WordPress/wp-includes/formatting.php
Gary Pendergast 2c277e3952 Emoji: Clean up the emoji browser support tests.
As new sets of emoji are added to Unicode, and browsers add support for them at random intervals, we'll inevitably need to add new tests to the emoji loader. This change makes it much easier to add new tests as they're needed.

Fixes #35300.


Built from https://develop.svn.wordpress.org/trunk@36816


git-svn-id: http://core.svn.wordpress.org/trunk@36783 1a063a9b-81f0-0310-95a4-ce76da25c4cd
2016-03-03 05:17:26 +00:00

4806 lines
155 KiB
PHP

<?php
/**
* Main WordPress Formatting API.
*
* Handles many functions for formatting output.
*
* @package WordPress
*/
/**
* Replaces common plain text characters into formatted entities
*
* As an example,
*
* 'cause today's effort makes it worth tomorrow's "holiday" ...
*
* Becomes:
*
* &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221; &#8230;
*
* Code within certain html blocks are skipped.
*
* Do not use this function before the 'init' action hook; everything will break.
*
* @since 0.71
*
* @global array $wp_cockneyreplace Array of formatted entities for certain common phrases
* @global array $shortcode_tags
* @staticvar array $static_characters
* @staticvar array $static_replacements
* @staticvar array $dynamic_characters
* @staticvar array $dynamic_replacements
* @staticvar array $default_no_texturize_tags
* @staticvar array $default_no_texturize_shortcodes
* @staticvar bool $run_texturize
*
* @param string $text The text to be formatted
* @param bool $reset Set to true for unit testing. Translated patterns will reset.
* @return string The string replaced with html entities
*/
function wptexturize( $text, $reset = false ) {
global $wp_cockneyreplace, $shortcode_tags;
static $static_characters = null,
$static_replacements = null,
$dynamic_characters = null,
$dynamic_replacements = null,
$default_no_texturize_tags = null,
$default_no_texturize_shortcodes = null,
$run_texturize = true,
$apos = null,
$prime = null,
$double_prime = null,
$opening_quote = null,
$closing_quote = null,
$opening_single_quote = null,
$closing_single_quote = null,
$open_q_flag = '<!--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 ) ) {
/**
* Filter whether to skip running wptexturize().
*
* Passing false to the filter will effectively short-circuit wptexturize().
* returning the original text passed to the function instead.
*
* The filter runs only once, the first time wptexturize() is called.
*
* @since 4.0.0
*
* @see wptexturize()
*
* @param bool $run_texturize Whether to short-circuit wptexturize().
*/
$run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
if ( false === $run_texturize ) {
return $text;
}
/* translators: opening curly double quote */
$opening_quote = _x( '&#8220;', 'opening curly double quote' );
/* translators: closing curly double quote */
$closing_quote = _x( '&#8221;', 'closing curly double quote' );
/* translators: apostrophe, for example in 'cause or can't */
$apos = _x( '&#8217;', 'apostrophe' );
/* translators: prime, for example in 9' (nine feet) */
$prime = _x( '&#8242;', 'prime' );
/* translators: double prime, for example in 9" (nine inches) */
$double_prime = _x( '&#8243;', 'double prime' );
/* translators: opening curly single quote */
$opening_single_quote = _x( '&#8216;', 'opening curly single quote' );
/* translators: closing curly single quote */
$closing_single_quote = _x( '&#8217;', 'closing curly single quote' );
/* translators: en dash */
$en_dash = _x( '&#8211;', 'en dash' );
/* translators: em dash */
$em_dash = _x( '&#8212;', 'em dash' );
$default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
$default_no_texturize_shortcodes = array('code');
// if a plugin has provided an autocorrect array, use it
if ( isset($wp_cockneyreplace) ) {
$cockney = array_keys( $wp_cockneyreplace );
$cockneyreplace = array_values( $wp_cockneyreplace );
} else {
/* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
* for example... 'We do not have enough words yet' ... is a typical quoted phrase. But when we write
* lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
*/
$cockney = explode( ',', _x( "'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
'Comma-separated list of words to texturize in your language' ) );
$cockneyreplace = explode( ',', _x( '&#8217;tain&#8217;t,&#8217;twere,&#8217;twas,&#8217;tis,&#8217;twill,&#8217;til,&#8217;bout,&#8217;nuff,&#8217;round,&#8217;cause,&#8217;em',
'Comma-separated list of replacement words in your language' ) );
}
$static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
$static_replacements = array_merge( array( '&#8230;', $opening_quote, $closing_quote, ' &#8482;' ), $cockneyreplace );
// Pattern-based replacements of characters.
// Sort the remaining patterns into several arrays for performance tuning.
$dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
$dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
$dynamic = array();
$spaces = wp_spaces_regexp();
// '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
if ( "'" !== $apos || "'" !== $closing_single_quote ) {
$dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
}
if ( "'" !== $apos || '"' !== $closing_quote ) {
$dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
}
// '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
if ( "'" !== $apos ) {
$dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos_flag;
}
// Quoted Numbers like '0.42'
if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
$dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
}
// Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
if ( "'" !== $opening_single_quote ) {
$dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $open_sq_flag;
}
// Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
if ( "'" !== $apos ) {
$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
}
$dynamic_characters['apos'] = array_keys( $dynamic );
$dynamic_replacements['apos'] = array_values( $dynamic );
$dynamic = array();
// Quoted Numbers like "42"
if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
$dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
}
// Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
if ( '"' !== $opening_quote ) {
$dynamic[ '/(?<=\A|[([{\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
}
$dynamic_characters['quote'] = array_keys( $dynamic );
$dynamic_replacements['quote'] = array_values( $dynamic );
$dynamic = array();
// Dashes and spaces
$dynamic[ '/---/' ] = $em_dash;
$dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash;
$dynamic[ '/(?<!xn)--/' ] = $en_dash;
$dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ] = $en_dash;
$dynamic_characters['dash'] = array_keys( $dynamic );
$dynamic_replacements['dash'] = array_values( $dynamic );
}
// Must do this every time in case plugins use these filters in a context sensitive manner
/**
* Filter 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 = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
/**
* Filter 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 = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
$no_texturize_tags_stack = array();
$no_texturize_shortcodes_stack = array();
// Look for shortcodes and HTML elements.
preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
$tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
$found_shortcodes = ! empty( $tagnames );
$shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
$regex = _get_wptexturize_split_regex( $shortcode_regex );
$textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
foreach ( $textarr as &$curl ) {
// Only call _wptexturize_pushpop_element if $curl is a delimiter.
$first = $curl[0];
if ( '<' === $first ) {
if ( '<!--' === substr( $curl, 0, 4 ) ) {
// This is an HTML comment delimiter.
continue;
} else {
// This is an HTML element delimiter.
// Replace each & with &#038; unless it already looks like an entity.
$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );
_wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
}
} elseif ( '' === trim( $curl ) ) {
// This is a newline between delimiters. Performance improves when we check this.
continue;
} elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
// This is a shortcode delimiter.
if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
// Looks like a normal shortcode.
_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
} else {
// Looks like an escaped shortcode.
continue;
}
} elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
// This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
$curl = str_replace( $static_characters, $static_replacements, $curl );
if ( false !== strpos( $curl, "'" ) ) {
$curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
$curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
$curl = str_replace( $apos_flag, $apos, $curl );
$curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
}
if ( false !== strpos( $curl, '"' ) ) {
$curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
$curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
$curl = str_replace( $open_q_flag, $opening_quote, $curl );
}
if ( false !== strpos( $curl, '-' ) ) {
$curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
}
// 9x9 (times), but never 0x9999
if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
// Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
$curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1&#215;$2', $curl );
}
// Replace each & with &#038; unless it already looks like an entity.
$curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $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|[.,:;!?)}\\-\\]]|&gt;|" . $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 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. 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
*
* Example: in the case <pre>sadsadasd</code>"baba"</pre>
* "baba" won't be texturize
*/
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'.
*
* @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.
* @return string Text which has been converted into correct paragraph tags.
*/
function wpautop( $pee, $br = true ) {
$pre_tags = array();
if ( trim($pee) === '' )
return '';
// Just to make things a little easier, pad the end.
$pee = $pee . "\n";
/*
* Pre tags shouldn't be touched by autop.
* Replace pre tags with placeholders and bring them back after autop.
*/
if ( strpos($pee, '<pre') !== false ) {
$pee_parts = explode( '</pre>', $pee );
$last_pee = array_pop($pee_parts);
$pee = '';
$i = 0;
foreach ( $pee_parts as $pee_part ) {
$start = strpos($pee_part, '<pre');
// Malformed html?
if ( $start === false ) {
$pee .= $pee_part;
continue;
}
$name = "<pre wp-pre-tag-$i></pre>";
$pre_tags[$name] = substr( $pee_part, $start ) . '</pre>';
$pee .= substr( $pee_part, 0, $start ) . $name;
$i++;
}
$pee .= $last_pee;
}
// 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);
// Add a double line break below block-level closing tags.
$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
// 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 ) {
$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 ) {
$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 );
}
// 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";
}
// 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);
// 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);
// 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
*
* @since 3.1.0
* @access private
*
* @param array $matches preg_replace_callback matches array
* @return string
*/
function _autop_newline_preservation_helper( $matches ) {
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>`.
*
* @since 2.9.0
*
* @global array $shortcode_tags
*
* @param string $pee The content.
* @return string The filtered content.
*/
function shortcode_unautop( $pee ) {
global $shortcode_tags;
if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
return $pee;
}
$tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
$spaces = wp_spaces_regexp();
$pattern =
'/'
. '<p>' // Opening paragraph
. '(?:' . $spaces . ')*+' // Optional leading whitespace
. '(' // 1: The shortcode
. '\\[' // Opening bracket
. "($tagregexp)" // 2: Shortcode name
. '(?![\\w-])' // Not followed by word character or hyphen
// Unroll the loop: Inside the opening shortcode tag
. '[^\\]\\/]*' // Not a closing bracket or forward slash
. '(?:'
. '\\/(?!\\])' // A forward slash not followed by a closing bracket
. '[^\\]\\/]*' // Not a closing bracket or forward slash
. ')*?'
. '(?:'
. '\\/\\]' // Self closing tag and closing bracket
. '|'
. '\\]' // Closing bracket
. '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
. '[^\\[]*+' // Not an opening bracket
. '(?:'
. '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
. '[^\\[]*+' // Not an opening bracket
. ')*+'
. '\\[\\/\\2\\]' // Closing shortcode tag
. ')?'
. ')'
. ')'
. '(?:' . $spaces . ')*+' // optional trailing whitespace
. '<\\/p>' // closing paragraph
. '/';
return preg_replace( $pattern, '$1', $pee );
}
/**
* Checks to see if a string is utf8 encoded.
*
* NOTE: This function checks for 5-Byte sequences, UTF8
* has Bytes Sequences with a maximum length of 4.
*
* @author bmorel at ssi dot fr (modified)
* @since 1.2.1
*
* @param string $str The string to be checked
* @return bool True if $str fits a UTF-8 model, false otherwise.
*/
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; $j++) { // n bytes matching 10bbbbbb follow ?
if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
return false;
}
}
return true;
}
/**
* Converts a number of special characters into their HTML entities.
*
* Specifically deals with: &, <, >, ", and '.
*
* $quote_style can be set to ENT_COMPAT to encode " to
* &quot;, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
*
* @since 1.2.2
* @access private
*
* @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 ) {
$string = (string) $string;
if ( 0 === strlen( $string ) )
return '';
// Don't bother if there are no specialchars - saves some processing
if ( ! preg_match( '/[&<>"\']/', $string ) )
return $string;
// Account for the previous behaviour of the function when the $quote_style is not an accepted value
if ( empty( $quote_style ) )
$quote_style = ENT_NOQUOTES;
elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
$quote_style = ENT_QUOTES;
// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
if ( ! $charset ) {
static $_charset = null;
if ( ! isset( $_charset ) ) {
$alloptions = wp_load_alloptions();
$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
}
$charset = $_charset;
}
if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
$charset = 'UTF-8';
$_quote_style = $quote_style;
if ( $quote_style === 'double' ) {
$quote_style = ENT_COMPAT;
$_quote_style = ENT_COMPAT;
} elseif ( $quote_style === 'single' ) {
$quote_style = ENT_NOQUOTES;
}
if ( ! $double_encode ) {
// Guarantee every &entity; is valid, convert &garbage; into &amp;garbage;
// This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
$string = wp_kses_normalize_entities( $string );
}
$string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode );
// Backwards compatibility
if ( 'single' === $_quote_style )
$string = str_replace( "'", '&#039;', $string );
return $string;
}
/**
* Converts a number of HTML entities into their special characters.
*
* Specifically deals with: &, <, >, ", and '.
*
* $quote_style can be set to ENT_COMPAT to decode " entities,
* or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
*
* @since 2.8.0
*
* @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 ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Don't bother if there are no entities - saves a lot of processing
if ( strpos( $string, '&' ) === false ) {
return $string;
}
// Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
// More complete than get_html_translation_table( HTML_SPECIALCHARS )
$single = array( '&#039;' => '\'', '&#x27;' => '\'' );
$single_preg = array( '/&#0*39;/' => '&#039;', '/&#x0*27;/i' => '&#x27;' );
$double = array( '&quot;' => '"', '&#034;' => '"', '&#x22;' => '"' );
$double_preg = array( '/&#0*34;/' => '&#034;', '/&#x0*22;/i' => '&#x22;' );
$others = array( '&lt;' => '<', '&#060;' => '<', '&gt;' => '>', '&#062;' => '>', '&amp;' => '&', '&#038;' => '&', '&#x26;' => '&' );
$others_preg = array( '/&#0*60;/' => '&#060;', '/&#0*62;/' => '&#062;', '/&#0*38;/' => '&#038;', '/&#x0*26;/i' => '&#x26;' );
if ( $quote_style === ENT_QUOTES ) {
$translation = array_merge( $single, $double, $others );
$translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
} elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
$translation = array_merge( $double, $others );
$translation_preg = array_merge( $double_preg, $others_preg );
} elseif ( $quote_style === 'single' ) {
$translation = array_merge( $single, $others );
$translation_preg = array_merge( $single_preg, $others_preg );
} elseif ( $quote_style === ENT_NOQUOTES ) {
$translation = $others;
$translation_preg = $others_preg;
}
// Remove zero padding on numeric entities
$string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
// Replace characters according to translation table
return strtr( $string, $translation );
}
/**
* Checks for invalid UTF8 in a string.
*
* @since 2.8.0
*
* @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 ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Store the site charset as a static to avoid multiple calls to get_option()
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 ) {
return $string;
}
// Check for support for utf8 in the installed PCRE library once and store the result in a static
static $utf8_pcre = null;
if ( ! isset( $utf8_pcre ) ) {
$utf8_pcre = @preg_match( '/^./u', 'a' );
}
// We can't demand utf8 in the PCRE installation, so just return the string in those cases
if ( !$utf8_pcre ) {
return $string;
}
// preg_match fails when it encounters invalid UTF8 in $string
if ( 1 === @preg_match( '/^./us', $string ) ) {
return $string;
}
// Attempt to strip the bad chars if requested (not recommended)
if ( $strip && function_exists( 'iconv' ) ) {
return iconv( 'utf-8', 'utf-8', $string );
}
return '';
}
/**
* Encode the Unicode values to be used in the URI.
*
* @since 1.5.0
*
* @param string $utf8_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 ) {
$unicode = '';
$values = array();
$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 ] );
if ( $value < 128 ) {
if ( $length && ( $unicode_length >= $length ) )
break;
$unicode .= chr($value);
$unicode_length++;
} else {
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 ) {
for ( $j = 0; $j < $num_octets; $j++ ) {
$unicode .= '%' . dechex( $values[ $j ] );
}
$unicode_length += $num_octets * 3;
$values = array();
$num_octets = 1;
}
}
}
return $unicode;
}
/**
* Converts all accent characters to ASCII characters.
*
* If there are no accent characters, then the string given is just returned.
*
* @since 1.2.1
*
* @param string $string Text that might have accent characters
* @return string Filtered string with replaced "nice" characters.
*/
function remove_accents( $string ) {
if ( !preg_match('/[\x80-\xff]/', $string) )
return $string;
if (seems_utf8($string)) {
$chars = array(
// Decompositions for Latin-1 Supplement
chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
// Decompositions for Latin Extended-A
chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
// Decompositions for Latin Extended-B
chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
// Euro Sign
chr(226).chr(130).chr(172) => 'E',
// GBP (Pound) Sign
chr(194).chr(163) => '',
// Vowels with diacritic (Vietnamese)
// unmarked
chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
// grave accent
chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
// hook
chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
// tilde
chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
// acute accent
chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
// dot below
chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
// Vowels with diacritic (Chinese, Hanyu Pinyin)
chr(201).chr(145) => 'a',
// macron
chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
// acute accent
chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
// caron
chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
// grave accent
chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
);
// Used for locale-specific rules
$locale = get_locale();
if ( 'de_DE' == $locale || 'de_DE_formal' == $locale ) {
$chars[ chr(195).chr(132) ] = 'Ae';
$chars[ chr(195).chr(164) ] = 'ae';
$chars[ chr(195).chr(150) ] = 'Oe';
$chars[ chr(195).chr(182) ] = 'oe';
$chars[ chr(195).chr(156) ] = 'Ue';
$chars[ chr(195).chr(188) ] = 'ue';
$chars[ chr(195).chr(159) ] = 'ss';
} elseif ( 'da_DK' === $locale ) {
$chars[ chr(195).chr(134) ] = 'Ae';
$chars[ chr(195).chr(166) ] = 'ae';
$chars[ chr(195).chr(152) ] = 'Oe';
$chars[ chr(195).chr(184) ] = 'oe';
$chars[ chr(195).chr(133) ] = 'Aa';
$chars[ chr(195).chr(165) ] = 'aa';
}
$string = strtr($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)
.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
.chr(252).chr(253).chr(255);
$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);
}
return $string;
}
/**
* Sanitizes a filename, replacing whitespace with dashes.
*
* Removes special characters that are illegal in filenames on certain
* 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.
*
* @since 2.1.0
*
* @param string $filename The filename to be sanitized
* @return string The sanitized filename
*/
function sanitize_file_name( $filename ) {
$filename_raw = $filename;
$special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%", "+", chr(0));
/**
* Filter the list of characters to remove from a filename.
*
* @since 2.8.0
*
* @param array $special_chars Characters to remove.
* @param string $filename_raw Filename as it was passed into sanitize_file_name().
*/
$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 = str_replace( array( '%20', '+' ), '-', $filename );
$filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
$filename = trim( $filename, '.-_' );
// 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.
*
* @since 2.8.0
*
* @param string $filename Sanitized filename.
* @param string $filename_raw The filename prior to sanitization.
*/
return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
}
// Process multiple extensions
$filename = array_shift($parts);
$extension = array_pop($parts);
$mimes = get_allowed_mime_types();
/*
* Loop over any intermediate extensions. Postfix them with a trailing underscore
* if they are a 2 - 5 character long alpha string not in the extension whitelist.
*/
foreach ( (array) $parts as $part) {
$filename .= '.' . $part;
if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
$allowed = false;
foreach ( $mimes as $ext_preg => $mime_match ) {
$ext_preg = '!^(' . $ext_preg . ')$!i';
if ( preg_match( $ext_preg, $part ) ) {
$allowed = true;
break;
}
}
if ( !$allowed )
$filename .= '_';
}
}
$filename .= '.' . $extension;
/** This filter is documented in wp-includes/formatting.php */
return apply_filters('sanitize_file_name', $filename, $filename_raw);
}
/**
* Sanitizes a username, stripping out unsafe characters.
*
* 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.
*
* @since 2.0.0
*
* @param string $username The username to be sanitized.
* @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 ) {
$raw_username = $username;
$username = wp_strip_all_tags( $username );
$username = remove_accents( $username );
// Kill octets
$username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
$username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
// If strict, reduce to ASCII for max portability.
if ( $strict )
$username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
$username = trim( $username );
// Consolidate contiguous whitespace
$username = preg_replace( '|\s+|', ' ', $username );
/**
* Filter a sanitized username string.
*
* @since 2.0.1
*
* @param string $username Sanitized username.
* @param string $raw_username The username prior to sanitization.
* @param bool $strict Whether to limit the sanitization to specific characters. Default false.
*/
return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
}
/**
* Sanitizes a string key.
*
* Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
*
* @since 3.0.0
*
* @param string $key String key
* @return string Sanitized key
*/
function sanitize_key( $key ) {
$raw_key = $key;
$key = strtolower( $key );
$key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
/**
* Filter a sanitized key string.
*
* @since 3.0.0
*
* @param string $key Sanitized key.
* @param string $raw_key The key prior to sanitization.
*/
return apply_filters( 'sanitize_key', $key, $raw_key );
}
/**
* Sanitizes a title, or returns a fallback title.
*
* Specifically, HTML and PHP tags are stripped. Further actions can be added
* via the plugin API. If $title is empty and $fallback_title is set, the latter
* will be used.
*
* @since 1.0.0
*
* @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
* @return string The sanitized string.
*/
function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
$raw_title = $title;
if ( 'save' == $context )
$title = remove_accents($title);
/**
* Filter a sanitized title string.
*
* @since 1.2.0
*
* @param string $title Sanitized title.
* @param string $raw_title The title prior to sanitization.
* @param string $context The context for which the title is being sanitized.
*/
$title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
if ( '' === $title || false === $title )
$title = $fallback_title;
return $title;
}
/**
* Sanitizes a title with the 'query' context.
*
* Used for querying the database for a value from URL.
*
* @since 3.1.0
*
* @param string $title The string to be sanitized.
* @return string The sanitized string.
*/
function sanitize_title_for_query( $title ) {
return sanitize_title( $title, '', 'query' );
}
/**
* Sanitizes a title, replacing whitespace and a few other characters with dashes.
*
* Limits the output to alphanumeric characters, underscore (_) and dash (-).
* Whitespace becomes a dash.
*
* @since 1.2.0
*
* @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.
* @return string The sanitized title.
*/
function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
$title = strip_tags($title);
// Preserve escaped octets.
$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
// Remove percent signs that are not part of an octet.
$title = str_replace('%', '', $title);
// Restore octets.
$title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
if (seems_utf8($title)) {
if (function_exists('mb_strtolower')) {
$title = mb_strtolower($title, 'UTF-8');
}
$title = utf8_uri_encode($title, 200);
}
$title = strtolower($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( '&nbsp;', '&#160;', '&ndash;', '&#8211;', '&mdash;', '&#8212;' ), '-', $title );
// Strip these characters entirely
$title = str_replace( array(
// iexcl and iquest
'%c2%a1', '%c2%bf',
// angle quotes
'%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
// curly quotes
'%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
'%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
// copy, reg, deg, hellip and trade
'%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
// acute accents
'%c2%b4', '%cb%8a', '%cc%81', '%cd%81',
// grave accent, macron, caron
'%cc%80', '%cc%84', '%cc%8c',
), '', $title );
// Convert times to x
$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);
$title = trim($title, '-');
return $title;
}
/**
* Ensures a string is a valid SQL 'order by' clause.
*
* 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 clause to be validated.
* @return string|false Returns $orderby if valid, false otherwise.
*/
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;
}
/**
* Sanitizes an HTML classname to ensure it only contains valid characters.
*
* Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
* string then it will return the alternative value supplied.
*
* @todo Expand to support the full range of CDATA that a class attribute can contain.
*
* @since 2.8.0
*
* @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
*/
function sanitize_html_class( $class, $fallback = '' ) {
//Strip out any % encoded octets
$sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
//Limit to A-Z,a-z,0-9,_,-
$sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
if ( '' == $sanitized && $fallback ) {
return sanitize_html_class( $fallback );
}
/**
* Filter a sanitized HTML class string.
*
* @since 2.8.0
*
* @param string $sanitized The sanitized HTML class.
* @param string $class HTML class before sanitization.
* @param string $fallback The fallback string.
*/
return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
}
/**
* Converts lone & characters into `&#038;` (a.k.a. `&amp;`)
*
* @since 0.71
*
* @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 ) ) {
_deprecated_argument( __FUNCTION__, '0.71' );
}
if ( strpos( $content, '&' ) !== false ) {
$content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content );
}
return $content;
}
/**
* 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(
'&#128;' => '&#8364;', // the Euro sign
'&#129;' => '',
'&#130;' => '&#8218;', // these are Windows CP1252 specific characters
'&#131;' => '&#402;', // they would look weird on non-Windows browsers
'&#132;' => '&#8222;',
'&#133;' => '&#8230;',
'&#134;' => '&#8224;',
'&#135;' => '&#8225;',
'&#136;' => '&#710;',
'&#137;' => '&#8240;',
'&#138;' => '&#352;',
'&#139;' => '&#8249;',
'&#140;' => '&#338;',
'&#141;' => '',
'&#142;' => '&#381;',
'&#143;' => '',
'&#144;' => '',
'&#145;' => '&#8216;',
'&#146;' => '&#8217;',
'&#147;' => '&#8220;',
'&#148;' => '&#8221;',
'&#149;' => '&#8226;',
'&#150;' => '&#8211;',
'&#151;' => '&#8212;',
'&#152;' => '&#732;',
'&#153;' => '&#8482;',
'&#154;' => '&#353;',
'&#155;' => '&#8250;',
'&#156;' => '&#339;',
'&#157;' => '',
'&#158;' => '&#382;',
'&#159;' => '&#376;'
);
if ( strpos( $content, '&#1' ) !== false ) {
$content = strtr( $content, $wp_htmltranswinuni );
}
return $content;
}
/**
* Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
*
* @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.
* @return string Balanced text
*/
function balanceTags( $text, $force = false ) {
if ( $force || get_option('use_balanceTags') == 1 ) {
return force_balance_tags( $text );
} else {
return $text;
}
}
/**
* Balances tags of string using a modified stack.
*
* @since 2.0.4
*
* @author Leonard Lin <leonard@acm.org>
* @license GPL
* @copyright November 4, 2001
* @version 1.1
* @todo Make better - change loop condition to $text in 1.2
* @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
* 1.1 Fixed handling of append/stack pop order of end text
* Added Cleaning Hooks
* 1.0 First Version
*
* @param string $text Text to be balanced.
* @return string Balanced text.
*/
function force_balance_tags( $text ) {
$tagstack = array();
$stacksize = 0;
$tagqueue = '';
$newtext = '';
// Known single-entity/self-closing tags
$single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
// Tags that can be immediately nested within themselves
$nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
// WP bug fix for comments - in case you REALLY meant to type '< !--'
$text = str_replace('< !--', '< !--', $text);
// WP bug fix for LOVE <3 (and other situations with '<' before a number)
$text = preg_replace('#<([0-9]{1})#', '&lt;$1', $text);
while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
$newtext .= $tagqueue;
$i = strpos($text, $regex[0]);
$l = strlen($regex[0]);
// clear the shifter
$tagqueue = '';
// Pop or Push
if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
$tag = strtolower(substr($regex[1],1));
// if too many closing tags
if ( $stacksize <= 0 ) {
$tag = '';
// or close to be safe $tag = '/' . $tag;
}
// if stacktop value = tag close value then pop
elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
$tag = '</' . $tag . '>'; // Close Tag
// Pop
array_pop( $tagstack );
$stacksize--;
} else { // closing tag not at top, search for it
for ( $j = $stacksize-1; $j >= 0; $j-- ) {
if ( $tagstack[$j] == $tag ) {
// add tag to tagqueue
for ( $k = $stacksize-1; $k >= $j; $k--) {
$tagqueue .= '</' . array_pop( $tagstack ) . '>';
$stacksize--;
}
break;
}
}
$tag = '';
}
} else { // Begin Tag
$tag = strtolower($regex[1]);
// Tag Cleaning
// If it's an empty tag "< >", do nothing
if ( '' == $tag ) {
// do nothing
}
// ElseIf it presents itself as a self-closing tag...
elseif ( substr( $regex[2], -1 ) == '/' ) {
// ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
// immediately close it with a closing tag (the tag will encapsulate no text as a result)
if ( ! in_array( $tag, $single_tags ) )
$regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
}
// ElseIf it's a known single-entity tag but it doesn't close itself, do so
elseif ( in_array($tag, $single_tags) ) {
$regex[2] .= '/';
}
// Else it's not a single-entity tag
else {
// If the top of the stack is the same as the tag we want to push, close previous tag
if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
$tagqueue = '</' . array_pop( $tagstack ) . '>';
$stacksize--;
}
$stacksize = array_push( $tagstack, $tag );
}
// Attributes
$attributes = $regex[2];
if ( ! empty( $attributes ) && $attributes[0] != '>' )
$attributes = ' ' . $attributes;
$tag = '<' . $tag . $attributes . '>';
//If already queuing a close tag, then put this tag on, too
if ( !empty($tagqueue) ) {
$tagqueue .= $tag;
$tag = '';
}
}
$newtext .= substr($text, 0, $i) . $tag;
$text = substr($text, $i + $l);
}
// Clear Tag Queue
$newtext .= $tagqueue;
// Add Remaining text
$newtext .= $text;
// Empty Stack
while( $x = array_pop($tagstack) )
$newtext .= '</' . $x . '>'; // Add remaining tags to close
// WP fix for the bug with HTML comments
$newtext = str_replace("< !--","<!--",$newtext);
$newtext = str_replace("< !--","< !--",$newtext);
return $newtext;
}
/**
* 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 $richedit is set to true,
* it is simply a holder for the 'format_to_edit' filter.
*
* @since 0.71
* @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
*
* @param string $content The text about to be edited.
* @param bool $rich_text Optional. Whether `$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, $rich_text = false ) {
/**
* Filter 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 ( ! $rich_text )
$content = esc_textarea( $content );
return $content;
}
/**
* Add leading zeros when necessary.
*
* If you set the threshold to '4' and the number is '10', then you will get
* back '0010'. If you set the threshold to '4' and the number is '5000', then you
* will get back '5000'.
*
* Uses sprintf to append the amount of zeros based on the $threshold parameter
* and the size of the number. If the number is large enough, then no zeros will
* be appended.
*
* @since 0.71
*
* @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 );
}
/**
* Adds backslashes before letters and before a number at the start of a string.
*
* @since 0.71
*
* @param string $string Value to which backslashes will be added.
* @return string String with backslashes inserted.
*/
function backslashit( $string ) {
if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' )
$string = '\\\\' . $string;
return addcslashes( $string, 'A..Za..z' );
}
/**
* Appends a trailing slash.
*
* Will remove trailing forward and backslashes if it exists already before adding
* a trailing forward slash. This prevents double slashing a string or path.
*
* The primary use of this is for paths and thus should be used for paths. It is
* not restricted to paths and offers no specific path support.
*
* @since 1.2.0
*
* @param string $string What to add the trailing slash to.
* @return string String with trailing slash added.
*/
function trailingslashit( $string ) {
return untrailingslashit( $string ) . '/';
}
/**
* Removes trailing forward slashes and backslashes if they exist.
*
* The primary use of this is for paths and thus should be used for paths. It is
* not restricted to paths and offers no specific path support.
*
* @since 2.2.0
*
* @param string $string What to remove the trailing slashes from.
* @return string String without the trailing slashes.
*/
function untrailingslashit( $string ) {
return rtrim( $string, '/\\' );
}
/**
* 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.
*
* @since 0.71
*
* @param string $gpc The string returned from HTTP request data.
* @return string Returns a string escaped with slashes.
*/
function addslashes_gpc($gpc) {
if ( get_magic_quotes_gpc() )
$gpc = stripslashes($gpc);
return wp_slash($gpc);
}
/**
* 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 ) {
return map_deep( $value, 'stripslashes_from_strings_only' );
}
/**
* 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 mixed $value The array or string to be encoded.
* @return mixed $value The encoded value.
*/
function urlencode_deep( $value ) {
return map_deep( $value, 'urlencode' );
}
/**
* Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
*
* @since 3.4.0
*
* @param mixed $value The array or string to be encoded.
* @return mixed $value The encoded value.
*/
function rawurlencode_deep( $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' );
}
/**
* Converts email addresses characters to HTML entities to block spam bots.
*
* @since 0.71
*
* @param string $email_address Email address.
* @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, $len = strlen( $email_address ); $i < $len; $i++ ) {
$j = rand( 0, 1 + $hex_encoding );
if ( $j == 0 ) {
$email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
} elseif ( $j == 1 ) {
$email_no_spam_address .= $email_address[$i];
} elseif ( $j == 2 ) {
$email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[$i] ) ), 2 );
}
}
return str_replace( '@', '&#64;', $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()}.
*
* @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 ) {
$url = $matches[2];
if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
// If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
// Then we can let the parenthesis balancer do its thing below.
$url .= $matches[3];
$suffix = '';
} else {
$suffix = $matches[3];
}
// Include parentheses in the URL only if paired
while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
$suffix = strrchr( $url, ')' ) . $suffix;
$url = substr( $url, 0, strrpos( $url, ')' ) );
}
$url = esc_url($url);
if ( empty($url) )
return $matches[0];
return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
}
/**
* 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()}.
*
* @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 ) {
$ret = '';
$dest = $matches[2];
$dest = 'http://' . $dest;
// removed trailing [.,;:)] from URL
if ( in_array( substr($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()}.
*
* @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 ) {
$email = $matches[2] . '@' . $matches[3];
return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
}
/**
* Convert plaintext URI to HTML links.
*
* Converts URI, www and ftp, and email addresses. Finishes by fixing links
* within links.
*
* @since 0.71
*
* @param string $text Content to convert URIs.
* @return string Content with converted URIs.
*/
function make_clickable( $text ) {
$r = '';
$textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
$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 ) || preg_match( '|^<script[\s>]|i', $piece ) || preg_match( '|^<style[\s>]|i', $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 ) ) ) {
$r .= $piece;
continue;
}
// Long strings might contain expensive edge cases ...
if ( 10000 < strlen( $piece ) ) {
// ... break it up
foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
if ( 2101 < strlen( $chunk ) ) {
$r .= $chunk; // Too big, no whitespace: bail.
} else {
$r .= make_clickable( $chunk );
}
}
} else {
$ret = " $piece "; // Pad with whitespace to simplify the regexes
$url_clickable = '~
([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
( # 2: URL
[\\w]{1,20}+:// # Scheme and hier-part prefix
(?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
(?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
[\'.,;:!?)] # Punctuation URL character
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
)*
)
(\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
// Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
$ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
$ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
$ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
$ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
$r .= $ret;
}
}
// Cleanup of accidental links within links
return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
}
/**
* Breaks a string into chunks by splitting at whitespace characters.
* The length of each returned chunk is as close to the specified length goal as possible,
* with the caveat that each chunk includes its trailing delimiter.
* Chunks longer than the goal are guaranteed to not have any inner whitespace.
*
* Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
*
* Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
*
* _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.
* @return array Numeric array of chunks.
*/
function _split_str_by_whitespace( $string, $goal ) {
$chunks = array();
$string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
while ( $goal < strlen( $string_nullspace ) ) {
$pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
if ( false === $pos ) {
$pos = strpos( $string_nullspace, "\000", $goal + 1 );
if ( false === $pos ) {
break;
}
}
$chunks[] = substr( $string, 0, $pos + 1 );
$string = substr( $string, $pos + 1 );
$string_nullspace = substr( $string_nullspace, $pos + 1 );
}
if ( $string ) {
$chunks[] = $string;
}
return $chunks;
}
/**
* Adds rel nofollow string to all HTML A elements in content.
*
* @since 1.5.0
*
* @param string $text Content that may contain HTML A elements.
* @return string Converted content.
*/
function wp_rel_nofollow( $text ) {
// 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);
return wp_slash( $text );
}
/**
* Callback to add rel=nofollow string to HTML A element.
*
* Will remove already existing rel="nofollow" and rel='nofollow' from the
* string to prevent from invalidating (X)HTML.
*
* @since 2.3.0
*
* @param array $matches Single Match
* @return string HTML A Element with rel nofollow.
*/
function wp_rel_nofollow_callback( $matches ) {
$text = $matches[1];
$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()}.
* Looks up one smiley code in the $wpsmiliestrans global array and returns an
* `<img>` string for that smiley.
*
* @since 2.8.0
*
* @global array $wpsmiliestrans
*
* @param array $matches Single match. Smiley code to convert to image.
* @return string Image string for smiley.
*/
function translate_smiley( $matches ) {
global $wpsmiliestrans;
if ( count( $matches ) == 0 )
return '';
$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.
*
* @since 2.9.0
*
* @param string $smiley_url URL for the smiley image.
* @param string $img Filename for the smiley image.
* @param string $site_url Site URL, as returned by site_url().
*/
$src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
}
/**
* Convert text equivalent of smilies to images.
*
* Will only convert smilies if the option 'use_smilies' is true and the global
* used in the function isn't empty.
*
* @since 0.71
*
* @global string|array $wp_smiliessearch
*
* @param string $text Content to convert smilies from text.
* @return string Converted content with text smilies replaced with images.
*/
function convert_smilies( $text ) {
global $wp_smiliessearch;
$output = '';
if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
// HTML loop taken from texturize function, could possible be consolidated
$textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
$stop = count( $textarr );// loop stuff
// Ignore proessing 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] ) {
$content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
}
// did we exit ignore block
if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
$ignore_block_element = '';
}
$output .= $content;
}
} else {
// return default text.
$output = $text;
}
return $output;
}
/**
* Verifies that an email is valid.
*
* Does not grok i18n domains. Not RFC compliant.
*
* @since 0.71
*
* @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' );
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
/**
* Filter 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',
* 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
*
* @since 2.8.0
*
* @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 $context Context under which the email was tested.
*/
return apply_filters( 'is_email', false, $email, 'email_too_short' );
}
// Test for an @ character after the first position
if ( strpos( $email, '@', 1 ) === false ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'email_no_at' );
}
// Split out the local and domain parts
list( $local, $domain ) = explode( '@', $email, 2 );
// LOCAL PART
// Test for invalid characters
if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
}
// DOMAIN PART
// Test for sequences of periods
if ( preg_match( '/\.{2,}/', $domain ) ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
}
// Test for leading and trailing periods and whitespace
if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
}
// Split the domain into subs
$subs = explode( '.', $domain );
// Assume the domain will have at least two subs
if ( 2 > count( $subs ) ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
}
// Loop through each sub
foreach ( $subs as $sub ) {
// Test for leading and trailing hyphens and whitespace
if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
}
// Test for invalid characters
if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
}
}
// Congratulations your email made it!
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', $email, $email, null );
}
/**
* Convert to ASCII from email subjects.
*
* @since 1.2.0
*
* @param string $string Subject line
* @return string Converted string to ASCII
*/
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]);
return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
}
}
/**
* Helper function to convert hex encoded chars to ASCII
*
* @since 3.1.0
* @access private
*
* @param array $match The preg_replace_callback matches array
* @return string Converted chars
*/
function _wp_iso_convert( $match ) {
return chr( hexdec( strtolower( $match[1] ) ) );
}
/**
* Returns a date in the GMT equivalent.
*
* Requires and returns a date in the Y-m-d H:i:s format. If there is a
* timezone_string available, the date is assumed to be in that timezone,
* otherwise it simply subtracts the value of the 'gmt_offset' option. Return
* format can be overridden using the $format parameter.
*
* @since 1.2.0
*
* @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.
*/
function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
$tz = get_option( 'timezone_string' );
if ( $tz ) {
$datetime = date_create( $string, new DateTimeZone( $tz ) );
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 ) ) {
$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 );
}
return $string_gmt;
}
/**
* Converts a GMT date into the correct format for the blog.
*
* Requires and returns a date in the Y-m-d H:i:s format. If there is a
* timezone_string available, the returned date is in that timezone, otherwise
* it simply adds the value of gmt_offset. Return format can be overridden
* using the $format parameter
*
* @since 1.2.0
*
* @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 Formatted date relative to the timezone / GMT offset.
*/
function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
$tz = get_option( 'timezone_string' );
if ( $tz ) {
$datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
if ( ! $datetime )
return date( $format, 0 );
$datetime->setTimezone( new DateTimeZone( $tz ) );
$string_localtime = $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 date( $format, 0 );
$string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
$string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
}
return $string_localtime;
}
/**
* Computes an offset in seconds from an iso8601 timezone.
*
* @since 1.5.0
*
* @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
* @return int|float The offset in seconds.
*/
function iso8601_timezone_to_offset( $timezone ) {
// $timezone is either 'Z' or '[+|-]hhmm'
if ($timezone == 'Z') {
$offset = 0;
} else {
$sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
$hours = intval(substr($timezone, 1, 2));
$minutes = intval(substr($timezone, 3, 4)) / 60;
$offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
}
return $offset;
}
/**
* Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
*
* @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'.
* @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
*/
function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
$timezone = strtolower($timezone);
if ($timezone == 'gmt') {
preg_match('#([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}#', $date_string, $date_bits);
if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
$offset = iso8601_timezone_to_offset($date_bits[7]);
} else { // we don't have a timezone, so we assume user local timezone (not server's!)
$offset = HOUR_IN_SECONDS * get_option('gmt_offset');
}
$timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
$timestamp -= $offset;
return gmdate('Y-m-d H:i:s', $timestamp);
} elseif ($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);
}
}
/**
* Strips out all characters that are not allowable in an email.
*
* @since 1.5.0
*
* @param string $email Email address to filter.
* @return string Filtered email address.
*/
function sanitize_email( $email ) {
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
/**
* Filter 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',
* 'domain_no_periods', 'domain_no_valid_subs', or no context.
*
* @since 2.8.0
*
* @param string $email The sanitized email address.
* @param string $email The email address, as provided to sanitize_email().
* @param string $message A message to pass to the user.
*/
return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
}
// Test for an @ character after the first position
if ( strpos( $email, '@', 1 ) === false ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
}
// Split out the local and domain parts
list( $local, $domain ) = explode( '@', $email, 2 );
// LOCAL PART
// Test for invalid characters
$local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
if ( '' === $local ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
}
// DOMAIN PART
// Test for sequences of periods
$domain = preg_replace( '/\.{2,}/', '', $domain );
if ( '' === $domain ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
}
// Test for leading and trailing periods and whitespace
$domain = trim( $domain, " \t\n\r\0\x0B." );
if ( '' === $domain ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
}
// Split the domain into subs
$subs = explode( '.', $domain );
// Assume the domain will have at least two subs
if ( 2 > count( $subs ) ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
}
// Create an array that will contain valid subs
$new_subs = array();
// Loop through each sub
foreach ( $subs as $sub ) {
// Test for leading and trailing hyphens
$sub = trim( $sub, " \t\n\r\0\x0B-" );
// Test for invalid characters
$sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
// If there's anything left, add it to the valid subs
if ( '' !== $sub ) {
$new_subs[] = $sub;
}
}
// If there aren't 2 or more valid subs
if ( 2 > count( $new_subs ) ) {
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
}
// Join valid subs into the new domain
$domain = join( '.', $new_subs );
// Put the email back together
$email = $local . '@' . $domain;
// Congratulations your email made it!
/** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', $email, $email, null );
}
/**
* Determines the difference between two timestamps.
*
* The difference is returned in a human readable format such as "1 hour",
* "5 mins", "2 days".
*
* @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.
* @return string Human readable time difference.
*/
function human_time_diff( $from, $to = '' ) {
if ( empty( $to ) ) {
$to = time();
}
$diff = (int) abs( $to - $from );
if ( $diff < HOUR_IN_SECONDS ) {
$mins = round( $diff / MINUTE_IN_SECONDS );
if ( $mins <= 1 )
$mins = 1;
/* translators: min=minute */
$since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
} elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
$hours = round( $diff / HOUR_IN_SECONDS );
if ( $hours <= 1 )
$hours = 1;
$since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
} elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
$days = round( $diff / DAY_IN_SECONDS );
if ( $days <= 1 )
$days = 1;
$since = sprintf( _n( '%s day', '%s days', $days ), $days );
} 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 >= MONTH_IN_SECONDS ) {
$months = round( $diff / MONTH_IN_SECONDS );
if ( $months <= 1 )
$months = 1;
$since = sprintf( _n( '%s month', '%s months', $months ), $months );
} elseif ( $diff >= YEAR_IN_SECONDS ) {
$years = round( $diff / YEAR_IN_SECONDS );
if ( $years <= 1 )
$years = 1;
$since = sprintf( _n( '%s year', '%s years', $years ), $years );
}
/**
* Filter 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 );
}
/**
* Generates an excerpt from the content, if needed.
*
* The excerpt word amount will be 55 words and if the amount is greater than
* that, then the string ' [&hellip;]' 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 ' [&hellip;]' string can be modified by plugins/themes using the 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 = '' ) {
$raw_excerpt = $text;
if ( '' == $text ) {
$text = get_the_content('');
$text = strip_shortcodes( $text );
/** This filter is documented in wp-includes/post-template.php */
$text = apply_filters( 'the_content', $text );
$text = str_replace(']]>', ']]&gt;', $text);
/**
* Filter the number of words in an excerpt.
*
* @since 2.7.0
*
* @param int $number The number of words. Default 55.
*/
$excerpt_length = apply_filters( 'excerpt_length', 55 );
/**
* Filter the string in the "more" link displayed after a trimmed excerpt.
*
* @since 2.9.0
*
* @param string $more_string The string shown within the more link.
*/
$excerpt_more = apply_filters( 'excerpt_more', ' ' . '[&hellip;]' );
$text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
}
/**
* Filter the trimmed excerpt string.
*
* @since 2.8.0
*
* @param string $text The trimmed text.
* @param string $raw_excerpt The text prior to trimming.
*/
return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
}
/**
* Trims text to a certain number of words.
*
* This function is localized. For languages that count 'words' by the individual
* character (such as East Asian languages), the $num_words argument will apply
* to the number of individual characters.
*
* @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 '&hellip;'.
* @return string Trimmed text.
*/
function wp_trim_words( $text, $num_words = 55, $more = null ) {
if ( null === $more ) {
$more = __( '&hellip;' );
}
$original_text = $text;
$text = wp_strip_all_tags( $text );
/*
* translators: If your word count is based on single characters (e.g. East Asian characters),
* enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
* Do not translate into your own language.
*/
if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && preg_match( '/^utf\-?8$/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 );
$sep = '';
} else {
$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 );
$text = $text . $more;
} else {
$text = implode( $sep, $words_array );
}
/**
* Filter the text content after words have been trimmed.
*
* @since 3.3.0
*
* @param string $text The trimmed text.
* @param int $num_words The number of words to trim the text to. Default 5.
* @param string $more An optional string to append to the end of the trimmed text, e.g. &hellip;.
* @param string $original_text The text before it was trimmed.
*/
return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
}
/**
* Converts named entities into numbered entities.
*
* @since 1.5.1
*
* @param string $text The text within which entities will be converted.
* @return string Text with converted entities.
*/
function ent2ncr( $text ) {
/**
* Filter text before named entities are converted into numbered entities.
*
* A non-null string must be returned for the filter to be evaluated.
*
* @since 3.3.0
*
* @param null $converted_text The text to be converted. Default null.
* @param string $text The text prior to entity conversion.
*/
$filtered = apply_filters( 'pre_ent2ncr', null, $text );
if ( null !== $filtered )
return $filtered;
$to_ncr = array(
'&quot;' => '&#34;',
'&amp;' => '&#38;',
'&lt;' => '&#60;',
'&gt;' => '&#62;',
'|' => '&#124;',
'&nbsp;' => '&#160;',
'&iexcl;' => '&#161;',
'&cent;' => '&#162;',
'&pound;' => '&#163;',
'&curren;' => '&#164;',
'&yen;' => '&#165;',
'&brvbar;' => '&#166;',
'&brkbar;' => '&#166;',
'&sect;' => '&#167;',
'&uml;' => '&#168;',
'&die;' => '&#168;',
'&copy;' => '&#169;',
'&ordf;' => '&#170;',
'&laquo;' => '&#171;',
'&not;' => '&#172;',
'&shy;' => '&#173;',
'&reg;' => '&#174;',
'&macr;' => '&#175;',
'&hibar;' => '&#175;',
'&deg;' => '&#176;',
'&plusmn;' => '&#177;',
'&sup2;' => '&#178;',
'&sup3;' => '&#179;',
'&acute;' => '&#180;',
'&micro;' => '&#181;',
'&para;' => '&#182;',
'&middot;' => '&#183;',
'&cedil;' => '&#184;',
'&sup1;' => '&#185;',
'&ordm;' => '&#186;',
'&raquo;' => '&#187;',
'&frac14;' => '&#188;',
'&frac12;' => '&#189;',
'&frac34;' => '&#190;',
'&iquest;' => '&#191;',
'&Agrave;' => '&#192;',
'&Aacute;' => '&#193;',
'&Acirc;' => '&#194;',
'&Atilde;' => '&#195;',
'&Auml;' => '&#196;',
'&Aring;' => '&#197;',
'&AElig;' => '&#198;',
'&Ccedil;' => '&#199;',
'&Egrave;' => '&#200;',
'&Eacute;' => '&#201;',
'&Ecirc;' => '&#202;',
'&Euml;' => '&#203;',
'&Igrave;' => '&#204;',
'&Iacute;' => '&#205;',
'&Icirc;' => '&#206;',
'&Iuml;' => '&#207;',
'&ETH;' => '&#208;',
'&Ntilde;' => '&#209;',
'&Ograve;' => '&#210;',
'&Oacute;' => '&#211;',
'&Ocirc;' => '&#212;',
'&Otilde;' => '&#213;',
'&Ouml;' => '&#214;',
'&times;' => '&#215;',
'&Oslash;' => '&#216;',
'&Ugrave;' => '&#217;',
'&Uacute;' => '&#218;',
'&Ucirc;' => '&#219;',
'&Uuml;' => '&#220;',
'&Yacute;' => '&#221;',
'&THORN;' => '&#222;',
'&szlig;' => '&#223;',
'&agrave;' => '&#224;',
'&aacute;' => '&#225;',
'&acirc;' => '&#226;',
'&atilde;' => '&#227;',
'&auml;' => '&#228;',
'&aring;' => '&#229;',
'&aelig;' => '&#230;',
'&ccedil;' => '&#231;',
'&egrave;' => '&#232;',
'&eacute;' => '&#233;',
'&ecirc;' => '&#234;',
'&euml;' => '&#235;',
'&igrave;' => '&#236;',
'&iacute;' => '&#237;',
'&icirc;' => '&#238;',
'&iuml;' => '&#239;',
'&eth;' => '&#240;',
'&ntilde;' => '&#241;',
'&ograve;' => '&#242;',
'&oacute;' => '&#243;',
'&ocirc;' => '&#244;',
'&otilde;' => '&#245;',
'&ouml;' => '&#246;',
'&divide;' => '&#247;',
'&oslash;' => '&#248;',
'&ugrave;' => '&#249;',
'&uacute;' => '&#250;',
'&ucirc;' => '&#251;',
'&uuml;' => '&#252;',
'&yacute;' => '&#253;',
'&thorn;' => '&#254;',
'&yuml;' => '&#255;',
'&OElig;' => '&#338;',
'&oelig;' => '&#339;',
'&Scaron;' => '&#352;',
'&scaron;' => '&#353;',
'&Yuml;' => '&#376;',
'&fnof;' => '&#402;',
'&circ;' => '&#710;',
'&tilde;' => '&#732;',
'&Alpha;' => '&#913;',
'&Beta;' => '&#914;',
'&Gamma;' => '&#915;',
'&Delta;' => '&#916;',
'&Epsilon;' => '&#917;',
'&Zeta;' => '&#918;',
'&Eta;' => '&#919;',
'&Theta;' => '&#920;',
'&Iota;' => '&#921;',
'&Kappa;' => '&#922;',
'&Lambda;' => '&#923;',
'&Mu;' => '&#924;',
'&Nu;' => '&#925;',
'&Xi;' => '&#926;',
'&Omicron;' => '&#927;',
'&Pi;' => '&#928;',
'&Rho;' => '&#929;',
'&Sigma;' => '&#931;',
'&Tau;' => '&#932;',
'&Upsilon;' => '&#933;',
'&Phi;' => '&#934;',
'&Chi;' => '&#935;',
'&Psi;' => '&#936;',
'&Omega;' => '&#937;',
'&alpha;' => '&#945;',
'&beta;' => '&#946;',
'&gamma;' => '&#947;',
'&delta;' => '&#948;',
'&epsilon;' => '&#949;',
'&zeta;' => '&#950;',
'&eta;' => '&#951;',
'&theta;' => '&#952;',
'&iota;' => '&#953;',
'&kappa;' => '&#954;',
'&lambda;' => '&#955;',
'&mu;' => '&#956;',
'&nu;' => '&#957;',
'&xi;' => '&#958;',
'&omicron;' => '&#959;',
'&pi;' => '&#960;',
'&rho;' => '&#961;',
'&sigmaf;' => '&#962;',
'&sigma;' => '&#963;',
'&tau;' => '&#964;',
'&upsilon;' => '&#965;',
'&phi;' => '&#966;',
'&chi;' => '&#967;',
'&psi;' => '&#968;',
'&omega;' => '&#969;',
'&thetasym;' => '&#977;',
'&upsih;' => '&#978;',
'&piv;' => '&#982;',
'&ensp;' => '&#8194;',
'&emsp;' => '&#8195;',
'&thinsp;' => '&#8201;',
'&zwnj;' => '&#8204;',
'&zwj;' => '&#8205;',
'&lrm;' => '&#8206;',
'&rlm;' => '&#8207;',
'&ndash;' => '&#8211;',
'&mdash;' => '&#8212;',
'&lsquo;' => '&#8216;',
'&rsquo;' => '&#8217;',
'&sbquo;' => '&#8218;',
'&ldquo;' => '&#8220;',
'&rdquo;' => '&#8221;',
'&bdquo;' => '&#8222;',
'&dagger;' => '&#8224;',
'&Dagger;' => '&#8225;',
'&bull;' => '&#8226;',
'&hellip;' => '&#8230;',
'&permil;' => '&#8240;',
'&prime;' => '&#8242;',
'&Prime;' => '&#8243;',
'&lsaquo;' => '&#8249;',
'&rsaquo;' => '&#8250;',
'&oline;' => '&#8254;',
'&frasl;' => '&#8260;',
'&euro;' => '&#8364;',
'&image;' => '&#8465;',
'&weierp;' => '&#8472;',
'&real;' => '&#8476;',
'&trade;' => '&#8482;',
'&alefsym;' => '&#8501;',
'&crarr;' => '&#8629;',
'&lArr;' => '&#8656;',
'&uArr;' => '&#8657;',
'&rArr;' => '&#8658;',
'&dArr;' => '&#8659;',
'&hArr;' => '&#8660;',
'&forall;' => '&#8704;',
'&part;' => '&#8706;',
'&exist;' => '&#8707;',
'&empty;' => '&#8709;',
'&nabla;' => '&#8711;',
'&isin;' => '&#8712;',
'&notin;' => '&#8713;',
'&ni;' => '&#8715;',
'&prod;' => '&#8719;',
'&sum;' => '&#8721;',
'&minus;' => '&#8722;',
'&lowast;' => '&#8727;',
'&radic;' => '&#8730;',
'&prop;' => '&#8733;',
'&infin;' => '&#8734;',
'&ang;' => '&#8736;',
'&and;' => '&#8743;',
'&or;' => '&#8744;',
'&cap;' => '&#8745;',
'&cup;' => '&#8746;',
'&int;' => '&#8747;',
'&there4;' => '&#8756;',
'&sim;' => '&#8764;',
'&cong;' => '&#8773;',
'&asymp;' => '&#8776;',
'&ne;' => '&#8800;',
'&equiv;' => '&#8801;',
'&le;' => '&#8804;',
'&ge;' => '&#8805;',
'&sub;' => '&#8834;',
'&sup;' => '&#8835;',
'&nsub;' => '&#8836;',
'&sube;' => '&#8838;',
'&supe;' => '&#8839;',
'&oplus;' => '&#8853;',
'&otimes;' => '&#8855;',
'&perp;' => '&#8869;',
'&sdot;' => '&#8901;',
'&lceil;' => '&#8968;',
'&rceil;' => '&#8969;',
'&lfloor;' => '&#8970;',
'&rfloor;' => '&#8971;',
'&lang;' => '&#9001;',
'&rang;' => '&#9002;',
'&larr;' => '&#8592;',
'&uarr;' => '&#8593;',
'&rarr;' => '&#8594;',
'&darr;' => '&#8595;',
'&harr;' => '&#8596;',
'&loz;' => '&#9674;',
'&spades;' => '&#9824;',
'&clubs;' => '&#9827;',
'&hearts;' => '&#9829;',
'&diams;' => '&#9830;'
);
return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
}
/**
* Formats text for the editor.
*
* Generally the browsers treat everything inside a textarea as text, but
* it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
*
* The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
* filter will be applied to an empty string.
*
* @since 4.3.0
*
* @see _WP_Editors::editor()
*
* @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 format_for_editor( $text, $default_editor = null ) {
if ( $text ) {
$text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
}
/**
* Filter the text after it is formatted for the editor.
*
* @since 4.3.0
*
* @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( 'format_for_editor', $text, $default_editor );
}
/**
* Perform a deep string replace operation to ensure the values in $search are no longer present
*
* Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
* e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
* str_replace would return
*
* @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.
* @return string The string with the replaced svalues.
*/
function _deep_replace( $search, $subject ) {
$subject = (string) $subject;
$count = 1;
while ( $count ) {
$subject = str_replace( $search, '', $subject, $count );
}
return $subject;
}
/**
* Escapes data for use in a MySQL query.
*
* Usually you should prepare queries using wpdb::prepare().
* Sometimes, spot-escaping is required or useful. One example
* 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
*/
function esc_sql( $data ) {
global $wpdb;
return $wpdb->_escape( $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
* is applied to the returned cleaned URL.
*
* @since 2.8.0
*
* @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 'clean_url' filter is applied.
*/
function esc_url( $url, $protocols = null, $_context = 'display' ) {
$original_url = $url;
if ( '' == $url )
return $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(';//', '://', $url);
/* If the URL doesn't appear to contain a scheme, we
* presume it needs http:// prepended (unless a relative
* link starting with /, # or ? or a php file).
*/
if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
$url = 'http://' . $url;
// Replace ampersands and single quotes only when displaying.
if ( 'display' == $_context ) {
$url = wp_kses_normalize_entities( $url );
$url = str_replace( '&amp;', '&#038;', $url );
$url = str_replace( "'", '&#039;', $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 {
if ( ! is_array( $protocols ) )
$protocols = wp_allowed_protocols();
$good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
return '';
}
/**
* Filter a string cleaned and escaped for output as a URL.
*
* @since 2.3.0
*
* @param string $good_protocol_url The cleaned URL to be returned.
* @param string $original_url The URL prior to cleaning.
* @param string $_context If 'display', replace ampersands and single quotes only.
*/
return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
}
/**
* Performs esc_url() for database usage.
*
* @since 2.8.0
*
* @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 ) {
return esc_url( $url, $protocols, 'db' );
}
/**
* Convert entities, while preserving already-encoded entities.
*
* @link http://www.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 ) {
$translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
$translation_table[chr(38)] = '&';
return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&amp;", strtr($myHTML, $translation_table) );
}
/**
* Escape single quotes, htmlspecialchar " < > &, and fix line endings.
*
* 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.
*
* @since 2.8.0
*
* @param string $text The text to be escaped.
* @return string Escaped text.
*/
function esc_js( $text ) {
$safe_text = wp_check_invalid_utf8( $text );
$safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
$safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
$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.
*
* Text passed to esc_js() is stripped of invalid or special characters,
* and properly slashed for output.
*
* @since 2.0.6
*
* @param string $safe_text The text after it has been escaped.
* @param string $text The text prior to being escaped.
*/
return apply_filters( 'js_escape', $safe_text, $text );
}
/**
* Escaping for HTML blocks.
*
* @since 2.8.0
*
* @param string $text
* @return string
*/
function esc_html( $text ) {
$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.
*
* Text passed to esc_html() is stripped of invalid or special characters
* before output.
*
* @since 2.8.0
*
* @param string $safe_text The text after it has been escaped.
* @param string $text The text prior to being escaped.
*/
return apply_filters( 'esc_html', $safe_text, $text );
}
/**
* Escaping for HTML attributes.
*
* @since 2.8.0
*
* @param string $text
* @return string
*/
function esc_attr( $text ) {
$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.
*
* Text passed to esc_attr() is stripped of invalid or special characters
* before output.
*
* @since 2.0.6
*
* @param string $safe_text The text after it has been escaped.
* @param string $text The text prior to being escaped.
*/
return apply_filters( 'attribute_escape', $safe_text, $text );
}
/**
* Escaping for textarea values.
*
* @since 3.1.0
*
* @param string $text
* @return string
*/
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.
*
* @since 3.1.0
*
* @param string $safe_text The text after it has been escaped.
* @param string $text The text prior to being escaped.
*/
return apply_filters( 'esc_textarea', $safe_text, $text );
}
/**
* Escape an HTML tag name.
*
* @since 2.5.0
*
* @param string $tag_name
* @return string
*/
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.
*
* @since 2.8.0
*
* @param string $safe_tag The tag name after it has been escaped.
* @param string $tag_name The text before it was escaped.
*/
return apply_filters( 'tag_escape', $safe_tag, $tag_name );
}
/**
* Convert full URL paths to absolute paths.
*
* Removes the http or https protocols and the domain. Keeps the path '/' at the
* 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', '$2', $link );
}
/**
* Sanitises various option values based on the nature of the option.
*
* This is basically a switch statement which will pass $value through a number
* of functions depending on the $option.
*
* @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.
* @return string Sanitized value.
*/
function sanitize_option( $option, $value ) {
global $wpdb;
$original_value = $value;
$error = '';
switch ( $option ) {
case 'admin_email' :
case 'new_admin_email' :
$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_w':
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 'comment_max_links':
case 'page_on_front':
case 'page_for_posts':
case 'rss_excerpt_length':
case 'default_category':
case 'default_email_category':
case 'default_link_category':
case 'close_comments_days_old':
case 'comments_per_page':
case 'thread_comments_depth':
case 'users_can_register':
case 'start_of_week':
case 'site_icon':
$value = absint( $value );
break;
case 'posts_per_page':
case 'posts_per_rss':
$value = (int) $value;
if ( empty($value) )
$value = 1;
if ( $value < -1 )
$value = abs($value);
break;
case 'default_ping_status':
case 'default_comment_status':
// Options that if not there have 0 value but need to be something like "closed"
if ( $value == '0' || $value == '')
$value = 'closed';
break;
case 'blogdescription':
case 'blogname':
$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_html( $value );
}
break;
case 'blog_charset':
$value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
break;
case 'blog_public':
// This is the value if the settings checkbox is not checked on POST. Don't rely on this.
if ( null === $value )
$value = 1;
else
$value = intval( $value );
break;
case 'date_format':
case 'time_format':
case 'mailserver_url':
case 'mailserver_login':
case 'mailserver_pass':
case 'upload_path':
$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':
$value = explode( "\n", $value );
$value = array_filter( array_map( 'trim', $value ) );
$value = array_filter( array_map( 'esc_url_raw', $value ) );
$value = implode( "\n", $value );
break;
case 'gmt_offset':
$value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
break;
case 'siteurl':
$value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
if ( is_wp_error( $value ) ) {
$error = $value->get_error_message();
} else {
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':
$value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
if ( is_wp_error( $value ) ) {
$error = $value->get_error_message();
} else {
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 ( ! 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':
$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 ) ) );
if ( ! $value )
$value = '';
}
break;
case 'limited_email_domains':
case 'banned_email_domains':
$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();
foreach ( $domains as $domain ) {
if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
$value[] = $domain;
}
}
if ( ! $value )
$value = '';
}
break;
case 'timezone_string':
$allowed_zones = timezone_identifiers_list();
if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
$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 = $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 );
}
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}", $error );
}
}
/**
* Filter an option value following sanitization.
*
* @since 2.3.0
* @since 4.3.0 Added the `$original_value` parameter.
*
* @param string $value The sanitized option value.
* @param string $option The option name.
* @param string $original_value The original value passed to the function.
*/
return apply_filters( "sanitize_option_{$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.
*
* @since 2.2.1
*
* @param string $string The string to be parsed.
* @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.
*
* @since 2.3.0
*
* @param array $array The array populated with variables.
*/
$array = apply_filters( 'wp_parse_str', $array );
}
/**
* Convert lone less than signs.
*
* KSES already converts lone greater than signs.
*
* @since 2.3.0
*
* @param string $text Text to be converted.
* @return string Converted text.
*/
function wp_pre_kses_less_than( $text ) {
return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
}
/**
* Callback function used by preg_replace.
*
* @since 2.3.0
*
* @param array $matches Populated by matches to preg_replace.
* @return string The text returned after esc_html if needed.
*/
function wp_pre_kses_less_than_callback( $matches ) {
if ( false === strpos($matches[0], '>') )
return esc_html($matches[0]);
return $matches[0];
}
/**
* WordPress implementation of PHP sprintf() with filters.
*
* @since 2.5.0
* @link http://www.php.net/sprintf
*
* @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 ) {
$args = func_get_args();
$len = strlen($pattern);
$start = 0;
$result = '';
$arg_index = 0;
while ( $len > $start ) {
// Last character: append and break
if ( strlen($pattern) - 1 == $start ) {
$result .= substr($pattern, -1);
break;
}
// Literal %: append and continue
if ( substr($pattern, $start, 2) == '%%' ) {
$start += 2;
$result .= '%';
continue;
}
// Get fragment before next %
$end = strpos($pattern, '%', $start + 1);
if ( false === $end )
$end = $len;
$fragment = substr($pattern, $start, $end - $start);
// Fragment has a specifier
if ( $pattern[$start] == '%' ) {
// Find numbered arguments or take the next one in order
if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
$arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
$fragment = str_replace("%{$matches[1]}$", '%', $fragment);
} else {
++$arg_index;
$arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
}
/**
* Filter 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 $fragment A fragment from the pattern.
* @param string $arg The argument.
*/
$_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
if ( $_fragment != $fragment )
$fragment = $_fragment;
else
$fragment = sprintf($fragment, strval($arg) );
}
// Append to result and move to next fragment
$result .= $fragment;
$start = $end;
}
return $result;
}
/**
* Localize list items before the rest of the content.
*
* The '%l' must be at the first characters can then contain the rest of the
* content. The list items will have ', ', ', and', and ' and ' added depending
* on the amount of list items in the $args parameter.
*
* @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'.
* @return string Localized list items and rest of the content.
*/
function wp_sprintf_l( $pattern, $args ) {
// Not a match
if ( substr($pattern, 0, 2) != '%l' )
return $pattern;
// Nothing to work with
if ( empty($args) )
return '';
/**
* Filter 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.
*
* Please note: Ampersands and entities should be avoided here.
*
* @since 2.5.0
*
* @param array $delimiters An array of translated delimiters.
*/
$l = apply_filters( 'wp_sprintf_l', array(
/* translators: used to join items in a list with more than 2 items */
'between' => sprintf( __('%s, %s'), '', '' ),
/* translators: used to join last two items in a list with more than 2 times */
'between_last_two' => sprintf( __('%s, and %s'), '', '' ),
/* translators: used to join items in a list with only 2 items */
'between_only_two' => sprintf( __('%s and %s'), '', '' ),
) );
$args = (array) $args;
$result = array_shift($args);
if ( count($args) == 1 )
$result .= $l['between_only_two'] . array_shift($args);
// Loop when more than two args
$i = count($args);
while ( $i ) {
$arg = array_shift($args);
$i--;
if ( 0 == $i )
$result .= $l['between_last_two'] . $arg;
else
$result .= $l['between'] . $arg;
}
return $result . substr($pattern, 2);
}
/**
* Safely extracts not more than the first $count characters from html string.
*
* UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
* be counted as one character. For example &amp; will be counted as 4, &lt; as
* 3, etc.
*
* @since 2.5.0
*
* @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 ) {
if ( null === $more )
$more = '';
$str = wp_strip_all_tags( $str, true );
$excerpt = mb_substr( $str, 0, $count );
// remove part of an entity at the end
$excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
if ( $str != $excerpt )
$excerpt = trim( $excerpt ) . $more;
return $excerpt;
}
/**
* Add a Base url to relative links in passed content.
*
* By default it supports the 'src' and 'href' attributes. However this can be
* changed via the 3rd param.
*
* @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.
* @return string The processed content.
*/
function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
global $_links_add_base;
$_links_add_base = $base;
$attrs = implode('|', (array)$attrs);
return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
}
/**
* Callback to add a base url to relative links in passed content.
*
* @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 ) {
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] :
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
* modified by the 3rd param.
*
* *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.
* @return string The processed content.
*/
function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
global $_links_add_target;
$_links_add_target = $target;
$tags = implode('|', (array)$tags);
return preg_replace_callback( "!<($tags)([^>]*)>!i", '_links_add_target', $content );
}
/**
* Callback to add a target attribute to all links in passed content.
*
* @since 2.7.0
* @access private
*
* @global string $_links_add_target
*
* @param string $m The matched link.
* @return string The processed link.
*/
function _links_add_target( $m ) {
global $_links_add_target;
$tag = $m[1];
$link = preg_replace('|( target=([\'"])(.*?)\2)|i', '', $m[2]);
return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
}
/**
* Normalize EOL characters and strip duplicate whitespace.
*
* @since 2.7.0
*
* @param string $str The string to normalize.
* @return string The normalized string.
*/
function normalize_whitespace( $str ) {
$str = trim( $str );
$str = str_replace( "\r", "\n", $str );
$str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
return $str;
}
/**
* 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>' )`
* will return 'something'. wp_strip_all_tags will return ''
*
* @since 2.9.0
*
* @param string $string String containing HTML tags
* @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars
* @return string The processed string.
*/
function wp_strip_all_tags($string, $remove_breaks = false) {
$string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
$string = strip_tags($string);
if ( $remove_breaks )
$string = preg_replace('/[\r\n\t ]+/', ' ', $string);
return trim( $string );
}
/**
* Sanitize a string from user input or from the db
*
* check for invalid UTF-8,
* Convert single < characters to entity,
* strip all tags,
* remove line breaks, tabs and extra white space,
* strip octets.
*
* @since 2.9.0
*
* @param string $str
* @return string
*/
function sanitize_text_field( $str ) {
$filtered = wp_check_invalid_utf8( $str );
if ( strpos($filtered, '<') !== false ) {
$filtered = wp_pre_kses_less_than( $filtered );
// This will strip extra whitespace for us.
$filtered = wp_strip_all_tags( $filtered, true );
} else {
$filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
}
$found = false;
while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
$filtered = str_replace($match[0], '', $filtered);
$found = true;
}
if ( $found ) {
// Strip out the whitespace that may now exist after removing the octets.
$filtered = trim( preg_replace('/ +/', ' ', $filtered) );
}
/**
* Filter a sanitized text field string.
*
* @since 2.9.0
*
* @param string $filtered The sanitized string.
* @param string $str The string prior to being sanitized.
*/
return apply_filters( 'sanitize_text_field', $filtered, $str );
}
/**
* i18n friendly version of basename()
*
* @since 3.1.0
*
* @param string $path A path.
* @param string $suffix If the filename ends in suffix this will also be cut off.
* @return string
*/
function wp_basename( $path, $suffix = '' ) {
return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
}
/**
* Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
*
* 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
$current_filter = current_filter();
if ( 'the_title' === $current_filter || 'wp_title' === $current_filter )
return str_replace( 'Wordpress', 'WordPress', $text );
// Still here? Use the more judicious replacement
static $dblq = false;
if ( false === $dblq ) {
$dblq = _x( '&#8220;', 'opening curly double quote' );
}
return str_replace(
array( ' Wordpress', '&#8216;Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
array( ' WordPress', '&#8216;WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
$text );
}
/**
* Sanitize a mime type
*
* @since 3.1.3
*
* @param string $mime_type Mime type
* @return string Sanitized mime type
*/
function sanitize_mime_type( $mime_type ) {
$sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
/**
* Filter a mime type following sanitization.
*
* @since 3.1.3
*
* @param string $sani_mime_type The sanitized mime type.
* @param string $mime_type The mime type prior to sanitization.
*/
return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
}
/**
* Sanitize space or carriage return separated URLs that are used to send trackbacks.
*
* @since 3.4.0
*
* @param string $to_ping Space or carriage return separated URLs
* @return string URLs starting with the http or https protocol, separated by a carriage return.
*/
function sanitize_trackback_urls( $to_ping ) {
$urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
foreach ( $urls_to_ping as $k => $url ) {
if ( !preg_match( '#^https?://.#i', $url ) )
unset( $urls_to_ping[$k] );
}
$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.
*
* The string returned here consists of a space or carriage return-delimited list
* of trackback URLs.
*
* @since 3.4.0
*
* @param string $urls_to_ping Sanitized space or carriage return separated URLs.
* @param string $to_ping Space or carriage return separated URLs before sanitization.
*/
return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
}
/**
* Add slashes to a string or array of strings.
*
* This should be used when preparing data for core API that expects slashed data.
* This should not be used to escape data going directly into an SQL query.
*
* @since 3.6.0
*
* @param string|array $value String or array of strings to slash.
* @return string|array Slashed $value
*/
function wp_slash( $value ) {
if ( is_array( $value ) ) {
foreach ( $value as $k => $v ) {
if ( is_array( $v ) ) {
$value[$k] = wp_slash( $v );
} else {
$value[$k] = addslashes( $v );
}
}
} else {
$value = addslashes( $value );
}
return $value;
}
/**
* Remove slashes from a string or array of strings.
*
* This should be used to remove slashes from data passed to core API that
* expects data to be unslashed.
*
* @since 3.6.0
*
* @param string|array $value String or array of strings to unslash.
* @return string|array Unslashed $value
*/
function wp_unslash( $value ) {
return stripslashes_deep( $value );
}
/**
* Extract and return the first URL from passed content.
*
* @since 3.6.0
*
* @param string $content A string which might contain a URL.
* @return string|false The found URL.
*/
function get_url_in_content( $content ) {
if ( empty( $content ) ) {
return false;
}
if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) ) {
return esc_url_raw( $matches[2] );
}
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 ) ) {
/**
* Filter 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|&nbsp;' );
}
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
}
/**
*
* @global string $wp_version
* @staticvar bool $printed
*/
function print_emoji_detection_script() {
global $wp_version;
static $printed = false;
if ( $printed ) {
return;
}
$printed = true;
$settings = array(
/**
* Filter the URL where emoji images are hosted.
*
* @since 4.2.0
*
* @param string The emoji base URL.
*/
'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/72x72/' ),
/**
* Filter the extension of the emoji files.
*
* @since 4.2.0
*
* @param string The emoji extension. Default .png.
*/
'ext' => apply_filters( 'emoji_ext', '.png' ),
);
$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=b.createElement("canvas"),e=d.getContext&&d.getContext("2d"),f=String.fromCharCode;if(!e||!e.fillText)return!1;switch(e.textBaseline="top",e.font="600 32px Arial",a){case"flag":return e.fillText(f(55356,56806,55356,56826),0,0),d.toDataURL().length>3e3;case"diversity":return e.fillText(f(55356,57221),0,0),c=e.getImageData(16,16,1,1).data.toString(),e.fillText(f(55356,57221,55356,57343),0,0),c!==e.getImageData(16,16,1,1).data.toString();case"simple":return e.fillText(f(55357,56835),0,0),0!==e.getImageData(16,16,1,1).data[0];case"unicode8":return e.fillText(f(55356,57135),0,0),0!==e.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"),c.supports={everything:!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/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( '/(&#x1f1(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};|&#x1f[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 an 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 ) . '&hellip;';
}
return $short_url;
}