wptexturize

wptexturize: 這個函式用於將文字中的某些字元和符號轉換成HTML實體。例如，它可以將單引號和雙引號轉換為與之對應的HTML，即‘和’: 這個函式用於在WordPress部落格文章中以適合網路的方式顯示文字。

用格式化的實體替換常見的純文字字元。

返回給定文字，並將引號轉換為智慧引號、撇號、破折號、省略號、商標符號和乘法符號。

作為一個例子。

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

變成了：

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

某些HTML塊內的程式碼被跳過。

不要在{@see ‘init’}動作鉤子之前使用這個函式，一切都會中斷。

function wptexturize( $text, $reset = false ) {
	global $wp_cockneyreplace, $shortcode_tags;
	static $static_characters            = null,
		$static_replacements             = null,
		$dynamic_characters              = null,
		$dynamic_replacements            = null,
		$default_no_texturize_tags       = null,
		$default_no_texturize_shortcodes = null,
		$run_texturize                   = true,
		$apos                            = null,
		$prime                           = null,
		$double_prime                    = null,
		$opening_quote                   = null,
		$closing_quote                   = null,
		$opening_single_quote            = null,
		$closing_single_quote            = null,
		$open_q_flag                     = '<!--oq-->',
		$open_sq_flag                    = '<!--osq-->',
		$apos_flag                       = '<!--apos-->';

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

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

		/* translators: Opening curly double quote. */
		$opening_quote = _x( '“', 'opening curly double quote' );
		/* translators: Closing curly double quote. */
		$closing_quote = _x( '”', 'closing curly double quote' );

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

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

		/* translators: Opening curly single quote. */
		$opening_single_quote = _x( '‘', 'opening curly single quote' );
		/* translators: Closing curly single quote. */
		$closing_single_quote = _x( '’', 'closing curly single quote' );

		/* translators: En dash. */
		$en_dash = _x( '–', 'en dash' );
		/* translators: Em dash. */
		$em_dash = _x( '—', '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(
					'’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[ '/'(dd)'(?=Z|[.,:;!?)}-]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
		}
		if ( "'" !== $apos || '"' !== $closing_quote ) {
			$dynamic[ '/'(dd)"(?=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['/'(?=dd(?:Z|(?![%d]|[.,]d)))/'] = $apos_flag;
		}

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

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

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

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

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

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

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

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

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

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

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

	// Look for shortcodes and HTML elements.

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

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

	foreach ( $textarr as &$curl ) {
		// Only call _wptexturize_pushpop_element if $curl is a delimiter.
		$first = $curl[0];
		if ( '<' === $first ) {
			if ( '<!--' === substr( $curl, 0, 4 ) ) {
				// This is an HTML comment delimiter.
				continue;
			} else {
				// This is an HTML element delimiter.

				// Replace each & with & 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 ) ) {
			// This is a newline between delimiters. Performance improves when we check this.
			continue;

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

			if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
				// Looks like a normal shortcode.
				_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
			} else {
				// Looks like an escaped shortcode.
				continue;
			}
		} elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
			// This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.

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

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

			// 9x9 (times), but never 0x9999.
			if ( 1 === preg_match( '/(?<=d)xd/', $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×$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 );
}