X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/11be8dc178e77d0b46189bbd8e33a216a9b90942..refs/tags/wordpress-4.3.1:/wp-includes/formatting.php
diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index 53df8084..640e136f 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -1,183 +1,803 @@
- * 'cause today's effort makes it worth tomorrow's "holiday"...
- *
+ *
+ * 'cause today's effort makes it worth tomorrow's "holiday" ...
+ *
* Becomes:
- *
- * ’cause today’s effort makes it worth tomorrow’s “holiday”…
- *
+ *
+ * ’cause today’s effort makes it worth tomorrow’s “holiday” …
+ *
* Code within certain html blocks are skipped.
*
+ * Do not use this function before the 'init' action hook; everything will break.
+ *
* @since 0.71
- * @uses $wp_cockneyreplace Array of formatted entities for certain common phrases
+ *
+ * @global array $wp_cockneyreplace Array of formatted entities for certain common phrases
+ * @global array $shortcode_tags
+ * @staticvar array $static_characters
+ * @staticvar array $static_replacements
+ * @staticvar array $dynamic_characters
+ * @staticvar array $dynamic_replacements
+ * @staticvar array $default_no_texturize_tags
+ * @staticvar array $default_no_texturize_shortcodes
+ * @staticvar bool $run_texturize
*
* @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) {
- global $wp_cockneyreplace;
- $next = true;
- $has_pre_parent = false;
- $output = '';
- $curl = '';
- $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
- $stop = count($textarr);
-
- // 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 {
- $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
- $cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
+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;
}
- $static_characters = array_merge(array('---', ' -- ', '--', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
- $static_replacements = array_merge(array('—', ' — ', '–', 'xn--', '…', '“', '’s', '”', ' ™'), $cockneyreplace);
+ // Set up static variables. Run once only.
+ if ( $reset || ! isset( $static_characters ) ) {
+ /**
+ * Filter whether to skip running wptexturize().
+ *
+ * Passing false to the filter will effectively short-circuit wptexturize().
+ * returning 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;
+ }
- $dynamic_characters = array('/\'(\d\d(?:’|\')?s)/', '/(\s|\A|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A)"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
- $dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1“$2', '”$1', '’$1', '$1×$2');
+ /* translators: opening curly double quote */
+ $opening_quote = _x( '“', 'opening curly double quote' );
+ /* translators: closing curly double quote */
+ $closing_quote = _x( '”', 'closing curly double quote' );
- for ( $i = 0; $i < $stop; $i++ ) {
- $curl = $textarr[$i];
-
- if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0} && $next && !$has_pre_parent) { // If it's not a tag
- // static strings
- $curl = str_replace($static_characters, $static_replacements, $curl);
- // regular expressions
- $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
- } elseif (strpos($curl, '') !== false) {
- $has_pre_parent = false;
+ /* 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 {
- $next = true;
+ /* 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[ '/\'(\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;
+ }
+
+ // 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|[([{"\-]|<|' . $spaces . ')\'/' ] = $open_sq_flag;
+ }
+
+ // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
+ if ( "'" !== $apos ) {
+ $dynamic[ '/(? is found.
+ . '-(?!->)' // Dash not followed by end of comment.
+ . '[^\-]*+' // Consume non-dashes.
+ . ')*+' // Loop possessively.
+ . '(?:-->)?'; // End of comment. If not found, match all input.
+
+ $shortcode_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 ]]
+
+ $regex =
+ '/(' // Capture the entire match.
+ . '<' // Find start of element.
+ . '(?(?=!--)' // Is this a comment?
+ . $comment_regex // Find end of comment.
+ . '|'
+ . '[^>]*>' // Find end of element.
+ . ')'
+ . '|'
+ . $shortcode_regex // Find shortcodes.
+ . ')/s';
+
+ $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 && '';
+ $quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ")/";
+ $prime_pattern = "/(?<=\\d)$needle/";
+ $flag_after_digit = "/(?<=\\d)$flag/";
+ $flag_no_digit = "/(? &$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 ) {
+ // 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 && false !== strpos( $sentence, '"' ) ) {
+ $sentence = str_replace( '"', $close_quote, $sentence );
+ }
+ }
+
+ return implode( $open_quote, $sentences );
}
/**
- * Accepts matches array from preg_replace_callback in wpautop() or a string.
+ * Search for disabled element tags. Push element to stack on tag open and pop
+ * on tag close.
*
- * Ensures that the contents of a <>...<
> HTML block are not
- * converted into paragraphs or line-breaks.
+ * 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