<?php

/**

 * Main WordPress Formatting API.

 *

 * Handles many functions for formatting output.

 *

 * @package WordPress

 */

/**

 *

 * As an example,

 *

 *     'cause today's effort makes it worth tomorrow's "holiday" ...

 *

 * Becomes:

 *

 *     ’cause today’s effort makes it worth tomorrow’s “holiday” …

 *

 *

 * Do not use this function before the {@see 'init'} action hook; everything will break.

 *

 * @since 0.71

 *

 * @global array $shortcode_tags

 * @param bool   $reset Set to true for unit testing. Translated patterns will reset.

 */

function wptexturize( $text, $reset = false ) {

	global $wp_cockneyreplace, $shortcode_tags;

	static $static_characters            = null,

		$static_replacements             = null,

		$dynamic_characters              = null,

		$dynamic_replacements            = null,

		$default_no_texturize_tags       = null,

		$default_no_texturize_shortcodes = null,

		$run_texturize                   = true,

		$apos                            = null,

		$prime                           = null,

		$double_prime                    = null,

		$opening_quote                   = null,

		$closing_quote                   = null,

		$opening_single_quote            = null,

		$closing_single_quote            = null,

		$open_q_flag                     = '<!--oq-->',

		$open_sq_flag                    = '<!--osq-->',

		$apos_flag                       = '<!--apos-->';

	// If there's nothing to do, just stop.

	if ( empty( $text ) || false === $run_texturize ) {

		return $text;

	}

	// Set up static variables. Run once only.

	if ( $reset || ! isset( $static_characters ) ) {

		/**

		 * Filters whether to skip running wptexturize().

		 *

		 *

		 * 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;

		}

		$opening_quote = _x( '“', 'opening curly double quote' );

		$closing_quote = _x( '”', 'closing curly double quote' );

		$apos = _x( '’', 'apostrophe' );

		$prime = _x( '′', 'prime' );

		$double_prime = _x( '″', 'double prime' );

		$opening_single_quote = _x( '‘', 'opening curly single quote' );

		$closing_single_quote = _x( '’', 'closing curly single quote' );

		$en_dash = _x( '–', 'en dash' );

		$em_dash = _x( '—', 'em dash' );

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

		$default_no_texturize_shortcodes = array( 'code' );

		if ( isset( $wp_cockneyreplace ) ) {

			$cockney        = array_keys( $wp_cockneyreplace );

			$cockneyreplace = array_values( $wp_cockneyreplace );

		} else {

			 * 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(

					'’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em',

					'Comma-separated list of replacement words in your language'

				)

			);

		}

		$static_characters   = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );

		$static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );

		// Pattern-based replacements of characters.

		// Sort the remaining patterns into several arrays for performance tuning.

		$dynamic_characters   = array(

			'apos'  => array(),

			'quote' => array(),

			'dash'  => array(),

		);

		$dynamic_replacements = array(

			'apos'  => array(),

			'quote' => array(),

			'dash'  => array(),

		);

		$dynamic              = array();

		$spaces               = wp_spaces_regexp();

		// '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.

		if ( "'" !== $apos || "'" !== $closing_single_quote ) {

			$dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;

		}

		if ( "'" !== $apos || '"' !== $closing_quote ) {

			$dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|>|' . $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;

		}

		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;

		}

		if ( "'" !== $apos ) {

			$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;

		}

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

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

		$dynamic                      = array();

		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();

		$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 );

	}

	/**

	 * Filters the list of HTML elements not to texturize.

	 *

	 * @since 2.8.0

	 *

	 */

	$no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );

	/**

	 * Filters the list of shortcodes not to texturize.

	 *

	 * @since 2.8.0

	 *

	 */

	$no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );

	$no_texturize_tags_stack       = array();

	$no_texturize_shortcodes_stack = array();

	// Look for shortcodes and HTML elements.

	preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );

	$tagnames         = array_intersect( array_keys( $shortcode_tags ), $matches[1] );

	$found_shortcodes = ! empty( $tagnames );

	$shortcode_regex  = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';

	$regex            = _get_wptexturize_split_regex( $shortcode_regex );

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

	foreach ( $textarr as &$curl ) {

		// Only call _wptexturize_pushpop_element if $curl is a delimiter.

		$first = $curl[0];

		if ( '<' === $first ) {

			if ( '<!--' === substr( $curl, 0, 4 ) ) {

				// This is an HTML comment delimiter.

				continue;

			} else {

				// This is an HTML element delimiter.

				// Replace each & with & unless it already looks like an entity.

				$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );

				_wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );

			}

		} elseif ( '' === trim( $curl ) ) {

			continue;

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

			// This is a shortcode delimiter.

			if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {

				// Looks like a normal shortcode.

				_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );

			} else {

				// Looks like an escaped shortcode.

				continue;

			}

		} elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {

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

			if ( false !== strpos( $curl, "'" ) ) {

				$curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );

				$curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );

				$curl = str_replace( $apos_flag, $apos, $curl );

				$curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );

			}

			if ( false !== strpos( $curl, '"' ) ) {

				$curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );

				$curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );

				$curl = str_replace( $open_q_flag, $opening_quote, $curl );

			}

			if ( false !== strpos( $curl, '-' ) ) {

				$curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );

			}

			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 & unless it already looks like an entity.

			$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );

		}

	}

	return implode( '', $textarr );

}

/**

 * Implements a logic tree to determine whether or not "7'." represents seven feet,

 * then converts the special char into either a prime char or a closing quote char.

 *

 * @since 4.3.0

 *

 * @param string $haystack    The plain text to be searched.

 * @param string $needle      The character to search for such as ' or ".

 * @param string $prime       The prime char to use for replacement.

 * @param string $open_quote  The opening quote char. Opening quote replacement must be

 *                            accomplished already.

 * @param string $close_quote The closing quote char to use for replacement.

 * @return string The $haystack value after primes and quotes replacements.

 */

function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {

	$spaces           = wp_spaces_regexp();

	$flag             = '<!--wp-prime-or-quote-->';

	$quote_pattern    = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ')/';

	$prime_pattern    = "/(?<=\\d)$needle/";

	$flag_after_digit = "/(?<=\\d)$flag/";

	$flag_no_digit    = "/(?<!\\d)$flag/";

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

	foreach ( $sentences as $key => &$sentence ) {

		if ( false === strpos( $sentence, $needle ) ) {

			continue;

		} elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {

			$sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );

			if ( $count > 1 ) {

				$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 {

				$sentence = preg_replace( $prime_pattern, $prime, $sentence );

			}

		} else {

			$sentence = preg_replace( $prime_pattern, $prime, $sentence );

			$sentence = preg_replace( $quote_pattern, $close_quote, $sentence );

		}

			$sentence = str_replace( '"', $close_quote, $sentence );

		}

	}

	return implode( $open_quote, $sentences );

}

/**

 * Search for disabled element tags. Push element to stack on tag open and pop

 * on tag close.

 *

 * Assumes first char of $text is tag opening and last char is tag closing.

 * Assumes second char of $text is optionally '/' to indicate closing as in </html>.

 *

 * @since 2.9.0

 * @access private

 *

 */

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;

		// 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 ( $opening_tag ) {

			/*

			 * This disables texturize until we find a closing tag of our type

			 *

			 * Example: in the case <pre>sadsadasd</code>"baba"</pre>

			 */

			array_push( $stack, $tag );

		} elseif ( end( $stack ) == $tag ) {

			array_pop( $stack );

		}

	}

}

/**

 *

 * A group of regex replaces used to identify text formatted with newlines and

 * after conversion become <<br />> tags, unless $br is set to '0' or 'false'.

 *

 * @since 0.71

 *

 * @param string $pee The text which has to be formatted.

 * @return string Text which has been converted into correct paragraph tags.

 */

function wpautop( $pee, $br = true ) {

	$pre_tags = array();

	if ( trim( $pee ) === '' ) {

		return '';

	}

	// Just to make things a little easier, pad the end.

	$pee = $pee . "\n";

	/*

	 * Pre tags shouldn't be touched by autop.

	 * Replace pre tags with placeholders and bring them back after autop.

	 */

	if ( strpos( $pee, '<pre' ) !== false ) {

		$pee_parts = explode( '</pre>', $pee );

		$last_pee  = array_pop( $pee_parts );

		$pee       = '';

		$i         = 0;

		foreach ( $pee_parts as $pee_part ) {

			$start = strpos( $pee_part, '<pre' );

				$pee .= $pee_part;

				continue;

			}

			$name              = "<pre wp-pre-tag-$i></pre>";

			$pre_tags[ $name ] = substr( $pee_part, $start ) . '</pre>';

			$pee .= substr( $pee_part, 0, $start ) . $name;

			$i++;

		}

		$pee .= $last_pee;

	}

	$pee = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee );

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

	// Add a double line break above block-level opening tags.

	$pee = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $pee );

	// Add a double line break below block-level closing tags.

	$pee = preg_replace( '!(</' . $allblocks . '>)!', "$1\n\n", $pee );