* Replaces common plain text characters into formatted entities
*
* As an example,
- * <code>
- * 'cause today's effort makes it worth tomorrow's "holiday"...
- * </code>
+ *
+ * 'cause today's effort makes it worth tomorrow's "holiday" ...
+ *
* Becomes:
- * <code>
- * ’cause today’s effort makes it worth tomorrow’s “holiday”…
- * </code>
+ *
+ * ’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
- * @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;
- static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
- $default_no_texturize_tags, $default_no_texturize_shortcodes;
+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().
+ *
+ * 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;
+ }
- // No need to set up these static variables more than once
- if ( ! isset( $static_characters ) ) {
/* translators: opening curly double quote */
$opening_quote = _x( '“', 'opening curly double quote' );
/* translators: closing curly double quote */
// if a plugin has provided an autocorrect array, use it
if ( isset($wp_cockneyreplace) ) {
- $cockney = array_keys($wp_cockneyreplace);
- $cockneyreplace = array_values($wp_cockneyreplace);
- } elseif ( "'" != $apos ) { // Only bother if we're doing a replacement.
- $cockney = array( "'tain't", "'twere", "'twas", "'tis", "'twill", "'til", "'bout", "'nuff", "'round", "'cause" );
- $cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause" );
+ $cockney = array_keys( $wp_cockneyreplace );
+ $cockneyreplace = array_values( $wp_cockneyreplace );
} else {
- $cockney = $cockneyreplace = array();
- }
+ /* 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' ) );
- $static_characters = array_merge( array( '---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)' ), $cockney );
- $static_replacements = array_merge( array( $em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
+ $cockneyreplace = explode( ',', _x( '’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em',
+ 'Comma-separated list of replacement words in your language' ) );
+ }
- /*
- * Regex for common whitespace characters.
- *
- * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
- * This is designed to replace the PCRE \s sequence. In #WP22692, that sequence
- * was found to be unreliable due to random inclusion of the A0 byte.
- */
- $spaces = '[\r\n\t ]|\xC2\xA0| ';
+ $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 '99s '99's (apostrophe)
- if ( "'" !== $apos ) {
- $dynamic[ '/\'(?=\d)/' ] = $apos;
+ // '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;
}
- // Single quote at start, or preceded by (, {, <, [, ", or spaces.
- if ( "'" !== $opening_single_quote ) {
- $dynamic[ '/(?<=\A|[([{<"]|' . $spaces . ')\'/' ] = $opening_single_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;
}
- // 9" (double prime)
- if ( '"' !== $double_prime ) {
- $dynamic[ '/(?<=\d)"/' ] = $double_prime;
+ // Quoted Numbers like '0.42'
+ if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
+ $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
}
- // 9' (prime)
- if ( "'" !== $prime ) {
- $dynamic[ '/(?<=\d)\'/' ] = $prime;
+ // 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 or double primes.
+ // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
if ( "'" !== $apos ) {
- $dynamic[ '/(?<!' . $spaces . ')\'(?!\'|' . $spaces . ')/' ] = $apos;
+ $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
}
- // Double quote at start, or preceded by (, {, <, [, or spaces, and not followed by spaces.
- if ( '"' !== $opening_quote ) {
- $dynamic[ '/(?<=\A|[([{<]|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
- }
+ $dynamic_characters['apos'] = array_keys( $dynamic );
+ $dynamic_replacements['apos'] = array_values( $dynamic );
+ $dynamic = array();
- // Any remaining double quotes.
- if ( '"' !== $closing_quote ) {
- $dynamic[ '/"/' ] = $closing_quote;
+ // Quoted Numbers like "42"
+ if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
+ $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
}
- // Single quotes followed by spaces or a period.
- if ( "'" !== $closing_single_quote ) {
- $dynamic[ '/\'(?=\Z|\.|' . $spaces . ')/' ] = $closing_single_quote;
+ // 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 = array_keys( $dynamic );
- $dynamic_replacements = array_values( $dynamic );
+ $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 );
}
- // Transform into regexp sub-expression used in _wptexturize_pushpop_element
// Must do this every time in case plugins use these filters in a context sensitive manner
/**
- * Filter the list of HTML elements not to texturize.
+ * Filters the list of HTML elements not to texturize.
*
* @since 2.8.0
*
* @param array $default_no_texturize_tags An array of HTML element names.
*/
- $no_texturize_tags = '(' . implode( '|', apply_filters( 'no_texturize_tags', $default_no_texturize_tags ) ) . ')';
+ $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
/**
- * Filter the list of shortcodes not to texturize.
+ * Filters the list of shortcodes not to texturize.
*
* @since 2.8.0
*
* @param array $default_no_texturize_shortcodes An array of shortcode names.
*/
- $no_texturize_shortcodes = '(' . implode( '|', apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes ) ) . ')';
+ $no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
$no_texturize_tags_stack = array();
$no_texturize_shortcodes_stack = array();
- $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
+ // Look for shortcodes and HTML elements.
- foreach ( $textarr as &$curl ) {
- if ( empty( $curl ) ) {
- continue;
- }
+ 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 );
- // Only call _wptexturize_pushpop_element if first char is correct tag opening
+ $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 ( '<' === $first ) {
- _wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
- } elseif ( '[' === $first ) {
- _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
- } elseif ( empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack) ) {
+ 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.
- // This is not a tag, nor is the texturization disabled static strings
- $curl = str_replace($static_characters, $static_replacements, $curl);
+ 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.
- // regular expressions
- $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
+ $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)
- if ( 1 === preg_match( '/(?<=\d)x\d/', $text ) ) {
+ // 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+)x(\d+)\b/', '$1×$2', $curl );
+ $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('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $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 ) {
+ // 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 );
+}
+
/**
* Search for disabled element tags. Push element to stack on tag open and pop
- * on tag close. Assumes first character of $text is tag opening.
+ * 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. First character is assumed to be $opening
- * @param array $stack Array used as stack of opened tag elements
- * @param string $disabled_elements Tags to match against formatted as regexp sub-expression
- * @param string $opening Tag opening character, assumed to be 1 character long
- * @param string $closing Tag closing character
- */
-function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
- // Check if it is a closing tag -- otherwise assume opening tag
- if (strncmp($opening . '/', $text, 2)) {
- // Opening? Check $text+1 against disabled elements
- if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {
+ * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
+ * @param array $stack List of open tag elements.
+ * @param array $disabled_elements The 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 ) ) {
+ if ( $opening_tag ) {
/*
* This disables texturize until we find a closing tag of our type
* (e.g. <pre>) even if there was invalid nesting before that
* "baba" won't be texturize
*/
- array_push($stack, $matches[1]);
- }
- } else {
- // Closing? Check $text+2 against disabled elements
- $c = preg_quote($closing, '/');
- if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {
- $last = array_pop($stack);
-
- // Make sure it matches the opening tag
- if ( $last != $matches[1] ) {
- array_push( $stack, $last );
- }
+ 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 <<br />> tags, unless $br is set to '0'
- * or 'false'.
+ * replace double line-breaks with HTML paragraph tags. The remaining line-breaks
+ * 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.
- * @param bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
+ * @param bool $br Optional. If set, this will convert all remaining line-breaks
+ * after paragraphing. Default true.
* @return string Text which has been converted into correct paragraph tags.
*/
-function wpautop($pee, $br = true) {
+function wpautop( $pee, $br = true ) {
$pre_tags = array();
if ( trim($pee) === '' )
return '';
- $pee = $pee . "\n"; // just to make things a little easier, pad the end
+ // 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 .= $last_pee;
}
+ // Change multiple <br>s into two line breaks, which will turn into paragraphs.
+ $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 single line break above block-level opening tags.
+ $pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n$1", $pee);
- $pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
- // Space things out a little
- $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|noscript|legend|section|article|aside|hgroup|header|footer|nav|figure|details|menu|summary)';
- $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
+ // Add a double line break below block-level closing tags.
$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
- $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
+ // Standardize newline characters to "\n".
+ $pee = str_replace(array("\r\n", "\r"), "\n", $pee);
+
+ // Find newlines in all elements and add placeholders.
+ $pee = wp_replace_in_html_tags( $pee, array( "\n" => " <!-- wpnl --> " ) );
+
+ // Collapse line breaks before and after <option> elements so they don't get autop'd.
+ if ( strpos( $pee, '<option' ) !== false ) {
+ $pee = preg_replace( '|\s*<option|', '<option', $pee );
+ $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
+ }
+
+ /*
+ * Collapse line breaks inside <object> elements, before <param> and <embed> elements
+ * so they don't get autop'd.
+ */
if ( strpos( $pee, '</object>' ) !== false ) {
- // no P/BR around param and embed
$pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
$pee = preg_replace( '|\s*</object>|', '</object>', $pee );
$pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
}
+ /*
+ * Collapse line breaks inside <audio> and <video> elements,
+ * before and after <source> and <track> elements.
+ */
if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
- // no P/BR around source and track
$pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
$pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
$pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
}
- $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
- // make paragraphs, including one at the end
+ // Remove more than two contiguous line breaks.
+ $pee = preg_replace("/\n\n+/", "\n\n", $pee);
+
+ // Split up the contents into an array of strings, separated by double line breaks.
$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
+
+ // Reset $pee prior to rebuilding.
$pee = '';
+ // Rebuild the content as a string, wrapping every bit with a <p>.
foreach ( $pees as $tinkle ) {
$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
}
- $pee = preg_replace('|<p>\s*</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
+ // Under certain strange conditions it could create a P of entirely whitespace.
+ $pee = preg_replace('|<p>\s*</p>|', '', $pee);
+
+ // Add a closing <p> inside <div>, <address>, or <form> tag if missing.
$pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
- $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
- $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
+
+ // If an opening or closing block element tag is wrapped in a <p>, unwrap it.
+ $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
+
+ // In some cases <li> may get wrapped in <p>, fix them.
+ $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee);
+
+ // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
$pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
+
+ // If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
+
+ // If an opening or closing block element tag is followed by a closing <p> tag, remove it.
$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
+ // Optionally insert line breaks.
if ( $br ) {
+ // Replace newlines that shouldn't be touched with a placeholder.
$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
- $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
+
+ // Normalize <br>
+ $pee = str_replace( array( '<br>', '<br/>' ), '<br />', $pee );
+
+ // Replace any new line characters that aren't preceded by a <br /> with a <br />.
+ $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee);
+
+ // Replace newline placeholders with newlines.
$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
}
+ // If a <br /> tag is after an opening or closing block tag, remove it.
$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
+
+ // If a <br /> tag is before a subset of opening or closing block tags, remove it.
$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
$pee = preg_replace( "|\n</p>$|", '</p>', $pee );
+ // Replace placeholder <pre> tags with their original content.
if ( !empty($pre_tags) )
$pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
+ // Restore newlines in all elements.
+ if ( false !== strpos( $pee, '<!-- wpnl -->' ) ) {
+ $pee = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $pee );
+ }
+
return $pee;
}
+/**
+ * Separate HTML elements and comments from the text.
+ *
+ * @since 4.2.4
+ *
+ * @param string $input The text which has to be formatted.
+ * @return array The formatted text.
+ */
+function wp_html_split( $input ) {
+ return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
+}
+
+/**
+ * Retrieve 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 ) ) {
+ $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.
+ . ')'
+ . ')/';
+ }
+
+ return $regex;
+}
+
+/**
+ * Retrieve 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 The result from _get_wptexturize_shortcode_regex(). Optional.
+ * @return string The regular expression
+ */
+function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
+ static $html_regex;
+
+ if ( ! isset( $html_regex ) ) {
+ $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.
+ . ')';
+ }
+
+ if ( empty( $shortcode_regex ) ) {
+ $regex = '/(' . $html_regex . ')/';
+ } else {
+ $regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
+ }
+
+ return $regex;
+}
+
+/**
+ * Retrieve the regular expression for shortcodes.
+ *
+ * @access private
+ * @ignore
+ * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
+ * @since 4.4.0
+ *
+ * @param array $tagnames List of shortcodes to find.
+ * @return string The regular expression
+ */
+function _get_wptexturize_shortcode_regex( $tagnames ) {
+ $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
+ $tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
+ $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 ]]
+
+ return $regex;
+}
+
+/**
+ * Replace 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.
+ foreach ( $replace_pairs as $needle => $replace );
+
+ // Loop through delimiters (elements) only.
+ for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
+ if ( false !== strpos( $textarr[$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 ( false !== strpos( $textarr[$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
*
* @return string
*/
function _autop_newline_preservation_helper( $matches ) {
- return str_replace("\n", "<WPPreserveNewline />", $matches[0]);
+ return str_replace( "\n", "<WPPreserveNewline />", $matches[0] );
}
/**
* Don't auto-p wrap shortcodes that stand alone
*
- * Ensures that shortcodes are not wrapped in <<p>>...<</p>>.
+ * Ensures that shortcodes are not wrapped in `<p>...</p>`.
*
* @since 2.9.0
*
+ * @global array $shortcode_tags
+ *
* @param string $pee The content.
* @return string The filtered content.
*/
}
$tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
+ $spaces = wp_spaces_regexp();
$pattern =
'/'
. '<p>' // Opening paragraph
- . '\\s*+' // Optional leading whitespace
+ . '(?:' . $spaces . ')*+' // Optional leading whitespace
. '(' // 1: The shortcode
. '\\[' // Opening bracket
. "($tagregexp)" // 2: Shortcode name
. ')?'
. ')'
. ')'
- . '\\s*+' // optional trailing whitespace
+ . '(?:' . $spaces . ')*+' // optional trailing whitespace
. '<\\/p>' // closing paragraph
- . '/s';
+ . '/';
return preg_replace( $pattern, '$1', $pee );
}
* @param string $str The string to be checked
* @return bool True if $str fits a UTF-8 model, false otherwise.
*/
-function seems_utf8($str) {
+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; $j++) { # n bytes matching 10bbbbbb follow ?
+ if ($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;
}
* @since 1.2.2
* @access private
*
- * @param string $string The text which is to be encoded.
- * @param mixed $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 values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
- * @param string $charset Optional. The character encoding of the string. Default is false.
- * @param boolean $double_encode Optional. Whether to encode existing html entities. Default is false.
+ * @staticvar string $_charset
+ *
+ * @param string $string 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.
+ * 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 string $charset Optional. The character encoding of the string. Default is false.
+ * @param bool $double_encode Optional. Whether to encode existing html entities. Default is false.
* @return string The encoded text with HTML entities.
*/
function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
if ( ! $charset ) {
- static $_charset;
+ static $_charset = null;
if ( ! isset( $_charset ) ) {
$alloptions = wp_load_alloptions();
$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
$quote_style = ENT_NOQUOTES;
}
- // Handle double encoding ourselves
- if ( $double_encode ) {
- $string = @htmlspecialchars( $string, $quote_style, $charset );
- } else {
- // Decode & into &
- $string = wp_specialchars_decode( $string, $_quote_style );
-
- // Guarantee every &entity; is valid or re-encode the &
+ if ( ! $double_encode ) {
+ // Guarantee every &entity; is valid, convert &garbage; into &garbage;
+ // This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
$string = wp_kses_normalize_entities( $string );
-
- // Now re-encode everything except &entity;
- $string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE );
-
- for ( $i = 0; $i < count( $string ); $i += 2 )
- $string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset );
-
- $string = implode( '', $string );
}
- // Backwards compatibility
+ $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode );
+
+ // Back-compat.
if ( 'single' === $_quote_style )
$string = str_replace( "'", ''', $string );
*
* @since 2.8.0
*
- * @param string $string The text which is to be decoded.
- * @param mixed $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.
+ * @param string $string 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( $string, $quote_style = ENT_NOQUOTES ) {
*
* @since 2.8.0
*
- * @param string $string The text which is to be checked.
- * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
+ * @staticvar bool $is_utf8
+ * @staticvar bool $utf8_pcre
+ *
+ * @param string $string The text which is to be checked.
+ * @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
* @return string The checked text.
*/
function wp_check_invalid_utf8( $string, $strip = false ) {
}
// Store the site charset as a static to avoid multiple calls to get_option()
- static $is_utf8;
- if ( !isset( $is_utf8 ) ) {
+ static $is_utf8 = null;
+ if ( ! isset( $is_utf8 ) ) {
$is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
}
- if ( !$is_utf8 ) {
+ if ( ! $is_utf8 ) {
return $string;
}
// Check for support for utf8 in the installed PCRE library once and store the result in a static
- static $utf8_pcre;
- if ( !isset( $utf8_pcre ) ) {
+ static $utf8_pcre = null;
+ if ( ! isset( $utf8_pcre ) ) {
$utf8_pcre = @preg_match( '/^./u', 'a' );
}
// We can't demand utf8 in the PCRE installation, so just return the string in those cases
* @since 1.5.0
*
* @param string $utf8_string
- * @param int $length Max length of the string
+ * @param int $length Max length of the string
* @return string String with Unicode encoded for URI.
*/
function utf8_uri_encode( $utf8_string, $length = 0 ) {
$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 ] );
$unicode .= chr($value);
$unicode_length++;
} else {
- if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
+ 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 ) == $num_octets ) {
- if ($num_octets == 3) {
- $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
- $unicode_length += 9;
- } else {
- $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
- $unicode_length += 6;
+ for ( $j = 0; $j < $num_octets; $j++ ) {
+ $unicode .= '%' . dechex( $values[ $j ] );
}
+ $unicode_length += $num_octets * 3;
+
$values = array();
$num_octets = 1;
}
*
* 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 | Π| 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 | Latin small letter t with cedilla |
+ * | U+0164 | Ť | T | Latin capital letter T with caron |
+ * | U+0165 | ť | t | Latin small letter t with caron |
+ * | U+0166 | Ŧ | T | Latin capital letter T with stroke |
+ * | U+0167 | ŧ | t | Latin small letter t with stroke |
+ * | U+0168 | Ũ | U | Latin capital letter U with tilde |
+ * | U+0169 | ũ | u | Latin small letter u with tilde |
+ * | U+016A | Ū | U | Latin capital letter U with macron |
+ * | U+016B | ū | u | Latin small letter u with macron |
+ * | U+016C | Ŭ | U | Latin capital letter U with breve |
+ * | U+016D | ŭ | u | Latin small letter u with breve |
+ * | U+016E | Ů | U | Latin capital letter U with ring above |
+ * | U+016F | ů | u | Latin small letter u with ring above |
+ * | U+0170 | Ű | U | Latin capital letter U with double acute |
+ * | U+0171 | ű | u | Latin small letter u with double acute |
+ * | U+0172 | Ų | U | Latin capital letter U with ogonek |
+ * | U+0173 | ų | u | Latin small letter u with ogonek |
+ * | U+0174 | Ŵ | W | Latin capital letter W with circumflex |
+ * | U+0175 | ŵ | w | Latin small letter w with circumflex |
+ * | U+0176 | Ŷ | Y | Latin capital letter Y with circumflex |
+ * | U+0177 | ŷ | y | Latin small letter y with circumflex |
+ * | U+0178 | Ÿ | Y | Latin capital letter Y with diaeresis |
+ * | U+0179 | Ź | Z | Latin capital letter Z with acute |
+ * | U+017A | ź | z | Latin small letter z with acute |
+ * | U+017B | Ż | Z | Latin capital letter Z with dot above |
+ * | U+017C | ż | z | Latin small letter z with dot above |
+ * | U+017D | Ž | Z | Latin capital letter Z with caron |
+ * | U+017E | ž | z | Latin small letter z with caron |
+ * | U+017F | ſ | s | Latin small letter long s |
+ * | U+01A0 | Ơ | O | Latin capital letter O with horn |
+ * | U+01A1 | ơ | o | Latin small letter o with horn |
+ * | U+01AF | Ư | U | Latin capital letter U with horn |
+ * | U+01B0 | ư | u | Latin small letter u with horn |
+ * | U+01CD | Ǎ | A | Latin capital letter A with caron |
+ * | U+01CE | ǎ | a | Latin small letter a with caron |
+ * | U+01CF | Ǐ | I | Latin capital letter I with caron |
+ * | U+01D0 | ǐ | i | Latin small letter i with caron |
+ * | U+01D1 | Ǒ | O | Latin capital letter O with caron |
+ * | U+01D2 | ǒ | o | Latin small letter o with caron |
+ * | U+01D3 | Ǔ | U | Latin capital letter U with caron |
+ * | U+01D4 | ǔ | u | Latin small letter u with caron |
+ * | U+01D5 | Ǖ | U | Latin capital letter U with diaeresis and macron |
+ * | U+01D6 | ǖ | u | Latin small letter u with diaeresis and macron |
+ * | U+01D7 | Ǘ | U | Latin capital letter U with diaeresis and acute |
+ * | U+01D8 | ǘ | u | Latin small letter u with diaeresis and acute |
+ * | U+01D9 | Ǚ | U | Latin capital letter U with diaeresis and caron |
+ * | U+01DA | ǚ | u | Latin small letter u with diaeresis and caron |
+ * | U+01DB | Ǜ | U | Latin capital letter U with diaeresis and grave |
+ * | U+01DC | ǜ | u | Latin small letter u with diaeresis and grave |
+ *
+ * Decompositions for Latin Extended-B:
+ *
+ * | Code | Glyph | Replacement | Description |
+ * | -------- | ----- | ----------- | ----------------------------------------- |
+ * | U+0218 | Ș | S | Latin capital letter S with comma below |
+ * | U+0219 | ș | s | Latin small letter s with comma below |
+ * | U+021A | Ț | T | Latin capital letter T with comma below |
+ * | U+021B | ț | t | Latin small letter t with comma below |
+ *
+ * Vowels with diacritic (Chinese, Hanyu Pinyin):
+ *
+ * | Code | Glyph | Replacement | Description |
+ * | -------- | ----- | ----------- | ----------------------------------------------------- |
+ * | U+0251 | ɑ | a | Latin small letter alpha |
+ * | U+1EA0 | Ạ | A | Latin capital letter A with dot below |
+ * | U+1EA1 | ạ | a | Latin small letter a with dot below |
+ * | U+1EA2 | Ả | A | Latin capital letter A with hook above |
+ * | U+1EA3 | ả | a | Latin small letter a with hook above |
+ * | U+1EA4 | Ấ | A | Latin capital letter A with circumflex and acute |
+ * | U+1EA5 | ấ | a | Latin small letter a with circumflex and acute |
+ * | U+1EA6 | Ầ | A | Latin capital letter A with circumflex and grave |
+ * | U+1EA7 | ầ | a | Latin small letter a with circumflex and grave |
+ * | U+1EA8 | Ẩ | A | Latin capital letter A with circumflex and hook above |
+ * | U+1EA9 | ẩ | a | Latin small letter a with circumflex and hook above |
+ * | U+1EAA | Ẫ | A | Latin capital letter A with circumflex and tilde |
+ * | U+1EAB | ẫ | a | Latin small letter a with circumflex and tilde |
+ * | U+1EA6 | Ậ | A | Latin capital letter A with circumflex and dot below |
+ * | U+1EAD | ậ | a | Latin small letter a with circumflex and dot below |
+ * | U+1EAE | Ắ | A | Latin capital letter A with breve and acute |
+ * | U+1EAF | ắ | a | Latin small letter a with breve and acute |
+ * | U+1EB0 | Ằ | A | Latin capital letter A with breve and grave |
+ * | U+1EB1 | ằ | a | Latin small letter a with breve and grave |
+ * | U+1EB2 | Ẳ | A | Latin capital letter A with breve and hook above |
+ * | U+1EB3 | ẳ | a | Latin small letter a with breve and hook above |
+ * | U+1EB4 | Ẵ | A | Latin capital letter A with breve and tilde |
+ * | U+1EB5 | ẵ | a | Latin small letter a with breve and tilde |
+ * | U+1EB6 | Ặ | A | Latin capital letter A with breve and dot below |
+ * | U+1EB7 | ặ | a | Latin small letter a with breve and dot below |
+ * | U+1EB8 | Ẹ | E | Latin capital letter E with dot below |
+ * | U+1EB9 | ẹ | e | Latin small letter e with dot below |
+ * | U+1EBA | Ẻ | E | Latin capital letter E with hook above |
+ * | U+1EBB | ẻ | e | Latin small letter e with hook above |
+ * | U+1EBC | Ẽ | E | Latin capital letter E with tilde |
+ * | U+1EBD | ẽ | e | Latin small letter e with tilde |
+ * | U+1EBE | Ế | E | Latin capital letter E with circumflex and acute |
+ * | U+1EBF | ế | e | Latin small letter e with circumflex and acute |
+ * | U+1EC0 | Ề | E | Latin capital letter E with circumflex and grave |
+ * | U+1EC1 | ề | e | Latin small letter e with circumflex and grave |
+ * | U+1EC2 | Ể | E | Latin capital letter E with circumflex and hook above |
+ * | U+1EC3 | ể | e | Latin small letter e with circumflex and hook above |
+ * | U+1EC4 | Ễ | E | Latin capital letter E with circumflex and tilde |
+ * | U+1EC5 | ễ | e | Latin small letter e with circumflex and tilde |
+ * | U+1EC6 | Ệ | E | Latin capital letter E with circumflex and dot below |
+ * | U+1EC7 | ệ | e | Latin small letter e with circumflex and dot below |
+ * | U+1EC8 | Ỉ | I | Latin capital letter I with hook above |
+ * | U+1EC9 | ỉ | i | Latin small letter i with hook above |
+ * | U+1ECA | Ị | I | Latin capital letter I with dot below |
+ * | U+1ECB | ị | i | Latin small letter i with dot below |
+ * | U+1ECC | Ọ | O | Latin capital letter O with dot below |
+ * | U+1ECD | ọ | o | Latin small letter o with dot below |
+ * | U+1ECE | Ỏ | O | Latin capital letter O with hook above |
+ * | U+1ECF | ỏ | o | Latin small letter o with hook above |
+ * | U+1ED0 | Ố | O | Latin capital letter O with circumflex and acute |
+ * | U+1ED1 | ố | o | Latin small letter o with circumflex and acute |
+ * | U+1ED2 | Ồ | O | Latin capital letter O with circumflex and grave |
+ * | U+1ED3 | ồ | o | Latin small letter o with circumflex and grave |
+ * | U+1ED4 | Ổ | O | Latin capital letter O with circumflex and hook above |
+ * | U+1ED5 | ổ | o | Latin small letter o with circumflex and hook above |
+ * | U+1ED6 | Ỗ | O | Latin capital letter O with circumflex and tilde |
+ * | U+1ED7 | ỗ | o | Latin small letter o with circumflex and tilde |
+ * | U+1ED8 | Ộ | O | Latin capital letter O with circumflex and dot below |
+ * | U+1ED9 | ộ | o | Latin small letter o with circumflex and dot below |
+ * | U+1EDA | Ớ | O | Latin capital letter O with horn and acute |
+ * | U+1EDB | ớ | o | Latin small letter o with horn and acute |
+ * | U+1EDC | Ờ | O | Latin capital letter O with horn and grave |
+ * | U+1EDD | ờ | o | Latin small letter o with horn and grave |
+ * | U+1EDE | Ở | O | Latin capital letter O with horn and hook above |
+ * | U+1EDF | ở | o | Latin small letter o with horn and hook above |
+ * | U+1EE0 | Ỡ | O | Latin capital letter O with horn and tilde |
+ * | U+1EE1 | ỡ | o | Latin small letter o with horn and tilde |
+ * | U+1EE2 | Ợ | O | Latin capital letter O with horn and dot below |
+ * | U+1EE3 | ợ | o | Latin small letter o with horn and dot below |
+ * | U+1EE4 | Ụ | U | Latin capital letter U with dot below |
+ * | U+1EE5 | ụ | u | Latin small letter u with dot below |
+ * | U+1EE6 | Ủ | U | Latin capital letter U with hook above |
+ * | U+1EE7 | ủ | u | Latin small letter u with hook above |
+ * | U+1EE8 | Ứ | U | Latin capital letter U with horn and acute |
+ * | U+1EE9 | ứ | u | Latin small letter u with horn and acute |
+ * | U+1EEA | Ừ | U | Latin capital letter U with horn and grave |
+ * | U+1EEB | ừ | u | Latin small letter u with horn and grave |
+ * | U+1EEC | Ử | U | Latin capital letter U with horn and hook above |
+ * | U+1EED | ử | u | Latin small letter u with horn and hook above |
+ * | U+1EEE | Ữ | U | Latin capital letter U with horn and tilde |
+ * | U+1EEF | ữ | u | Latin small letter u with horn and tilde |
+ * | U+1EF0 | Ự | U | Latin capital letter U with horn and dot below |
+ * | U+1EF1 | ự | u | Latin small letter u with horn and dot below |
+ * | U+1EF2 | Ỳ | Y | Latin capital letter Y with grave |
+ * | U+1EF3 | ỳ | y | Latin small letter y with grave |
+ * | U+1EF4 | Ỵ | Y | Latin capital letter Y with dot below |
+ * | U+1EF5 | ỵ | y | Latin small letter y with dot below |
+ * | U+1EF6 | Ỷ | Y | Latin capital letter Y with hook above |
+ * | U+1EF7 | ỷ | y | Latin small letter y with hook above |
+ * | U+1EF8 | Ỹ | Y | Latin capital letter Y with tilde |
+ * | U+1EF9 | ỹ | y | Latin small letter y with tilde |
+ *
+ * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`),
+ * and German (Switzerland) informal (`de_CH_informal`) locales:
+ *
+ * | Code | Glyph | Replacement | Description |
+ * | -------- | ----- | ----------- | --------------------------------------- |
+ * | U+00C4 | Ä | Ae | Latin capital letter A with diaeresis |
+ * | U+00E4 | ä | ae | Latin small letter a with diaeresis |
+ * | U+00D6 | Ö | Oe | Latin capital letter O with diaeresis |
+ * | U+00F6 | ö | oe | Latin small letter o with diaeresis |
+ * | U+00DC | Ü | Ue | Latin capital letter U with diaeresis |
+ * | U+00FC | ü | ue | Latin small letter u with diaeresis |
+ * | U+00DF | ß | ss | Latin small letter sharp s |
+ *
+ * Danish (`da_DK`) locale:
+ *
+ * | Code | Glyph | Replacement | Description |
+ * | -------- | ----- | ----------- | --------------------------------------- |
+ * | U+00C6 | Æ | Ae | Latin capital letter AE |
+ * | U+00E6 | æ | ae | Latin small letter ae |
+ * | U+00D8 | Ø | Oe | Latin capital letter O with stroke |
+ * | U+00F8 | ø | oe | Latin small letter o with stroke |
+ * | U+00C5 | Å | Aa | Latin capital letter A with ring above |
+ * | U+00E5 | å | aa | Latin small letter a with ring above |
+ *
+ * Catalan (`ca`) locale:
+ *
+ * | Code | Glyph | Replacement | Description |
+ * | -------- | ----- | ----------- | --------------------------------------- |
+ * | U+00B7 | l·l | ll | Flown dot (between two Ls) |
+ *
* @since 1.2.1
+ * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`.
*
* @param string $string Text that might have accent characters
* @return string Filtered string with replaced "nice" characters.
*/
-function remove_accents($string) {
+function remove_accents( $string ) {
if ( !preg_match('/[\x80-\xff]/', $string) )
return $string;
// Used for locale-specific rules
$locale = get_locale();
- if ( 'de_DE' == $locale ) {
+ if ( 'de_DE' == $locale || 'de_DE_formal' == $locale || 'de_CH' == $locale || 'de_CH_informal' == $locale ) {
$chars[ chr(195).chr(132) ] = 'Ae';
$chars[ chr(195).chr(164) ] = 'ae';
$chars[ chr(195).chr(150) ] = 'Oe';
$chars[ chr(195).chr(184) ] = 'oe';
$chars[ chr(195).chr(133) ] = 'Aa';
$chars[ chr(195).chr(165) ] = 'aa';
+ } elseif ( 'ca' === $locale ) {
+ $chars[ chr(108).chr(194).chr(183).chr(108) ] = 'll';
}
$string = strtr($string, $chars);
} else {
+ $chars = array();
// Assume ISO-8859-1 if not UTF-8
$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
$string = strtr($string, $chars['in'], $chars['out']);
+ $double_chars = array();
$double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
$string = str_replace($double_chars['in'], $double_chars['out'], $string);
* operating systems and special characters requiring special escaping
* to manipulate at the command line. Replaces spaces and consecutive
* dashes with a single dash. Trims period, dash and underscore from beginning
- * and end of filename.
+ * and end of filename. It is not guaranteed that this function will return a
+ * filename that is allowed to be uploaded.
*
* @since 2.1.0
*
*/
function sanitize_file_name( $filename ) {
$filename_raw = $filename;
- $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));
+ $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%", "+", chr(0));
/**
- * Filter the list of characters to remove from a filename.
+ * Filters the list of characters to remove from a filename.
*
* @since 2.8.0
*
*/
$special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
$filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
- $filename = str_replace($special_chars, '', $filename);
- $filename = preg_replace('/[\s-]+/', '-', $filename);
- $filename = trim($filename, '.-_');
+ $filename = str_replace( $special_chars, '', $filename );
+ $filename = str_replace( array( '%20', '+' ), '-', $filename );
+ $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
+ $filename = trim( $filename, '.-_' );
+
+ if ( false === strpos( $filename, '.' ) ) {
+ $mime_types = wp_get_mime_types();
+ $filetype = wp_check_filetype( 'test.' . $filename, $mime_types );
+ if ( $filetype['ext'] === $filename ) {
+ $filename = 'unnamed-file.' . $filetype['ext'];
+ }
+ }
// Split the filename into a base and extension[s]
$parts = explode('.', $filename);
// Return if only one extension
if ( count( $parts ) <= 2 ) {
/**
- * Filter a sanitized filename string.
+ * Filters a sanitized filename string.
*
* @since 2.8.0
*
* Removes tags, octets, entities, and if strict is enabled, will only keep
* alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
* raw username (the username in the parameter), and the value of $strict as
- * parameters for the 'sanitize_user' filter.
+ * parameters for the {@see 'sanitize_user'} filter.
*
* @since 2.0.0
*
* @param string $username The username to be sanitized.
- * @param bool $strict If set limits $username to specific characters. Default false.
+ * @param bool $strict If set limits $username to specific characters. Default false.
* @return string The sanitized username, after passing through filters.
*/
function sanitize_user( $username, $strict = false ) {
$username = preg_replace( '|\s+|', ' ', $username );
/**
- * Filter a sanitized username string.
+ * Filters a sanitized username string.
*
* @since 2.0.1
*
$key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
/**
- * Filter a sanitized key string.
+ * Filters a sanitized key string.
*
* @since 3.0.0
*
*
* @since 1.0.0
*
- * @param string $title The string to be sanitized.
+ * @param string $title The string to be sanitized.
* @param string $fallback_title Optional. A title to use if $title is empty.
- * @param string $context Optional. The operation for which the string is sanitized
+ * @param string $context Optional. The operation for which the string is sanitized
* @return string The sanitized string.
*/
function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
$title = remove_accents($title);
/**
- * Filter a sanitized title string.
+ * Filters a sanitized title string.
*
* @since 1.2.0
*
* Used for querying the database for a value from URL.
*
* @since 3.1.0
- * @uses sanitize_title()
*
* @param string $title The string to be sanitized.
* @return string The sanitized string.
*
* @since 1.2.0
*
- * @param string $title The title to be sanitized.
+ * @param string $title The title to be sanitized.
* @param string $raw_title Optional. Not used.
- * @param string $context Optional. The operation for which the string is sanitized.
+ * @param string $context Optional. The operation for which the string is sanitized.
* @return string The sanitized title.
*/
function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
}
$title = strtolower($title);
- $title = preg_replace('/&.+?;/', '', $title); // kill entities
- $title = str_replace('.', '-', $title);
if ( 'save' == $context ) {
// Convert nbsp, ndash and mdash to hyphens
$title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
+ // Convert nbsp, ndash and mdash HTML entities to hyphens
+ $title = str_replace( array( ' ', ' ', '–', '–', '—', '—' ), '-', $title );
// Strip these characters entirely
$title = str_replace( array(
$title = str_replace( '%c3%97', 'x', $title );
}
+ $title = preg_replace('/&.+?;/', '', $title); // kill entities
+ $title = str_replace('.', '-', $title);
+
$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
$title = preg_replace('/\s+/', '-', $title);
$title = preg_replace('|-+|', '-', $title);
}
/**
- * Ensures a string is a valid SQL order by clause.
+ * Ensures a string is a valid SQL 'order by' clause.
*
- * Accepts one or more columns, with or without ASC/DESC, and also accepts
- * RAND().
+ * Accepts one or more columns, with or without a sort order (ASC / DESC).
+ * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
+ *
+ * Also accepts 'RAND()'.
*
* @since 2.5.1
*
- * @param string $orderby Order by string to be checked.
- * @return string|bool Returns the order by clause if it is a match, false otherwise.
+ * @param string $orderby Order by clause to be validated.
+ * @return string|false Returns $orderby if valid, false otherwise.
*/
-function sanitize_sql_orderby( $orderby ){
- preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);
- if ( !$obmatches )
- return false;
- return $orderby;
+function sanitize_sql_orderby( $orderby ) {
+ if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) {
+ return $orderby;
+ }
+ return false;
}
/**
*
* @since 2.8.0
*
- * @param string $class The classname to be sanitized
- * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string.
+ * @param string $class The classname to be sanitized
+ * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
* Defaults to an empty string.
* @return string The sanitized value
*/
//Limit to A-Z,a-z,0-9,_,-
$sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
- if ( '' == $sanitized )
- $sanitized = $fallback;
-
+ if ( '' == $sanitized && $fallback ) {
+ return sanitize_html_class( $fallback );
+ }
/**
- * Filter a sanitized HTML class string.
+ * Filters a sanitized HTML class string.
*
* @since 2.8.0
*
}
/**
- * Converts a number of characters from a string.
- *
- * Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are
- * converted into correct XHTML and Unicode characters are converted to the
- * valid range.
+ * Converts lone & characters into `&` (a.k.a. `&`)
*
* @since 0.71
*
- * @param string $content String of characters to be converted.
+ * @param string $content String of characters to be converted.
* @param string $deprecated Not used.
* @return string Converted string.
*/
-function convert_chars($content, $deprecated = '') {
- if ( !empty( $deprecated ) )
+function convert_chars( $content, $deprecated = '' ) {
+ if ( ! empty( $deprecated ) ) {
_deprecated_argument( __FUNCTION__, '0.71' );
+ }
- // Translation of invalid Unicode references range to valid range
- $wp_htmltranswinuni = array(
- '€' => '€', // the Euro sign
- '' => '',
- '‚' => '‚', // these are Windows CP1252 specific characters
- 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
- '„' => '„',
- '…' => '…',
- '†' => '†',
- '‡' => '‡',
- 'ˆ' => 'ˆ',
- '‰' => '‰',
- 'Š' => 'Š',
- '‹' => '‹',
- 'Œ' => 'Œ',
- '' => '',
- 'Ž' => 'Ž',
- '' => '',
- '' => '',
- '‘' => '‘',
- '’' => '’',
- '“' => '“',
- '”' => '”',
- '•' => '•',
- '–' => '–',
- '—' => '—',
- '˜' => '˜',
- '™' => '™',
- 'š' => 'š',
- '›' => '›',
- 'œ' => 'œ',
- '' => '',
- 'ž' => 'ž',
- 'Ÿ' => 'Ÿ'
- );
-
- // Remove metadata tags
- $content = preg_replace('/<title>(.+?)<\/title>/','',$content);
- $content = preg_replace('/<category>(.+?)<\/category>/','',$content);
+ if ( strpos( $content, '&' ) !== false ) {
+ $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content );
+ }
- // Converts lone & characters into & (a.k.a. &)
- $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);
+ return $content;
+}
- // Fix Word pasting
- $content = strtr($content, $wp_htmltranswinuni);
+/**
+ * Converts invalid Unicode references range to valid range.
+ *
+ * @since 4.3.0
+ *
+ * @param string $content String with entities that need converting.
+ * @return string Converted string.
+ */
+function convert_invalid_entities( $content ) {
+ $wp_htmltranswinuni = array(
+ '€' => '€', // the Euro sign
+ '' => '',
+ '‚' => '‚', // these are Windows CP1252 specific characters
+ 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
+ '„' => '„',
+ '…' => '…',
+ '†' => '†',
+ '‡' => '‡',
+ 'ˆ' => 'ˆ',
+ '‰' => '‰',
+ 'Š' => 'Š',
+ '‹' => '‹',
+ 'Œ' => 'Œ',
+ '' => '',
+ 'Ž' => 'Ž',
+ '' => '',
+ '' => '',
+ '‘' => '‘',
+ '’' => '’',
+ '“' => '“',
+ '”' => '”',
+ '•' => '•',
+ '–' => '–',
+ '—' => '—',
+ '˜' => '˜',
+ '™' => '™',
+ 'š' => 'š',
+ '›' => '›',
+ 'œ' => 'œ',
+ '' => '',
+ 'ž' => 'ž',
+ 'Ÿ' => 'Ÿ'
+ );
- // Just a little XHTML help
- $content = str_replace('<br>', '<br />', $content);
- $content = str_replace('<hr>', '<hr />', $content);
+ if ( strpos( $content, '' ) !== false ) {
+ $content = strtr( $content, $wp_htmltranswinuni );
+ }
return $content;
}
*
* @since 0.71
*
- * @param string $text Text to be balanced
- * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
+ * @param string $text Text to be balanced
+ * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
* @return string Balanced text
*/
function balanceTags( $text, $force = false ) {
if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
$tag = strtolower(substr($regex[1],1));
// if too many closing tags
- if( $stacksize <= 0 ) {
+ if ( $stacksize <= 0 ) {
$tag = '';
// or close to be safe $tag = '/' . $tag;
}
// if stacktop value = tag close value then pop
- else if ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
+ elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
$tag = '</' . $tag . '>'; // Close Tag
// Pop
array_pop( $tagstack );
// Attributes
$attributes = $regex[2];
- if( ! empty( $attributes ) && $attributes[0] != '>' )
+ if ( ! empty( $attributes ) && $attributes[0] != '>' )
$attributes = ' ' . $attributes;
$tag = '<' . $tag . $attributes . '>';
* Acts on text which is about to be edited.
*
* The $content is run through esc_textarea(), which uses htmlspecialchars()
- * to convert special characters to HTML entities. If $richedit is set to true,
- * it is simply a holder for the 'format_to_edit' filter.
+ * to convert special characters to HTML entities. If `$richedit` is set to true,
+ * it is simply a holder for the {@see 'format_to_edit'} filter.
*
* @since 0.71
+ * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
*
- * @param string $content The text about to be edited.
- * @param bool $richedit Whether the $content should not pass through htmlspecialchars(). Default false (meaning it will be passed).
+ * @param string $content The text about to be edited.
+ * @param bool $rich_text Optional. Whether `$content` should be considered rich text,
+ * in which case it would not be passed through esc_textarea().
+ * Default false.
* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
*/
-function format_to_edit( $content, $richedit = false ) {
+function format_to_edit( $content, $rich_text = false ) {
/**
- * Filter the text to be formatted for editing.
+ * Filters the text to be formatted for editing.
*
* @since 1.2.0
*
* @param string $content The text, prior to formatting for editing.
*/
$content = apply_filters( 'format_to_edit', $content );
- if ( ! $richedit )
+ if ( ! $rich_text )
$content = esc_textarea( $content );
return $content;
}
*
* @since 0.71
*
- * @param mixed $number Number to append zeros to if not greater than threshold.
- * @param int $threshold Digit places number needs to be to not have zeros added.
+ * @param int $number Number to append zeros to if not greater than threshold.
+ * @param int $threshold Digit places number needs to be to not have zeros added.
* @return string Adds leading zeros to number if needed.
*/
-function zeroise($number, $threshold) {
- return sprintf('%0'.$threshold.'s', $number);
+function zeroise( $number, $threshold ) {
+ return sprintf( '%0' . $threshold . 's', $number );
}
/**
* @param string $string Value to which backslashes will be added.
* @return string String with backslashes inserted.
*/
-function backslashit($string) {
+function backslashit( $string ) {
if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' )
$string = '\\\\' . $string;
return addcslashes( $string, 'A..Za..z' );
* Adds slashes to escape strings.
*
* Slashes will first be removed if magic_quotes_gpc is set, see {@link
- * http://www.php.net/magic_quotes} for more details.
+ * https://secure.php.net/magic_quotes} for more details.
*
* @since 0.71
*
}
/**
- * Navigates through an array and removes slashes from the values.
- *
- * If an array is passed, the array_map() function causes a callback to pass the
- * value back to the function. The slashes from this value will removed.
+ * Navigates through an array, object, or scalar, and removes slashes from the values.
*
* @since 2.0.0
*
* @param mixed $value The value to be stripped.
* @return mixed Stripped value.
*/
-function stripslashes_deep($value) {
- if ( is_array($value) ) {
- $value = array_map('stripslashes_deep', $value);
- } elseif ( is_object($value) ) {
- $vars = get_object_vars( $value );
- foreach ($vars as $key=>$data) {
- $value->{$key} = stripslashes_deep( $data );
- }
- } elseif ( is_string( $value ) ) {
- $value = stripslashes($value);
- }
-
- return $value;
+function stripslashes_deep( $value ) {
+ return map_deep( $value, 'stripslashes_from_strings_only' );
}
/**
- * Navigates through an array and encodes the values to be used in a URL.
+ * Callback function for `stripslashes_deep()` which strips slashes from strings.
+ *
+ * @since 4.4.0
*
+ * @param mixed $value The array or string to be stripped.
+ * @return mixed $value The stripped value.
+ */
+function stripslashes_from_strings_only( $value ) {
+ return is_string( $value ) ? stripslashes( $value ) : $value;
+}
+
+/**
+ * Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
*
* @since 2.2.0
*
- * @param array|string $value The array or string to be encoded.
- * @return array|string $value The encoded array (or string from the callback).
+ * @param mixed $value The array or string to be encoded.
+ * @return mixed $value The encoded value.
*/
-function urlencode_deep($value) {
- $value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value);
- return $value;
+function urlencode_deep( $value ) {
+ return map_deep( $value, 'urlencode' );
}
/**
- * Navigates through an array and raw encodes the values to be used in a URL.
+ * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
*
* @since 3.4.0
*
- * @param array|string $value The array or string to be encoded.
- * @return array|string $value The encoded array (or string from the callback).
+ * @param mixed $value The array or string to be encoded.
+ * @return mixed $value The encoded value.
*/
function rawurlencode_deep( $value ) {
- return is_array( $value ) ? array_map( 'rawurlencode_deep', $value ) : rawurlencode( $value );
+ return map_deep( $value, 'rawurlencode' );
+}
+
+/**
+ * Navigates through an array, object, or scalar, and decodes URL-encoded values
+ *
+ * @since 4.4.0
+ *
+ * @param mixed $value The array or string to be decoded.
+ * @return mixed $value The decoded value.
+ */
+function urldecode_deep( $value ) {
+ return map_deep( $value, 'urldecode' );
}
/**
* @since 0.71
*
* @param string $email_address Email address.
- * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
+ * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
* @return string Converted email address.
*/
function antispambot( $email_address, $hex_encoding = 0 ) {
$email_no_spam_address = '';
- for ( $i = 0; $i < strlen( $email_address ); $i++ ) {
+ for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
$j = rand( 0, 1 + $hex_encoding );
if ( $j == 0 ) {
$email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
}
}
- $email_no_spam_address = str_replace( '@', '@', $email_no_spam_address );
-
- return $email_no_spam_address;
+ return str_replace( '@', '@', $email_no_spam_address );
}
/**
* Callback to convert URI match to HTML A element.
*
- * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
- * make_clickable()}.
+ * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
*
* @since 2.3.2
* @access private
* @param array $matches Single Regex Match.
* @return string HTML A element with URI address.
*/
-function _make_url_clickable_cb($matches) {
+function _make_url_clickable_cb( $matches ) {
$url = $matches[2];
if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
/**
* Callback to convert URL match to HTML A element.
*
- * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
- * make_clickable()}.
+ * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
*
* @since 2.3.2
* @access private
* @param array $matches Single Regex Match.
* @return string HTML A element with URL address.
*/
-function _make_web_ftp_clickable_cb($matches) {
+function _make_web_ftp_clickable_cb( $matches ) {
$ret = '';
$dest = $matches[2];
$dest = 'http://' . $dest;
- $dest = esc_url($dest);
- if ( empty($dest) )
- return $matches[0];
// removed trailing [.,;:)] from URL
if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
$ret = substr($dest, -1);
$dest = substr($dest, 0, strlen($dest)-1);
}
+
+ $dest = esc_url($dest);
+ if ( empty($dest) )
+ return $matches[0];
+
return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
}
/**
* Callback to convert email address match to HTML A element.
*
- * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
- * make_clickable()}.
+ * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
*
* @since 2.3.2
* @access private
* @param array $matches Single Regex Match.
* @return string HTML A element with email address.
*/
-function _make_email_clickable_cb($matches) {
+function _make_email_clickable_cb( $matches ) {
$email = $matches[2] . '@' . $matches[3];
return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
}
$nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
foreach ( $textarr as $piece ) {
- if ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) )
+ if ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) || preg_match( '|^<script[\s>]|i', $piece ) || preg_match( '|^<style[\s>]|i', $piece ) )
$nested_code_pre++;
- elseif ( ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) ) && $nested_code_pre )
+ elseif ( $nested_code_pre && ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) || '</script>' === strtolower( $piece ) || '</style>' === strtolower( $piece ) ) )
$nested_code_pre--;
if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
}
// Cleanup of accidental links within links
- $r = preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
- return $r;
+ return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
}
/**
*
* Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
*
- * <code>
- * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
- * array (
- * 0 => '1234 67890 ', // 11 characters: Perfect split
- * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
- * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
- * 3 => '1234 890 ', // 11 characters: Perfect split
- * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
- * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
- * 6 => ' 45678 ', // 11 characters: Perfect split
- * 7 => '1 3 5 7 9', // 9 characters: End of $string
- * );
- * </code>
+ * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
+ * array (
+ * 0 => '1234 67890 ', // 11 characters: Perfect split
+ * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
+ * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
+ * 3 => '1234 890 ', // 11 characters: Perfect split
+ * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
+ * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
+ * 6 => ' 45678 ', // 11 characters: Perfect split
+ * 7 => '1 3 5 7 90 ', // 11 characters: End of $string
+ * );
*
* @since 3.4.0
* @access private
*
* @param string $string The string to split.
- * @param int $goal The desired chunk length.
+ * @param int $goal The desired chunk length.
* @return array Numeric array of chunks.
*/
function _split_str_by_whitespace( $string, $goal ) {
// This is a pre save filter, so text is already escaped.
$text = stripslashes($text);
$text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
- $text = wp_slash($text);
- return $text;
+ return wp_slash( $text );
}
/**
*/
function wp_rel_nofollow_callback( $matches ) {
$text = $matches[1];
- $text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text);
- return "<a $text rel=\"nofollow\">";
+ $atts = shortcode_parse_atts( $matches[1] );
+ $rel = 'nofollow';
+
+ if ( preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'http' ) ) . ')%i', $text ) ||
+ preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'https' ) ) . ')%i', $text )
+ ) {
+ return "<a $text>";
+ }
+
+ if ( ! empty( $atts['rel'] ) ) {
+ $parts = array_map( 'trim', explode( ' ', $atts['rel'] ) );
+ if ( false === array_search( 'nofollow', $parts ) ) {
+ $parts[] = 'nofollow';
+ }
+ $rel = implode( ' ', $parts );
+ unset( $atts['rel'] );
+
+ $html = '';
+ foreach ( $atts as $name => $value ) {
+ $html .= "{$name}=\"$value\" ";
+ }
+ $text = trim( $html );
+ }
+ return "<a $text rel=\"$rel\">";
}
/**
* Convert one smiley code to the icon graphic file equivalent.
*
- * Callback handler for {@link convert_smilies()}.
+ * Callback handler for convert_smilies().
+ *
* Looks up one smiley code in the $wpsmiliestrans global array and returns an
- * <img> string for that smiley.
+ * `<img>` string for that smiley.
*
- * @global array $wpsmiliestrans
* @since 2.8.0
*
+ * @global array $wpsmiliestrans
+ *
* @param array $matches Single match. Smiley code to convert to image.
* @return string Image string for smiley.
*/
$smiley = trim( reset( $matches ) );
$img = $wpsmiliestrans[ $smiley ];
+ $matches = array();
+ $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
+ $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
+
+ // Don't convert smilies that aren't images - they're probably emoji.
+ if ( ! in_array( $ext, $image_exts ) ) {
+ return $img;
+ }
+
/**
- * Filter the Smiley image URL before it's used in the image element.
+ * Filters the Smiley image URL before it's used in the image element.
*
* @since 2.9.0
*
*/
$src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
- return sprintf( ' <img src="%s" alt="%s" class="wp-smiley" /> ', esc_url( $src_url ), esc_attr( $smiley ) );
+ return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
}
/**
* used in the function isn't empty.
*
* @since 0.71
- * @uses $wp_smiliessearch
+ *
+ * @global string|array $wp_smiliessearch
*
* @param string $text Content to convert smilies from text.
* @return string Converted content with text smilies replaced with images.
*
* @since 0.71
*
- * @param string $email Email address to verify.
- * @param boolean $deprecated Deprecated.
+ * @param string $email Email address to verify.
+ * @param bool $deprecated Deprecated.
* @return string|bool Either false or the valid email address.
*/
function is_email( $email, $deprecated = false ) {
if ( ! empty( $deprecated ) )
- _deprecated_argument( __FUNCTION__, '3.0' );
+ _deprecated_argument( __FUNCTION__, '3.0.0' );
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
/**
- * Filter whether an email address is valid.
+ * Filters whether an email address is valid.
*
* This filter is evaluated under several different contexts, such as 'email_too_short',
* 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
*
* @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
* @param string $email The email address being checked.
- * @param string $message An explanatory message to the user.
* @param string $context Context under which the email was tested.
*/
return apply_filters( 'is_email', false, $email, 'email_too_short' );
* @param string $string Subject line
* @return string Converted string to ASCII
*/
-function wp_iso_descrambler($string) {
+function wp_iso_descrambler( $string ) {
/* this may only work with iso-8859-1, I'm afraid */
if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
return $string;
} else {
$subject = str_replace('_', ' ', $matches[2]);
- $subject = preg_replace_callback('#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject);
- return $subject;
+ return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
}
}
* @access private
*
* @param array $match The preg_replace_callback matches array
- * @return array Converted chars
+ * @return string Converted chars
*/
function _wp_iso_convert( $match ) {
return chr( hexdec( strtolower( $match[1] ) ) );
*
* @since 1.2.0
*
- * @uses get_option() to retrieve the value of 'gmt_offset'.
* @param string $string The date to be converted.
* @param string $format The format string for the returned date (default is Y-m-d H:i:s)
* @return string GMT version of the date provided.
$tz = get_option( 'timezone_string' );
if ( $tz ) {
$datetime = date_create( $string, new DateTimeZone( $tz ) );
- if ( ! $datetime )
+ if ( ! $datetime ) {
return gmdate( $format, 0 );
+ }
$datetime->setTimezone( new DateTimeZone( 'UTC' ) );
$string_gmt = $datetime->format( $format );
} else {
- if ( ! preg_match( '#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches ) )
- return gmdate( $format, 0 );
+ if ( ! preg_match( '#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches ) ) {
+ $datetime = strtotime( $string );
+ if ( false === $datetime ) {
+ return gmdate( $format, 0 );
+ }
+ return gmdate( $format, $datetime );
+ }
$string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
$string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
}
* @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
* @return int|float The offset in seconds.
*/
-function iso8601_timezone_to_offset($timezone) {
+function iso8601_timezone_to_offset( $timezone ) {
// $timezone is either 'Z' or '[+|-]hhmm'
if ($timezone == 'Z') {
$offset = 0;
*
* @since 1.5.0
*
- * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
- * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
+ * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}.
+ * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
* @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
*/
-function iso8601_to_datetime($date_string, $timezone = 'user') {
+function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
$timezone = strtolower($timezone);
if ($timezone == 'gmt') {
return gmdate('Y-m-d H:i:s', $timestamp);
- } else if ($timezone == 'user') {
+ } elseif ($timezone == 'user') {
return preg_replace('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', '$1-$2-$3 $4:$5:$6', $date_string);
}
}
/**
- * Adds a element attributes to open links in new windows.
- *
- * Comment text in popup windows should be filtered through this. Right now it's
- * a moderately dumb function, ideally it would detect whether a target or rel
- * attribute was already there and adjust its actions accordingly.
+ * Strips out all characters that are not allowable in an email.
*
- * @since 0.71
- *
- * @param string $text Content to replace links to open in a new window.
- * @return string Content that has filtered links.
- */
-function popuplinks($text) {
- $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
- return $text;
-}
-
-/**
- * Strips out all characters that are not allowable in an email.
- *
- * @since 1.5.0
+ * @since 1.5.0
*
* @param string $email Email address to filter.
* @return string Filtered email address.
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
/**
- * Filter a sanitized email address.
+ * Filters a sanitized email address.
*
* This filter is evaluated under several contexts, including 'email_too_short',
* 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
* @since 1.5.0
*
* @param int $from Unix timestamp from which the difference begins.
- * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
+ * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
* @return string Human readable time difference.
*/
function human_time_diff( $from, $to = '' ) {
- if ( empty( $to ) )
+ if ( empty( $to ) ) {
$to = time();
+ }
$diff = (int) abs( $to - $from );
if ( $days <= 1 )
$days = 1;
$since = sprintf( _n( '%s day', '%s days', $days ), $days );
- } elseif ( $diff < 30 * DAY_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
+ } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
$weeks = round( $diff / WEEK_IN_SECONDS );
if ( $weeks <= 1 )
$weeks = 1;
$since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
- } elseif ( $diff < YEAR_IN_SECONDS && $diff >= 30 * DAY_IN_SECONDS ) {
- $months = round( $diff / ( 30 * DAY_IN_SECONDS ) );
+ } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
+ $months = round( $diff / MONTH_IN_SECONDS );
if ( $months <= 1 )
$months = 1;
$since = sprintf( _n( '%s month', '%s months', $months ), $months );
$since = sprintf( _n( '%s year', '%s years', $years ), $years );
}
- return $since;
+ /**
+ * Filters the human readable difference between two timestamps.
+ *
+ * @since 4.0.0
+ *
+ * @param string $since The difference in human readable text.
+ * @param int $diff The difference in seconds.
+ * @param int $from Unix timestamp from which the difference begins.
+ * @param int $to Unix timestamp to end the time difference.
+ */
+ return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
}
/**
* that, then the string ' […]' will be appended to the excerpt. If the string
* is less than 55 words, then the content will be returned as is.
*
- * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
- * The ' […]' string can be modified by plugins/themes using the excerpt_more filter
+ * The 55 word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter
+ * The ' […]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter
*
* @since 1.5.0
*
* @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
* @return string The excerpt.
*/
-function wp_trim_excerpt($text = '') {
+function wp_trim_excerpt( $text = '' ) {
$raw_excerpt = $text;
if ( '' == $text ) {
$text = get_the_content('');
$text = str_replace(']]>', ']]>', $text);
/**
- * Filter the number of words in an excerpt.
+ * Filters the number of words in an excerpt.
*
* @since 2.7.0
*
*/
$excerpt_length = apply_filters( 'excerpt_length', 55 );
/**
- * Filter the string in the "more" link displayed after a trimmed excerpt.
+ * Filters the string in the "more" link displayed after a trimmed excerpt.
*
* @since 2.9.0
*
$text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
}
/**
- * Filter the trimmed excerpt string.
+ * Filters the trimmed excerpt string.
*
* @since 2.8.0
*
*
* @since 3.3.0
*
- * @param string $text Text to trim.
- * @param int $num_words Number of words. Default 55.
- * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
+ * @param string $text Text to trim.
+ * @param int $num_words Number of words. Default 55.
+ * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
* @return string Trimmed text.
*/
function wp_trim_words( $text, $num_words = 55, $more = null ) {
- if ( null === $more )
+ if ( null === $more ) {
$more = __( '…' );
+ }
+
$original_text = $text;
$text = wp_strip_all_tags( $text );
- /* translators: If your word count is based on single characters (East Asian characters),
- enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
- if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
+
+ /*
+ * translators: If your word count is based on single characters (e.g. East Asian characters),
+ * enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
+ * Do not translate into your own language.
+ */
+ if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
$text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
preg_match_all( '/./u', $text, $words_array );
$words_array = array_slice( $words_array[0], 0, $num_words + 1 );
$words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
$sep = ' ';
}
+
if ( count( $words_array ) > $num_words ) {
array_pop( $words_array );
$text = implode( $sep, $words_array );
} else {
$text = implode( $sep, $words_array );
}
+
/**
- * Filter the text content after words have been trimmed.
+ * Filters the text content after words have been trimmed.
*
* @since 3.3.0
*
* @param string $text The text within which entities will be converted.
* @return string Text with converted entities.
*/
-function ent2ncr($text) {
+function ent2ncr( $text ) {
/**
- * Filter text before named entities are converted into numbered entities.
+ * Filters text before named entities are converted into numbered entities.
*
* A non-null string must be returned for the filter to be evaluated.
*
* @param string $text The text prior to entity conversion.
*/
$filtered = apply_filters( 'pre_ent2ncr', null, $text );
- if( null !== $filtered )
+ if ( null !== $filtered )
return $filtered;
$to_ncr = array(
}
/**
- * Formats text for the rich text editor.
+ * Formats text for the editor.
*
- * The filter 'richedit_pre' is applied here. If $text is empty the filter will
- * be applied to an empty string.
+ * Generally the browsers treat everything inside a textarea as text, but
+ * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
*
- * @since 2.0.0
+ * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
+ * filter will be applied to an empty string.
*
- * @param string $text The text to be formatted.
- * @return string The formatted text after filter is applied.
- */
-function wp_richedit_pre($text) {
- if ( empty( $text ) ) {
- /**
- * Filter text returned for the rich text editor.
- *
- * This filter is first evaluated, and the value returned, if an empty string
- * is passed to wp_richedit_pre(). If an empty string is passed, it results
- * in a break tag and line feed.
- *
- * If a non-empty string is passed, the filter is evaluated on the wp_richedit_pre()
- * return after being formatted.
- *
- * @since 2.0.0
- *
- * @param string $output Text for the rich text editor.
- */
- return apply_filters( 'richedit_pre', '' );
- }
-
- $output = convert_chars($text);
- $output = wpautop($output);
- $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) );
-
- /** This filter is documented in wp-includes/formatting.php */
- return apply_filters( 'richedit_pre', $output );
-}
-
-/**
- * Formats text for the HTML editor.
+ * @since 4.3.0
*
- * Unless $output is empty it will pass through htmlspecialchars before the
- * 'htmledit_pre' filter is applied.
+ * @see _WP_Editors::editor()
*
- * @since 2.5.0
- *
- * @param string $output The text to be formatted.
- * @return string Formatted text after filter applied.
+ * @param string $text The text to be formatted.
+ * @param string $default_editor The default editor for the current user.
+ * It is usually either 'html' or 'tinymce'.
+ * @return string The formatted text after filter is applied.
*/
-function wp_htmledit_pre($output) {
- if ( !empty($output) )
- $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) ); // convert only < > &
+function format_for_editor( $text, $default_editor = null ) {
+ if ( $text ) {
+ $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
+ }
/**
- * Filter the text before it is formatted for the HTML editor.
+ * Filters the text after it is formatted for the editor.
*
- * @since 2.5.0
+ * @since 4.3.0
*
- * @param string $output The HTML-formatted text.
+ * @param string $text The formatted text.
+ * @param string $default_editor The default editor for the current user.
+ * It is usually either 'html' or 'tinymce'.
*/
- return apply_filters( 'htmledit_pre', $output );
+ return apply_filters( 'format_for_editor', $text, $default_editor );
}
/**
* @since 2.8.1
* @access private
*
- * @param string|array $search The value being searched for, otherwise known as the needle. An array may be used to designate multiple needles.
- * @param string $subject The string being searched and replaced on, otherwise known as the haystack.
+ * @param string|array $search The value being searched for, otherwise known as the needle.
+ * An array may be used to designate multiple needles.
+ * @param string $subject The string being searched and replaced on, otherwise known as the haystack.
* @return string The string with the replaced svalues.
*/
function _deep_replace( $search, $subject ) {
* is preparing an array for use in an IN clause.
*
* @since 2.8.0
+ *
+ * @global wpdb $wpdb WordPress database abstraction object.
+ *
* @param string|array $data Unescaped data
* @return string|array Escaped data
*/
* Checks and cleans a URL.
*
* A number of characters are removed from the URL. If the URL is for displaying
- * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
+ * (the default behaviour) ampersands are also replaced. The {@see 'clean_url'} filter
* is applied to the returned cleaned URL.
*
* @since 2.8.0
- * @uses wp_kses_bad_protocol() To only permit protocols in the URL set
- * via $protocols or the common ones set in the function.
*
- * @param string $url The URL to be cleaned.
- * @param array $protocols Optional. An array of acceptable protocols.
- * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn' if not set.
- * @param string $_context Private. Use esc_url_raw() for database usage.
- * @return string The cleaned $url after the 'clean_url' filter is applied.
+ * @param string $url The URL to be cleaned.
+ * @param array $protocols Optional. An array of acceptable protocols.
+ * Defaults to return value of wp_allowed_protocols()
+ * @param string $_context Private. Use esc_url_raw() for database usage.
+ * @return string The cleaned $url after the {@see 'clean_url'} filter is applied.
*/
function esc_url( $url, $protocols = null, $_context = 'display' ) {
$original_url = $url;
if ( '' == $url )
return $url;
- $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url);
- $strip = array('%0d', '%0a', '%0D', '%0A');
- $url = _deep_replace($strip, $url);
+
+ $url = str_replace( ' ', '%20', $url );
+ $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url);
+
+ if ( '' === $url ) {
+ return $url;
+ }
+
+ if ( 0 !== stripos( $url, 'mailto:' ) ) {
+ $strip = array('%0d', '%0a', '%0D', '%0A');
+ $url = _deep_replace($strip, $url);
+ }
+
$url = str_replace(';//', '://', $url);
/* If the URL doesn't appear to contain a scheme, we
- * presume it needs http:// appended (unless a relative
+ * presume it needs http:// prepended (unless a relative
* link starting with /, # or ? or a php file).
*/
if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
$url = str_replace( "'", ''', $url );
}
+ if ( ( false !== strpos( $url, '[' ) ) || ( false !== strpos( $url, ']' ) ) ) {
+
+ $parsed = wp_parse_url( $url );
+ $front = '';
+
+ if ( isset( $parsed['scheme'] ) ) {
+ $front .= $parsed['scheme'] . '://';
+ } elseif ( '/' === $url[0] ) {
+ $front .= '//';
+ }
+
+ if ( isset( $parsed['user'] ) ) {
+ $front .= $parsed['user'];
+ }
+
+ if ( isset( $parsed['pass'] ) ) {
+ $front .= ':' . $parsed['pass'];
+ }
+
+ if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) {
+ $front .= '@';
+ }
+
+ if ( isset( $parsed['host'] ) ) {
+ $front .= $parsed['host'];
+ }
+
+ if ( isset( $parsed['port'] ) ) {
+ $front .= ':' . $parsed['port'];
+ }
+
+ $end_dirty = str_replace( $front, '', $url );
+ $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty );
+ $url = str_replace( $end_dirty, $end_clean, $url );
+
+ }
+
if ( '/' === $url[0] ) {
$good_protocol_url = $url;
} else {
}
/**
- * Filter a string cleaned and escaped for output as a URL.
+ * Filters a string cleaned and escaped for output as a URL.
*
* @since 2.3.0
*
* Performs esc_url() for database usage.
*
* @since 2.8.0
- * @uses esc_url()
*
- * @param string $url The URL to be cleaned.
- * @param array $protocols An array of acceptable protocols.
+ * @param string $url The URL to be cleaned.
+ * @param array $protocols An array of acceptable protocols.
* @return string The cleaned URL.
*/
function esc_url_raw( $url, $protocols = null ) {
/**
* Convert entities, while preserving already-encoded entities.
*
- * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
+ * @link https://secure.php.net/htmlentities Borrowed from the PHP Manual user notes.
*
* @since 1.2.2
*
* @param string $myHTML The text to be converted.
* @return string Converted text.
*/
-function htmlentities2($myHTML) {
+function htmlentities2( $myHTML ) {
$translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
$translation_table[chr(38)] = '&';
return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
*
* Escapes text strings for echoing in JS. It is intended to be used for inline JS
* (in a tag attribute, for example onclick="..."). Note that the strings have to
- * be in single quotes. The filter 'js_escape' is also applied here.
+ * be in single quotes. The {@see 'js_escape'} filter is also applied here.
*
* @since 2.8.0
*
$safe_text = str_replace( "\r", '', $safe_text );
$safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
/**
- * Filter a string cleaned and escaped for output in JavaScript.
+ * Filters a string cleaned and escaped for output in JavaScript.
*
* Text passed to esc_js() is stripped of invalid or special characters,
* and properly slashed for output.
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
/**
- * Filter a string cleaned and escaped for output in HTML.
+ * Filters a string cleaned and escaped for output in HTML.
*
* Text passed to esc_html() is stripped of invalid or special characters
* before output.
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
/**
- * Filter a string cleaned and escaped for output in an HTML attribute.
+ * Filters a string cleaned and escaped for output in an HTML attribute.
*
* Text passed to esc_attr() is stripped of invalid or special characters
* before output.
function esc_textarea( $text ) {
$safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
/**
- * Filter a string cleaned and escaped for output in a textarea element.
+ * Filters a string cleaned and escaped for output in a textarea element.
*
* @since 3.1.0
*
* @param string $tag_name
* @return string
*/
-function tag_escape($tag_name) {
+function tag_escape( $tag_name ) {
$safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
/**
- * Filter a string cleaned and escaped for output as an HTML tag.
+ * Filters a string cleaned and escaped for output as an HTML tag.
*
* @since 2.8.0
*
return apply_filters( 'tag_escape', $safe_tag, $tag_name );
}
-/**
- * Escapes text for SQL LIKE special characters % and _.
- *
- * @since 2.5.0
- *
- * @param string $text The text to be escaped.
- * @return string text, safe for inclusion in LIKE query.
- */
-function like_escape($text) {
- return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
-}
-
/**
* Convert full URL paths to absolute paths.
*
* beginning, so it isn't a true relative link, but from the web root base.
*
* @since 2.1.0
+ * @since 4.1.0 Support was added for relative URLs.
*
* @param string $link Full URL path.
* @return string Absolute path.
*/
function wp_make_link_relative( $link ) {
- return preg_replace( '|https?://[^/]+(/.*)|i', '$1', $link );
+ return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link );
}
/**
*
* @since 2.0.5
*
+ * @global wpdb $wpdb WordPress database abstraction object.
+ *
* @param string $option The name of the option.
- * @param string $value The unsanitised value.
+ * @param string $value The unsanitised value.
* @return string Sanitized value.
*/
-function sanitize_option($option, $value) {
+function sanitize_option( $option, $value ) {
+ global $wpdb;
+
+ $original_value = $value;
+ $error = '';
switch ( $option ) {
case 'admin_email' :
case 'new_admin_email' :
- $value = sanitize_email( $value );
- if ( ! is_email( $value ) ) {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists( 'add_settings_error' ) )
- add_settings_error( $option, 'invalid_admin_email', __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ) );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = sanitize_email( $value );
+ if ( ! is_email( $value ) ) {
+ $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
+ }
}
break;
case 'thumbnail_size_h':
case 'medium_size_w':
case 'medium_size_h':
+ case 'medium_large_size_w':
+ case 'medium_large_size_h':
case 'large_size_w':
case 'large_size_h':
case 'mailserver_port':
case 'thread_comments_depth':
case 'users_can_register':
case 'start_of_week':
+ case 'site_icon':
$value = absint( $value );
break;
case 'blogdescription':
case 'blogname':
- $value = wp_kses_post( $value );
- $value = esc_html( $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( $value !== $original_value ) {
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) );
+ }
+
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = esc_html( $value );
+ }
break;
case 'blog_charset':
case 'mailserver_login':
case 'mailserver_pass':
case 'upload_path':
- $value = strip_tags( $value );
- $value = wp_kses_data( $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = strip_tags( $value );
+ $value = wp_kses_data( $value );
+ }
break;
case 'ping_sites':
break;
case 'siteurl':
- if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
- $value = esc_url_raw($value);
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
} else {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.'));
+ if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
+ $value = esc_url_raw( $value );
+ } else {
+ $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
+ }
}
break;
case 'home':
- if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
- $value = esc_url_raw($value);
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
} else {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.'));
+ if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
+ $value = esc_url_raw( $value );
+ } else {
+ $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
+ }
}
break;
case 'WPLANG':
$allowed = get_available_languages();
- if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
+ if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
+ $allowed[] = WPLANG;
+ }
+ if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
$value = get_option( $option );
+ }
break;
case 'illegal_names':
- if ( ! is_array( $value ) )
- $value = explode( ' ', $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ if ( ! is_array( $value ) )
+ $value = explode( ' ', $value );
- $value = array_values( array_filter( array_map( 'trim', $value ) ) );
+ $value = array_values( array_filter( array_map( 'trim', $value ) ) );
- if ( ! $value )
- $value = '';
+ if ( ! $value )
+ $value = '';
+ }
break;
case 'limited_email_domains':
case 'banned_email_domains':
- if ( ! is_array( $value ) )
- $value = explode( "\n", $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ if ( ! is_array( $value ) )
+ $value = explode( "\n", $value );
- $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
- $value = array();
+ $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
+ $value = array();
- foreach ( $domains as $domain ) {
- if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) )
- $value[] = $domain;
+ foreach ( $domains as $domain ) {
+ if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
+ $value[] = $domain;
+ }
+ }
+ if ( ! $value )
+ $value = '';
}
- if ( ! $value )
- $value = '';
break;
case 'timezone_string':
$allowed_zones = timezone_identifiers_list();
if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('timezone_string', 'invalid_timezone_string', __('The timezone you have entered is not valid. Please select a valid timezone.') );
+ $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
}
break;
case 'permalink_structure':
case 'category_base':
case 'tag_base':
- $value = esc_url_raw( $value );
- $value = str_replace( 'http://', '', $value );
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = esc_url_raw( $value );
+ $value = str_replace( 'http://', '', $value );
+ }
+
+ if ( 'permalink_structure' === $option && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value ) ) {
+ $error = sprintf(
+ /* translators: %s: Codex URL */
+ __( 'A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>' ),
+ __( 'https://codex.wordpress.org/Using_Permalinks#Choosing_your_permalink_structure' )
+ );
+ }
break;
case 'default_role' :
if ( ! get_role( $value ) && get_role( 'subscriber' ) )
$value = 'subscriber';
break;
+
+ case 'moderation_keys':
+ case 'blacklist_keys':
+ $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
+ if ( is_wp_error( $value ) ) {
+ $error = $value->get_error_message();
+ } else {
+ $value = explode( "\n", $value );
+ $value = array_filter( array_map( 'trim', $value ) );
+ $value = array_unique( $value );
+ $value = implode( "\n", $value );
+ }
+ break;
+ }
+
+ if ( ! empty( $error ) ) {
+ $value = get_option( $option );
+ if ( function_exists( 'add_settings_error' ) ) {
+ add_settings_error( $option, "invalid_{$option}", $error );
+ }
}
/**
- * Filter an option value following sanitization.
+ * Filters an option value following sanitization.
*
* @since 2.3.0
+ * @since 4.3.0 Added the `$original_value` parameter.
*
- * @param string $value The sanitized option value.
- * @param string $option The option name.
+ * @param string $value The sanitized option value.
+ * @param string $option The option name.
+ * @param string $original_value The original value passed to the function.
*/
- $value = apply_filters( "sanitize_option_{$option}", $value, $option );
+ return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value );
+}
+
+/**
+ * Maps a function to all non-iterable elements of an array or an object.
+ *
+ * This is similar to `array_walk_recursive()` but acts upon objects too.
+ *
+ * @since 4.4.0
+ *
+ * @param mixed $value The array, object, or scalar.
+ * @param callable $callback The function to map onto $value.
+ * @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
+ */
+function map_deep( $value, $callback ) {
+ if ( is_array( $value ) ) {
+ foreach ( $value as $index => $item ) {
+ $value[ $index ] = map_deep( $item, $callback );
+ }
+ } elseif ( is_object( $value ) ) {
+ $object_vars = get_object_vars( $value );
+ foreach ( $object_vars as $property_name => $property_value ) {
+ $value->$property_name = map_deep( $property_value, $callback );
+ }
+ } else {
+ $value = call_user_func( $callback, $value );
+ }
return $value;
}
/**
* Parses a string into variables to be stored in an array.
*
- * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
- * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
+ * Uses {@link https://secure.php.net/parse_str parse_str()} and stripslashes if
+ * {@link https://secure.php.net/magic_quotes magic_quotes_gpc} is on.
*
* @since 2.2.1
*
* @param string $string The string to be parsed.
- * @param array $array Variables will be stored in this array.
+ * @param array $array Variables will be stored in this array.
*/
function wp_parse_str( $string, &$array ) {
parse_str( $string, $array );
if ( get_magic_quotes_gpc() )
$array = stripslashes_deep( $array );
/**
- * Filter the array of variables derived from a parsed string.
+ * Filters the array of variables derived from a parsed string.
*
* @since 2.3.0
*
*
* KSES already converts lone greater than signs.
*
- * @uses wp_pre_kses_less_than_callback in the callback function.
* @since 2.3.0
*
* @param string $text Text to be converted.
/**
* Callback function used by preg_replace.
*
- * @uses esc_html to format the $matches text.
* @since 2.3.0
*
* @param array $matches Populated by matches to preg_replace.
* WordPress implementation of PHP sprintf() with filters.
*
* @since 2.5.0
- * @link http://www.php.net/sprintf
+ * @link https://secure.php.net/sprintf
*
- * @param string $pattern The string which formatted args are inserted.
- * @param mixed $args,... Arguments to be formatted into the $pattern string.
+ * @param string $pattern The string which formatted args are inserted.
+ * @param mixed $args ,... Arguments to be formatted into the $pattern string.
* @return string The formatted string.
*/
function wp_sprintf( $pattern ) {
}
/**
- * Filter a fragment from the pattern passed to wp_sprintf().
+ * Filters a fragment from the pattern passed to wp_sprintf().
*
* If the fragment is unchanged, then sprintf() will be run on the fragment.
*
* @since 2.5.0
*
* @param string $pattern Content containing '%l' at the beginning.
- * @param array $args List items to prepend to the content and replace '%l'.
+ * @param array $args List items to prepend to the content and replace '%l'.
* @return string Localized list items and rest of the content.
*/
-function wp_sprintf_l($pattern, $args) {
+function wp_sprintf_l( $pattern, $args ) {
// Not a match
if ( substr($pattern, 0, 2) != '%l' )
return $pattern;
return '';
/**
- * Filter the translated delimiters used by wp_sprintf_l().
+ * Filters the translated delimiters used by wp_sprintf_l().
* Placeholders (%s) are included to assist translators and then
* removed before the array of strings reaches the filter.
*
*
* @since 2.5.0
*
- * @param string $str String to get the excerpt from.
- * @param integer $count Maximum number of characters to take.
- * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
+ * @param string $str String to get the excerpt from.
+ * @param int $count Maximum number of characters to take.
+ * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
* @return string The excerpt.
*/
function wp_html_excerpt( $str, $count, $more = null ) {
*
* @since 2.7.0
*
+ * @global string $_links_add_base
+ *
* @param string $content String to search for links in.
- * @param string $base The base URL to prefix to links.
- * @param array $attrs The attributes which should be processed.
+ * @param string $base The base URL to prefix to links.
+ * @param array $attrs The attributes which should be processed.
* @return string The processed content.
*/
function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
* @since 2.7.0
* @access private
*
+ * @global string $_links_add_base
+ *
* @param string $m The matched link.
* @return string The processed link.
*/
-function _links_add_base($m) {
+function _links_add_base( $m ) {
global $_links_add_base;
//1 = attribute name 2 = quotation mark 3 = URL
return $m[1] . '=' . $m[2] .
( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
$m[3] :
- path_join( $_links_add_base, $m[3] ) )
+ WP_Http::make_absolute_url( $m[3], $_links_add_base )
+ )
. $m[2];
}
/**
* Adds a Target attribute to all links in passed content.
*
- * This function by default only applies to <a> tags, however this can be
+ * This function by default only applies to `<a>` tags, however this can be
* modified by the 3rd param.
*
- * <b>NOTE:</b> Any current target attributed will be stripped and replaced.
+ * *NOTE:* Any current target attributed will be stripped and replaced.
*
* @since 2.7.0
*
+ * @global string $_links_add_target
+ *
* @param string $content String to search for links in.
- * @param string $target The Target to add to the links.
- * @param array $tags An array of tags to apply to.
+ * @param string $target The Target to add to the links.
+ * @param array $tags An array of tags to apply to.
* @return string The processed content.
*/
function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
* @since 2.7.0
* @access private
*
+ * @global string $_links_add_target
+ *
* @param string $m The matched link.
* @return string The processed link.
*/
* Properly strip all HTML tags including script and style
*
* This differs from strip_tags() because it removes the contents of
- * the <script> and <style> tags. E.g. strip_tags( '<script>something</script>' )
+ * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
* will return 'something'. wp_strip_all_tags will return ''
*
* @since 2.9.0
*
- * @param string $string String containing HTML tags
- * @param bool $remove_breaks optional Whether to remove left over line breaks and white space chars
+ * @param string $string String containing HTML tags
+ * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars
* @return string The processed string.
*/
function wp_strip_all_tags($string, $remove_breaks = false) {
}
/**
- * Sanitize a string from user input or from the db
+ * Sanitizes a string from user input or from the database.
*
- * check for invalid UTF-8,
- * Convert single < characters to entity,
- * strip all tags,
- * remove line breaks, tabs and extra white space,
- * strip octets.
+ * - Checks for invalid UTF-8,
+ * - Converts single `<` characters to entities
+ * - Strips all tags
+ * - Removes line breaks, tabs, and extra whitespace
+ * - Strips octets
*
* @since 2.9.0
*
- * @param string $str
- * @return string
+ * @see wp_check_invalid_utf8()
+ * @see wp_strip_all_tags()
+ *
+ * @param string $str String to sanitize.
+ * @return string Sanitized string.
*/
-function sanitize_text_field($str) {
+function sanitize_text_field( $str ) {
$filtered = wp_check_invalid_utf8( $str );
if ( strpos($filtered, '<') !== false ) {
}
/**
- * Filter a sanitized text field string.
+ * Filters a sanitized text field string.
*
* @since 2.9.0
*
*
* @since 3.1.0
*
- * @param string $path A path.
+ * @param string $path A path.
* @param string $suffix If the filename ends in suffix this will also be cut off.
* @return string
*/
* Violating our coding standards for a good function name.
*
* @since 3.0.0
+ *
+ * @staticvar string|false $dblq
+ *
+ * @param string $text The text to be modified.
+ * @return string The modified text.
*/
function capital_P_dangit( $text ) {
// Simple replacement for titles
return str_replace( 'Wordpress', 'WordPress', $text );
// Still here? Use the more judicious replacement
static $dblq = false;
- if ( false === $dblq )
+ if ( false === $dblq ) {
$dblq = _x( '“', 'opening curly double quote' );
+ }
return str_replace(
array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
$text );
-
}
/**
function sanitize_mime_type( $mime_type ) {
$sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
/**
- * Filter a mime type following sanitization.
+ * Filters a mime type following sanitization.
*
* @since 3.1.3
*
$urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
$urls_to_ping = implode( "\n", $urls_to_ping );
/**
- * Filter a list of trackback URLs following sanitization.
+ * Filters a list of trackback URLs following sanitization.
*
* The string returned here consists of a space or carriage return-delimited list
* of trackback URLs.
* @since 3.6.0
*
* @param string $content A string which might contain a URL.
- * @return string The found URL.
+ * @return string|false The found URL.
*/
function get_url_in_content( $content ) {
if ( empty( $content ) ) {
return false;
}
+
+/**
+ * Returns the regexp for common whitespace characters.
+ *
+ * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
+ * This is designed to replace the PCRE \s sequence. In ticket #22692, that
+ * sequence was found to be unreliable due to random inclusion of the A0 byte.
+ *
+ * @since 4.0.0
+ *
+ * @staticvar string $spaces
+ *
+ * @return string The spaces regexp.
+ */
+function wp_spaces_regexp() {
+ static $spaces = '';
+
+ if ( empty( $spaces ) ) {
+ /**
+ * Filters the regexp for common whitespace characters.
+ *
+ * This string is substituted for the \s sequence as needed in regular
+ * expressions. For websites not written in English, different characters
+ * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0
+ * sequence may not be in use.
+ *
+ * @since 4.0.0
+ *
+ * @param string $spaces Regexp pattern for matching common whitespace characters.
+ */
+ $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' );
+ }
+
+ return $spaces;
+}
+
+/**
+ * Print the important emoji-related styles.
+ *
+ * @since 4.2.0
+ *
+ * @staticvar bool $printed
+ */
+function print_emoji_styles() {
+ static $printed = false;
+
+ if ( $printed ) {
+ return;
+ }
+
+ $printed = true;
+?>
+<style type="text/css">
+img.wp-smiley,
+img.emoji {
+ display: inline !important;
+ border: none !important;
+ box-shadow: none !important;
+ height: 1em !important;
+ width: 1em !important;
+ margin: 0 .07em !important;
+ vertical-align: -0.1em !important;
+ background: none !important;
+ padding: 0 !important;
+}
+</style>
+<?php
+}
+
+/**
+ * Print the inline Emoji detection script if it is not already printed.
+ *
+ * @since 4.2.0
+ * @staticvar bool $printed
+ */
+function print_emoji_detection_script() {
+ static $printed = false;
+
+ if ( $printed ) {
+ return;
+ }
+
+ $printed = true;
+
+ _print_emoji_detection_script();
+}
+
+/**
+ * Prints inline Emoji dection script
+ *
+ * @ignore
+ * @since 4.6.0
+ * @access private
+ *
+ * @global string $wp_version WordPress version string.
+ */
+function _print_emoji_detection_script() {
+ global $wp_version;
+
+ $settings = array(
+ /**
+ * Filters the URL where emoji png images are hosted.
+ *
+ * @since 4.2.0
+ *
+ * @param string The emoji base URL for png images.
+ */
+ 'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/2/72x72/' ),
+
+ /**
+ * Filters the extension of the emoji png files.
+ *
+ * @since 4.2.0
+ *
+ * @param string The emoji extension for png files. Default .png.
+ */
+ 'ext' => apply_filters( 'emoji_ext', '.png' ),
+
+ /**
+ * Filters the URL where emoji SVG images are hosted.
+ *
+ * @since 4.6.0
+ *
+ * @param string The emoji base URL for svg images.
+ */
+ 'svgUrl' => apply_filters( 'emoji_svg_url', 'https://s.w.org/images/core/emoji/2/svg/' ),
+
+ /**
+ * Filters the extension of the emoji SVG files.
+ *
+ * @since 4.6.0
+ *
+ * @param string The emoji extension for svg files. Default .svg.
+ */
+ 'svgExt' => apply_filters( 'emoji_svg_ext', '.svg' ),
+ );
+
+ $version = 'ver=' . $wp_version;
+
+ if ( SCRIPT_DEBUG ) {
+ $settings['source'] = array(
+ /** This filter is documented in wp-includes/class.wp-scripts.php */
+ 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ),
+ /** This filter is documented in wp-includes/class.wp-scripts.php */
+ 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ),
+ );
+
+ ?>
+ <script type="text/javascript">
+ window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
+ <?php readfile( ABSPATH . WPINC . "/js/wp-emoji-loader.js" ); ?>
+ </script>
+ <?php
+ } else {
+ $settings['source'] = array(
+ /** This filter is documented in wp-includes/class.wp-scripts.php */
+ 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ),
+ );
+
+ /*
+ * If you're looking at a src version of this file, you'll see an "include"
+ * statement below. This is used by the `grunt build` process to directly
+ * include a minified version of wp-emoji-loader.js, instead of using the
+ * readfile() method from above.
+ *
+ * If you're looking at a build version of this file, you'll see a string of
+ * minified JavaScript. If you need to debug it, please turn on SCRIPT_DEBUG
+ * and edit wp-emoji-loader.js directly.
+ */
+ ?>
+ <script type="text/javascript">
+ window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
+ !function(a,b,c){function d(a){var c,d,e,f,g,h=b.createElement("canvas"),i=h.getContext&&h.getContext("2d"),j=String.fromCharCode;if(!i||!i.fillText)return!1;switch(i.textBaseline="top",i.font="600 32px Arial",a){case"flag":return i.fillText(j(55356,56806,55356,56826),0,0),!(h.toDataURL().length<3e3)&&(i.clearRect(0,0,h.width,h.height),i.fillText(j(55356,57331,65039,8205,55356,57096),0,0),c=h.toDataURL(),i.clearRect(0,0,h.width,h.height),i.fillText(j(55356,57331,55356,57096),0,0),d=h.toDataURL(),c!==d);case"diversity":return i.fillText(j(55356,57221),0,0),e=i.getImageData(16,16,1,1).data,f=e[0]+","+e[1]+","+e[2]+","+e[3],i.fillText(j(55356,57221,55356,57343),0,0),e=i.getImageData(16,16,1,1).data,g=e[0]+","+e[1]+","+e[2]+","+e[3],f!==g;case"simple":return i.fillText(j(55357,56835),0,0),0!==i.getImageData(16,16,1,1).data[0];case"unicode8":return i.fillText(j(55356,57135),0,0),0!==i.getImageData(16,16,1,1).data[0];case"unicode9":return i.fillText(j(55358,56631),0,0),0!==i.getImageData(16,16,1,1).data[0]}return!1}function e(a){var c=b.createElement("script");c.src=a,c.type="text/javascript",b.getElementsByTagName("head")[0].appendChild(c)}var f,g,h,i;for(i=Array("simple","flag","unicode8","diversity","unicode9"),c.supports={everything:!0,everythingExceptFlag:!0},h=0;h<i.length;h++)c.supports[i[h]]=d(i[h]),c.supports.everything=c.supports.everything&&c.supports[i[h]],"flag"!==i[h]&&(c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&c.supports[i[h]]);c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&!c.supports.flag,c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.everything||(g=function(){c.readyCallback()},b.addEventListener?(b.addEventListener("DOMContentLoaded",g,!1),a.addEventListener("load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onreadystatechange",function(){"complete"===b.readyState&&c.readyCallback()})),f=c.source||{},f.concatemoji?e(f.concatemoji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(window,document,window._wpemojiSettings);
+ </script>
+ <?php
+ }
+}
+
+/**
+ * Convert any 4 byte emoji in a string to their equivalent HTML entity.
+ *
+ * Currently, only Unicode 7 emoji are supported. Skin tone modifiers are allowed,
+ * all other Unicode 8 emoji will be added when the spec is finalised.
+ *
+ * This allows us to store emoji in a DB using the utf8 character set.
+ *
+ * @since 4.2.0
+ *
+ * @param string $content The content to encode.
+ * @return string The encoded content.
+ */
+function wp_encode_emoji( $content ) {
+ if ( function_exists( 'mb_convert_encoding' ) ) {
+ $regex = '/(
+ \x23\xE2\x83\xA3 # Digits
+ [\x30-\x39]\xE2\x83\xA3
+ | \xF0\x9F[\x85-\x88][\xA6-\xBF] # Enclosed characters
+ | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc
+ | \xF0\x9F\x98[\x80-\xBF] # Smilies
+ | \xF0\x9F\x99[\x80-\x8F]
+ | \xF0\x9F\x9A[\x80-\xBF] # Transport and map symbols
+ )/x';
+
+ $matches = array();
+ if ( preg_match_all( $regex, $content, $matches ) ) {
+ if ( ! empty( $matches[1] ) ) {
+ foreach ( $matches[1] as $emoji ) {
+ /*
+ * UTF-32's hex encoding is the same as HTML's hex encoding.
+ * So, by converting the emoji from UTF-8 to UTF-32, we magically
+ * get the correct hex encoding.
+ */
+ $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) );
+ if ( isset( $unpacked[1] ) ) {
+ $entity = '&#x' . ltrim( $unpacked[1], '0' ) . ';';
+ $content = str_replace( $emoji, $entity, $content );
+ }
+ }
+ }
+ }
+ }
+
+ return $content;
+}
+
+/**
+ * Convert emoji to a static img element.
+ *
+ * @since 4.2.0
+ *
+ * @param string $text The content to encode.
+ * @return string The encoded content.
+ */
+function wp_staticize_emoji( $text ) {
+ $text = wp_encode_emoji( $text );
+
+ /** This filter is documented in wp-includes/formatting.php */
+ $cdn_url = apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/2/72x72/' );
+
+ /** This filter is documented in wp-includes/formatting.php */
+ $ext = apply_filters( 'emoji_ext', '.png' );
+
+ $output = '';
+ /*
+ * HTML loop taken from smiley function, which was taken from texturize function.
+ * It'll never be consolidated.
+ *
+ * First, capture the tags as well as in between.
+ */
+ $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
+ $stop = count( $textarr );
+
+ // Ignore processing of specific tags.
+ $tags_to_ignore = 'code|pre|style|script|textarea';
+ $ignore_block_element = '';
+
+ for ( $i = 0; $i < $stop; $i++ ) {
+ $content = $textarr[$i];
+
+ // If we're in an ignore block, wait until we find its closing tag.
+ if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
+ $ignore_block_element = $matches[1];
+ }
+
+ // If it's not a tag and not in ignore block.
+ if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
+ $matches = array();
+ if ( preg_match_all( '/(DZ(e[6-9a-f]|f[0-9a-f]);){2}/', $content, $matches ) ) {
+ if ( ! empty( $matches[0] ) ) {
+ foreach ( $matches[0] as $flag ) {
+ $chars = str_replace( array( '&#x', ';'), '', $flag );
+
+ list( $char1, $char2 ) = str_split( $chars, 5 );
+ $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char1 . '-' . $char2 . $ext, html_entity_decode( $flag ) );
+
+ $content = str_replace( $flag, $entity, $content );
+ }
+ }
+ }
+
+ // Loosely match the Emoji Unicode range.
+ $regex = '/(&#x[2-3][0-9a-f]{3};|[1-6][0-9a-f]{2};)/';
+
+ $matches = array();
+ if ( preg_match_all( $regex, $content, $matches ) ) {
+ if ( ! empty( $matches[1] ) ) {
+ foreach ( $matches[1] as $emoji ) {
+ $char = str_replace( array( '&#x', ';'), '', $emoji );
+ $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char . $ext, html_entity_decode( $emoji ) );
+
+ $content = str_replace( $emoji, $entity, $content );
+ }
+ }
+ }
+ }
+
+ // Did we exit ignore block.
+ if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
+ $ignore_block_element = '';
+ }
+
+ $output .= $content;
+ }
+
+ return $output;
+}
+
+/**
+ * Convert emoji in emails into static images.
+ *
+ * @since 4.2.0
+ *
+ * @param array $mail The email data array.
+ * @return array The email data array, with emoji in the message staticized.
+ */
+function wp_staticize_emoji_for_email( $mail ) {
+ if ( ! isset( $mail['message'] ) ) {
+ return $mail;
+ }
+
+ /*
+ * We can only transform the emoji into images if it's a text/html email.
+ * To do that, here's a cut down version of the same process that happens
+ * in wp_mail() - get the Content-Type from the headers, if there is one,
+ * then pass it through the wp_mail_content_type filter, in case a plugin
+ * is handling changing the Content-Type.
+ */
+ $headers = array();
+ if ( isset( $mail['headers'] ) ) {
+ if ( is_array( $mail['headers'] ) ) {
+ $headers = $mail['headers'];
+ } else {
+ $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) );
+ }
+ }
+
+ foreach ( $headers as $header ) {
+ if ( strpos($header, ':') === false ) {
+ continue;
+ }
+
+ // Explode them out.
+ list( $name, $content ) = explode( ':', trim( $header ), 2 );
+
+ // Cleanup crew.
+ $name = trim( $name );
+ $content = trim( $content );
+
+ if ( 'content-type' === strtolower( $name ) ) {
+ if ( strpos( $content, ';' ) !== false ) {
+ list( $type, $charset ) = explode( ';', $content );
+ $content_type = trim( $type );
+ } else {
+ $content_type = trim( $content );
+ }
+ break;
+ }
+ }
+
+ // Set Content-Type if we don't have a content-type from the input headers.
+ if ( ! isset( $content_type ) ) {
+ $content_type = 'text/plain';
+ }
+
+ /** This filter is documented in wp-includes/pluggable.php */
+ $content_type = apply_filters( 'wp_mail_content_type', $content_type );
+
+ if ( 'text/html' === $content_type ) {
+ $mail['message'] = wp_staticize_emoji( $mail['message'] );
+ }
+
+ return $mail;
+}
+
+/**
+ * Shorten a URL, to be used as link text.
+ *
+ * @since 1.2.0
+ * @since 4.4.0 Moved to wp-includes/formatting.php from wp-admin/includes/misc.php and added $length param.
+ *
+ * @param string $url URL to shorten.
+ * @param int $length Optional. Maximum length of the shortened URL. Default 35 characters.
+ * @return string Shortened URL.
+ */
+function url_shorten( $url, $length = 35 ) {
+ $stripped = str_replace( array( 'https://', 'http://', 'www.' ), '', $url );
+ $short_url = untrailingslashit( $stripped );
+
+ if ( strlen( $short_url ) > $length ) {
+ $short_url = substr( $short_url, 0, $length - 3 ) . '…';
+ }
+ return $short_url;
+}
+
+/**
+ * Sanitizes a hex color.
+ *
+ * Returns either '', a 3 or 6 digit hex color (with #), or nothing.
+ * For sanitizing values without a #, see sanitize_hex_color_no_hash().
+ *
+ * @since 3.4.0
+ *
+ * @param string $color
+ * @return string|void
+ */
+function sanitize_hex_color( $color ) {
+ if ( '' === $color ) {
+ return '';
+ }
+
+ // 3 or 6 hex digits, or the empty string.
+ if ( preg_match('|^#([A-Fa-f0-9]{3}){1,2}$|', $color ) ) {
+ return $color;
+ }
+}
+
+/**
+ * Sanitizes a hex color without a hash. Use sanitize_hex_color() when possible.
+ *
+ * Saving hex colors without a hash puts the burden of adding the hash on the
+ * UI, which makes it difficult to use or upgrade to other color types such as
+ * rgba, hsl, rgb, and html color names.
+ *
+ * Returns either '', a 3 or 6 digit hex color (without a #), or null.
+ *
+ * @since 3.4.0
+ *
+ * @param string $color
+ * @return string|null
+ */
+function sanitize_hex_color_no_hash( $color ) {
+ $color = ltrim( $color, '#' );
+
+ if ( '' === $color ) {
+ return '';
+ }
+
+ return sanitize_hex_color( '#' . $color ) ? $color : null;
+}
+
+/**
+ * Ensures that any hex color is properly hashed.
+ * Otherwise, returns value untouched.
+ *
+ * This method should only be necessary if using sanitize_hex_color_no_hash().
+ *
+ * @since 3.4.0
+ *
+ * @param string $color
+ * @return string
+ */
+function maybe_hash_hex_color( $color ) {
+ if ( $unhashed = sanitize_hex_color_no_hash( $color ) ) {
+ return '#' . $unhashed;
+ }
+
+ return $color;
+}
scripts.mit.edu / autoinstalls / wordpress.git / blobdiff