.
$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*(?' . $allblocks . '[^>]*>)!', '$1', $text );
// If an opening or closing block element tag is followed by a closing
tag, remove it.
$text = preg_replace( '!(?' . $allblocks . '[^>]*>)\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( '!(?' . $allblocks . '[^>]*>)\s*
!', '$1', $text );
// If a
tag is before a subset of opening or closing block tags, remove it.
$text = preg_replace( '!
(\s*?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$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;
}
function wp_html_split( $input ) {
return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
}
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;
}
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;
}
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;
}
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.
$needle = array_key_first( $replace_pairs );
$replace = $replace_pairs[ $needle ];
// 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;
}
function _autop_newline_preservation_helper( $matches ) {
return str_replace( "\n", '', $matches[0] );
}
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 );
}
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;
}
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;
}
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 );
}
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 '';
}
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;
}
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;
}
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( '#\p{Zs}#siu', ' ', $filename );
}
$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 ) {
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;
return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
}
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 );
return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
}
function sanitize_key( $key ) {
$sanitized_key = '';
if ( is_scalar( $key ) ) {
$sanitized_key = strtolower( $key );
$sanitized_key = preg_replace( '/[^a-z0-9_\-]/', '', $sanitized_key );
}
return apply_filters( 'sanitize_key', $sanitized_key, $key );
}
function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
$raw_title = $title;
if ( 'save' === $context ) {
$title = remove_accents( $title );
}
$title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
if ( '' === $title || false === $title ) {
$title = $fallback_title;
}
return $title;
}
function sanitize_title_for_query( $title ) {
return sanitize_title( $title, '', 'query' );
}
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;
}
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;
}
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 );
}
return apply_filters( 'sanitize_html_class', $sanitized, $classname, $fallback );
}
function sanitize_locale_name( $locale_name ) {
// Limit to A-Z, a-z, 0-9, '_', '-'.
$sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $locale_name );
return apply_filters( 'sanitize_locale_name', $sanitized, $locale_name );
}
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;
}
function convert_invalid_entities( $content ) {
$wp_htmltranswinuni = array(
'' => '€', // The Euro sign.
'' => '',
'' => '‚', // These are Windows CP1252 specific characters.
'' => 'ƒ', // They would look weird on non-Windows browsers.
'' => '„',
'
' => '…',
'' => '†',
'' => '‡',
'' => 'ˆ',
'' => '‰',
'' => 'Š',
'' => '‹',
'' => 'Œ',
'' => '',
'' => 'Ž',
'' => '',
'' => '',
'' => '‘',
'' => '’',
'' => '“',
'' => '”',
'' => '•',
'' => '–',
'' => '—',
'' => '˜',
'' => '™',
'' => 'š',
'' => '›',
'' => 'œ',
'' => '',
'' => 'ž',
'' => 'Ÿ',
);
if ( str_contains( $content, '' ) ) {
$content = strtr( $content, $wp_htmltranswinuni );
}
return $content;
}
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;
}
}
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 );
$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 = '' . $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
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 .= '' . $x . '>'; // Add remaining tags to close.
}
// WP fix for the bug with HTML comments.
$newtext = str_replace( '< !--', '