X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/76aea3697c6043c1613370f172395b4f65ee71f0..8d3bb1a5dcfdea9857d3c88c3751f09593e34dc8:/wp-includes/formatting.php
diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index eeafe0b4..2701c1a1 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -1,879 +1,3398 @@
|\[.*\])/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");
+/**
+ * Replaces common plain text characters into formatted entities
+ *
+ * As an example,
+ *
+ * 'cause today's effort makes it worth tomorrow's "holiday" ...
+ *
+ * Becomes:
+ *
+ * ’cause today’s effort makes it worth tomorrow’s “holiday” …
+ *
+ * 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
+ * @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, $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 ) ) {
+ /**
+ * Filters 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 (isset($curl{0}) && '<' != $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, ' ', "\n", $text);
- $text = str_replace('') !== 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' ) );
}
- $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
- $output .= $curl;
- }
+ $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
+ $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
- return $output;
-}
-// Accepts matches array from preg_replace_callback in wpautop()
-// or a string
-function clean_pre($matches) {
- if ( is_array($matches) )
- $text = $matches[1] . $matches[2] . "";
- else
- $text = $matches;
+ // 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();
- $text = str_replace('
', '', $text);
- $text = str_replace('
\s*
|', "\n\n", $pee);
- // Space things out a little
- $allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)';
- $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
- $pee = preg_replace('!(' . $allblocks . '>)!', "$1\n\n", $pee);
- $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
- if ( strpos($pee, '
\s*(?' . $allblocks . '[^>]*>)!', "$1", $pee); - $pee = preg_replace('!(?' . $allblocks . '[^>]*>)\s*
!', "$1", $pee); - if ($br) { - $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", ")(.*?)!is', 'clean_pre', $pee ); - $pee = preg_replace( "|\n$|", '', $pee ); - $pee = preg_replace('/
\s*?(' . get_shortcode_regex() . ')\s*<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone + // Quoted Numbers like '0.42' + if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) { + $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote; + } - return $pee; -} + // 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[ '/(?', '>', $text); - if ( 'double' === $quotes ) { - $text = str_replace('"', '"', $text); - } elseif ( 'single' === $quotes ) { - $text = str_replace("'", ''', $text); - } elseif ( $quotes ) { - $text = str_replace('"', '"', $text); - $text = str_replace("'", ''', $text); + // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces. + if ( '"' !== $opening_quote ) { + $dynamic[ '/(?<=\A|[([{\-]|<|' . $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[ '/(?&/\[\]\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 ( ''; + $quote_pattern = "/$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, $sentence ); + } + } - if (seems_utf8($string)) { - $chars = array( - // Decompositions for Latin-1 Supplement - chr(195).chr(128) => 'A', chr(195).chr(129) => 'A', - chr(195).chr(130) => 'A', chr(195).chr(131) => 'A', - chr(195).chr(132) => 'A', chr(195).chr(133) => 'A', - chr(195).chr(135) => 'C', chr(195).chr(136) => 'E', - chr(195).chr(137) => 'E', chr(195).chr(138) => 'E', - chr(195).chr(139) => 'E', chr(195).chr(140) => 'I', - chr(195).chr(141) => 'I', chr(195).chr(142) => 'I', - chr(195).chr(143) => 'I', chr(195).chr(145) => 'N', - chr(195).chr(146) => 'O', chr(195).chr(147) => 'O', - chr(195).chr(148) => 'O', chr(195).chr(149) => 'O', - chr(195).chr(150) => 'O', chr(195).chr(153) => 'U', - chr(195).chr(154) => 'U', chr(195).chr(155) => 'U', - chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y', - chr(195).chr(159) => 's', chr(195).chr(160) => 'a', - chr(195).chr(161) => 'a', chr(195).chr(162) => 'a', - chr(195).chr(163) => 'a', chr(195).chr(164) => 'a', - chr(195).chr(165) => 'a', chr(195).chr(167) => 'c', - chr(195).chr(168) => 'e', chr(195).chr(169) => 'e', - chr(195).chr(170) => 'e', chr(195).chr(171) => 'e', - chr(195).chr(172) => 'i', chr(195).chr(173) => 'i', - chr(195).chr(174) => 'i', chr(195).chr(175) => 'i', - chr(195).chr(177) => 'n', chr(195).chr(178) => 'o', - chr(195).chr(179) => 'o', chr(195).chr(180) => 'o', - chr(195).chr(181) => 'o', chr(195).chr(182) => 'o', - chr(195).chr(182) => 'o', chr(195).chr(185) => 'u', - chr(195).chr(186) => 'u', chr(195).chr(187) => 'u', - chr(195).chr(188) => 'u', chr(195).chr(189) => 'y', - chr(195).chr(191) => 'y', - // Decompositions for Latin Extended-A - chr(196).chr(128) => 'A', chr(196).chr(129) => 'a', - chr(196).chr(130) => 'A', chr(196).chr(131) => 'a', - chr(196).chr(132) => 'A', chr(196).chr(133) => 'a', - chr(196).chr(134) => 'C', chr(196).chr(135) => 'c', - chr(196).chr(136) => 'C', chr(196).chr(137) => 'c', - chr(196).chr(138) => 'C', chr(196).chr(139) => 'c', - chr(196).chr(140) => 'C', chr(196).chr(141) => 'c', - chr(196).chr(142) => 'D', chr(196).chr(143) => 'd', - chr(196).chr(144) => 'D', chr(196).chr(145) => 'd', - chr(196).chr(146) => 'E', chr(196).chr(147) => 'e', - chr(196).chr(148) => 'E', chr(196).chr(149) => 'e', - chr(196).chr(150) => 'E', chr(196).chr(151) => 'e', - chr(196).chr(152) => 'E', chr(196).chr(153) => 'e', - chr(196).chr(154) => 'E', chr(196).chr(155) => 'e', - chr(196).chr(156) => 'G', chr(196).chr(157) => 'g', - chr(196).chr(158) => 'G', chr(196).chr(159) => 'g', - chr(196).chr(160) => 'G', chr(196).chr(161) => 'g', - chr(196).chr(162) => 'G', chr(196).chr(163) => 'g', - chr(196).chr(164) => 'H', chr(196).chr(165) => 'h', - chr(196).chr(166) => 'H', chr(196).chr(167) => 'h', - chr(196).chr(168) => 'I', chr(196).chr(169) => 'i', - chr(196).chr(170) => 'I', chr(196).chr(171) => 'i', - chr(196).chr(172) => 'I', chr(196).chr(173) => 'i', - chr(196).chr(174) => 'I', chr(196).chr(175) => 'i', - chr(196).chr(176) => 'I', chr(196).chr(177) => 'i', - chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij', - chr(196).chr(180) => 'J', chr(196).chr(181) => 'j', - chr(196).chr(182) => 'K', chr(196).chr(183) => 'k', - chr(196).chr(184) => 'k', chr(196).chr(185) => 'L', - chr(196).chr(186) => 'l', chr(196).chr(187) => 'L', - chr(196).chr(188) => 'l', chr(196).chr(189) => 'L', - chr(196).chr(190) => 'l', chr(196).chr(191) => 'L', - chr(197).chr(128) => 'l', chr(197).chr(129) => 'L', - chr(197).chr(130) => 'l', chr(197).chr(131) => 'N', - chr(197).chr(132) => 'n', chr(197).chr(133) => 'N', - chr(197).chr(134) => 'n', chr(197).chr(135) => 'N', - chr(197).chr(136) => 'n', chr(197).chr(137) => 'N', - chr(197).chr(138) => 'n', chr(197).chr(139) => 'N', - chr(197).chr(140) => 'O', chr(197).chr(141) => 'o', - chr(197).chr(142) => 'O', chr(197).chr(143) => 'o', - chr(197).chr(144) => 'O', chr(197).chr(145) => 'o', - chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe', - chr(197).chr(148) => 'R',chr(197).chr(149) => 'r', - chr(197).chr(150) => 'R',chr(197).chr(151) => 'r', - chr(197).chr(152) => 'R',chr(197).chr(153) => 'r', - chr(197).chr(154) => 'S',chr(197).chr(155) => 's', - chr(197).chr(156) => 'S',chr(197).chr(157) => 's', - chr(197).chr(158) => 'S',chr(197).chr(159) => 's', - chr(197).chr(160) => 'S', chr(197).chr(161) => 's', - chr(197).chr(162) => 'T', chr(197).chr(163) => 't', - chr(197).chr(164) => 'T', chr(197).chr(165) => 't', - chr(197).chr(166) => 'T', chr(197).chr(167) => 't', - chr(197).chr(168) => 'U', chr(197).chr(169) => 'u', - chr(197).chr(170) => 'U', chr(197).chr(171) => 'u', - chr(197).chr(172) => 'U', chr(197).chr(173) => 'u', - chr(197).chr(174) => 'U', chr(197).chr(175) => 'u', - chr(197).chr(176) => 'U', chr(197).chr(177) => 'u', - chr(197).chr(178) => 'U', chr(197).chr(179) => 'u', - chr(197).chr(180) => 'W', chr(197).chr(181) => 'w', - chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y', - chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z', - chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z', - chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z', - chr(197).chr(190) => 'z', chr(197).chr(191) => 's', - // Euro Sign - chr(226).chr(130).chr(172) => 'E', - // GBP (Pound) Sign - chr(194).chr(163) => ''); + return implode( $open_quote, $sentences ); +} - $string = strtr($string, $chars); +/** + * 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