may get wrapped in , fix them.
$text = preg_replace( '|
(|', '$1', $text );
// If a is wrapped with a , move it inside the
.
$text = preg_replace( '|]*)>|i', '', $text );
$text = str_replace( '
', '', $text );
// If an opening or closing block element tag is preceded by an opening tag, remove it.
$text = preg_replace( '!
\s*(]*>)!', '$1', $text );
// If an opening or closing block element tag is followed by a closing
tag, remove it.
$text = preg_replace( '!(]*>)\s*
!', '$1', $text );
// Optionally insert line breaks.
if ( $br ) {
// Replace newlines that shouldn't be touched with a placeholder.
$text = preg_replace_callback( '/<(script|style|svg|math).*?<\/\\1>/s', '_autop_newline_preservation_helper', $text );
// Normalize
$text = str_replace( array( '
', '
' ), '
', $text );
// Replace any new line characters that aren't preceded by a
with a
.
$text = preg_replace( '|(?)\s*\n|', "
\n", $text );
// Replace newline placeholders with newlines.
$text = str_replace( '', "\n", $text );
}
// If a
tag is after an opening or closing block tag, remove it.
$text = preg_replace( '!(]*>)\s*
!', '$1', $text );
// If a
tag is before a subset of opening or closing block tags, remove it.
$text = preg_replace( '!
(\s*]*>)!', '$1', $text );
$text = preg_replace( "|\n$|", '', $text );
// Replace placeholder tags with their original content.
if ( ! empty( $pre_tags ) ) {
$text = str_replace( array_keys( $pre_tags ), array_values( $pre_tags ), $text );
}
// Restore newlines in all elements.
if ( str_contains( $text, '' ) ) {
$text = str_replace( array( ' ', '' ), "\n", $text );
}
return $text;
}
/**
* Separates 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 );
}
/**
* Retrieves 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;
}
/**
* Retrieves 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 Optional. The result from _get_wptexturize_shortcode_regex().
* @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;
}
/**
* Retrieves 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 = implode( '|', 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;
}
/**
* Replaces 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 ( str_contains( $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 ( str_contains( $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", '', $matches[0] );
}
/**
* Don't auto-p wrap shortcodes that stand alone.
*
* Ensures that shortcodes are not wrapped in `...
`.
*
* @since 2.9.0
*
* @global array $shortcode_tags
*
* @param string $text The content.
* @return string The filtered content.
*/
function shortcode_unautop( $text ) {
global $shortcode_tags;
if ( empty( $shortcode_tags ) || ! is_array( $shortcode_tags ) ) {
return $text;
}
$tagregexp = implode( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
$spaces = wp_spaces_regexp();
// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound,Universal.WhiteSpace.PrecisionAlignment.Found -- don't remove regex indentation
$pattern =
'/'
. '' // 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', $text );
}
/**
* 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
* `"`, 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 $text 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( $text, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
$text = (string) $text;
if ( 0 === strlen( $text ) ) {
return '';
}
// Don't bother if there are no specialchars - saves some processing.
if ( ! preg_match( '/[&<>"\']/', $text ) ) {
return $text;
}
// Account for the previous behavior 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;
}
$charset = _canonical_charset( $charset ? $charset : get_option( 'blog_charset' ) );
$_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 &garbage;
* This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
*/
$text = wp_kses_normalize_entities( $text, ( $quote_style & ENT_XML1 ) ? 'xml' : 'html' );
}
$text = htmlspecialchars( $text, $quote_style, $charset, $double_encode );
// Back-compat.
if ( 'single' === $_quote_style ) {
$text = str_replace( "'", ''', $text );
}
return $text;
}
/**
* Converts a number of HTML entities into their special characters.
*
* Specifically deals with: `&`, `<`, `>`, `"`, and `'`.
*
* `$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 $text 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( $text, $quote_style = ENT_NOQUOTES ) {
$text = (string) $text;
if ( 0 === strlen( $text ) ) {
return '';
}
// Don't bother if there are no entities - saves a lot of processing.
if ( ! str_contains( $text, '&' ) ) {
return $text;
}
// Match the previous behavior of _wp_specialchars() when the $quote_style is not an accepted value.
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
// More complete than get_html_translation_table( HTML_SPECIALCHARS ).
$single = array(
''' => '\'',
''' => '\'',
);
$single_preg = array(
'/�*39;/' => ''',
'/�*27;/i' => ''',
);
$double = array(
'"' => '"',
'"' => '"',
'"' => '"',
);
$double_preg = array(
'/�*34;/' => '"',
'/�*22;/i' => '"',
);
$others = array(
'<' => '<',
'<' => '<',
'>' => '>',
'>' => '>',
'&' => '&',
'&' => '&',
'&' => '&',
);
$others_preg = array(
'/�*60;/' => '<',
'/�*62;/' => '>',
'/�*38;/' => '&',
'/�*26;/i' => '&',
);
if ( 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.
$text = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $text );
// Replace characters according to translation table.
return strtr( $text, $translation );
}
/**
* Checks for invalid UTF8 in a string.
*
* @since 2.8.0
*
* @param string $text 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( $text, $strip = false ) {
$text = (string) $text;
if ( 0 === strlen( $text ) ) {
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 = is_utf8_charset();
}
if ( ! $is_utf8 ) {
return $text;
}
// 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 $text;
}
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged -- preg_match fails when it encounters invalid UTF8 in $text.
if ( 1 === @preg_match( '/^./us', $text ) ) {
return $text;
}
// Attempt to strip the bad chars if requested (not recommended).
if ( $strip && function_exists( 'iconv' ) ) {
return iconv( 'utf-8', 'utf-8', $text );
}
return '';
}
/**
* Encodes the Unicode values to be used in the URI.
*
* @since 1.5.0
* @since 5.8.3 Added the `encode_ascii_characters` parameter.
*
* @param string $utf8_string String to encode.
* @param int $length Max length of the string
* @param bool $encode_ascii_characters Whether to encode ascii characters such as < " '
* @return string String with Unicode encoded for URI.
*/
function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters = false ) {
$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 ) {
$char = chr( $value );
$encoded_char = $encode_ascii_characters ? rawurlencode( $char ) : $char;
$encoded_char_length = strlen( $encoded_char );
if ( $length && ( $unicode_length + $encoded_char_length ) > $length ) {
break;
}
$unicode .= $encoded_char;
$unicode_length += $encoded_char_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+018F | Ə | E | Latin capital letter Ə |
* | U+0259 | ǝ | e | Latin small letter ǝ |
* | 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`),
* German (Switzerland) informal (`de_CH_informal`), and German (Austria) (`de_AT`) 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`.
* @since 5.7.0 Added locale support for `de_AT`.
* @since 6.0.0 Added the `$locale` parameter.
* @since 6.1.0 Added Unicode NFC encoding normalization support.
*
* @param string $text Text that might have accent characters.
* @param string $locale Optional. The locale to use for accent removal. Some character
* replacements depend on the locale being used (e.g. 'de_DE').
* Defaults to the current locale.
* @return string Filtered string with replaced "nice" characters.
*/
function remove_accents( $text, $locale = '' ) {
if ( ! preg_match( '/[\x80-\xff]/', $text ) ) {
return $text;
}
if ( seems_utf8( $text ) ) {
/*
* Unicode sequence normalization from NFD (Normalization Form Decomposed)
* to NFC (Normalization Form [Pre]Composed), the encoding used in this function.
*/
if ( function_exists( 'normalizer_is_normalized' )
&& function_exists( 'normalizer_normalize' )
) {
if ( ! normalizer_is_normalized( $text ) ) {
$text = normalizer_normalize( $text );
}
}
$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.
'Ə' => 'E',
'ǝ' => 'e',
'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.
if ( empty( $locale ) ) {
$locale = get_locale();
}
/*
* German has various locales (de_DE, de_CH, de_AT, ...) with formal and informal variants.
* There is no 3-letter locale like 'def', so checking for 'de' instead of 'de_' is safe,
* since 'de' itself would be a valid locale too.
*/
if ( str_starts_with( $locale, 'de' ) ) {
$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';
}
$text = strtr( $text, $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';
$text = strtr( $text, $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' );
$text = str_replace( $double_chars['in'], $double_chars['out'], $text );
}
return $text;
}
/**
* 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( '/\.{2,}/', '.', $filename );
$filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
$filename = trim( $filename, '.-_' );
if ( ! str_contains( $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 ) {
/** This filter is documented in wp-includes/formatting.php */
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;
/**
* 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 );
}
/**
* Sanitizes a username, stripping out unsafe characters.
*
* Removes tags, percent-encoded characters, HTML 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 to true, 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 );
// Remove percent-encoded characters.
$username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
// Remove HTML 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 ) {
$sanitized_key = '';
if ( is_scalar( $key ) ) {
$sanitized_key = strtolower( $key );
$sanitized_key = preg_replace( '/[^a-z0-9_\-]/', '', $sanitized_key );
}
/**
* Filters a sanitized key string.
*
* @since 3.0.0
*
* @param string $sanitized_key Sanitized key.
* @param string $key The key prior to sanitization.
*/
return apply_filters( 'sanitize_key', $sanitized_key, $key );
}
/**
* Sanitizes a string into a slug, which can be used in URLs or HTML attributes.
*
* By default, converts accent characters to ASCII characters and further
* limits the output to alphanumeric characters, underscore (_) and dash (-)
* through the {@see 'sanitize_title'} filter.
*
* If `$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.
* When set to 'save', the string runs through remove_accents().
* 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.
* When set to 'save', additional entities are converted to hyphens
* or stripped entirely. 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 , &ndash, and &mdash to hyphens.
$title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
// Convert , &ndash, and &mdash HTML entities to hyphens.
$title = str_replace( array( ' ', ' ', '–', '–', '—', '—' ), '-', $title );
// Convert forward slash to hyphen.
$title = str_replace( '/', '-', $title );
// Strip these characters entirely.
$title = str_replace(
array(
// Soft hyphens.
'%c2%ad',
// ¡ and ¿.
'%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',
// ©, ®, °, &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',
// Non-visible characters that display without a width.
'%e2%80%8b', // Zero width space.
'%e2%80%8c', // Zero width non-joiner.
'%e2%80%8d', // Zero width joiner.
'%e2%80%8e', // Left-to-right mark.
'%e2%80%8f', // Right-to-left mark.
'%e2%80%aa', // Left-to-right embedding.
'%e2%80%ab', // Right-to-left embedding.
'%e2%80%ac', // Pop directional formatting.
'%e2%80%ad', // Left-to-right override.
'%e2%80%ae', // Right-to-left override.
'%ef%bb%bf', // Byte order mark.
'%ef%bf%bc', // Object replacement character.
),
'',
$title
);
// Convert non-visible characters that display with a width to hyphen.
$title = str_replace(
array(
'%e2%80%80', // En quad.
'%e2%80%81', // Em quad.
'%e2%80%82', // En space.
'%e2%80%83', // Em space.
'%e2%80%84', // Three-per-em space.
'%e2%80%85', // Four-per-em space.
'%e2%80%86', // Six-per-em space.
'%e2%80%87', // Figure space.
'%e2%80%88', // Punctuation space.
'%e2%80%89', // Thin space.
'%e2%80%8a', // Hair space.
'%e2%80%a8', // Line separator.
'%e2%80%a9', // Paragraph separator.
'%e2%80%af', // Narrow no-break space.
),
'-',
$title
);
// Convert × to 'x'.
$title = str_replace( '%c3%97', 'x', $title );
}
// Remove HTML 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 $classname The classname to be sanitized.
* @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
* Default empty string.
* @return string The sanitized value.
*/
function sanitize_html_class( $classname, $fallback = '' ) {
// Strip out any percent-encoded characters.
$sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $classname );
// 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 $classname HTML class before sanitization.
* @param string $fallback The fallback string.
*/
return apply_filters( 'sanitize_html_class', $sanitized, $classname, $fallback );
}
/**
* Strips out all characters not allowed in a locale name.
*
* @since 6.2.1
*
* @param string $locale_name The locale name to be sanitized.
* @return string The sanitized value.
*/
function sanitize_locale_name( $locale_name ) {
// Limit to A-Z, a-z, 0-9, '_', '-'.
$sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $locale_name );
/**
* Filters a sanitized locale name string.
*
* @since 6.2.1
*
* @param string $sanitized The sanitized locale name.
* @param string $locale_name The locale name before sanitization.
*/
return apply_filters( 'sanitize_locale_name', $sanitized, $locale_name );
}
/**
* Converts lone & characters into `&` (a.k.a. `&`)
*
* @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 ( str_contains( $content, '&' ) ) {
$content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$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(
'€' => '€', // The Euro sign.
'' => '',
'‚' => '‚', // These are Windows CP1252 specific characters.
'ƒ' => 'ƒ', // They would look weird on non-Windows browsers.
'„' => '„',
'…' => '…',
'†' => '†',
'‡' => '‡',
'ˆ' => 'ˆ',
'‰' => '‰',
'Š' => 'Š',
'‹' => '‹',
'Œ' => 'Œ',
'' => '',
'Ž' => 'Ž',
'' => '',
'' => '',
'‘' => '‘',
'’' => '’',
'“' => '“',
'”' => '”',
'•' => '•',
'–' => '–',
'—' => '—',
'˜' => '˜',
'™' => '™',
'š' => 'š',
'›' => '›',
'œ' => 'œ',
'' => '',
'ž' => 'ž',
'Ÿ' => 'Ÿ',
);
if ( str_contains( $content, '' ) ) {
$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
* @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', 'track', 'wbr' );
// Tags that can be immediately nested within themselves.
$nestable_tags = array( 'article', 'aside', 'blockquote', 'details', 'div', 'figure', 'object', 'q', 'section', '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})#', '<$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://html.spec.whatwg.org/multipage/custom-elements.html#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 = str_ends_with( $attributes, '/' );
$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 = ''; // 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-- ) {
$tagqueue .= '';
--$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 ) ) . "> 0 && ! in_array( $tag, $nestable_tags, true ) && $tagstack[ $stacksize - 1 ] === $tag ) {
$tagqueue = '';
--$stacksize;
}
$stacksize = array_push( $tagstack, $tag );
}
// Attributes.
if ( $has_self_closer && $is_single_tag ) {
// We need some space - avoid
and prefer
.
$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 .= ''; // Add remaining tags to close.
}
// WP fix for the bug with HTML comments.
$newtext = str_replace( '< !--', '