( $special_chars, '', $filename );
$filename = str_replace( array( '%20', '+' ), '-', $filename );
$filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
$filename = trim( $filename, '.-_' );
if ( false === strpos( $filename, '.' ) ) {
$mime_types = wp_get_mime_types();
$filetype = wp_check_filetype( 'test.' . $filename, $mime_types );
if ( $filetype['ext'] === $filename ) {
$filename = 'unnamed-file.' . $filetype['ext'];
}
}
// Split the filename into a base and extension[s].
$parts = explode( '.', $filename );
// Return if only one extension.
if ( count( $parts ) <= 2 ) {
/**
* Filters 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. Postfix them with a trailing underscore
* if they are a 2 - 5 character long alpha string not in the allowed extension list.
*/
foreach ( (array) $parts as $part ) {
$filename .= '.' . $part;
if ( preg_match( '/^[a-zA-Z]{2,5}\d?$/', $part ) ) {
$allowed = false;
foreach ( $mimes as $ext_preg => $mime_match ) {
$ext_preg = '!^(' . $ext_preg . ')$!i';
if ( preg_match( $ext_preg, $part ) ) {
$allowed = true;
break;
}
}
if ( ! $allowed ) {
$filename .= '_';
}
}
}
$filename .= '.' . $extension;
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
}
/**
* Sanitizes a username, stripping out unsafe characters.
*
* Removes tags, octets, entities, and if strict is enabled, will only keep
* alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
* raw username (the username in the parameter), and the value of $strict as
* parameters for the {@see 'sanitize_user'} filter.
*
* @since 2.0.0
*
* @param string $username The username to be sanitized.
* @param bool $strict Optional. If set limits $username to specific characters.
* Default false.
* @return string The sanitized username, after passing through filters.
*/
function sanitize_user( $username, $strict = false ) {
$raw_username = $username;
$username = wp_strip_all_tags( $username );
$username = remove_accents( $username );
// Kill octets.
$username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
// Kill entities.
$username = preg_replace( '/&.+?;/', '', $username );
// If strict, reduce to ASCII for max portability.
if ( $strict ) {
$username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
}
$username = trim( $username );
// Consolidate contiguous whitespace.
$username = preg_replace( '|\s+|', ' ', $username );
/**
* Filters 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.
*/
return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
}
/**
* Sanitizes a string key.
*
* Keys are used as internal identifiers. Lowercase alphanumeric characters,
* dashes, and underscores are allowed.
*
* @since 3.0.0
*
* @param string $key String key
* @return string Sanitized key
*/
function sanitize_key( $key ) {
$raw_key = $key;
$key = strtolower( $key );
$key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
/**
* Filters 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, $raw_key );
}
/**
* Sanitizes a string into a slug, which can be used in URLs or HTML attributes.
*
* By default, converts accent characters to ASCII characters and further
* limits the output to alphanumeric characters, underscore (_) and dash (-)
* through the {@see 'sanitize_title'} filter.
*
* If `$title` is empty and `$fallback_title` is set, the latter will be used.
*
* @since 1.0.0
*
* @param string $title The string to be sanitized.
* @param string $fallback_title Optional. A title to use if $title is empty. Default empty.
* @param string $context Optional. The operation for which the string is sanitized.
* Default 'save'.
* @return string The sanitized string.
*/
function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
$raw_title = $title;
if ( 'save' === $context ) {
$title = remove_accents( $title );
}
/**
* Filters 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;
}
return $title;
}
/**
* Sanitizes a title with the 'query' context.
*
* Used for querying the database for a value from URL.
*
* @since 3.1.0
*
* @param string $title The string to be sanitized.
* @return string The sanitized string.
*/
function sanitize_title_for_query( $title ) {
return sanitize_title( $title, '', 'query' );
}
/**
* Sanitizes a title, replacing whitespace and a few other characters with dashes.
*
* Limits the output to alphanumeric characters, underscore (_) and dash (-).
* Whitespace becomes a dash.
*
* @since 1.2.0
*
* @param string $title The title to be sanitized.
* @param string $raw_title Optional. Not used. Default empty.
* @param string $context Optional. The operation for which the string is sanitized.
* Default 'display'.
* @return string The sanitized title.
*/
function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
$title = strip_tags( $title );
// Preserve escaped octets.
$title = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title );
// Remove percent signs that are not part of an octet.
$title = str_replace( '%', '', $title );
// Restore octets.
$title = preg_replace( '|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title );
if ( seems_utf8( $title ) ) {
if ( function_exists( 'mb_strtolower' ) ) {
$title = mb_strtolower( $title, 'UTF-8' );
}
$title = utf8_uri_encode( $title, 200 );
}
$title = strtolower( $title );
if ( 'save' === $context ) {
// Convert &nbsp, &ndash, and &mdash to hyphens.
$title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
// Convert &nbsp, &ndash, and &mdash HTML entities to hyphens.
$title = str_replace( array( '&nbsp;', '&#160;', '&ndash;', '&#8211;', '&mdash;', '&#8212;' ), '-', $title );
// Convert forward slash to hyphen.
$title = str_replace( '/', '-', $title );
// Strip these characters entirely.
$title = str_replace(
array(
// Soft hyphens.
'%c2%ad',
// &iexcl and &iquest.
'%c2%a1',
'%c2%bf',
// Angle quotes.
'%c2%ab',
'%c2%bb',
'%e2%80%b9',
'%e2%80%ba',
// Curly quotes.
'%e2%80%98',
'%e2%80%99',
'%e2%80%9c',
'%e2%80%9d',
'%e2%80%9a',
'%e2%80%9b',
'%e2%80%9e',
'%e2%80%9f',
// Bullet.
'%e2%80%a2',
// &copy, &reg, &deg, &hellip, and &trade.
'%c2%a9',
'%c2%ae',
'%c2%b0',
'%e2%80%a6',
'%e2%84%a2',
// Acute accents.
'%c2%b4',
'%cb%8a',
'%cc%81',
'%cd%81',
// Grave accent, macron, caron.
'%cc%80',
'%cc%84',
'%cc%8c',
),
'',
$title
);
// Convert &times to 'x'.
$title = str_replace( '%c3%97', 'x', $title );
}
// Kill entities.
$title = preg_replace( '/&.+?;/', '', $title );
$title = str_replace( '.', '-', $title );
$title = preg_replace( '/[^%a-z0-9 _-]/', '', $title );
$title = preg_replace( '/\s+/', '-', $title );
$title = preg_replace( '|-+|', '-', $title );
$title = trim( $title, '-' );
return $title;
}
/**
* 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.
*
* Also accepts 'RAND()'.
*
* @since 2.5.1
*
* @param string $orderby Order by clause to be validated.
* @return string|false Returns $orderby if valid, false otherwise.
*/
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;
}
/**
* Sanitizes an HTML classname to ensure it only contains valid characters.
*
* Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
* string then it will return the alternative value supplied.
*
* @todo Expand to support the full range of CDATA that a class attribute can contain.
*
* @since 2.8.0
*
* @param string $class The classname to be sanitized
* @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
* Defaults to an empty string.
* @return string The sanitized value
*/
function sanitize_html_class( $class, $fallback = '' ) {
// Strip out any %-encoded octets.
$sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
// Limit to A-Z, a-z, 0-9, '_', '-'.
$sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
if ( '' === $sanitized && $fallback ) {
return sanitize_html_class( $fallback );
}
/**
* Filters 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 lone & characters into `&#038;` (a.k.a. `&amp;`)
*
* @since 0.71
*
* @param string $content String of characters to be converted.
* @param string $deprecated Not used.
* @return string Converted string.
*/
function convert_chars( $content, $deprecated = '' ) {
if ( ! empty( $deprecated ) ) {
_deprecated_argument( __FUNCTION__, '0.71' );
}
if ( strpos( $content, '&' ) !== false ) {
$content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content );
}
return $content;
}
/**
* Converts invalid Unicode references range to valid range.
*
* @since 4.3.0
*
* @param string $content String with entities that need converting.
* @return string Converted string.
*/
function convert_invalid_entities( $content ) {
$wp_htmltranswinuni = array(
'&#128;' => '&#8364;', // The Euro sign.
'&#129;' => '',
'&#130;' => '&#8218;', // These are Windows CP1252 specific characters.
'&#131;' => '&#402;', // They would look weird on non-Windows browsers.
'&#132;' => '&#8222;',
'&#133;' => '&#8230;',
'&#134;' => '&#8224;',
'&#135;' => '&#8225;',
'&#136;' => '&#710;',
'&#137;' => '&#8240;',
'&#138;' => '&#352;',
'&#139;' => '&#8249;',
'&#140;' => '&#338;',
'&#141;' => '',
'&#142;' => '&#381;',
'&#143;' => '',
'&#144;' => '',
'&#145;' => '&#8216;',
'&#146;' => '&#8217;',
'&#147;' => '&#8220;',
'&#148;' => '&#8221;',
'&#149;' => '&#8226;',
'&#150;' => '&#8211;',
'&#151;' => '&#8212;',
'&#152;' => '&#732;',
'&#153;' => '&#8482;',
'&#154;' => '&#353;',
'&#155;' => '&#8250;',
'&#156;' => '&#339;',
'&#157;' => '',
'&#158;' => '&#382;',
'&#159;' => '&#376;',
);
if ( strpos( $content, '&#1' ) !== false ) {
$content = strtr( $content, $wp_htmltranswinuni );
}
return $content;
}
/**
* Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
*
* @since 0.71
*
* @param string $text Text to be balanced
* @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
* @return string Balanced text
*/
function balanceTags( $text, $force = false ) { // phpcs:ignore WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid
if ( $force || (int) get_option( 'use_balanceTags' ) === 1 ) {
return force_balance_tags( $text );
} else {
return $text;
}
}
/**
* Balances tags of string using a modified stack.
*
* @since 2.0.4
* @since 5.3.0 Improve accuracy and add support for custom element tags.
*
* @author Leonard Lin <leonard@acm.org>
* @license GPL
* @copyright November 4, 2001
* @version 1.1
* @todo Make better - change loop condition to $text in 1.2
* @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
* 1.1 Fixed handling of append/stack pop order of end text
* Added Cleaning Hooks
* 1.0 First Version
*
* @param string $text Text to be balanced.
* @return string Balanced text.
*/
function force_balance_tags( $text ) {
$tagstack = array();
$stacksize = 0;
$tagqueue = '';
$newtext = '';
// Known single-entity/self-closing tags.
$single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
// Tags that can be immediately nested within themselves.
$nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
// WP bug fix for comments - in case you REALLY meant to type '< !--'.
$text = str_replace( '< !--', '< !--', $text );
// WP bug fix for LOVE <3 (and other situations with '<' before a number).
$text = preg_replace( '#<([0-9]{1})#', '&lt;$1', $text );
/**
* Matches supported tags.
*
* To get the pattern as a string without the comments paste into a PHP
* REPL like `php -a`.
*
* @see https://html.spec.whatwg.org/#elements-2
* @see https://w3c.github.io/webcomponents/spec/custom/#valid-custom-element-name
*
* @example
* ~# php -a
* php > $s = [paste copied contents of expression below including parentheses];
* php > echo $s;
*/
$tag_pattern = (
'#<' . // Start with an opening bracket.
'(/?)' . // Group 1 - If it's a closing tag it'll have a leading slash.
'(' . // Group 2 - Tag name.
// Custom element tags have more lenient rules than HTML tag names.
'(?:[a-z](?:[a-z0-9._]*)-(?:[a-z0-9._-]+)+)' .
'|' .
// Traditional tag rules approximate HTML tag names.
'(?:[\w:]+)' .
')' .
'(?:' .
// We either immediately close the tag with its '>' and have nothing here.
'\s*' .
'(/?)' . // Group 3 - "attributes" for empty tag.
'|' .
// Or we must start with space characters to separate the tag name from the attributes (or whitespace).
'(\s+)' . // Group 4 - Pre-attribute whitespace.
'([^>]*)' . // Group 5 - Attributes.
')' .
'>#' // End with a closing bracket.
);
while ( preg_match( $tag_pattern, $text, $regex ) ) {
$full_match = $regex[0];
$has_leading_slash = ! empty( $regex[1] );
$tag_name = $regex[2];
$tag = strtolower( $tag_name );
$is_single_tag = in_array( $tag, $single_tags, true );
$pre_attribute_ws = isset( $regex[4] ) ? $regex[4] : '';
$attributes = trim( isset( $regex[5] ) ? $regex[5] : $regex[3] );
$has_self_closer = '/' === substr( $attributes, -1 );
$newtext .= $tagqueue;
$i = strpos( $text, $full_match );
$l = strlen( $full_match );
// Clear the shifter.
$tagqueue = '';
if ( $has_leading_slash ) { // End tag.
// If too many closing tags.
if ( $stacksize <= 0 ) {
$tag = '';
// Or close to be safe $tag = '/' . $tag.
// If stacktop value = tag close value, then pop.
} elseif ( $tagstack[ $stacksize - 1 ] === $tag ) { // Found closing tag.
$tag = '</' . $tag . '>'; // Close tag.
array_pop( $tagstack );
$stacksize--;
} else { // Closing tag not at top, search for it.
for ( $j = $stacksize - 1; $j >= 0; $j-- ) {
if ( $tagstack[ $j ] === $tag ) {
// Add tag to tagqueue.
for ( $k = $stacksize - 1; $k >= $j; $k-- ) {
$tagqueue .= '</' . array_pop( $tagstack ) . '>';
$stacksize--;
}
break;
}
}
$tag = '';
}
} else { // Begin tag.
if ( $has_self_closer ) { // If it presents itself as a self-closing tag...
// ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such
// and immediately close it with a closing tag (the tag will encapsulate no text as a result).
if ( ! $is_single_tag ) {
$attributes = trim( substr( $attributes, 0, -1 ) ) . "></$tag";
}
} elseif ( $is_single_tag ) { // Else if it's a known single-entity tag but it doesn't close itself, do so.
$pre_attribute_ws = ' ';
$attributes .= '/';
} else { // It's not a single-entity tag.
// If the top of the stack is the same as the tag we want to push, close previous tag.
if ( $stacksize > 0 && ! in_array( $tag, $nestable_tags, true ) && $tagstack[ $stacksize - 1 ] === $tag ) {
$tagqueue = '</' . array_pop( $tagstack ) . '>';
$stacksize--;
}
$stacksize = array_push( $tagstack, $tag );
}
// Attributes.
if ( $has_self_closer && $is_single_tag ) {
// We need some space - avoid <br/> and prefer <br />.
$pre_attribute_ws = ' ';
}
$tag = '<' . $tag . $pre_attribute_ws . $attributes . '>';
// If already queuing a close tag, then put this tag on too.
if ( ! empty( $tagqueue ) ) {
$tagqueue .= $tag;
$tag = '';
}
}
$newtext .= substr( $text, 0, $i ) . $tag;
$text = substr( $text, $i + $l );
}
// Clear tag queue.
$newtext .= $tagqueue;
// Add remaining text.
$newtext .= $text;
while ( $x = array_pop( $tagstack ) ) {
$newtext .= '</' . $x . '>'; // Add remaining tags to close.
}
// WP fix for the bug with HTML comments.
$newtext = str_replace( '< !--', '<!--', $newtext );
$newtext = str_replace( '< !--', '< !--', $newtext );
return $newtext;
}
/**
* Acts on text which is about to be edited.
*
* The $content is run through esc_textarea(), which uses htmlspecialchars()
* to convert special characters to HTML entities. If `$richedit` is set to true,
* it is simply a holder for the {@see 'format_to_edit'} filter.
*
* @since 0.71
* @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
*
* @param string $content The text about to be edited.
* @param bool $rich_text Optional. Whether `$content` should be considered rich text,
* in which case it would not be passed through esc_textarea().
* Default false.
* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
*/
function format_to_edit( $content, $rich_text = false ) {
/**
* Filters 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 ( ! $rich_text ) {
$content = esc_textarea( $content );
}
return $content;
}
/**
* Add leading zeros when necessary.
*
* If you set the threshold to '4' and the number is '10', then you will get
* back '0010'. If you set the threshold to '4' and the number is '5000', then you
* will get back '5000'.
*
* Uses sprintf to append the amount of zeros based on the $threshold parameter
* and the size of the number. If the number is large enough, then no zeros will
* be appended.
*
* @since 0.71
*
* @param int $number Number to append zeros to if not greater than threshold.
* @param int $threshold Digit places number needs to be to not have zeros added.
* @return string Adds leading zeros to number if needed.
*/
function zeroise( $number, $threshold ) {
return sprintf( '%0' . $threshold . 's', $number );
}
/**
* Adds backslashes before letters and before a number at the start of a string.
*
* @since 0.71
*
* @param string $string Value to which backslashes will be added.
* @return string String with backslashes inserted.
*/
function backslashit( $string ) {
if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' ) {
$string = '\\\\' . $string;
}
return addcslashes( $string, 'A..Za..z' );
}
/**
* Appends a trailing slash.
*
* 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
*
* @param string $string What to add the trailing slash to.
* @return string String with trailing slash added.
*/
function trailingslashit( $string ) {
return untrailingslashit( $string ) . '/';
}
/**
* Removes trailing 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 slashes from.
* @return string String without the trailing slashes.
*/
function untrailingslashit( $string ) {
return rtrim( $string, '/\\' );
}
/**
* Adds slashes to escape strings.
*
* Slashes will first be removed if magic_quotes_gpc is set, see {@link
* https://www.php.net/magic_quotes} for more details.
*
* @since 0.71
*
* @param string $gpc The string returned from HTTP request data.
* @return string Returns a string escaped with slashes.
*/
function addslashes_gpc( $gpc ) {
return wp_slash( $gpc );
}
/**
* Navigates through an array, object, or scalar, and removes slashes from the values.
*
* @since 2.0.0
*
* @param mixed $value The value to be stripped.
* @return mixed Stripped value.
*/
function stripslashes_deep( $value ) {
return map_deep( $value, 'stripslashes_from_strings_only' );
}
/**
* Callback function for `stripslashes_deep()` which strips slashes from strings.
*
* @since 4.4.0
*
* @param mixed $value The array or string to be stripped.
* @return mixed The stripped value.
*/
function stripslashes_from_strings_only( $value ) {
return is_string( $value ) ? stripslashes( $value ) : $value;
}
/**
* Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
*
* @since 2.2.0
*
* @param mixed $value The array or string to be encoded.
* @return mixed The encoded value.
*/
function urlencode_deep( $value ) {
return map_deep( $value, 'urlencode' );
}
/**
* Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
*
* @since 3.4.0
*
* @param mixed $value The array or string to be encoded.
* @return mixed The encoded value.
*/
function rawurlencode_deep( $value ) {
return map_deep( $value, 'rawurlencode' );
}
/**
* Navigates through an array, object, or scalar, and decodes URL-encoded values
*
* @since 4.4.0
*
* @param mixed $value The array or string to be decoded.
* @return mixed The decoded value.
*/
function urldecode_deep( $value ) {
return map_deep( $value, 'urldecode' );
}
/**
* Converts email addresses characters to HTML entities to block spam bots.
*
* @since 0.71
*
* @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( $email_address, $hex_encoding = 0 ) {
$email_no_spam_address = '';
for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
$j = rand( 0, 1 + $hex_encoding );
if ( 0 == $j ) {
$email_no_spam_address .= '&#' . ord( $email_address[ $i ] ) . ';';
} elseif ( 1 == $j ) {
$email_no_spam_address .= $email_address[ $i ];
} elseif ( 2 == $j ) {
$email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[ $i ] ) ), 2 );
}
}
return str_replace( '@', '&#64;', $email_no_spam_address );
}
/**
* Callback to convert URI match to HTML A element.
*
* This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
*
* @since 2.3.2
* @access private
*
* @param array $matches Single Regex Match.
* @return string HTML A element with URI address.
*/
function _make_url_clickable_cb( $matches ) {
$url = $matches[2];
if ( ')' === $matches[3] && strpos( $url, '(' ) ) {
// If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it,
// add the closing parenthesis to the URL. Then we can let the parenthesis balancer do its thing below.
$url .= $matches[3];
$suffix = '';
} else {
$suffix = $matches[3];
}
// Include parentheses in the URL only if paired.
while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
$suffix = strrchr( $url, ')' ) . $suffix;
$url = substr( $url, 0, strrpos( $url, ')' ) );
}
$url = esc_url( $url );
if ( empty( $url ) ) {
return $matches[0];
}
if ( 'comment_text' === current_filter() ) {
$rel = 'nofollow ugc';
} else {
$rel = 'nofollow';
}
/**
* Filters the rel value that is added to URL matches converted to links.
*
* @since 5.3.0
*
* @param string $rel The rel value.
* @param string $url The matched URL being converted to a link tag.
*/
$rel = apply_filters( 'make_clickable_rel', $rel, $url );
$rel = esc_attr( $rel );
return $matches[1] . "<a href=\"$url\" rel=\"$rel\">$url</a>" . $suffix;
}
/**
* Callback to convert URL match to HTML A element.
*
* This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
*
* @since 2.3.2
* @access private
*
* @param array $matches Single Regex Match.
* @return string HTML A element with URL address.
*/
function _make_web_ftp_clickable_cb( $matches ) {
$ret = '';
$dest = $matches[2];
$dest = 'http://' . $dest;
// Removed trailing [.,;:)] from URL.
$last_char = substr( $dest, -1 );
if ( in_array( $last_char, array( '.', ',', ';', ':', ')' ), true ) === true ) {
$ret = $last_char;
$dest = substr( $dest, 0, strlen( $dest ) - 1 );
}
$dest = esc_url( $dest );
if ( empty( $dest ) ) {
return $matches[0];
}
if ( 'comment_text' === current_filter() ) {
$rel = 'nofollow ugc';
} else {
$rel = 'nofollow';
}
/** This filter is documented in wp-includes/formatting.php */
$rel = apply_filters( 'make_clickable_rel', $rel, $dest );
$rel = esc_attr( $rel );
return $matches[1] . "<a href=\"$dest\" rel=\"$rel\">$dest</a>$ret";
}
/**
* Callback to convert email address match to HTML A element.
*
* This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
*
* @since 2.3.2
* @access private
*
* @param array $matches Single Regex Match.
* @return string HTML A element with email address.
*/
function _make_email_clickable_cb( $matches ) {
$email = $matches[2] . '@' . $matches[3];
return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
}
/**
* Convert plaintext URI to HTML links.
*
* Converts URI, www and ftp, and email addresses. Finishes by fixing links
* within links.
*
* @since 0.71
*
* @param string $text Content to convert URIs.
* @return string Content with converted URIs.
*/
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 ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) || preg_match( '|^<script[\s>]|i', $piece ) || preg_match( '|^<style[\s>]|i', $piece ) ) {
$nested_code_pre++;
} elseif ( $nested_code_pre && ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) || '</script>' === strtolower( $piece ) || '</style>' === strtolower( $piece ) ) ) {
$nested_code_pre--;
}
if ( $nested_code_pre || empty( $piece ) || ( '<' === $piece[0] && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
$r .= $piece;
continue;
}
// Long strings might contain expensive edge cases...
if ( 10000 < strlen( $piece ) ) {
// ...break it up.
foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses.
if ( 2101 < strlen( $chunk ) ) {
$r .= $chunk; // Too big, no whitespace: bail.
} else {
$r .= make_clickable( $chunk );
}
}
} else {
$ret = " $piece "; // Pad with whitespace to simplify the regexes.
$url_clickable = '~
([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation.
( # 2: URL.
[\\w]{1,20}+:// # Scheme and hier-part prefix.
(?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long.
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character.
(?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character.
[\'.,;:!?)] # Punctuation URL character.
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character.
)*
)
(\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing).
~xS';
// The regex is a non-anchored pattern and does not have a single fixed starting character.
// Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.