Manager

Back Back Up Advanced Editor

<?php
/**
 * Main WordPress Formatting API.
 *
 * Handles many functions for formatting output.
 *
 * @package WordPress
 */

/**
 * Replaces common plain text characters with formatted entities.
 *
 * Returns given text with transformations of quotes into smart quotes, apostrophes,
 * dashes, ellipses, the trademark symbol, and the multiplication symbol.
 *
 * As an example,
 *
 * 'cause today's effort makes it worth tomorrow's "holiday" ...
 *
 * Becomes:
 *
 * &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221; &#8230;
 *
 * Code within certain HTML blocks are skipped.
 *
 * Do not use this function before the {@see 'init'} action hook; everything will break.
 *
 * @since 0.71
 *
 * @global array $wp_cockneyreplace Array of formatted entities for certain common phrases.
 * @global array $shortcode_tags
 *
 * @param string $text The text to be formatted.
 * @param bool $reset Set to true for unit testing. Translated patterns will reset.
 * @return string The string replaced with HTML entities.
 */
function wptexturize( $text, $reset = false ) {
	global $wp_cockneyreplace, $shortcode_tags;
	static $static_characters = null,
		$static_replacements = null,
		$dynamic_characters = null,
		$dynamic_replacements = null,
		$default_no_texturize_tags = null,
		$default_no_texturize_shortcodes = null,
		$run_texturize = true,
		$apos = null,
		$prime = null,
		$double_prime = null,
		$opening_quote = null,
		$closing_quote = null,
		$opening_single_quote = null,
		$closing_single_quote = null,
		$open_q_flag = '',
		$open_sq_flag = '',
		$apos_flag = '';

// If there's nothing to do, just stop.
	if ( empty( $text ) || false === $run_texturize ) {
		return $text;
	}

// Set up static variables. Run once only.
	if ( $reset || ! isset( $static_characters ) ) {
		/**
		 * Filters whether to skip running wptexturize().
		 *
		 * Returning false from the filter will effectively short-circuit wptexturize()
		 * and return the original text passed to the function instead.
		 *
		 * The filter runs only once, the first time wptexturize() is called.
		 *
		 * @since 4.0.0
		 *
		 * @see wptexturize()
		 *
		 * @param bool $run_texturize Whether to short-circuit wptexturize().
		 */
		$run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
		if ( false === $run_texturize ) {
			return $text;
		}

/* translators: Opening curly double quote. */
		$opening_quote = _x( '&#8220;', 'opening curly double quote' );
		/* translators: Closing curly double quote. */
		$closing_quote = _x( '&#8221;', 'closing curly double quote' );

/* translators: Apostrophe, for example in 'cause or can't. */
		$apos = _x( '&#8217;', 'apostrophe' );

/* translators: Prime, for example in 9' (nine feet). */
		$prime = _x( '&#8242;', 'prime' );
		/* translators: Double prime, for example in 9" (nine inches). */
		$double_prime = _x( '&#8243;', 'double prime' );

/* translators: Opening curly single quote. */
		$opening_single_quote = _x( '&#8216;', 'opening curly single quote' );
		/* translators: Closing curly single quote. */
		$closing_single_quote = _x( '&#8217;', 'closing curly single quote' );

/* translators: En dash. */
		$en_dash = _x( '&#8211;', 'en dash' );
		/* translators: Em dash. */
		$em_dash = _x( '&#8212;', 'em dash' );

$default_no_texturize_tags       = array( 'pre', 'code', 'kbd', 'style', 'script', 'tt' );
		$default_no_texturize_shortcodes = array( 'code' );

// If a plugin has provided an autocorrect array, use it.
		if ( isset( $wp_cockneyreplace ) ) {
			$cockney        = array_keys( $wp_cockneyreplace );
			$cockneyreplace = array_values( $wp_cockneyreplace );
		} else {
			/*
			 * translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
			 * for example... 'We do not have enough words yet'... is a typical quoted phrase. But when we write
			 * lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
			 */
			$cockney = explode(
				',',
				_x(
					"'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
					'Comma-separated list of words to texturize in your language'
				)
			);

$cockneyreplace = explode(
				',',
				_x(
					'&#8217;tain&#8217;t,&#8217;twere,&#8217;twas,&#8217;tis,&#8217;twill,&#8217;til,&#8217;bout,&#8217;nuff,&#8217;round,&#8217;cause,&#8217;em',
					'Comma-separated list of replacement words in your language'
				)
			);
		}

$static_characters   = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
		$static_replacements = array_merge( array( '&#8230;', $opening_quote, $closing_quote, ' &#8482;' ), $cockneyreplace );

/*
		 * Pattern-based replacements of characters.
		 * Sort the remaining patterns into several arrays for performance tuning.
		 */
		$dynamic_characters   = array(
			'apos'  => array(),
			'quote' => array(),
			'dash'  => array(),
		);
		$dynamic_replacements = array(
			'apos'  => array(),
			'quote' => array(),
			'dash'  => array(),
		);
		$dynamic              = array();
		$spaces               = wp_spaces_regexp();

// '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
		if ( "'" !== $apos || "'" !== $closing_single_quote ) {
			$dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
		}
		if ( "'" !== $apos || '"' !== $closing_quote ) {
			$dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
		}

// '99 '99s '99's (apostrophe)  But never '9 or '99% or '999 or '99.0.
		if ( "'" !== $apos ) {
			$dynamic['/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/'] = $apos_flag;
		}

// Quoted numbers like '0.42'.
		if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
			$dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
		}

// Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
		if ( "'" !== $opening_single_quote ) {
			$dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $open_sq_flag;
		}

// Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
		if ( "'" !== $apos ) {
			$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
		}

$dynamic_characters['apos']   = array_keys( $dynamic );
		$dynamic_replacements['apos'] = array_values( $dynamic );
		$dynamic                      = array();

// Quoted numbers like "42".
		if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
			$dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
		}

// Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
		if ( '"' !== $opening_quote ) {
			$dynamic[ '/(?<=\A|[([{\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
		}

$dynamic_characters['quote']   = array_keys( $dynamic );
		$dynamic_replacements['quote'] = array_values( $dynamic );
		$dynamic                       = array();

// Dashes and spaces.
		$dynamic['/---/'] = $em_dash;
		$dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash;
		$dynamic['/(?<!xn)--/'] = $en_dash;
		$dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ] = $en_dash;

$dynamic_characters['dash']   = array_keys( $dynamic );
		$dynamic_replacements['dash'] = array_values( $dynamic );
	}

// Must do this every time in case plugins use these filters in a context sensitive manner.
	/**
	 * Filters the list of HTML elements not to texturize.
	 *
	 * @since 2.8.0
	 *
	 * @param string[] $default_no_texturize_tags An array of HTML element names.
	 */
	$no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
	/**
	 * Filters the list of shortcodes not to texturize.
	 *
	 * @since 2.8.0
	 *
	 * @param string[] $default_no_texturize_shortcodes An array of shortcode names.
	 */
	$no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );

$no_texturize_tags_stack       = array();
	$no_texturize_shortcodes_stack = array();

// Look for shortcodes and HTML elements.

preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
	$tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
	$found_shortcodes = ! empty( $tagnames );
	$shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
	$regex = _get_wptexturize_split_regex( $shortcode_regex );

$textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );

foreach ( $textarr as &$curl ) {
		// Only call _wptexturize_pushpop_element if $curl is a delimiter.
		$first = $curl[0];
		if ( '<' === $first ) {
			if ( str_starts_with( $curl, '<!--' ) ) {
				// This is an HTML comment delimiter.
				continue;
			} else {
				// This is an HTML element delimiter.

// Replace each & with &#038; unless it already looks like an entity.
				$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );

_wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
			}
		} elseif ( '' === trim( $curl ) ) {
			// This is a newline between delimiters. Performance improves when we check this.
			continue;

} elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
			// This is a shortcode delimiter.

if ( ! str_starts_with( $curl, '[[' ) && ! str_ends_with( $curl, ']]' ) ) {
				// Looks like a normal shortcode.
				_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
			} else {
				// Looks like an escaped shortcode.
				continue;
			}
		} elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
			// This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.

$curl = str_replace( $static_characters, $static_replacements, $curl );

if ( str_contains( $curl, "'" ) ) {
				$curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
				$curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
				$curl = str_replace( $apos_flag, $apos, $curl );
				$curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
			}
			if ( str_contains( $curl, '"' ) ) {
				$curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
				$curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
				$curl = str_replace( $open_q_flag, $opening_quote, $curl );
			}
			if ( str_contains( $curl, '-' ) ) {
				$curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
			}

// 9x9 (times), but never 0x9999.
			if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
				// Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
				$curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1&#215;$2', $curl );
			}

// Replace each & with &#038; unless it already looks like an entity.
			$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );
		}
	}

return implode( '', $textarr );
}

/**
 * Implements a logic tree to determine whether or not "7'." represents seven feet,
 * then converts the special char into either a prime char or a closing quote char.
 *
 * @since 4.3.0
 *
 * @param string $haystack The plain text to be searched.
 * @param string $needle The character to search for such as ' or ".
 * @param string $prime The prime char to use for replacement.
 * @param string $open_quote The opening quote char. Opening quote replacement must be
 * accomplished already.
 * @param string $close_quote The closing quote char to use for replacement.
 * @return string The $haystack value after primes and quotes replacements.
 */
function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
	$spaces = wp_spaces_regexp();
	$flag = '';
	$quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|&gt;|" . $spaces . ')/';
	$prime_pattern = "/(?<=\\d)$needle/";
	$flag_after_digit = "/(?<=\\d)$flag/";
	$flag_no_digit = "/(?<!\\d)$flag/";

$sentences = explode( $open_quote, $haystack );

foreach ( $sentences as $key => &$sentence ) {
		if ( ! str_contains( $sentence, $needle ) ) {
			continue;
		} elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
			$sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
			if ( $count > 1 ) {
				// This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
				$sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
				if ( 0 === $count2 ) {
					// Try looking for a quote followed by a period.
					$count2 = substr_count( $sentence, "$flag." );
					if ( $count2 > 0 ) {
						// Assume the rightmost quote-period match is the end of quotation.
						$pos = strrpos( $sentence, "$flag." );
					} else {
						/*
						 * When all else fails, make the rightmost candidate a closing quote.
						 * This is most likely to be problematic in the context of bug #18549.
						 */
						$pos = strrpos( $sentence, $flag );
					}
					$sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
				}
				// Use conventional replacement on any remaining primes and quotes.
				$sentence = preg_replace( $prime_pattern, $prime, $sentence );
				$sentence = preg_replace( $flag_after_digit, $prime, $sentence );
				$sentence = str_replace( $flag, $close_quote, $sentence );
			} elseif ( 1 === $count ) {
				// Found only one closing quote candidate, so give it priority over primes.
				$sentence = str_replace( $flag, $close_quote, $sentence );
				$sentence = preg_replace( $prime_pattern, $prime, $sentence );
			} else {
				// No closing quotes found. Just run primes pattern.
				$sentence = preg_replace( $prime_pattern, $prime, $sentence );
			}
		} else {
			$sentence = preg_replace( $prime_pattern, $prime, $sentence );
			$sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
		}
		if ( '"' === $needle && str_contains( $sentence, '"' ) ) {
			$sentence = str_replace( '"', $close_quote, $sentence );
		}
	}

return implode( $open_quote, $sentences );
}

/**
 * Searches for disabled element tags. Pushes element to stack on tag open
 * and pops on tag close.
 *
 * Assumes first char of `$text` is tag opening and last char is tag closing.
 * Assumes second char of `$text` is optionally `/` to indicate closing as in `</html>`.
 *
 * @since 2.9.0
 * @access private
 *
 * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
 * @param string[] $stack Array of open tag elements.
 * @param string[] $disabled_elements Array of tag names to match against. Spaces are not allowed in tag names.
 */
function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) {
	// Is it an opening tag or closing tag?
	if ( isset( $text[1] ) && '/' !== $text[1] ) {
		$opening_tag = true;
		$name_offset = 1;
	} elseif ( 0 === count( $stack ) ) {
		// Stack is empty. Just stop.
		return;
	} else {
		$opening_tag = false;
		$name_offset = 2;
	}

// Parse out the tag name.
	$space = strpos( $text, ' ' );
	if ( false === $space ) {
		$space = -1;
	} else {
		$space -= $name_offset;
	}
	$tag = substr( $text, $name_offset, $space );

// Handle disabled tags.
	if ( in_array( $tag, $disabled_elements, true ) ) {
		if ( $opening_tag ) {
			/*
			 * This disables texturize until we find a closing tag of our type
			 * (e.g. <pre>) even if there was invalid nesting before that.
			 *
			 * Example: in the case <pre>sadsadasd</code>"baba"</pre>
			 * "baba" won't be texturized.
			 */

array_push( $stack, $tag );
		} elseif ( end( $stack ) === $tag ) {
			array_pop( $stack );
		}
	}
}

/**
 * Replaces double line breaks with paragraph elements.
 *
 * A group of regex replaces used to identify text formatted with newlines and
 * replace double line breaks with HTML paragraph tags. The remaining line breaks
 * after conversion become ` ` tags, unless `$br` is set to '0' or 'false'.
 *
 * @since 0.71
 *
 * @param string $text The text which has to be formatted.
 * @param bool $br Optional. If set, this will convert all remaining line breaks
 * after paragraphing. Line breaks within `<script>`, `<style>`,
 * and `<svg>` tags are not affected. Default true.
 * @return string Text which has been converted into correct paragraph tags.
 */
function wpautop( $text, $br = true ) {
	$pre_tags = array();

if ( trim( $text ) === '' ) {
		return '';
	}

// Just to make things a little easier, pad the end.
	$text = $text . "\n";

/*
	 * Pre tags shouldn't be touched by autop.
	 * Replace pre tags with placeholders and bring them back after autop.
	 */
	if ( str_contains( $text, '<pre' ) ) {
		$text_parts = explode( '</pre>', $text );
		$last_part = array_pop( $text_parts );
		$text = '';
		$i = 0;

foreach ( $text_parts as $text_part ) {
			$start = strpos( $text_part, '<pre' );

// Malformed HTML?
			if ( false === $start ) {
				$text .= $text_part;
				continue;
			}

$name = "<pre wp-pre-tag-$i></pre>";
			$pre_tags[ $name ] = substr( $text_part, $start ) . '</pre>';

$text .= substr( $text_part, 0, $start ) . $name;
			++$i;
		}

$text .= $last_part;
	}
	// Change multiple 's into two line breaks, which will turn into paragraphs.
	$text = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $text );

$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';

// Add a double line break above block-level opening tags.
	$text = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $text );

// Add a double line break below block-level closing tags.
	$text = preg_replace( '!(</' . $allblocks . '>)!', "$1\n\n", $text );

// Add a double line break after hr tags, which are self closing.
	$text = preg_replace( '!(<hr\s*?/?>)!', "$1\n\n", $text );

// Standardize newline characters to "\n".
	$text = str_replace( array( "\r\n", "\r" ), "\n", $text );

// Find newlines in all elements and add placeholders.
	$text = wp_replace_in_html_tags( $text, array( "\n" => '  ' ) );

// Collapse line breaks before and after <option> elements so they don't get autop'd.
	if ( str_contains( $text, '<option' ) ) {
		$text = preg_replace( '|\s*<option|', '<option', $text );
		$text = preg_replace( '|</option>\s*|', '</option>', $text );
	}

/*
	 * Collapse line breaks inside <object> elements, before <param> and <embed> elements
	 * so they don't get autop'd.
	 */
	if ( str_contains( $text, '</object>' ) ) {
		$text = preg_replace( '|(<object[^>]*>)\s*|', '$1', $text );
		$text = preg_replace( '|\s*</object>|', '</object>', $text );
		$text = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $text );
	}

/*
	 * Collapse line breaks inside <audio> and <video> elements,
	 * before and after <source> and <track> elements.
	 */
	if ( str_contains( $text, '<source' ) || str_contains( $text, '<track' ) ) {
		$text = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $text );
		$text = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $text );
		$text = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $text );
	}

// Collapse line breaks before and after <figcaption> elements.
	if ( str_contains( $text, '<figcaption' ) ) {
		$text = preg_replace( '|\s*(<figcaption[^>]*>)|', '$1', $text );
		$text = preg_replace( '|</figcaption>\s*|', '</figcaption>', $text );
	}

// Remove more than two contiguous line breaks.
	$text = preg_replace( "/\n\n+/", "\n\n", $text );

// Split up the contents into an array of strings, separated by double line breaks.
	$paragraphs = preg_split( '/\n\s*\n/', $text, -1, PREG_SPLIT_NO_EMPTY );

// Reset $text prior to rebuilding.
	$text = '';

// Rebuild the content as a string, wrapping every bit with a .
	foreach ( $paragraphs as $paragraph ) {
		$text .= '' . trim( $paragraph, "\n" ) . "\n";
	}

// Under certain strange conditions it could create a P of entirely whitespace.
	$text = preg_replace( '|\s*|', '', $text );

// Add a closing inside <div>, <address>, or <form> tag if missing.
	$text = preg_replace( '!([^<]+)</(div|address|form)>!', '$1</$2>', $text );

// If an opening or closing block element tag is wrapped in a , unwrap it.
	$text = preg_replace( '!\s*(</?' . $allblocks . '[^>]*>)\s*!', '$1', $text );

// In some cases <li> may get wrapped in , fix them.
	$text = preg_replace( '|(<li.+?)|', '$1', $text );

// If a <blockquote> is wrapped with a , move it inside the <blockquote>.
	$text = preg_replace( '|<blockquote([^>]*)>|i', '<blockquote$1>', $text );
	$text = str_replace( '</blockquote>', '</blockquote>', $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( '<WPPreserveNewline />', "\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 <pre> 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.
		$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;
}

/**
 * Newline preservation help function for wpautop().
 *
 * @since 3.1.0
 * @access private
 *
 * @param array $matches preg_replace_callback matches array
 * @return string
 */
function _autop_newline_preservation_helper( $matches ) {
	return str_replace( "\n", '<WPPreserveNewline />', $matches[0] );
}

/**
 * Don't auto-p wrap shortcodes that stand alone.
 *
 * Ensures that shortcodes are not wrapped in `...`.
 *
 * @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 `'`.
 *
 * `$quote_style` can be set to ENT_COMPAT to encode `"` to
 * `&quot;`, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
 *
 * @since 1.2.2
 * @since 5.5.0 `$quote_style` also accepts `ENT_XML1`.
 * @access private
 *
 * @param string $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 &amp;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( "'", '&#039;', $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(
		'&#039;' => '\'',
		'&#x27;' => '\'',
	);
	$single_preg = array(
		'/&#0*39;/' => '&#039;',
		'/&#x0*27;/i' => '&#x27;',
	);
	$double = array(
		'&quot;' => '"',
		'&#034;' => '"',
		'&#x22;' => '"',
	);
	$double_preg = array(
		'/&#0*34;/' => '&#034;',
		'/&#x0*22;/i' => '&#x22;',
	);
	$others = array(
		'&lt;' => '<',
		'&#060;' => '<',
		'&gt;' => '>',
		'&#062;' => '>',
		'&amp;' => '&',
		'&#038;' => '&',
		'&#x26;' => '&',
	);
	$others_preg = array(
		'/&#0*60;/' => '&#060;',
		'/&#0*62;/' => '&#062;',
		'/&#0*38;/' => '&#038;',
		'/&#x0*26;/i' => '&#x26;',
	);

if ( ENT_QUOTES === $quote_style ) {
		$translation      = array_merge( $single, $double, $others );
		$translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
	} elseif ( ENT_COMPAT === $quote_style || 'double' === $quote_style ) {
		$translation      = array_merge( $double, $others );
		$translation_preg = array_merge( $double_preg, $others_preg );
	} elseif ( 'single' === $quote_style ) {
		$translation      = array_merge( $single, $others );
		$translation_preg = array_merge( $single_preg, $others_preg );
	} elseif ( ENT_NOQUOTES === $quote_style ) {
		$translation      = $others;
		$translation_preg = $others_preg;
	}

// Remove zero padding on numeric entities.
	$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  | Œ     | 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           |