| [ Index ] |
PHP Cross Reference of WordPress Trunk (Updated Daily) |
[Summary view] [Print] [Text view]
1 <?php 2 /** 3 * Main WordPress Formatting API. 4 * 5 * Handles many functions for formatting output. 6 * 7 * @package WordPress 8 */ 9 10 /** 11 * Replaces common plain text characters with formatted entities. 12 * 13 * Returns given text with transformations of quotes into smart quotes, apostrophes, 14 * dashes, ellipses, the trademark symbol, and the multiplication symbol. 15 * 16 * As an example, 17 * 18 * 'cause today's effort makes it worth tomorrow's "holiday" ... 19 * 20 * Becomes: 21 * 22 * ’cause today’s effort makes it worth tomorrow’s “holiday” … 23 * 24 * Code within certain HTML blocks are skipped. 25 * 26 * Do not use this function before the {@see 'init'} action hook; everything will break. 27 * 28 * @since 0.71 29 * 30 * @global array $wp_cockneyreplace Array of formatted entities for certain common phrases. 31 * @global array $shortcode_tags 32 * 33 * @param string $text The text to be formatted. 34 * @param bool $reset Set to true for unit testing. Translated patterns will reset. 35 * @return string The string replaced with HTML entities. 36 */ 37 function wptexturize( $text, $reset = false ) { 38 global $wp_cockneyreplace, $shortcode_tags; 39 static $static_characters = null, 40 $static_replacements = null, 41 $dynamic_characters = null, 42 $dynamic_replacements = null, 43 $default_no_texturize_tags = null, 44 $default_no_texturize_shortcodes = null, 45 $run_texturize = true, 46 $apos = null, 47 $prime = null, 48 $double_prime = null, 49 $opening_quote = null, 50 $closing_quote = null, 51 $opening_single_quote = null, 52 $closing_single_quote = null, 53 $open_q_flag = '<!--oq-->', 54 $open_sq_flag = '<!--osq-->', 55 $apos_flag = '<!--apos-->'; 56 57 // If there's nothing to do, just stop. 58 if ( empty( $text ) || false === $run_texturize ) { 59 return $text; 60 } 61 62 // Set up static variables. Run once only. 63 if ( $reset || ! isset( $static_characters ) ) { 64 /** 65 * Filters whether to skip running wptexturize(). 66 * 67 * Returning false from the filter will effectively short-circuit wptexturize() 68 * and return the original text passed to the function instead. 69 * 70 * The filter runs only once, the first time wptexturize() is called. 71 * 72 * @since 4.0.0 73 * 74 * @see wptexturize() 75 * 76 * @param bool $run_texturize Whether to short-circuit wptexturize(). 77 */ 78 $run_texturize = apply_filters( 'run_wptexturize', $run_texturize ); 79 if ( false === $run_texturize ) { 80 return $text; 81 } 82 83 /* translators: Opening curly double quote. */ 84 $opening_quote = _x( '“', 'opening curly double quote' ); 85 /* translators: Closing curly double quote. */ 86 $closing_quote = _x( '”', 'closing curly double quote' ); 87 88 /* translators: Apostrophe, for example in 'cause or can't. */ 89 $apos = _x( '’', 'apostrophe' ); 90 91 /* translators: Prime, for example in 9' (nine feet). */ 92 $prime = _x( '′', 'prime' ); 93 /* translators: Double prime, for example in 9" (nine inches). */ 94 $double_prime = _x( '″', 'double prime' ); 95 96 /* translators: Opening curly single quote. */ 97 $opening_single_quote = _x( '‘', 'opening curly single quote' ); 98 /* translators: Closing curly single quote. */ 99 $closing_single_quote = _x( '’', 'closing curly single quote' ); 100 101 /* translators: En dash. */ 102 $en_dash = _x( '–', 'en dash' ); 103 /* translators: Em dash. */ 104 $em_dash = _x( '—', 'em dash' ); 105 106 $default_no_texturize_tags = array( 'pre', 'code', 'kbd', 'style', 'script', 'tt' ); 107 $default_no_texturize_shortcodes = array( 'code' ); 108 109 // If a plugin has provided an autocorrect array, use it. 110 if ( isset( $wp_cockneyreplace ) ) { 111 $cockney = array_keys( $wp_cockneyreplace ); 112 $cockneyreplace = array_values( $wp_cockneyreplace ); 113 } else { 114 /* 115 * translators: This is a comma-separated list of words that defy the syntax of quotations in normal use, 116 * for example... 'We do not have enough words yet'... is a typical quoted phrase. But when we write 117 * lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes. 118 */ 119 $cockney = explode( 120 ',', 121 _x( 122 "'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em", 123 'Comma-separated list of words to texturize in your language' 124 ) 125 ); 126 127 $cockneyreplace = explode( 128 ',', 129 _x( 130 '’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em', 131 'Comma-separated list of replacement words in your language' 132 ) 133 ); 134 } 135 136 $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney ); 137 $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace ); 138 139 /* 140 * Pattern-based replacements of characters. 141 * Sort the remaining patterns into several arrays for performance tuning. 142 */ 143 $dynamic_characters = array( 144 'apos' => array(), 145 'quote' => array(), 146 'dash' => array(), 147 ); 148 $dynamic_replacements = array( 149 'apos' => array(), 150 'quote' => array(), 151 'dash' => array(), 152 ); 153 $dynamic = array(); 154 $spaces = wp_spaces_regexp(); 155 156 // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation. 157 if ( "'" !== $apos || "'" !== $closing_single_quote ) { 158 $dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote; 159 } 160 if ( "'" !== $apos || '"' !== $closing_quote ) { 161 $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote; 162 } 163 164 // '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0. 165 if ( "'" !== $apos ) { 166 $dynamic['/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/'] = $apos_flag; 167 } 168 169 // Quoted numbers like '0.42'. 170 if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) { 171 $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote; 172 } 173 174 // Single quote at start, or preceded by (, {, <, [, ", -, or spaces. 175 if ( "'" !== $opening_single_quote ) { 176 $dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $open_sq_flag; 177 } 178 179 // Apostrophe in a word. No spaces, double apostrophes, or other punctuation. 180 if ( "'" !== $apos ) { 181 $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag; 182 } 183 184 $dynamic_characters['apos'] = array_keys( $dynamic ); 185 $dynamic_replacements['apos'] = array_values( $dynamic ); 186 $dynamic = array(); 187 188 // Quoted numbers like "42". 189 if ( '"' !== $opening_quote && '"' !== $closing_quote ) { 190 $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote; 191 } 192 193 // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces. 194 if ( '"' !== $opening_quote ) { 195 $dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag; 196 } 197 198 $dynamic_characters['quote'] = array_keys( $dynamic ); 199 $dynamic_replacements['quote'] = array_values( $dynamic ); 200 $dynamic = array(); 201 202 // Dashes and spaces. 203 $dynamic['/---/'] = $em_dash; 204 $dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash; 205 $dynamic['/(?<!xn)--/'] = $en_dash; 206 $dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ] = $en_dash; 207 208 $dynamic_characters['dash'] = array_keys( $dynamic ); 209 $dynamic_replacements['dash'] = array_values( $dynamic ); 210 } 211 212 // Must do this every time in case plugins use these filters in a context sensitive manner. 213 /** 214 * Filters the list of HTML elements not to texturize. 215 * 216 * @since 2.8.0 217 * 218 * @param string[] $default_no_texturize_tags An array of HTML element names. 219 */ 220 $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags ); 221 /** 222 * Filters the list of shortcodes not to texturize. 223 * 224 * @since 2.8.0 225 * 226 * @param string[] $default_no_texturize_shortcodes An array of shortcode names. 227 */ 228 $no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes ); 229 230 $no_texturize_tags_stack = array(); 231 $no_texturize_shortcodes_stack = array(); 232 233 // Look for shortcodes and HTML elements. 234 235 preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches ); 236 $tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] ); 237 $found_shortcodes = ! empty( $tagnames ); 238 $shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : ''; 239 $regex = _get_wptexturize_split_regex( $shortcode_regex ); 240 241 $textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY ); 242 243 foreach ( $textarr as &$curl ) { 244 // Only call _wptexturize_pushpop_element if $curl is a delimiter. 245 $first = $curl[0]; 246 if ( '<' === $first ) { 247 if ( str_starts_with( $curl, '<!--' ) ) { 248 // This is an HTML comment delimiter. 249 continue; 250 } else { 251 // This is an HTML element delimiter. 252 253 // Replace each & with & unless it already looks like an entity. 254 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl ); 255 256 _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags ); 257 } 258 } elseif ( '' === trim( $curl ) ) { 259 // This is a newline between delimiters. Performance improves when we check this. 260 continue; 261 262 } elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) { 263 // This is a shortcode delimiter. 264 265 if ( ! str_starts_with( $curl, '[[' ) && ! str_ends_with( $curl, ']]' ) ) { 266 // Looks like a normal shortcode. 267 _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes ); 268 } else { 269 // Looks like an escaped shortcode. 270 continue; 271 } 272 } elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) { 273 // This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize. 274 275 $curl = str_replace( $static_characters, $static_replacements, $curl ); 276 277 if ( str_contains( $curl, "'" ) ) { 278 $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl ); 279 $curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote ); 280 $curl = str_replace( $apos_flag, $apos, $curl ); 281 $curl = str_replace( $open_sq_flag, $opening_single_quote, $curl ); 282 } 283 if ( str_contains( $curl, '"' ) ) { 284 $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl ); 285 $curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote ); 286 $curl = str_replace( $open_q_flag, $opening_quote, $curl ); 287 } 288 if ( str_contains( $curl, '-' ) ) { 289 $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl ); 290 } 291 292 // 9x9 (times), but never 0x9999. 293 if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) { 294 // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one! 295 $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1×$2', $curl ); 296 } 297 298 // Replace each & with & unless it already looks like an entity. 299 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl ); 300 } 301 } 302 303 return implode( '', $textarr ); 304 } 305 306 /** 307 * Implements a logic tree to determine whether or not "7'." represents seven feet, 308 * then converts the special char into either a prime char or a closing quote char. 309 * 310 * @since 4.3.0 311 * 312 * @param string $haystack The plain text to be searched. 313 * @param string $needle The character to search for such as ' or ". 314 * @param string $prime The prime char to use for replacement. 315 * @param string $open_quote The opening quote char. Opening quote replacement must be 316 * accomplished already. 317 * @param string $close_quote The closing quote char to use for replacement. 318 * @return string The $haystack value after primes and quotes replacements. 319 */ 320 function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) { 321 $spaces = wp_spaces_regexp(); 322 $flag = '<!--wp-prime-or-quote-->'; 323 $quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ')/'; 324 $prime_pattern = "/(?<=\\d)$needle/"; 325 $flag_after_digit = "/(?<=\\d)$flag/"; 326 $flag_no_digit = "/(?<!\\d)$flag/"; 327 328 $sentences = explode( $open_quote, $haystack ); 329 330 foreach ( $sentences as $key => &$sentence ) { 331 if ( ! str_contains( $sentence, $needle ) ) { 332 continue; 333 } elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) { 334 $sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count ); 335 if ( $count > 1 ) { 336 // This sentence appears to have multiple closing quotes. Attempt Vulcan logic. 337 $sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 ); 338 if ( 0 === $count2 ) { 339 // Try looking for a quote followed by a period. 340 $count2 = substr_count( $sentence, "$flag." ); 341 if ( $count2 > 0 ) { 342 // Assume the rightmost quote-period match is the end of quotation. 343 $pos = strrpos( $sentence, "$flag." ); 344 } else { 345 /* 346 * When all else fails, make the rightmost candidate a closing quote. 347 * This is most likely to be problematic in the context of bug #18549. 348 */ 349 $pos = strrpos( $sentence, $flag ); 350 } 351 $sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) ); 352 } 353 // Use conventional replacement on any remaining primes and quotes. 354 $sentence = preg_replace( $prime_pattern, $prime, $sentence ); 355 $sentence = preg_replace( $flag_after_digit, $prime, $sentence ); 356 $sentence = str_replace( $flag, $close_quote, $sentence ); 357 } elseif ( 1 === $count ) { 358 // Found only one closing quote candidate, so give it priority over primes. 359 $sentence = str_replace( $flag, $close_quote, $sentence ); 360 $sentence = preg_replace( $prime_pattern, $prime, $sentence ); 361 } else { 362 // No closing quotes found. Just run primes pattern. 363 $sentence = preg_replace( $prime_pattern, $prime, $sentence ); 364 } 365 } else { 366 $sentence = preg_replace( $prime_pattern, $prime, $sentence ); 367 $sentence = preg_replace( $quote_pattern, $close_quote, $sentence ); 368 } 369 if ( '"' === $needle && str_contains( $sentence, '"' ) ) { 370 $sentence = str_replace( '"', $close_quote, $sentence ); 371 } 372 } 373 374 return implode( $open_quote, $sentences ); 375 } 376 377 /** 378 * Searches for disabled element tags. Pushes element to stack on tag open 379 * and pops on tag close. 380 * 381 * Assumes first char of `$text` is tag opening and last char is tag closing. 382 * Assumes second char of `$text` is optionally `/` to indicate closing as in `</html>`. 383 * 384 * @since 2.9.0 385 * @access private 386 * 387 * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`. 388 * @param string[] $stack Array of open tag elements. 389 * @param string[] $disabled_elements Array of tag names to match against. Spaces are not allowed in tag names. 390 */ 391 function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) { 392 // Is it an opening tag or closing tag? 393 if ( isset( $text[1] ) && '/' !== $text[1] ) { 394 $opening_tag = true; 395 $name_offset = 1; 396 } elseif ( 0 === count( $stack ) ) { 397 // Stack is empty. Just stop. 398 return; 399 } else { 400 $opening_tag = false; 401 $name_offset = 2; 402 } 403 404 // Parse out the tag name. 405 $space = strpos( $text, ' ' ); 406 if ( false === $space ) { 407 $space = -1; 408 } else { 409 $space -= $name_offset; 410 } 411 $tag = substr( $text, $name_offset, $space ); 412 413 // Handle disabled tags. 414 if ( in_array( $tag, $disabled_elements, true ) ) { 415 if ( $opening_tag ) { 416 /* 417 * This disables texturize until we find a closing tag of our type 418 * (e.g. <pre>) even if there was invalid nesting before that. 419 * 420 * Example: in the case <pre>sadsadasd</code>"baba"</pre> 421 * "baba" won't be texturized. 422 */ 423 424 array_push( $stack, $tag ); 425 } elseif ( end( $stack ) === $tag ) { 426 array_pop( $stack ); 427 } 428 } 429 } 430 431 /** 432 * Replaces double line breaks with paragraph elements. 433 * 434 * A group of regex replaces used to identify text formatted with newlines and 435 * replace double line breaks with HTML paragraph tags. The remaining line breaks 436 * after conversion become `<br />` tags, unless `$br` is set to '0' or 'false'. 437 * 438 * @since 0.71 439 * 440 * @param string $text The text which has to be formatted. 441 * @param bool $br Optional. If set, this will convert all remaining line breaks 442 * after paragraphing. Line breaks within `<script>`, `<style>`, 443 * and `<svg>` tags are not affected. Default true. 444 * @return string Text which has been converted into correct paragraph tags. 445 */ 446 function wpautop( $text, $br = true ) { 447 $pre_tags = array(); 448 449 if ( '' === trim( $text ) ) { 450 return ''; 451 } 452 453 // Just to make things a little easier, pad the end. 454 $text = $text . "\n"; 455 456 /* 457 * Pre tags shouldn't be touched by autop. 458 * Replace pre tags with placeholders and bring them back after autop. 459 */ 460 if ( str_contains( $text, '<pre' ) ) { 461 $text_parts = explode( '</pre>', $text ); 462 $last_part = array_pop( $text_parts ); 463 $text = ''; 464 $i = 0; 465 466 foreach ( $text_parts as $text_part ) { 467 $start = strpos( $text_part, '<pre' ); 468 469 // Malformed HTML? 470 if ( false === $start ) { 471 $text .= $text_part; 472 continue; 473 } 474 475 $name = "<pre wp-pre-tag-$i></pre>"; 476 $pre_tags[ $name ] = substr( $text_part, $start ) . '</pre>'; 477 478 $text .= substr( $text_part, 0, $start ) . $name; 479 ++$i; 480 } 481 482 $text .= $last_part; 483 } 484 // Change multiple <br>'s into two line breaks, which will turn into paragraphs. 485 $text = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $text ); 486 487 $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)'; 488 489 // Add a double line break above block-level opening tags. 490 $text = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $text ); 491 492 // Add a double line break below block-level closing tags. 493 $text = preg_replace( '!(</' . $allblocks . '>)!', "$1\n\n", $text ); 494 495 // Add a double line break after hr tags, which are self closing. 496 $text = preg_replace( '!(<hr\s*?/?>)!', "$1\n\n", $text ); 497 498 // Standardize newline characters to "\n". 499 $text = str_replace( array( "\r\n", "\r" ), "\n", $text ); 500 501 // Find newlines in all elements and add placeholders. 502 $text = wp_replace_in_html_tags( $text, array( "\n" => ' <!-- wpnl --> ' ) ); 503 504 // Collapse line breaks before and after <option> elements so they don't get autop'd. 505 if ( str_contains( $text, '<option' ) ) { 506 $text = preg_replace( '|\s*<option|', '<option', $text ); 507 $text = preg_replace( '|</option>\s*|', '</option>', $text ); 508 } 509 510 /* 511 * Collapse line breaks inside <object> elements, before <param> and <embed> elements 512 * so they don't get autop'd. 513 */ 514 if ( str_contains( $text, '</object>' ) ) { 515 $text = preg_replace( '|(<object[^>]*>)\s*|', '$1', $text ); 516 $text = preg_replace( '|\s*</object>|', '</object>', $text ); 517 $text = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $text ); 518 } 519 520 /* 521 * Collapse line breaks inside <audio> and <video> elements, 522 * before and after <source> and <track> elements. 523 */ 524 if ( str_contains( $text, '<source' ) || str_contains( $text, '<track' ) ) { 525 $text = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $text ); 526 $text = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $text ); 527 $text = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $text ); 528 } 529 530 // Collapse line breaks before and after <figcaption> elements. 531 if ( str_contains( $text, '<figcaption' ) ) { 532 $text = preg_replace( '|\s*(<figcaption[^>]*>)|', '$1', $text ); 533 $text = preg_replace( '|</figcaption>\s*|', '</figcaption>', $text ); 534 } 535 536 // Remove more than two contiguous line breaks. 537 $text = preg_replace( "/\n\n+/", "\n\n", $text ); 538 539 // Split up the contents into an array of strings, separated by double line breaks. 540 $paragraphs = preg_split( '/\n\s*\n/', $text, -1, PREG_SPLIT_NO_EMPTY ); 541 542 // Reset $text prior to rebuilding. 543 $text = ''; 544 545 // Rebuild the content as a string, wrapping every bit with a <p>. 546 foreach ( $paragraphs as $paragraph ) { 547 $text .= '<p>' . trim( $paragraph, "\n" ) . "</p>\n"; 548 } 549 550 // Under certain strange conditions it could create a P of entirely whitespace. 551 $text = preg_replace( '|<p>\s*</p>|', '', $text ); 552 553 // Add a closing <p> inside <div>, <address>, or <form> tag if missing. 554 $text = preg_replace( '!<p>([^<]+)</(div|address|form)>!', '<p>$1</p></$2>', $text ); 555 556 // If an opening or closing block element tag is wrapped in a <p>, unwrap it. 557 $text = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $text ); 558 559 // In some cases <li> may get wrapped in <p>, fix them. 560 $text = preg_replace( '|<p>(<li.+?)</p>|', '$1', $text ); 561 562 // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>. 563 $text = preg_replace( '|<p><blockquote([^>]*)>|i', '<blockquote$1><p>', $text ); 564 $text = str_replace( '</blockquote></p>', '</p></blockquote>', $text ); 565 566 // If an opening or closing block element tag is preceded by an opening <p> tag, remove it. 567 $text = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)!', '$1', $text ); 568 569 // If an opening or closing block element tag is followed by a closing <p> tag, remove it. 570 $text = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $text ); 571 572 // Optionally insert line breaks. 573 if ( $br ) { 574 // Replace newlines that shouldn't be touched with a placeholder. 575 $text = preg_replace_callback( '/<(script|style|svg|math).*?<\/\\1>/s', '_autop_newline_preservation_helper', $text ); 576 577 // Normalize <br>. 578 $text = str_replace( array( '<br>', '<br/>' ), '<br />', $text ); 579 580 // Replace any new line characters that aren't preceded by a <br /> with a <br />. 581 $text = preg_replace( '|(?<!<br />)\s*\n|', "<br />\n", $text ); 582 583 // Replace newline placeholders with newlines. 584 $text = str_replace( '<WPPreserveNewline />', "\n", $text ); 585 } 586 587 // If a <br /> tag is after an opening or closing block tag, remove it. 588 $text = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*<br />!', '$1', $text ); 589 590 // If a <br /> tag is before a subset of opening or closing block tags, remove it. 591 $text = preg_replace( '!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $text ); 592 $text = preg_replace( "|\n</p>$|", '</p>', $text ); 593 594 // Replace placeholder <pre> tags with their original content. 595 if ( ! empty( $pre_tags ) ) { 596 $text = str_replace( array_keys( $pre_tags ), array_values( $pre_tags ), $text ); 597 } 598 599 // Restore newlines in all elements. 600 if ( str_contains( $text, '<!-- wpnl -->' ) ) { 601 $text = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $text ); 602 } 603 604 return $text; 605 } 606 607 /** 608 * Separates HTML elements and comments from the text. 609 * 610 * @since 4.2.4 611 * 612 * @param string $input The text which has to be formatted. 613 * @return string[] Array of the formatted text. 614 */ 615 function wp_html_split( $input ) { 616 return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE ); 617 } 618 619 /** 620 * Retrieves the regular expression for an HTML element. 621 * 622 * @since 4.4.0 623 * 624 * @return string The regular expression. 625 */ 626 function get_html_split_regex() { 627 static $regex; 628 629 if ( ! isset( $regex ) ) { 630 // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation 631 $comments = 632 '!' // Start of comment, after the <. 633 . '(?:' // Unroll the loop: Consume everything until --> is found. 634 . '-(?!->)' // Dash not followed by end of comment. 635 . '[^\-]*+' // Consume non-dashes. 636 . ')*+' // Loop possessively. 637 . '(?:-->)?'; // End of comment. If not found, match all input. 638 639 $cdata = 640 '!\[CDATA\[' // Start of comment, after the <. 641 . '[^\]]*+' // Consume non-]. 642 . '(?:' // Unroll the loop: Consume everything until ]]> is found. 643 . '](?!]>)' // One ] not followed by end of comment. 644 . '[^\]]*+' // Consume non-]. 645 . ')*+' // Loop possessively. 646 . '(?:]]>)?'; // End of comment. If not found, match all input. 647 648 $escaped = 649 '(?=' // Is the element escaped? 650 . '!--' 651 . '|' 652 . '!\[CDATA\[' 653 . ')' 654 . '(?(?=!-)' // If yes, which type? 655 . $comments 656 . '|' 657 . $cdata 658 . ')'; 659 660 $regex = 661 '/(' // Capture the entire match. 662 . '<' // Find start of element. 663 . '(?' // Conditional expression follows. 664 . $escaped // Find end of escaped element. 665 . '|' // ...else... 666 . '[^>]*>?' // Find end of normal element. 667 . ')' 668 . ')/'; 669 // phpcs:enable 670 } 671 672 return $regex; 673 } 674 675 /** 676 * Retrieves the combined regular expression for HTML and shortcodes. 677 * 678 * @access private 679 * @ignore 680 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap. 681 * @since 4.4.0 682 * 683 * @param string $shortcode_regex Optional. The result from _get_wptexturize_shortcode_regex(). 684 * @return string The regular expression. 685 */ 686 function _get_wptexturize_split_regex( $shortcode_regex = '' ) { 687 static $html_regex; 688 689 if ( ! isset( $html_regex ) ) { 690 // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation 691 $comment_regex = 692 '!' // Start of comment, after the <. 693 . '(?:' // Unroll the loop: Consume everything until --> is found. 694 . '-(?!->)' // Dash not followed by end of comment. 695 . '[^\-]*+' // Consume non-dashes. 696 . ')*+' // Loop possessively. 697 . '(?:-->)?'; // End of comment. If not found, match all input. 698 699 $html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap. 700 '<' // Find start of element. 701 . '(?(?=!--)' // Is this a comment? 702 . $comment_regex // Find end of comment. 703 . '|' 704 . '[^>]*>?' // Find end of element. If not found, match all input. 705 . ')'; 706 // phpcs:enable 707 } 708 709 if ( empty( $shortcode_regex ) ) { 710 $regex = '/(' . $html_regex . ')/'; 711 } else { 712 $regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/'; 713 } 714 715 return $regex; 716 } 717 718 /** 719 * Retrieves the regular expression for shortcodes. 720 * 721 * @access private 722 * @ignore 723 * @since 4.4.0 724 * 725 * @param string[] $tagnames Array of shortcodes to find. 726 * @return string The regular expression. 727 */ 728 function _get_wptexturize_shortcode_regex( $tagnames ) { 729 $tagregexp = implode( '|', array_map( 'preg_quote', $tagnames ) ); 730 $tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex(). 731 // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation 732 $regex = 733 '\[' // Find start of shortcode. 734 . '[\/\[]?' // Shortcodes may begin with [/ or [[. 735 . $tagregexp // Only match registered shortcodes, because performance. 736 . '(?:' 737 . '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical. 738 . '|' 739 . '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >. 740 . ')*+' // Possessive critical. 741 . '\]' // Find end of shortcode. 742 . '\]?'; // Shortcodes may end with ]]. 743 // phpcs:enable 744 745 return $regex; 746 } 747 748 /** 749 * Replaces characters or phrases within HTML elements only. 750 * 751 * @since 4.2.3 752 * 753 * @param string $haystack The text which has to be formatted. 754 * @param array $replace_pairs In the form array('from' => 'to', ...). 755 * @return string The formatted text. 756 */ 757 function wp_replace_in_html_tags( $haystack, $replace_pairs ) { 758 // Find all elements. 759 $textarr = wp_html_split( $haystack ); 760 $changed = false; 761 762 // Optimize when searching for one item. 763 if ( 1 === count( $replace_pairs ) ) { 764 // Extract $needle and $replace. 765 $needle = array_key_first( $replace_pairs ); 766 $replace = $replace_pairs[ $needle ]; 767 768 // Loop through delimiters (elements) only. 769 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) { 770 if ( str_contains( $textarr[ $i ], $needle ) ) { 771 $textarr[ $i ] = str_replace( $needle, $replace, $textarr[ $i ] ); 772 $changed = true; 773 } 774 } 775 } else { 776 // Extract all $needles. 777 $needles = array_keys( $replace_pairs ); 778 779 // Loop through delimiters (elements) only. 780 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) { 781 foreach ( $needles as $needle ) { 782 if ( str_contains( $textarr[ $i ], $needle ) ) { 783 $textarr[ $i ] = strtr( $textarr[ $i ], $replace_pairs ); 784 $changed = true; 785 // After one strtr() break out of the foreach loop and look at next element. 786 break; 787 } 788 } 789 } 790 } 791 792 if ( $changed ) { 793 $haystack = implode( $textarr ); 794 } 795 796 return $haystack; 797 } 798 799 /** 800 * Newline preservation help function for wpautop(). 801 * 802 * @since 3.1.0 803 * @access private 804 * 805 * @param array $matches preg_replace_callback matches array 806 * @return string Text with newlines replaced with placeholders. 807 */ 808 function _autop_newline_preservation_helper( $matches ) { 809 return str_replace( "\n", '<WPPreserveNewline />', $matches[0] ); 810 } 811 812 /** 813 * Don't auto-p wrap shortcodes that stand alone. 814 * 815 * Ensures that shortcodes are not wrapped in `<p>...</p>`. 816 * 817 * @since 2.9.0 818 * 819 * @global array $shortcode_tags 820 * 821 * @param string $text The content. 822 * @return string The filtered content. 823 */ 824 function shortcode_unautop( $text ) { 825 global $shortcode_tags; 826 827 if ( empty( $shortcode_tags ) || ! is_array( $shortcode_tags ) ) { 828 return $text; 829 } 830 831 $tagregexp = implode( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) ); 832 $spaces = wp_spaces_regexp(); 833 834 // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound,Universal.WhiteSpace.PrecisionAlignment.Found -- don't remove regex indentation 835 $pattern = 836 '/' 837 . '<p>' // Opening paragraph. 838 . '(?:' . $spaces . ')*+' // Optional leading whitespace. 839 . '(' // 1: The shortcode. 840 . '\\[' // Opening bracket. 841 . "($tagregexp)" // 2: Shortcode name. 842 . '(?![\\w-])' // Not followed by word character or hyphen. 843 // Unroll the loop: Inside the opening shortcode tag. 844 . '[^\\]\\/]*' // Not a closing bracket or forward slash. 845 . '(?:' 846 . '\\/(?!\\])' // A forward slash not followed by a closing bracket. 847 . '[^\\]\\/]*' // Not a closing bracket or forward slash. 848 . ')*?' 849 . '(?:' 850 . '\\/\\]' // Self closing tag and closing bracket. 851 . '|' 852 . '\\]' // Closing bracket. 853 . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags. 854 . '[^\\[]*+' // Not an opening bracket. 855 . '(?:' 856 . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag. 857 . '[^\\[]*+' // Not an opening bracket. 858 . ')*+' 859 . '\\[\\/\\2\\]' // Closing shortcode tag. 860 . ')?' 861 . ')' 862 . ')' 863 . '(?:' . $spaces . ')*+' // Optional trailing whitespace. 864 . '<\\/p>' // Closing paragraph. 865 . '/'; 866 // phpcs:enable 867 868 return preg_replace( $pattern, '$1', $text ); 869 } 870 871 /** 872 * Checks to see if a string is utf8 encoded. 873 * 874 * NOTE: This function checks for 5-Byte sequences, UTF8 875 * has Bytes Sequences with a maximum length of 4. 876 * 877 * @author bmorel at ssi dot fr (modified) 878 * @since 1.2.1 879 * @deprecated 6.9.0 Use {@see wp_is_valid_utf8()} instead. 880 * 881 * @param string $str The string to be checked. 882 * @return bool True if $str fits a UTF-8 model, false otherwise. 883 */ 884 function seems_utf8( $str ) { 885 _deprecated_function( __FUNCTION__, '6.9.0', 'wp_is_valid_utf8()' ); 886 887 mbstring_binary_safe_encoding(); 888 $length = strlen( $str ); 889 reset_mbstring_encoding(); 890 891 for ( $i = 0; $i < $length; $i++ ) { 892 $c = ord( $str[ $i ] ); 893 894 if ( $c < 0x80 ) { 895 $n = 0; // 0bbbbbbb 896 } elseif ( ( $c & 0xE0 ) === 0xC0 ) { 897 $n = 1; // 110bbbbb 898 } elseif ( ( $c & 0xF0 ) === 0xE0 ) { 899 $n = 2; // 1110bbbb 900 } elseif ( ( $c & 0xF8 ) === 0xF0 ) { 901 $n = 3; // 11110bbb 902 } elseif ( ( $c & 0xFC ) === 0xF8 ) { 903 $n = 4; // 111110bb 904 } elseif ( ( $c & 0xFE ) === 0xFC ) { 905 $n = 5; // 1111110b 906 } else { 907 return false; // Does not match any model. 908 } 909 910 for ( $j = 0; $j < $n; $j++ ) { // n bytes matching 10bbbbbb follow? 911 if ( ( ++$i === $length ) || ( ( ord( $str[ $i ] ) & 0xC0 ) !== 0x80 ) ) { 912 return false; 913 } 914 } 915 } 916 917 return true; 918 } 919 920 /** 921 * Converts a number of special characters into their HTML entities. 922 * 923 * Specifically deals with: `&`, `<`, `>`, `"`, and `'`. 924 * 925 * `$quote_style` can be set to ENT_COMPAT to encode `"` to 926 * `"`, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded. 927 * 928 * @since 1.2.2 929 * @since 5.5.0 `$quote_style` also accepts `ENT_XML1`. 930 * @access private 931 * 932 * @param string $text The text which is to be encoded. 933 * @param int|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT, 934 * both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. 935 * Converts single and double quotes, as well as converting HTML 936 * named entities (that are not also XML named entities) to their 937 * code points if set to ENT_XML1. Also compatible with old values; 938 * converting single quotes if set to 'single', 939 * double if set to 'double' or both if otherwise set. 940 * Default is ENT_NOQUOTES. 941 * @param false|string $charset Optional. The character encoding of the string. Default false. 942 * @param bool $double_encode Optional. Whether to encode existing HTML entities. Default false. 943 * @return string The encoded text with HTML entities. 944 */ 945 function _wp_specialchars( $text, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) { 946 $text = (string) $text; 947 948 if ( 0 === strlen( $text ) ) { 949 return ''; 950 } 951 952 // Don't bother if there are no specialchars - saves some processing. 953 if ( ! preg_match( '/[&<>"\']/', $text ) ) { 954 return $text; 955 } 956 957 // Account for the previous behavior of the function when the $quote_style is not an accepted value. 958 if ( empty( $quote_style ) ) { 959 $quote_style = ENT_NOQUOTES; 960 } elseif ( ENT_XML1 === $quote_style ) { 961 $quote_style = ENT_QUOTES | ENT_XML1; 962 } elseif ( ! in_array( $quote_style, array( ENT_NOQUOTES, ENT_COMPAT, ENT_QUOTES, 'single', 'double' ), true ) ) { 963 $quote_style = ENT_QUOTES; 964 } 965 966 $charset = _canonical_charset( $charset ? $charset : get_option( 'blog_charset' ) ); 967 968 $_quote_style = $quote_style; 969 970 if ( 'double' === $quote_style ) { 971 $quote_style = ENT_COMPAT; 972 $_quote_style = ENT_COMPAT; 973 } elseif ( 'single' === $quote_style ) { 974 $quote_style = ENT_NOQUOTES; 975 } 976 977 if ( ! $double_encode ) { 978 /* 979 * Guarantee every &entity; is valid, convert &garbage; into &garbage; 980 * This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable. 981 */ 982 $text = wp_kses_normalize_entities( $text, ( $quote_style & ENT_XML1 ) ? 'xml' : 'html' ); 983 } 984 985 $text = htmlspecialchars( $text, $quote_style, $charset, $double_encode ); 986 987 // Back-compat. 988 if ( 'single' === $_quote_style ) { 989 $text = str_replace( "'", ''', $text ); 990 } 991 992 return $text; 993 } 994 995 /** 996 * Converts a number of HTML entities into their special characters. 997 * 998 * Specifically deals with: `&`, `<`, `>`, `"`, and `'`. 999 * 1000 * `$quote_style` can be set to ENT_COMPAT to decode `"` entities, 1001 * or ENT_QUOTES to do both `"` and `'`. Default is ENT_NOQUOTES where no quotes are decoded. 1002 * 1003 * @since 2.8.0 1004 * 1005 * @param string $text The text which is to be decoded. 1006 * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT, 1007 * both single and double if set to ENT_QUOTES or 1008 * none if set to ENT_NOQUOTES. 1009 * Also compatible with old _wp_specialchars() values; 1010 * converting single quotes if set to 'single', 1011 * double if set to 'double' or both if otherwise set. 1012 * Default is ENT_NOQUOTES. 1013 * @return string The decoded text without HTML entities. 1014 */ 1015 function wp_specialchars_decode( $text, $quote_style = ENT_NOQUOTES ) { 1016 $text = (string) $text; 1017 1018 if ( 0 === strlen( $text ) ) { 1019 return ''; 1020 } 1021 1022 // Don't bother if there are no entities - saves a lot of processing. 1023 if ( ! str_contains( $text, '&' ) ) { 1024 return $text; 1025 } 1026 1027 // Match the previous behavior of _wp_specialchars() when the $quote_style is not an accepted value. 1028 if ( empty( $quote_style ) ) { 1029 $quote_style = ENT_NOQUOTES; 1030 } elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) { 1031 $quote_style = ENT_QUOTES; 1032 } 1033 1034 // More complete than get_html_translation_table( HTML_SPECIALCHARS ). 1035 $single = array( 1036 ''' => '\'', 1037 ''' => '\'', 1038 ); 1039 $single_preg = array( 1040 '/�*39;/' => ''', 1041 '/�*27;/i' => ''', 1042 ); 1043 $double = array( 1044 '"' => '"', 1045 '"' => '"', 1046 '"' => '"', 1047 ); 1048 $double_preg = array( 1049 '/�*34;/' => '"', 1050 '/�*22;/i' => '"', 1051 ); 1052 $others = array( 1053 '<' => '<', 1054 '<' => '<', 1055 '>' => '>', 1056 '>' => '>', 1057 '&' => '&', 1058 '&' => '&', 1059 '&' => '&', 1060 ); 1061 $others_preg = array( 1062 '/�*60;/' => '<', 1063 '/�*62;/' => '>', 1064 '/�*38;/' => '&', 1065 '/�*26;/i' => '&', 1066 ); 1067 1068 if ( ENT_QUOTES === $quote_style ) { 1069 $translation = array_merge( $single, $double, $others ); 1070 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg ); 1071 } elseif ( ENT_COMPAT === $quote_style || 'double' === $quote_style ) { 1072 $translation = array_merge( $double, $others ); 1073 $translation_preg = array_merge( $double_preg, $others_preg ); 1074 } elseif ( 'single' === $quote_style ) { 1075 $translation = array_merge( $single, $others ); 1076 $translation_preg = array_merge( $single_preg, $others_preg ); 1077 } elseif ( ENT_NOQUOTES === $quote_style ) { 1078 $translation = $others; 1079 $translation_preg = $others_preg; 1080 } 1081 1082 // Remove zero padding on numeric entities. 1083 $text = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $text ); 1084 1085 // Replace characters according to translation table. 1086 return strtr( $text, $translation ); 1087 } 1088 1089 /** 1090 * Checks for invalid UTF8 in a string. 1091 * 1092 * Note! This function only performs its work if the `blog_charset` is set 1093 * to UTF-8. For all other values it returns the input text unchanged. 1094 * 1095 * Note! Unless requested, this returns an empty string if the input contains 1096 * any sequences of invalid UTF-8. To replace invalid byte sequences, pass 1097 * `true` as the optional `$strip` parameter. 1098 * 1099 * Consider using {@see wp_scrub_utf8()} instead which does not depend on 1100 * the value of `blog_charset`. 1101 * 1102 * Example: 1103 * 1104 * // The `blog_charset` is `latin1`, so this returns the input unchanged. 1105 * $every_possible_input === wp_check_invalid_utf8( $every_possible_input ); 1106 * 1107 * // Valid strings come through unchanged. 1108 * 'test' === wp_check_invalid_utf8( 'test' ); 1109 * 1110 * $invalid = "the byte \xC0 is never allowed in a UTF-8 string."; 1111 * 1112 * // Invalid strings are rejected outright. 1113 * '' === wp_check_invalid_utf8( $invalid ); 1114 * 1115 * // “Stripping” invalid sequences produces the replacement character instead. 1116 * "the byte \u{FFFD} is never allowed in a UTF-8 string." === wp_check_invalid_utf8( $invalid, true ); 1117 * 'the byte � is never allowed in a UTF-8 string.' === wp_check_invalid_utf8( $invalid, true ); 1118 * 1119 * @since 2.8.0 1120 * @since 6.9.0 Stripping replaces invalid byte sequences with the Unicode replacement character U+FFFD (�). 1121 * 1122 * @param string $text String which is expected to be encoded as UTF-8 unless `blog_charset` is another encoding. 1123 * @param bool $strip Optional. Whether to replace invalid sequences of bytes with the Unicode replacement 1124 * character (U+FFFD `�`). Default `false` returns an empty string for invalid UTF-8 inputs. 1125 * @return string The checked text. 1126 */ 1127 function wp_check_invalid_utf8( $text, $strip = false ) { 1128 $text = (string) $text; 1129 1130 if ( 0 === strlen( $text ) ) { 1131 return ''; 1132 } 1133 1134 // Store the site charset as a static to avoid multiple calls to get_option(). 1135 static $is_utf8 = null; 1136 if ( ! isset( $is_utf8 ) ) { 1137 $is_utf8 = is_utf8_charset(); 1138 } 1139 1140 if ( ! $is_utf8 || wp_is_valid_utf8( $text ) ) { 1141 return $text; 1142 } 1143 1144 return $strip 1145 ? wp_scrub_utf8( $text ) 1146 : ''; 1147 } 1148 1149 /** 1150 * Encodes the Unicode values to be used in the URI. 1151 * 1152 * @since 1.5.0 1153 * @since 5.8.3 Added the `encode_ascii_characters` parameter. 1154 * 1155 * @param string $utf8_string String to encode. 1156 * @param int $length Max length of the string. 1157 * @param bool $encode_ascii_characters Whether to encode ascii characters such as < " ' 1158 * @return string String with Unicode encoded for URI. 1159 */ 1160 function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters = false ) { 1161 $unicode = ''; 1162 $values = array(); 1163 $num_octets = 1; 1164 $unicode_length = 0; 1165 1166 mbstring_binary_safe_encoding(); 1167 $string_length = strlen( $utf8_string ); 1168 reset_mbstring_encoding(); 1169 1170 for ( $i = 0; $i < $string_length; $i++ ) { 1171 1172 $value = ord( $utf8_string[ $i ] ); 1173 1174 if ( $value < 128 ) { 1175 $char = chr( $value ); 1176 $encoded_char = $encode_ascii_characters ? rawurlencode( $char ) : $char; 1177 $encoded_char_length = strlen( $encoded_char ); 1178 if ( $length && ( $unicode_length + $encoded_char_length ) > $length ) { 1179 break; 1180 } 1181 $unicode .= $encoded_char; 1182 $unicode_length += $encoded_char_length; 1183 } else { 1184 if ( 0 === count( $values ) ) { 1185 if ( $value < 224 ) { 1186 $num_octets = 2; 1187 } elseif ( $value < 240 ) { 1188 $num_octets = 3; 1189 } else { 1190 $num_octets = 4; 1191 } 1192 } 1193 1194 $values[] = $value; 1195 1196 if ( $length && ( $unicode_length + ( $num_octets * 3 ) ) > $length ) { 1197 break; 1198 } 1199 if ( count( $values ) === $num_octets ) { 1200 for ( $j = 0; $j < $num_octets; $j++ ) { 1201 $unicode .= '%' . dechex( $values[ $j ] ); 1202 } 1203 1204 $unicode_length += $num_octets * 3; 1205 1206 $values = array(); 1207 $num_octets = 1; 1208 } 1209 } 1210 } 1211 1212 return $unicode; 1213 } 1214 1215 /** 1216 * Converts all accent characters to ASCII characters. 1217 * 1218 * If there are no accent characters, then the string given is just returned. 1219 * 1220 * **Accent characters converted:** 1221 * 1222 * Currency signs: 1223 * 1224 * | Code | Glyph | Replacement | Description | 1225 * | -------- | ----- | ----------- | ------------------- | 1226 * | U+00A3 | £ | (empty) | British Pound sign | 1227 * | U+20AC | € | E | Euro sign | 1228 * 1229 * Decompositions for Latin-1 Supplement: 1230 * 1231 * | Code | Glyph | Replacement | Description | 1232 * | ------- | ----- | ----------- | -------------------------------------- | 1233 * | U+00AA | ª | a | Feminine ordinal indicator | 1234 * | U+00BA | º | o | Masculine ordinal indicator | 1235 * | U+00C0 | À | A | Latin capital letter A with grave | 1236 * | U+00C1 | Á | A | Latin capital letter A with acute | 1237 * | U+00C2 |  | A | Latin capital letter A with circumflex | 1238 * | U+00C3 | à | A | Latin capital letter A with tilde | 1239 * | U+00C4 | Ä | A | Latin capital letter A with diaeresis | 1240 * | U+00C5 | Å | A | Latin capital letter A with ring above | 1241 * | U+00C6 | Æ | AE | Latin capital letter AE | 1242 * | U+00C7 | Ç | C | Latin capital letter C with cedilla | 1243 * | U+00C8 | È | E | Latin capital letter E with grave | 1244 * | U+00C9 | É | E | Latin capital letter E with acute | 1245 * | U+00CA | Ê | E | Latin capital letter E with circumflex | 1246 * | U+00CB | Ë | E | Latin capital letter E with diaeresis | 1247 * | U+00CC | Ì | I | Latin capital letter I with grave | 1248 * | U+00CD | Í | I | Latin capital letter I with acute | 1249 * | U+00CE | Î | I | Latin capital letter I with circumflex | 1250 * | U+00CF | Ï | I | Latin capital letter I with diaeresis | 1251 * | U+00D0 | Ð | D | Latin capital letter Eth | 1252 * | U+00D1 | Ñ | N | Latin capital letter N with tilde | 1253 * | U+00D2 | Ò | O | Latin capital letter O with grave | 1254 * | U+00D3 | Ó | O | Latin capital letter O with acute | 1255 * | U+00D4 | Ô | O | Latin capital letter O with circumflex | 1256 * | U+00D5 | Õ | O | Latin capital letter O with tilde | 1257 * | U+00D6 | Ö | O | Latin capital letter O with diaeresis | 1258 * | U+00D8 | Ø | O | Latin capital letter O with stroke | 1259 * | U+00D9 | Ù | U | Latin capital letter U with grave | 1260 * | U+00DA | Ú | U | Latin capital letter U with acute | 1261 * | U+00DB | Û | U | Latin capital letter U with circumflex | 1262 * | U+00DC | Ü | U | Latin capital letter U with diaeresis | 1263 * | U+00DD | Ý | Y | Latin capital letter Y with acute | 1264 * | U+00DE | Þ | TH | Latin capital letter Thorn | 1265 * | U+00DF | ß | s | Latin small letter sharp s | 1266 * | U+00E0 | à | a | Latin small letter a with grave | 1267 * | U+00E1 | á | a | Latin small letter a with acute | 1268 * | U+00E2 | â | a | Latin small letter a with circumflex | 1269 * | U+00E3 | ã | a | Latin small letter a with tilde | 1270 * | U+00E4 | ä | a | Latin small letter a with diaeresis | 1271 * | U+00E5 | å | a | Latin small letter a with ring above | 1272 * | U+00E6 | æ | ae | Latin small letter ae | 1273 * | U+00E7 | ç | c | Latin small letter c with cedilla | 1274 * | U+00E8 | è | e | Latin small letter e with grave | 1275 * | U+00E9 | é | e | Latin small letter e with acute | 1276 * | U+00EA | ê | e | Latin small letter e with circumflex | 1277 * | U+00EB | ë | e | Latin small letter e with diaeresis | 1278 * | U+00EC | ì | i | Latin small letter i with grave | 1279 * | U+00ED | í | i | Latin small letter i with acute | 1280 * | U+00EE | î | i | Latin small letter i with circumflex | 1281 * | U+00EF | ï | i | Latin small letter i with diaeresis | 1282 * | U+00F0 | ð | d | Latin small letter Eth | 1283 * | U+00F1 | ñ | n | Latin small letter n with tilde | 1284 * | U+00F2 | ò | o | Latin small letter o with grave | 1285 * | U+00F3 | ó | o | Latin small letter o with acute | 1286 * | U+00F4 | ô | o | Latin small letter o with circumflex | 1287 * | U+00F5 | õ | o | Latin small letter o with tilde | 1288 * | U+00F6 | ö | o | Latin small letter o with diaeresis | 1289 * | U+00F8 | ø | o | Latin small letter o with stroke | 1290 * | U+00F9 | ù | u | Latin small letter u with grave | 1291 * | U+00FA | ú | u | Latin small letter u with acute | 1292 * | U+00FB | û | u | Latin small letter u with circumflex | 1293 * | U+00FC | ü | u | Latin small letter u with diaeresis | 1294 * | U+00FD | ý | y | Latin small letter y with acute | 1295 * | U+00FE | þ | th | Latin small letter Thorn | 1296 * | U+00FF | ÿ | y | Latin small letter y with diaeresis | 1297 * 1298 * Decompositions for Latin Extended-A: 1299 * 1300 * | Code | Glyph | Replacement | Description | 1301 * | ------- | ----- | ----------- | ------------------------------------------------- | 1302 * | U+0100 | Ā | A | Latin capital letter A with macron | 1303 * | U+0101 | ā | a | Latin small letter a with macron | 1304 * | U+0102 | Ă | A | Latin capital letter A with breve | 1305 * | U+0103 | ă | a | Latin small letter a with breve | 1306 * | U+0104 | Ą | A | Latin capital letter A with ogonek | 1307 * | U+0105 | ą | a | Latin small letter a with ogonek | 1308 * | U+01006 | Ć | C | Latin capital letter C with acute | 1309 * | U+0107 | ć | c | Latin small letter c with acute | 1310 * | U+0108 | Ĉ | C | Latin capital letter C with circumflex | 1311 * | U+0109 | ĉ | c | Latin small letter c with circumflex | 1312 * | U+010A | Ċ | C | Latin capital letter C with dot above | 1313 * | U+010B | ċ | c | Latin small letter c with dot above | 1314 * | U+010C | Č | C | Latin capital letter C with caron | 1315 * | U+010D | č | c | Latin small letter c with caron | 1316 * | U+010E | Ď | D | Latin capital letter D with caron | 1317 * | U+010F | ď | d | Latin small letter d with caron | 1318 * | U+0110 | Đ | D | Latin capital letter D with stroke | 1319 * | U+0111 | đ | d | Latin small letter d with stroke | 1320 * | U+0112 | Ē | E | Latin capital letter E with macron | 1321 * | U+0113 | ē | e | Latin small letter e with macron | 1322 * | U+0114 | Ĕ | E | Latin capital letter E with breve | 1323 * | U+0115 | ĕ | e | Latin small letter e with breve | 1324 * | U+0116 | Ė | E | Latin capital letter E with dot above | 1325 * | U+0117 | ė | e | Latin small letter e with dot above | 1326 * | U+0118 | Ę | E | Latin capital letter E with ogonek | 1327 * | U+0119 | ę | e | Latin small letter e with ogonek | 1328 * | U+011A | Ě | E | Latin capital letter E with caron | 1329 * | U+011B | ě | e | Latin small letter e with caron | 1330 * | U+011C | Ĝ | G | Latin capital letter G with circumflex | 1331 * | U+011D | ĝ | g | Latin small letter g with circumflex | 1332 * | U+011E | Ğ | G | Latin capital letter G with breve | 1333 * | U+011F | ğ | g | Latin small letter g with breve | 1334 * | U+0120 | Ġ | G | Latin capital letter G with dot above | 1335 * | U+0121 | ġ | g | Latin small letter g with dot above | 1336 * | U+0122 | Ģ | G | Latin capital letter G with cedilla | 1337 * | U+0123 | ģ | g | Latin small letter g with cedilla | 1338 * | U+0124 | Ĥ | H | Latin capital letter H with circumflex | 1339 * | U+0125 | ĥ | h | Latin small letter h with circumflex | 1340 * | U+0126 | Ħ | H | Latin capital letter H with stroke | 1341 * | U+0127 | ħ | h | Latin small letter h with stroke | 1342 * | U+0128 | Ĩ | I | Latin capital letter I with tilde | 1343 * | U+0129 | ĩ | i | Latin small letter i with tilde | 1344 * | U+012A | Ī | I | Latin capital letter I with macron | 1345 * | U+012B | ī | i | Latin small letter i with macron | 1346 * | U+012C | Ĭ | I | Latin capital letter I with breve | 1347 * | U+012D | ĭ | i | Latin small letter i with breve | 1348 * | U+012E | Į | I | Latin capital letter I with ogonek | 1349 * | U+012F | į | i | Latin small letter i with ogonek | 1350 * | U+0130 | İ | I | Latin capital letter I with dot above | 1351 * | U+0131 | ı | i | Latin small letter dotless i | 1352 * | U+0132 | IJ | IJ | Latin capital ligature IJ | 1353 * | U+0133 | ij | ij | Latin small ligature ij | 1354 * | U+0134 | Ĵ | J | Latin capital letter J with circumflex | 1355 * | U+0135 | ĵ | j | Latin small letter j with circumflex | 1356 * | U+0136 | Ķ | K | Latin capital letter K with cedilla | 1357 * | U+0137 | ķ | k | Latin small letter k with cedilla | 1358 * | U+0138 | ĸ | k | Latin small letter Kra | 1359 * | U+0139 | Ĺ | L | Latin capital letter L with acute | 1360 * | U+013A | ĺ | l | Latin small letter l with acute | 1361 * | U+013B | Ļ | L | Latin capital letter L with cedilla | 1362 * | U+013C | ļ | l | Latin small letter l with cedilla | 1363 * | U+013D | Ľ | L | Latin capital letter L with caron | 1364 * | U+013E | ľ | l | Latin small letter l with caron | 1365 * | U+013F | Ŀ | L | Latin capital letter L with middle dot | 1366 * | U+0140 | ŀ | l | Latin small letter l with middle dot | 1367 * | U+0141 | Ł | L | Latin capital letter L with stroke | 1368 * | U+0142 | ł | l | Latin small letter l with stroke | 1369 * | U+0143 | Ń | N | Latin capital letter N with acute | 1370 * | U+0144 | ń | n | Latin small letter N with acute | 1371 * | U+0145 | Ņ | N | Latin capital letter N with cedilla | 1372 * | U+0146 | ņ | n | Latin small letter n with cedilla | 1373 * | U+0147 | Ň | N | Latin capital letter N with caron | 1374 * | U+0148 | ň | n | Latin small letter n with caron | 1375 * | U+0149 | ʼn | n | Latin small letter n preceded by apostrophe | 1376 * | U+014A | Ŋ | N | Latin capital letter Eng | 1377 * | U+014B | ŋ | n | Latin small letter Eng | 1378 * | U+014C | Ō | O | Latin capital letter O with macron | 1379 * | U+014D | ō | o | Latin small letter o with macron | 1380 * | U+014E | Ŏ | O | Latin capital letter O with breve | 1381 * | U+014F | ŏ | o | Latin small letter o with breve | 1382 * | U+0150 | Ő | O | Latin capital letter O with double acute | 1383 * | U+0151 | ő | o | Latin small letter o with double acute | 1384 * | U+0152 | Œ | OE | Latin capital ligature OE | 1385 * | U+0153 | œ | oe | Latin small ligature oe | 1386 * | U+0154 | Ŕ | R | Latin capital letter R with acute | 1387 * | U+0155 | ŕ | r | Latin small letter r with acute | 1388 * | U+0156 | Ŗ | R | Latin capital letter R with cedilla | 1389 * | U+0157 | ŗ | r | Latin small letter r with cedilla | 1390 * | U+0158 | Ř | R | Latin capital letter R with caron | 1391 * | U+0159 | ř | r | Latin small letter r with caron | 1392 * | U+015A | Ś | S | Latin capital letter S with acute | 1393 * | U+015B | ś | s | Latin small letter s with acute | 1394 * | U+015C | Ŝ | S | Latin capital letter S with circumflex | 1395 * | U+015D | ŝ | s | Latin small letter s with circumflex | 1396 * | U+015E | Ş | S | Latin capital letter S with cedilla | 1397 * | U+015F | ş | s | Latin small letter s with cedilla | 1398 * | U+0160 | Š | S | Latin capital letter S with caron | 1399 * | U+0161 | š | s | Latin small letter s with caron | 1400 * | U+0162 | Ţ | T | Latin capital letter T with cedilla | 1401 * | U+0163 | ţ | t | Latin small letter t with cedilla | 1402 * | U+0164 | Ť | T | Latin capital letter T with caron | 1403 * | U+0165 | ť | t | Latin small letter t with caron | 1404 * | U+0166 | Ŧ | T | Latin capital letter T with stroke | 1405 * | U+0167 | ŧ | t | Latin small letter t with stroke | 1406 * | U+0168 | Ũ | U | Latin capital letter U with tilde | 1407 * | U+0169 | ũ | u | Latin small letter u with tilde | 1408 * | U+016A | Ū | U | Latin capital letter U with macron | 1409 * | U+016B | ū | u | Latin small letter u with macron | 1410 * | U+016C | Ŭ | U | Latin capital letter U with breve | 1411 * | U+016D | ŭ | u | Latin small letter u with breve | 1412 * | U+016E | Ů | U | Latin capital letter U with ring above | 1413 * | U+016F | ů | u | Latin small letter u with ring above | 1414 * | U+0170 | Ű | U | Latin capital letter U with double acute | 1415 * | U+0171 | ű | u | Latin small letter u with double acute | 1416 * | U+0172 | Ų | U | Latin capital letter U with ogonek | 1417 * | U+0173 | ų | u | Latin small letter u with ogonek | 1418 * | U+0174 | Ŵ | W | Latin capital letter W with circumflex | 1419 * | U+0175 | ŵ | w | Latin small letter w with circumflex | 1420 * | U+0176 | Ŷ | Y | Latin capital letter Y with circumflex | 1421 * | U+0177 | ŷ | y | Latin small letter y with circumflex | 1422 * | U+0178 | Ÿ | Y | Latin capital letter Y with diaeresis | 1423 * | U+0179 | Ź | Z | Latin capital letter Z with acute | 1424 * | U+017A | ź | z | Latin small letter z with acute | 1425 * | U+017B | Ż | Z | Latin capital letter Z with dot above | 1426 * | U+017C | ż | z | Latin small letter z with dot above | 1427 * | U+017D | Ž | Z | Latin capital letter Z with caron | 1428 * | U+017E | ž | z | Latin small letter z with caron | 1429 * | U+017F | ſ | s | Latin small letter long s | 1430 * | U+01A0 | Ơ | O | Latin capital letter O with horn | 1431 * | U+01A1 | ơ | o | Latin small letter o with horn | 1432 * | U+01AF | Ư | U | Latin capital letter U with horn | 1433 * | U+01B0 | ư | u | Latin small letter u with horn | 1434 * | U+01CD | Ǎ | A | Latin capital letter A with caron | 1435 * | U+01CE | ǎ | a | Latin small letter a with caron | 1436 * | U+01CF | Ǐ | I | Latin capital letter I with caron | 1437 * | U+01D0 | ǐ | i | Latin small letter i with caron | 1438 * | U+01D1 | Ǒ | O | Latin capital letter O with caron | 1439 * | U+01D2 | ǒ | o | Latin small letter o with caron | 1440 * | U+01D3 | Ǔ | U | Latin capital letter U with caron | 1441 * | U+01D4 | ǔ | u | Latin small letter u with caron | 1442 * | U+01D5 | Ǖ | U | Latin capital letter U with diaeresis and macron | 1443 * | U+01D6 | ǖ | u | Latin small letter u with diaeresis and macron | 1444 * | U+01D7 | Ǘ | U | Latin capital letter U with diaeresis and acute | 1445 * | U+01D8 | ǘ | u | Latin small letter u with diaeresis and acute | 1446 * | U+01D9 | Ǚ | U | Latin capital letter U with diaeresis and caron | 1447 * | U+01DA | ǚ | u | Latin small letter u with diaeresis and caron | 1448 * | U+01DB | Ǜ | U | Latin capital letter U with diaeresis and grave | 1449 * | U+01DC | ǜ | u | Latin small letter u with diaeresis and grave | 1450 * 1451 * Decompositions for Latin Extended-B: 1452 * 1453 * | Code | Glyph | Replacement | Description | 1454 * | -------- | ----- | ----------- | ----------------------------------------- | 1455 * | U+018F | Ə | E | Latin capital letter Ə | 1456 * | U+0259 | ǝ | e | Latin small letter ǝ | 1457 * | U+0218 | Ș | S | Latin capital letter S with comma below | 1458 * | U+0219 | ș | s | Latin small letter s with comma below | 1459 * | U+021A | Ț | T | Latin capital letter T with comma below | 1460 * | U+021B | ț | t | Latin small letter t with comma below | 1461 * 1462 * Vowels with diacritic (Chinese, Hanyu Pinyin): 1463 * 1464 * | Code | Glyph | Replacement | Description | 1465 * | -------- | ----- | ----------- | ----------------------------------------------------- | 1466 * | U+0251 | ɑ | a | Latin small letter alpha | 1467 * | U+1EA0 | Ạ | A | Latin capital letter A with dot below | 1468 * | U+1EA1 | ạ | a | Latin small letter a with dot below | 1469 * | U+1EA2 | Ả | A | Latin capital letter A with hook above | 1470 * | U+1EA3 | ả | a | Latin small letter a with hook above | 1471 * | U+1EA4 | Ấ | A | Latin capital letter A with circumflex and acute | 1472 * | U+1EA5 | ấ | a | Latin small letter a with circumflex and acute | 1473 * | U+1EA6 | Ầ | A | Latin capital letter A with circumflex and grave | 1474 * | U+1EA7 | ầ | a | Latin small letter a with circumflex and grave | 1475 * | U+1EA8 | Ẩ | A | Latin capital letter A with circumflex and hook above | 1476 * | U+1EA9 | ẩ | a | Latin small letter a with circumflex and hook above | 1477 * | U+1EAA | Ẫ | A | Latin capital letter A with circumflex and tilde | 1478 * | U+1EAB | ẫ | a | Latin small letter a with circumflex and tilde | 1479 * | U+1EA6 | Ậ | A | Latin capital letter A with circumflex and dot below | 1480 * | U+1EAD | ậ | a | Latin small letter a with circumflex and dot below | 1481 * | U+1EAE | Ắ | A | Latin capital letter A with breve and acute | 1482 * | U+1EAF | ắ | a | Latin small letter a with breve and acute | 1483 * | U+1EB0 | Ằ | A | Latin capital letter A with breve and grave | 1484 * | U+1EB1 | ằ | a | Latin small letter a with breve and grave | 1485 * | U+1EB2 | Ẳ | A | Latin capital letter A with breve and hook above | 1486 * | U+1EB3 | ẳ | a | Latin small letter a with breve and hook above | 1487 * | U+1EB4 | Ẵ | A | Latin capital letter A with breve and tilde | 1488 * | U+1EB5 | ẵ | a | Latin small letter a with breve and tilde | 1489 * | U+1EB6 | Ặ | A | Latin capital letter A with breve and dot below | 1490 * | U+1EB7 | ặ | a | Latin small letter a with breve and dot below | 1491 * | U+1EB8 | Ẹ | E | Latin capital letter E with dot below | 1492 * | U+1EB9 | ẹ | e | Latin small letter e with dot below | 1493 * | U+1EBA | Ẻ | E | Latin capital letter E with hook above | 1494 * | U+1EBB | ẻ | e | Latin small letter e with hook above | 1495 * | U+1EBC | Ẽ | E | Latin capital letter E with tilde | 1496 * | U+1EBD | ẽ | e | Latin small letter e with tilde | 1497 * | U+1EBE | Ế | E | Latin capital letter E with circumflex and acute | 1498 * | U+1EBF | ế | e | Latin small letter e with circumflex and acute | 1499 * | U+1EC0 | Ề | E | Latin capital letter E with circumflex and grave | 1500 * | U+1EC1 | ề | e | Latin small letter e with circumflex and grave | 1501 * | U+1EC2 | Ể | E | Latin capital letter E with circumflex and hook above | 1502 * | U+1EC3 | ể | e | Latin small letter e with circumflex and hook above | 1503 * | U+1EC4 | Ễ | E | Latin capital letter E with circumflex and tilde | 1504 * | U+1EC5 | ễ | e | Latin small letter e with circumflex and tilde | 1505 * | U+1EC6 | Ệ | E | Latin capital letter E with circumflex and dot below | 1506 * | U+1EC7 | ệ | e | Latin small letter e with circumflex and dot below | 1507 * | U+1EC8 | Ỉ | I | Latin capital letter I with hook above | 1508 * | U+1EC9 | ỉ | i | Latin small letter i with hook above | 1509 * | U+1ECA | Ị | I | Latin capital letter I with dot below | 1510 * | U+1ECB | ị | i | Latin small letter i with dot below | 1511 * | U+1ECC | Ọ | O | Latin capital letter O with dot below | 1512 * | U+1ECD | ọ | o | Latin small letter o with dot below | 1513 * | U+1ECE | Ỏ | O | Latin capital letter O with hook above | 1514 * | U+1ECF | ỏ | o | Latin small letter o with hook above | 1515 * | U+1ED0 | Ố | O | Latin capital letter O with circumflex and acute | 1516 * | U+1ED1 | ố | o | Latin small letter o with circumflex and acute | 1517 * | U+1ED2 | Ồ | O | Latin capital letter O with circumflex and grave | 1518 * | U+1ED3 | ồ | o | Latin small letter o with circumflex and grave | 1519 * | U+1ED4 | Ổ | O | Latin capital letter O with circumflex and hook above | 1520 * | U+1ED5 | ổ | o | Latin small letter o with circumflex and hook above | 1521 * | U+1ED6 | Ỗ | O | Latin capital letter O with circumflex and tilde | 1522 * | U+1ED7 | ỗ | o | Latin small letter o with circumflex and tilde | 1523 * | U+1ED8 | Ộ | O | Latin capital letter O with circumflex and dot below | 1524 * | U+1ED9 | ộ | o | Latin small letter o with circumflex and dot below | 1525 * | U+1EDA | Ớ | O | Latin capital letter O with horn and acute | 1526 * | U+1EDB | ớ | o | Latin small letter o with horn and acute | 1527 * | U+1EDC | Ờ | O | Latin capital letter O with horn and grave | 1528 * | U+1EDD | ờ | o | Latin small letter o with horn and grave | 1529 * | U+1EDE | Ở | O | Latin capital letter O with horn and hook above | 1530 * | U+1EDF | ở | o | Latin small letter o with horn and hook above | 1531 * | U+1EE0 | Ỡ | O | Latin capital letter O with horn and tilde | 1532 * | U+1EE1 | ỡ | o | Latin small letter o with horn and tilde | 1533 * | U+1EE2 | Ợ | O | Latin capital letter O with horn and dot below | 1534 * | U+1EE3 | ợ | o | Latin small letter o with horn and dot below | 1535 * | U+1EE4 | Ụ | U | Latin capital letter U with dot below | 1536 * | U+1EE5 | ụ | u | Latin small letter u with dot below | 1537 * | U+1EE6 | Ủ | U | Latin capital letter U with hook above | 1538 * | U+1EE7 | ủ | u | Latin small letter u with hook above | 1539 * | U+1EE8 | Ứ | U | Latin capital letter U with horn and acute | 1540 * | U+1EE9 | ứ | u | Latin small letter u with horn and acute | 1541 * | U+1EEA | Ừ | U | Latin capital letter U with horn and grave | 1542 * | U+1EEB | ừ | u | Latin small letter u with horn and grave | 1543 * | U+1EEC | Ử | U | Latin capital letter U with horn and hook above | 1544 * | U+1EED | ử | u | Latin small letter u with horn and hook above | 1545 * | U+1EEE | Ữ | U | Latin capital letter U with horn and tilde | 1546 * | U+1EEF | ữ | u | Latin small letter u with horn and tilde | 1547 * | U+1EF0 | Ự | U | Latin capital letter U with horn and dot below | 1548 * | U+1EF1 | ự | u | Latin small letter u with horn and dot below | 1549 * | U+1EF2 | Ỳ | Y | Latin capital letter Y with grave | 1550 * | U+1EF3 | ỳ | y | Latin small letter y with grave | 1551 * | U+1EF4 | Ỵ | Y | Latin capital letter Y with dot below | 1552 * | U+1EF5 | ỵ | y | Latin small letter y with dot below | 1553 * | U+1EF6 | Ỷ | Y | Latin capital letter Y with hook above | 1554 * | U+1EF7 | ỷ | y | Latin small letter y with hook above | 1555 * | U+1EF8 | Ỹ | Y | Latin capital letter Y with tilde | 1556 * | U+1EF9 | ỹ | y | Latin small letter y with tilde | 1557 * 1558 * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`), 1559 * German (Switzerland) informal (`de_CH_informal`), and German (Austria) (`de_AT`) locales: 1560 * 1561 * | Code | Glyph | Replacement | Description | 1562 * | -------- | ----- | ----------- | --------------------------------------- | 1563 * | U+00C4 | Ä | Ae | Latin capital letter A with diaeresis | 1564 * | U+00E4 | ä | ae | Latin small letter a with diaeresis | 1565 * | U+00D6 | Ö | Oe | Latin capital letter O with diaeresis | 1566 * | U+00F6 | ö | oe | Latin small letter o with diaeresis | 1567 * | U+00DC | Ü | Ue | Latin capital letter U with diaeresis | 1568 * | U+00FC | ü | ue | Latin small letter u with diaeresis | 1569 * | U+1E9E | ẞ | SS | Latin capital letter sharp s | 1570 * | U+00DF | ß | ss | Latin small letter sharp s | 1571 * 1572 * Danish (`da_DK`) locale: 1573 * 1574 * | Code | Glyph | Replacement | Description | 1575 * | -------- | ----- | ----------- | --------------------------------------- | 1576 * | U+00C6 | Æ | Ae | Latin capital letter AE | 1577 * | U+00E6 | æ | ae | Latin small letter ae | 1578 * | U+00D8 | Ø | Oe | Latin capital letter O with stroke | 1579 * | U+00F8 | ø | oe | Latin small letter o with stroke | 1580 * | U+00C5 | Å | Aa | Latin capital letter A with ring above | 1581 * | U+00E5 | å | aa | Latin small letter a with ring above | 1582 * 1583 * Catalan (`ca`) locale: 1584 * 1585 * | Code | Glyph | Replacement | Description | 1586 * | -------- | ----- | ----------- | --------------------------------------- | 1587 * | U+00B7 | l·l | ll | Flown dot (between two Ls) | 1588 * 1589 * Serbian (`sr_RS`) and Bosnian (`bs_BA`) locales: 1590 * 1591 * | Code | Glyph | Replacement | Description | 1592 * | -------- | ----- | ----------- | --------------------------------------- | 1593 * | U+0110 | Đ | DJ | Latin capital letter D with stroke | 1594 * | U+0111 | đ | dj | Latin small letter d with stroke | 1595 * 1596 * @since 1.2.1 1597 * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`. 1598 * @since 4.7.0 Added locale support for `sr_RS`. 1599 * @since 4.8.0 Added locale support for `bs_BA`. 1600 * @since 5.7.0 Added locale support for `de_AT`. 1601 * @since 6.0.0 Added the `$locale` parameter. 1602 * @since 6.1.0 Added Unicode NFC encoding normalization support. 1603 * @since 7.0.0 Added capital Eszett (U+1E9E) support for German locales. 1604 * 1605 * @param string $text Text that might have accent characters. 1606 * @param string $locale Optional. The locale to use for accent removal. Some character 1607 * replacements depend on the locale being used (e.g. 'de_DE'). 1608 * Defaults to the current locale. 1609 * @return string Filtered string with replaced "nice" characters. 1610 */ 1611 function remove_accents( $text, $locale = '' ) { 1612 if ( ! preg_match( '/[\x80-\xff]/', $text ) ) { 1613 return $text; 1614 } 1615 1616 if ( wp_is_valid_utf8( $text ) ) { 1617 1618 /* 1619 * Unicode sequence normalization from NFD (Normalization Form Decomposed) 1620 * to NFC (Normalization Form [Pre]Composed), the encoding used in this function. 1621 */ 1622 if ( function_exists( 'normalizer_is_normalized' ) 1623 && function_exists( 'normalizer_normalize' ) 1624 ) { 1625 if ( ! normalizer_is_normalized( $text ) ) { 1626 $text = normalizer_normalize( $text ); 1627 } 1628 } 1629 1630 $chars = array( 1631 // Decompositions for Latin-1 Supplement. 1632 'ª' => 'a', 1633 'º' => 'o', 1634 'À' => 'A', 1635 'Á' => 'A', 1636 'Â' => 'A', 1637 'Ã' => 'A', 1638 'Ä' => 'A', 1639 'Å' => 'A', 1640 'Æ' => 'AE', 1641 'Ç' => 'C', 1642 'È' => 'E', 1643 'É' => 'E', 1644 'Ê' => 'E', 1645 'Ë' => 'E', 1646 'Ì' => 'I', 1647 'Í' => 'I', 1648 'Î' => 'I', 1649 'Ï' => 'I', 1650 'Ð' => 'D', 1651 'Ñ' => 'N', 1652 'Ò' => 'O', 1653 'Ó' => 'O', 1654 'Ô' => 'O', 1655 'Õ' => 'O', 1656 'Ö' => 'O', 1657 'Ù' => 'U', 1658 'Ú' => 'U', 1659 'Û' => 'U', 1660 'Ü' => 'U', 1661 'Ý' => 'Y', 1662 'Þ' => 'TH', 1663 'ß' => 's', 1664 'à' => 'a', 1665 'á' => 'a', 1666 'â' => 'a', 1667 'ã' => 'a', 1668 'ä' => 'a', 1669 'å' => 'a', 1670 'æ' => 'ae', 1671 'ç' => 'c', 1672 'è' => 'e', 1673 'é' => 'e', 1674 'ê' => 'e', 1675 'ë' => 'e', 1676 'ì' => 'i', 1677 'í' => 'i', 1678 'î' => 'i', 1679 'ï' => 'i', 1680 'ð' => 'd', 1681 'ñ' => 'n', 1682 'ò' => 'o', 1683 'ó' => 'o', 1684 'ô' => 'o', 1685 'õ' => 'o', 1686 'ö' => 'o', 1687 'ø' => 'o', 1688 'ù' => 'u', 1689 'ú' => 'u', 1690 'û' => 'u', 1691 'ü' => 'u', 1692 'ý' => 'y', 1693 'þ' => 'th', 1694 'ÿ' => 'y', 1695 'Ø' => 'O', 1696 // Decompositions for Latin Extended-A. 1697 'Ā' => 'A', 1698 'ā' => 'a', 1699 'Ă' => 'A', 1700 'ă' => 'a', 1701 'Ą' => 'A', 1702 'ą' => 'a', 1703 'Ć' => 'C', 1704 'ć' => 'c', 1705 'Ĉ' => 'C', 1706 'ĉ' => 'c', 1707 'Ċ' => 'C', 1708 'ċ' => 'c', 1709 'Č' => 'C', 1710 'č' => 'c', 1711 'Ď' => 'D', 1712 'ď' => 'd', 1713 'Đ' => 'D', 1714 'đ' => 'd', 1715 'Ē' => 'E', 1716 'ē' => 'e', 1717 'Ĕ' => 'E', 1718 'ĕ' => 'e', 1719 'Ė' => 'E', 1720 'ė' => 'e', 1721 'Ę' => 'E', 1722 'ę' => 'e', 1723 'Ě' => 'E', 1724 'ě' => 'e', 1725 'Ĝ' => 'G', 1726 'ĝ' => 'g', 1727 'Ğ' => 'G', 1728 'ğ' => 'g', 1729 'Ġ' => 'G', 1730 'ġ' => 'g', 1731 'Ģ' => 'G', 1732 'ģ' => 'g', 1733 'Ĥ' => 'H', 1734 'ĥ' => 'h', 1735 'Ħ' => 'H', 1736 'ħ' => 'h', 1737 'Ĩ' => 'I', 1738 'ĩ' => 'i', 1739 'Ī' => 'I', 1740 'ī' => 'i', 1741 'Ĭ' => 'I', 1742 'ĭ' => 'i', 1743 'Į' => 'I', 1744 'į' => 'i', 1745 'İ' => 'I', 1746 'ı' => 'i', 1747 'IJ' => 'IJ', 1748 'ij' => 'ij', 1749 'Ĵ' => 'J', 1750 'ĵ' => 'j', 1751 'Ķ' => 'K', 1752 'ķ' => 'k', 1753 'ĸ' => 'k', 1754 'Ĺ' => 'L', 1755 'ĺ' => 'l', 1756 'Ļ' => 'L', 1757 'ļ' => 'l', 1758 'Ľ' => 'L', 1759 'ľ' => 'l', 1760 'Ŀ' => 'L', 1761 'ŀ' => 'l', 1762 'Ł' => 'L', 1763 'ł' => 'l', 1764 'Ń' => 'N', 1765 'ń' => 'n', 1766 'Ņ' => 'N', 1767 'ņ' => 'n', 1768 'Ň' => 'N', 1769 'ň' => 'n', 1770 'ʼn' => 'n', 1771 'Ŋ' => 'N', 1772 'ŋ' => 'n', 1773 'Ō' => 'O', 1774 'ō' => 'o', 1775 'Ŏ' => 'O', 1776 'ŏ' => 'o', 1777 'Ő' => 'O', 1778 'ő' => 'o', 1779 'Œ' => 'OE', 1780 'œ' => 'oe', 1781 'Ŕ' => 'R', 1782 'ŕ' => 'r', 1783 'Ŗ' => 'R', 1784 'ŗ' => 'r', 1785 'Ř' => 'R', 1786 'ř' => 'r', 1787 'Ś' => 'S', 1788 'ś' => 's', 1789 'Ŝ' => 'S', 1790 'ŝ' => 's', 1791 'Ş' => 'S', 1792 'ş' => 's', 1793 'Š' => 'S', 1794 'š' => 's', 1795 'Ţ' => 'T', 1796 'ţ' => 't', 1797 'Ť' => 'T', 1798 'ť' => 't', 1799 'Ŧ' => 'T', 1800 'ŧ' => 't', 1801 'Ũ' => 'U', 1802 'ũ' => 'u', 1803 'Ū' => 'U', 1804 'ū' => 'u', 1805 'Ŭ' => 'U', 1806 'ŭ' => 'u', 1807 'Ů' => 'U', 1808 'ů' => 'u', 1809 'Ű' => 'U', 1810 'ű' => 'u', 1811 'Ų' => 'U', 1812 'ų' => 'u', 1813 'Ŵ' => 'W', 1814 'ŵ' => 'w', 1815 'Ŷ' => 'Y', 1816 'ŷ' => 'y', 1817 'Ÿ' => 'Y', 1818 'Ź' => 'Z', 1819 'ź' => 'z', 1820 'Ż' => 'Z', 1821 'ż' => 'z', 1822 'Ž' => 'Z', 1823 'ž' => 'z', 1824 'ſ' => 's', 1825 // Decompositions for Latin Extended-B. 1826 'Ə' => 'E', 1827 'ǝ' => 'e', 1828 'Ș' => 'S', 1829 'ș' => 's', 1830 'Ț' => 'T', 1831 'ț' => 't', 1832 // Euro sign. 1833 '€' => 'E', 1834 // GBP (Pound) sign. 1835 '£' => '', 1836 // Vowels with diacritic (Vietnamese). Unmarked. 1837 'Ơ' => 'O', 1838 'ơ' => 'o', 1839 'Ư' => 'U', 1840 'ư' => 'u', 1841 // Grave accent. 1842 'Ầ' => 'A', 1843 'ầ' => 'a', 1844 'Ằ' => 'A', 1845 'ằ' => 'a', 1846 'Ề' => 'E', 1847 'ề' => 'e', 1848 'Ồ' => 'O', 1849 'ồ' => 'o', 1850 'Ờ' => 'O', 1851 'ờ' => 'o', 1852 'Ừ' => 'U', 1853 'ừ' => 'u', 1854 'Ỳ' => 'Y', 1855 'ỳ' => 'y', 1856 // Hook. 1857 'Ả' => 'A', 1858 'ả' => 'a', 1859 'Ẩ' => 'A', 1860 'ẩ' => 'a', 1861 'Ẳ' => 'A', 1862 'ẳ' => 'a', 1863 'Ẻ' => 'E', 1864 'ẻ' => 'e', 1865 'Ể' => 'E', 1866 'ể' => 'e', 1867 'Ỉ' => 'I', 1868 'ỉ' => 'i', 1869 'Ỏ' => 'O', 1870 'ỏ' => 'o', 1871 'Ổ' => 'O', 1872 'ổ' => 'o', 1873 'Ở' => 'O', 1874 'ở' => 'o', 1875 'Ủ' => 'U', 1876 'ủ' => 'u', 1877 'Ử' => 'U', 1878 'ử' => 'u', 1879 'Ỷ' => 'Y', 1880 'ỷ' => 'y', 1881 // Tilde. 1882 'Ẫ' => 'A', 1883 'ẫ' => 'a', 1884 'Ẵ' => 'A', 1885 'ẵ' => 'a', 1886 'Ẽ' => 'E', 1887 'ẽ' => 'e', 1888 'Ễ' => 'E', 1889 'ễ' => 'e', 1890 'Ỗ' => 'O', 1891 'ỗ' => 'o', 1892 'Ỡ' => 'O', 1893 'ỡ' => 'o', 1894 'Ữ' => 'U', 1895 'ữ' => 'u', 1896 'Ỹ' => 'Y', 1897 'ỹ' => 'y', 1898 // Acute accent. 1899 'Ấ' => 'A', 1900 'ấ' => 'a', 1901 'Ắ' => 'A', 1902 'ắ' => 'a', 1903 'Ế' => 'E', 1904 'ế' => 'e', 1905 'Ố' => 'O', 1906 'ố' => 'o', 1907 'Ớ' => 'O', 1908 'ớ' => 'o', 1909 'Ứ' => 'U', 1910 'ứ' => 'u', 1911 // Dot below. 1912 'Ạ' => 'A', 1913 'ạ' => 'a', 1914 'Ậ' => 'A', 1915 'ậ' => 'a', 1916 'Ặ' => 'A', 1917 'ặ' => 'a', 1918 'Ẹ' => 'E', 1919 'ẹ' => 'e', 1920 'Ệ' => 'E', 1921 'ệ' => 'e', 1922 'Ị' => 'I', 1923 'ị' => 'i', 1924 'Ọ' => 'O', 1925 'ọ' => 'o', 1926 'Ộ' => 'O', 1927 'ộ' => 'o', 1928 'Ợ' => 'O', 1929 'ợ' => 'o', 1930 'Ụ' => 'U', 1931 'ụ' => 'u', 1932 'Ự' => 'U', 1933 'ự' => 'u', 1934 'Ỵ' => 'Y', 1935 'ỵ' => 'y', 1936 // Vowels with diacritic (Chinese, Hanyu Pinyin). 1937 'ɑ' => 'a', 1938 // Macron. 1939 'Ǖ' => 'U', 1940 'ǖ' => 'u', 1941 // Acute accent. 1942 'Ǘ' => 'U', 1943 'ǘ' => 'u', 1944 // Caron. 1945 'Ǎ' => 'A', 1946 'ǎ' => 'a', 1947 'Ǐ' => 'I', 1948 'ǐ' => 'i', 1949 'Ǒ' => 'O', 1950 'ǒ' => 'o', 1951 'Ǔ' => 'U', 1952 'ǔ' => 'u', 1953 'Ǚ' => 'U', 1954 'ǚ' => 'u', 1955 // Grave accent. 1956 'Ǜ' => 'U', 1957 'ǜ' => 'u', 1958 ); 1959 1960 // Used for locale-specific rules. 1961 if ( empty( $locale ) ) { 1962 $locale = get_locale(); 1963 } 1964 1965 /* 1966 * German has various locales (de_DE, de_CH, de_AT, ...) with formal and informal variants. 1967 * There is no 3-letter locale like 'def', so checking for 'de' instead of 'de_' is safe, 1968 * since 'de' itself would be a valid locale too. 1969 */ 1970 if ( str_starts_with( $locale, 'de' ) ) { 1971 $chars['Ä'] = 'Ae'; 1972 $chars['ä'] = 'ae'; 1973 $chars['Ö'] = 'Oe'; 1974 $chars['ö'] = 'oe'; 1975 $chars['Ü'] = 'Ue'; 1976 $chars['ü'] = 'ue'; 1977 $chars['ẞ'] = 'SS'; 1978 $chars['ß'] = 'ss'; 1979 } elseif ( 'da_DK' === $locale ) { 1980 $chars['Æ'] = 'Ae'; 1981 $chars['æ'] = 'ae'; 1982 $chars['Ø'] = 'Oe'; 1983 $chars['ø'] = 'oe'; 1984 $chars['Å'] = 'Aa'; 1985 $chars['å'] = 'aa'; 1986 } elseif ( 'ca' === $locale ) { 1987 $chars['l·l'] = 'll'; 1988 } elseif ( 'sr_RS' === $locale || 'bs_BA' === $locale ) { 1989 $chars['Đ'] = 'DJ'; 1990 $chars['đ'] = 'dj'; 1991 } 1992 1993 $text = strtr( $text, $chars ); 1994 } else { 1995 $chars = array(); 1996 // Assume ISO-8859-1 if not UTF-8. 1997 $chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e" 1998 . "\x9f\xa2\xa5\xb5\xc0\xc1\xc2" 1999 . "\xc3\xc4\xc5\xc7\xc8\xc9\xca" 2000 . "\xcb\xcc\xcd\xce\xcf\xd1\xd2" 2001 . "\xd3\xd4\xd5\xd6\xd8\xd9\xda" 2002 . "\xdb\xdc\xdd\xe0\xe1\xe2\xe3" 2003 . "\xe4\xe5\xe7\xe8\xe9\xea\xeb" 2004 . "\xec\xed\xee\xef\xf1\xf2\xf3" 2005 . "\xf4\xf5\xf6\xf8\xf9\xfa\xfb" 2006 . "\xfc\xfd\xff"; 2007 2008 $chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy'; 2009 2010 $text = strtr( $text, $chars['in'], $chars['out'] ); 2011 $double_chars = array(); 2012 $double_chars['in'] = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" ); 2013 $double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' ); 2014 $text = str_replace( $double_chars['in'], $double_chars['out'], $text ); 2015 } 2016 2017 return $text; 2018 } 2019 2020 /** 2021 * Sanitizes a filename, replacing whitespace with dashes. 2022 * 2023 * Removes special characters that are illegal in filenames on certain 2024 * operating systems and special characters requiring special escaping 2025 * to manipulate at the command line. Replaces spaces and consecutive 2026 * dashes with a single dash. Trims period, dash and underscore from beginning 2027 * and end of filename. It is not guaranteed that this function will return a 2028 * filename that is allowed to be uploaded. 2029 * 2030 * @since 2.1.0 2031 * 2032 * @param string $filename The filename to be sanitized. 2033 * @return string The sanitized filename. 2034 */ 2035 function sanitize_file_name( $filename ) { 2036 $filename_raw = $filename; 2037 $filename = remove_accents( $filename ); 2038 2039 $special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '|', '~', '`', '!', '{', '}', '%', '+', '’', '«', '»', '”', '“', chr( 0 ) ); 2040 2041 if ( ! wp_is_valid_utf8( $filename ) ) { 2042 $_ext = pathinfo( $filename, PATHINFO_EXTENSION ); 2043 $_name = pathinfo( $filename, PATHINFO_FILENAME ); 2044 $filename = sanitize_title_with_dashes( $_name ) . '.' . $_ext; 2045 } 2046 2047 if ( _wp_can_use_pcre_u() ) { 2048 /** 2049 * Replace all whitespace characters with a basic space (U+0020). 2050 * 2051 * The “Zs” in the pattern selects characters in the `Space_Separator` 2052 * category, which is what Unicode considers space characters. 2053 * 2054 * @see https://www.unicode.org/reports/tr44/#General_Category_Values 2055 * @see https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-6/#G17548 2056 * @see https://www.php.net/manual/en/regexp.reference.unicode.php 2057 */ 2058 $filename = preg_replace( '#\p{Zs}#siu', ' ', $filename ); 2059 } 2060 2061 /** 2062 * Filters the list of characters to remove from a filename. 2063 * 2064 * @since 2.8.0 2065 * 2066 * @param string[] $special_chars Array of characters to remove. 2067 * @param string $filename_raw The original filename to be sanitized. 2068 */ 2069 $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw ); 2070 2071 $filename = str_replace( $special_chars, '', $filename ); 2072 $filename = str_replace( array( '%20', '+' ), '-', $filename ); 2073 $filename = preg_replace( '/\.{2,}/', '.', $filename ); 2074 $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename ); 2075 $filename = trim( $filename, '.-_' ); 2076 2077 if ( ! str_contains( $filename, '.' ) ) { 2078 $mime_types = wp_get_mime_types(); 2079 $filetype = wp_check_filetype( 'test.' . $filename, $mime_types ); 2080 if ( $filetype['ext'] === $filename ) { 2081 $filename = 'unnamed-file.' . $filetype['ext']; 2082 } 2083 } 2084 2085 // Split the filename into a base and extension[s]. 2086 $parts = explode( '.', $filename ); 2087 2088 // Return if only one extension. 2089 if ( count( $parts ) <= 2 ) { 2090 /** This filter is documented in wp-includes/formatting.php */ 2091 return apply_filters( 'sanitize_file_name', $filename, $filename_raw ); 2092 } 2093 2094 // Process multiple extensions. 2095 $filename = array_shift( $parts ); 2096 $extension = array_pop( $parts ); 2097 $mimes = get_allowed_mime_types(); 2098 2099 /* 2100 * Loop over any intermediate extensions. Postfix them with a trailing underscore 2101 * if they are a 2 - 5 character long alpha string not in the allowed extension list. 2102 */ 2103 foreach ( (array) $parts as $part ) { 2104 $filename .= '.' . $part; 2105 2106 if ( preg_match( '/^[a-zA-Z]{2,5}\d?$/', $part ) ) { 2107 $allowed = false; 2108 foreach ( $mimes as $ext_preg => $mime_match ) { 2109 $ext_preg = '!^(' . $ext_preg . ')$!i'; 2110 if ( preg_match( $ext_preg, $part ) ) { 2111 $allowed = true; 2112 break; 2113 } 2114 } 2115 if ( ! $allowed ) { 2116 $filename .= '_'; 2117 } 2118 } 2119 } 2120 2121 $filename .= '.' . $extension; 2122 2123 /** 2124 * Filters a sanitized filename string. 2125 * 2126 * @since 2.8.0 2127 * 2128 * @param string $filename Sanitized filename. 2129 * @param string $filename_raw The filename prior to sanitization. 2130 */ 2131 return apply_filters( 'sanitize_file_name', $filename, $filename_raw ); 2132 } 2133 2134 /** 2135 * Sanitizes a username, stripping out unsafe characters. 2136 * 2137 * Removes tags, percent-encoded characters, HTML entities, and if strict is enabled, 2138 * will only keep alphanumeric, _, space, ., -, @. After sanitizing, it passes the username, 2139 * raw username (the username in the parameter), and the value of $strict as parameters 2140 * for the {@see 'sanitize_user'} filter. 2141 * 2142 * @since 2.0.0 2143 * 2144 * @param string $username The username to be sanitized. 2145 * @param bool $strict Optional. If set to true, limits $username to specific characters. 2146 * Default false. 2147 * @return string The sanitized username, after passing through filters. 2148 */ 2149 function sanitize_user( $username, $strict = false ) { 2150 $raw_username = $username; 2151 $username = wp_strip_all_tags( $username ); 2152 $username = remove_accents( $username ); 2153 // Remove percent-encoded characters. 2154 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username ); 2155 // Remove HTML entities. 2156 $username = preg_replace( '/&.+?;/', '', $username ); 2157 2158 // If strict, reduce to ASCII for max portability. 2159 if ( $strict ) { 2160 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username ); 2161 } 2162 2163 $username = trim( $username ); 2164 // Consolidate contiguous whitespace. 2165 $username = preg_replace( '|\s+|', ' ', $username ); 2166 2167 /** 2168 * Filters a sanitized username string. 2169 * 2170 * @since 2.0.1 2171 * 2172 * @param string $username Sanitized username. 2173 * @param string $raw_username The username prior to sanitization. 2174 * @param bool $strict Whether to limit the sanitization to specific characters. 2175 */ 2176 return apply_filters( 'sanitize_user', $username, $raw_username, $strict ); 2177 } 2178 2179 2180 /** 2181 * Sanitizes a string key. 2182 * 2183 * Keys are used as internal identifiers. Lowercase alphanumeric characters, 2184 * dashes, and underscores are allowed. 2185 * 2186 * @since 3.0.0 2187 * 2188 * @param string $key String key. 2189 * @return string Sanitized key. 2190 */ 2191 function sanitize_key( $key ) { 2192 $sanitized_key = ''; 2193 2194 if ( is_scalar( $key ) ) { 2195 $sanitized_key = strtolower( $key ); 2196 $sanitized_key = preg_replace( '/[^a-z0-9_\-]/', '', $sanitized_key ); 2197 } 2198 2199 /** 2200 * Filters a sanitized key string. 2201 * 2202 * @since 3.0.0 2203 * 2204 * @param string $sanitized_key Sanitized key. 2205 * @param string $key The key prior to sanitization. 2206 */ 2207 return apply_filters( 'sanitize_key', $sanitized_key, $key ); 2208 } 2209 2210 /** 2211 * Sanitizes a string into a slug, which can be used in URLs or HTML attributes. 2212 * 2213 * By default, converts accent characters to ASCII characters and further 2214 * limits the output to alphanumeric characters, underscore (_) and dash (-) 2215 * through the {@see 'sanitize_title'} filter. 2216 * 2217 * If `$title` is empty and `$fallback_title` is set, the latter will be used. 2218 * 2219 * @since 1.0.0 2220 * 2221 * @param string $title The string to be sanitized. 2222 * @param string $fallback_title Optional. A title to use if $title is empty. Default empty. 2223 * @param string $context Optional. The operation for which the string is sanitized. 2224 * When set to 'save', the string runs through remove_accents(). 2225 * Default 'save'. 2226 * @return string The sanitized string. 2227 */ 2228 function sanitize_title( $title, $fallback_title = '', $context = 'save' ) { 2229 $raw_title = $title; 2230 2231 if ( 'save' === $context ) { 2232 $title = remove_accents( $title ); 2233 } 2234 2235 /** 2236 * Filters a sanitized title string. 2237 * 2238 * @since 1.2.0 2239 * 2240 * @param string $title Sanitized title. 2241 * @param string $raw_title The title prior to sanitization. 2242 * @param string $context The context for which the title is being sanitized. 2243 */ 2244 $title = apply_filters( 'sanitize_title', $title, $raw_title, $context ); 2245 2246 if ( '' === $title || false === $title ) { 2247 $title = $fallback_title; 2248 } 2249 2250 return $title; 2251 } 2252 2253 /** 2254 * Sanitizes a title with the 'query' context. 2255 * 2256 * Used for querying the database for a value from URL. 2257 * 2258 * @since 3.1.0 2259 * 2260 * @param string $title The string to be sanitized. 2261 * @return string The sanitized string. 2262 */ 2263 function sanitize_title_for_query( $title ) { 2264 return sanitize_title( $title, '', 'query' ); 2265 } 2266 2267 /** 2268 * Sanitizes a title, replacing whitespace and a few other characters with dashes. 2269 * 2270 * Limits the output to alphanumeric characters, underscore (_) and dash (-). 2271 * Whitespace becomes a dash. 2272 * 2273 * @since 1.2.0 2274 * 2275 * @param string $title The title to be sanitized. 2276 * @param string $raw_title Optional. Not used. Default empty. 2277 * @param string $context Optional. The operation for which the string is sanitized. 2278 * When set to 'save', additional entities are converted to hyphens 2279 * or stripped entirely. Default 'display'. 2280 * @return string The sanitized title. 2281 */ 2282 function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) { 2283 $title = strip_tags( $title ); 2284 // Preserve escaped octets. 2285 $title = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title ); 2286 // Remove percent signs that are not part of an octet. 2287 $title = str_replace( '%', '', $title ); 2288 // Restore octets. 2289 $title = preg_replace( '|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title ); 2290 2291 if ( wp_is_valid_utf8( $title ) ) { 2292 if ( function_exists( 'mb_strtolower' ) ) { 2293 $title = mb_strtolower( $title, 'UTF-8' ); 2294 } 2295 $title = utf8_uri_encode( $title, 200 ); 2296 } 2297 2298 $title = strtolower( $title ); 2299 2300 if ( 'save' === $context ) { 2301 // Convert  , non-breaking hyphen, &ndash, and &mdash to hyphens. 2302 $title = str_replace( array( '%c2%a0', '%e2%80%91', '%e2%80%93', '%e2%80%94' ), '-', $title ); 2303 // Convert  , non-breaking hyphen, &ndash, and &mdash HTML entities to hyphens. 2304 $title = str_replace( array( ' ', '‑', ' ', '–', '–', '—', '—' ), '-', $title ); 2305 // Convert forward slash to hyphen. 2306 $title = str_replace( '/', '-', $title ); 2307 2308 // Strip these characters entirely. 2309 $title = str_replace( 2310 array( 2311 // Soft hyphens. 2312 '%c2%ad', 2313 // ¡ and ¿. 2314 '%c2%a1', 2315 '%c2%bf', 2316 // Angle quotes. 2317 '%c2%ab', 2318 '%c2%bb', 2319 '%e2%80%b9', 2320 '%e2%80%ba', 2321 // Curly quotes. 2322 '%e2%80%98', 2323 '%e2%80%99', 2324 '%e2%80%9c', 2325 '%e2%80%9d', 2326 '%e2%80%9a', 2327 '%e2%80%9b', 2328 '%e2%80%9e', 2329 '%e2%80%9f', 2330 // Bullet. 2331 '%e2%80%a2', 2332 // ©, ®, °, &hellip, and &trade. 2333 '%c2%a9', 2334 '%c2%ae', 2335 '%c2%b0', 2336 '%e2%80%a6', 2337 '%e2%84%a2', 2338 // Acute accents. 2339 '%c2%b4', 2340 '%cb%8a', 2341 '%cc%81', 2342 '%cd%81', 2343 // Grave accent, macron, caron. 2344 '%cc%80', 2345 '%cc%84', 2346 '%cc%8c', 2347 // Non-visible characters that display without a width. 2348 '%e2%80%8b', // Zero width space. 2349 '%e2%80%8c', // Zero width non-joiner. 2350 '%e2%80%8d', // Zero width joiner. 2351 '%e2%80%8e', // Left-to-right mark. 2352 '%e2%80%8f', // Right-to-left mark. 2353 '%e2%80%aa', // Left-to-right embedding. 2354 '%e2%80%ab', // Right-to-left embedding. 2355 '%e2%80%ac', // Pop directional formatting. 2356 '%e2%80%ad', // Left-to-right override. 2357 '%e2%80%ae', // Right-to-left override. 2358 '%ef%bb%bf', // Byte order mark. 2359 '%ef%bf%bc', // Object replacement character. 2360 ), 2361 '', 2362 $title 2363 ); 2364 2365 // Convert non-visible characters that display with a width to hyphen. 2366 $title = str_replace( 2367 array( 2368 '%e2%80%80', // En quad. 2369 '%e2%80%81', // Em quad. 2370 '%e2%80%82', // En space. 2371 '%e2%80%83', // Em space. 2372 '%e2%80%84', // Three-per-em space. 2373 '%e2%80%85', // Four-per-em space. 2374 '%e2%80%86', // Six-per-em space. 2375 '%e2%80%87', // Figure space. 2376 '%e2%80%88', // Punctuation space. 2377 '%e2%80%89', // Thin space. 2378 '%e2%80%8a', // Hair space. 2379 '%e2%80%a8', // Line separator. 2380 '%e2%80%a9', // Paragraph separator. 2381 '%e2%80%af', // Narrow no-break space. 2382 ), 2383 '-', 2384 $title 2385 ); 2386 2387 // Convert × to 'x'. 2388 $title = str_replace( '%c3%97', 'x', $title ); 2389 } 2390 2391 // Remove HTML entities. 2392 $title = preg_replace( '/&.+?;/', '', $title ); 2393 $title = str_replace( '.', '-', $title ); 2394 2395 $title = preg_replace( '/[^%a-z0-9 _-]/', '', $title ); 2396 $title = preg_replace( '/\s+/', '-', $title ); 2397 $title = preg_replace( '|-+|', '-', $title ); 2398 $title = trim( $title, '-' ); 2399 2400 return $title; 2401 } 2402 2403 /** 2404 * Ensures a string is a valid SQL 'order by' clause. 2405 * 2406 * Accepts one or more columns, with or without a sort order (ASC / DESC). 2407 * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc. 2408 * 2409 * Also accepts 'RAND()'. 2410 * 2411 * @since 2.5.1 2412 * 2413 * @param string $orderby Order by clause to be validated. 2414 * @return string|false Returns $orderby if valid, false otherwise. 2415 */ 2416 function sanitize_sql_orderby( $orderby ) { 2417 if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) { 2418 return $orderby; 2419 } 2420 return false; 2421 } 2422 2423 /** 2424 * Sanitizes an HTML classname to ensure it only contains valid characters. 2425 * 2426 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty 2427 * string then it will return the alternative value supplied. 2428 * 2429 * @todo Expand to support the full range of CDATA that a class attribute can contain. 2430 * 2431 * @since 2.8.0 2432 * 2433 * @param string $classname The classname to be sanitized. 2434 * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string. 2435 * Default empty string. 2436 * @return string The sanitized value. 2437 */ 2438 function sanitize_html_class( $classname, $fallback = '' ) { 2439 // Strip out any percent-encoded characters. 2440 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $classname ); 2441 2442 // Limit to A-Z, a-z, 0-9, '_', '-'. 2443 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized ); 2444 2445 if ( '' === $sanitized && $fallback ) { 2446 return sanitize_html_class( $fallback ); 2447 } 2448 /** 2449 * Filters a sanitized HTML class string. 2450 * 2451 * @since 2.8.0 2452 * 2453 * @param string $sanitized The sanitized HTML class. 2454 * @param string $classname HTML class before sanitization. 2455 * @param string $fallback The fallback string. 2456 */ 2457 return apply_filters( 'sanitize_html_class', $sanitized, $classname, $fallback ); 2458 } 2459 2460 /** 2461 * Strips out all characters not allowed in a locale name. 2462 * 2463 * @since 6.2.1 2464 * 2465 * @param string $locale_name The locale name to be sanitized. 2466 * @return string The sanitized value. 2467 */ 2468 function sanitize_locale_name( $locale_name ) { 2469 // Limit to A-Z, a-z, 0-9, '_', '-'. 2470 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $locale_name ); 2471 2472 /** 2473 * Filters a sanitized locale name string. 2474 * 2475 * @since 6.2.1 2476 * 2477 * @param string $sanitized The sanitized locale name. 2478 * @param string $locale_name The locale name before sanitization. 2479 */ 2480 return apply_filters( 'sanitize_locale_name', $sanitized, $locale_name ); 2481 } 2482 2483 /** 2484 * Converts lone & characters into `&` (a.k.a. `&`) 2485 * 2486 * @since 0.71 2487 * 2488 * @param string $content String of characters to be converted. 2489 * @param string $deprecated Not used. 2490 * @return string Converted string. 2491 */ 2492 function convert_chars( $content, $deprecated = '' ) { 2493 if ( ! empty( $deprecated ) ) { 2494 _deprecated_argument( __FUNCTION__, '0.71' ); 2495 } 2496 2497 if ( str_contains( $content, '&' ) ) { 2498 $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content ); 2499 } 2500 2501 return $content; 2502 } 2503 2504 /** 2505 * Converts invalid Unicode references range to valid range. 2506 * 2507 * @since 4.3.0 2508 * 2509 * @param string $content String with entities that need converting. 2510 * @return string Converted string. 2511 */ 2512 function convert_invalid_entities( $content ) { 2513 $wp_htmltranswinuni = array( 2514 '€' => '€', // The Euro sign. 2515 '' => '', 2516 '‚' => '‚', // These are Windows CP1252 specific characters. 2517 'ƒ' => 'ƒ', // They would look weird on non-Windows browsers. 2518 '„' => '„', 2519 '…' => '…', 2520 '†' => '†', 2521 '‡' => '‡', 2522 'ˆ' => 'ˆ', 2523 '‰' => '‰', 2524 'Š' => 'Š', 2525 '‹' => '‹', 2526 'Œ' => 'Œ', 2527 '' => '', 2528 'Ž' => 'Ž', 2529 '' => '', 2530 '' => '', 2531 '‘' => '‘', 2532 '’' => '’', 2533 '“' => '“', 2534 '”' => '”', 2535 '•' => '•', 2536 '–' => '–', 2537 '—' => '—', 2538 '˜' => '˜', 2539 '™' => '™', 2540 'š' => 'š', 2541 '›' => '›', 2542 'œ' => 'œ', 2543 '' => '', 2544 'ž' => 'ž', 2545 'Ÿ' => 'Ÿ', 2546 ); 2547 2548 if ( str_contains( $content, '' ) ) { 2549 $content = strtr( $content, $wp_htmltranswinuni ); 2550 } 2551 2552 return $content; 2553 } 2554 2555 /** 2556 * Balances tags if forced to, or if the 'use_balanceTags' option is set to true. 2557 * 2558 * @since 0.71 2559 * 2560 * @param string $text Text to be balanced. 2561 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false. 2562 * @return string Balanced text. 2563 */ 2564 function balanceTags( $text, $force = false ) { // phpcs:ignore WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid 2565 if ( $force || 1 === (int) get_option( 'use_balanceTags' ) ) { 2566 return force_balance_tags( $text ); 2567 } else { 2568 return $text; 2569 } 2570 } 2571 2572 /** 2573 * Balances tags of string using a modified stack. 2574 * 2575 * {@internal Modified by Scott Reilly (coffee2code) 02 Aug 2004 2576 * 1.1 Fixed handling of append/stack pop order of end text 2577 * Added Cleaning Hooks 2578 * 1.0 First Version} 2579 * 2580 * @since 2.0.4 2581 * @since 5.3.0 Improve accuracy and add support for custom element tags. 2582 * 2583 * @author Leonard Lin <leonard@acm.org> 2584 * @license GPL 2585 * @copyright November 4, 2001 2586 * @version 1.1 2587 * @todo Make better - change loop condition to $text in 1.2 2588 * 2589 * @param string $text Text to be balanced. 2590 * @return string Balanced text. 2591 */ 2592 function force_balance_tags( $text ) { 2593 $tagstack = array(); 2594 $stacksize = 0; 2595 $tagqueue = ''; 2596 $newtext = ''; 2597 // Known single-entity/self-closing tags. 2598 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source', 'track', 'wbr' ); 2599 // Tags that can be immediately nested within themselves. 2600 $nestable_tags = array( 'article', 'aside', 'blockquote', 'details', 'div', 'figure', 'object', 'q', 'section', 'span' ); 2601 2602 // WP bug fix for comments - in case you REALLY meant to type '< !--'. 2603 $text = str_replace( '< !--', '< !--', $text ); 2604 // WP bug fix for LOVE <3 (and other situations with '<' before a number). 2605 $text = preg_replace( '#<([0-9]{1})#', '<$1', $text ); 2606 2607 /** 2608 * Matches supported tags. 2609 * 2610 * To get the pattern as a string without the comments paste into a PHP 2611 * REPL like `php -a`. 2612 * 2613 * @see https://html.spec.whatwg.org/#elements-2 2614 * @see https://html.spec.whatwg.org/multipage/custom-elements.html#valid-custom-element-name 2615 * 2616 * @example 2617 * ~# php -a 2618 * php > $s = [paste copied contents of expression below including parentheses]; 2619 * php > echo $s; 2620 */ 2621 $tag_pattern = ( 2622 '#<' . // Start with an opening bracket. 2623 '(/?)' . // Group 1 - If it's a closing tag it'll have a leading slash. 2624 '(' . // Group 2 - Tag name. 2625 // Custom element tags have more lenient rules than HTML tag names. 2626 '(?:[a-z](?:[a-z0-9._]*)-(?:[a-z0-9._-]+)+)' . 2627 '|' . 2628 // Traditional tag rules approximate HTML tag names. 2629 '(?:[\w:]+)' . 2630 ')' . 2631 '(?:' . 2632 // We either immediately close the tag with its '>' and have nothing here. 2633 '\s*' . 2634 '(/?)' . // Group 3 - "attributes" for empty tag. 2635 '|' . 2636 // Or we must start with space characters to separate the tag name from the attributes (or whitespace). 2637 '(\s+)' . // Group 4 - Pre-attribute whitespace. 2638 '([^>]*)' . // Group 5 - Attributes. 2639 ')' . 2640 '>#' // End with a closing bracket. 2641 ); 2642 2643 while ( preg_match( $tag_pattern, $text, $regex ) ) { 2644 $full_match = $regex[0]; 2645 $has_leading_slash = ! empty( $regex[1] ); 2646 $tag_name = $regex[2]; 2647 $tag = strtolower( $tag_name ); 2648 $is_single_tag = in_array( $tag, $single_tags, true ); 2649 $pre_attribute_ws = $regex[4] ?? ''; 2650 $attributes = trim( $regex[5] ?? $regex[3] ); 2651 $has_self_closer = str_ends_with( $attributes, '/' ); 2652 2653 $newtext .= $tagqueue; 2654 2655 $i = strpos( $text, $full_match ); 2656 $l = strlen( $full_match ); 2657 2658 // Clear the shifter. 2659 $tagqueue = ''; 2660 if ( $has_leading_slash ) { // End tag. 2661 // If too many closing tags. 2662 if ( $stacksize <= 0 ) { 2663 $tag = ''; 2664 // Or close to be safe $tag = '/' . $tag. 2665 2666 // If stacktop value = tag close value, then pop. 2667 } elseif ( $tagstack[ $stacksize - 1 ] === $tag ) { // Found closing tag. 2668 $tag = '</' . $tag . '>'; // Close tag. 2669 array_pop( $tagstack ); 2670 --$stacksize; 2671 } else { // Closing tag not at top, search for it. 2672 for ( $j = $stacksize - 1; $j >= 0; $j-- ) { 2673 if ( $tagstack[ $j ] === $tag ) { 2674 // Add tag to tagqueue. 2675 for ( $k = $stacksize - 1; $k >= $j; $k-- ) { 2676 $tagqueue .= '</' . array_pop( $tagstack ) . '>'; 2677 --$stacksize; 2678 } 2679 break; 2680 } 2681 } 2682 $tag = ''; 2683 } 2684 } else { // Begin tag. 2685 if ( $has_self_closer ) { 2686 /* 2687 * If it presents itself as a self-closing tag, but it isn't a known single-entity self-closing tag, 2688 * then don't let it be treated as such and immediately close it with a closing tag. 2689 * The tag will encapsulate no text as a result. 2690 */ 2691 if ( ! $is_single_tag ) { 2692 $attributes = trim( substr( $attributes, 0, -1 ) ) . "></$tag"; 2693 } 2694 } elseif ( $is_single_tag ) { 2695 // Else if it's a known single-entity tag but it doesn't close itself, do so. 2696 $pre_attribute_ws = ' '; 2697 $attributes .= '/'; 2698 } else { 2699 /* 2700 * It's not a single-entity tag. 2701 * If the top of the stack is the same as the tag we want to push, close previous tag. 2702 */ 2703 if ( $stacksize > 0 && ! in_array( $tag, $nestable_tags, true ) && $tagstack[ $stacksize - 1 ] === $tag ) { 2704 $tagqueue = '</' . array_pop( $tagstack ) . '>'; 2705 --$stacksize; 2706 } 2707 $stacksize = array_push( $tagstack, $tag ); 2708 } 2709 2710 // Attributes. 2711 if ( $has_self_closer && $is_single_tag ) { 2712 // We need some space - avoid <br/> and prefer <br />. 2713 $pre_attribute_ws = ' '; 2714 } 2715 2716 $tag = '<' . $tag . $pre_attribute_ws . $attributes . '>'; 2717 // If already queuing a close tag, then put this tag on too. 2718 if ( ! empty( $tagqueue ) ) { 2719 $tagqueue .= $tag; 2720 $tag = ''; 2721 } 2722 } 2723 $newtext .= substr( $text, 0, $i ) . $tag; 2724 $text = substr( $text, $i + $l ); 2725 } 2726 2727 // Clear tag queue. 2728 $newtext .= $tagqueue; 2729 2730 // Add remaining text. 2731 $newtext .= $text; 2732 2733 while ( $x = array_pop( $tagstack ) ) { 2734 $newtext .= '</' . $x . '>'; // Add remaining tags to close. 2735 } 2736 2737 // WP fix for the bug with HTML comments. 2738 $newtext = str_replace( '< !--', '<!--', $newtext ); 2739 $newtext = str_replace( '< !--', '< !--', $newtext ); 2740 2741 return $newtext; 2742 } 2743 2744 /** 2745 * Acts on text which is about to be edited. 2746 * 2747 * The $content is run through esc_textarea(), which uses htmlspecialchars() 2748 * to convert special characters to HTML entities. If `$richedit` is set to true, 2749 * it is simply a holder for the {@see 'format_to_edit'} filter. 2750 * 2751 * @since 0.71 2752 * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity. 2753 * 2754 * @param string $content The text about to be edited. 2755 * @param bool $rich_text Optional. Whether `$content` should be considered rich text, 2756 * in which case it would not be passed through esc_textarea(). 2757 * Default false. 2758 * @return string The text after the filter (and possibly htmlspecialchars()) has been run. 2759 */ 2760 function format_to_edit( $content, $rich_text = false ) { 2761 /** 2762 * Filters the text to be formatted for editing. 2763 * 2764 * @since 1.2.0 2765 * 2766 * @param string $content The text, prior to formatting for editing. 2767 */ 2768 $content = apply_filters( 'format_to_edit', $content ); 2769 if ( ! $rich_text ) { 2770 $content = esc_textarea( $content ); 2771 } 2772 return $content; 2773 } 2774 2775 /** 2776 * Add leading zeros when necessary. 2777 * 2778 * If you set the threshold to '4' and the number is '10', then you will get 2779 * back '0010'. If you set the threshold to '4' and the number is '5000', then you 2780 * will get back '5000'. 2781 * 2782 * Uses sprintf to append the amount of zeros based on the $threshold parameter 2783 * and the size of the number. If the number is large enough, then no zeros will 2784 * be appended. 2785 * 2786 * @since 0.71 2787 * 2788 * @param int $number Number to append zeros to if not greater than threshold. 2789 * @param int $threshold Digit places number needs to be to not have zeros added. 2790 * @return string Adds leading zeros to number if needed. 2791 */ 2792 function zeroise( $number, $threshold ) { 2793 return sprintf( '%0' . $threshold . 's', $number ); 2794 } 2795 2796 /** 2797 * Adds backslashes before letters and before a number at the start of a string. 2798 * 2799 * @since 0.71 2800 * 2801 * @param string $value Value to which backslashes will be added. 2802 * @return string String with backslashes inserted. 2803 */ 2804 function backslashit( $value ) { 2805 if ( isset( $value[0] ) && $value[0] >= '0' && $value[0] <= '9' ) { 2806 $value = '\\\\' . $value; 2807 } 2808 return addcslashes( $value, 'A..Za..z' ); 2809 } 2810 2811 /** 2812 * Appends a trailing slash. 2813 * 2814 * Will remove trailing forward and backslashes if it exists already before adding 2815 * a trailing forward slash. This prevents double slashing a string or path. 2816 * 2817 * The primary use of this is for paths and thus should be used for paths. It is 2818 * not restricted to paths and offers no specific path support. 2819 * 2820 * @since 1.2.0 2821 * 2822 * @param string $value Value to which trailing slash will be added. 2823 * @return string String with trailing slash added. 2824 */ 2825 function trailingslashit( $value ) { 2826 return untrailingslashit( $value ) . '/'; 2827 } 2828 2829 /** 2830 * Removes trailing forward slashes and backslashes if they exist. 2831 * 2832 * The primary use of this is for paths and thus should be used for paths. It is 2833 * not restricted to paths and offers no specific path support. 2834 * 2835 * @since 2.2.0 2836 * 2837 * @param string $value Value from which trailing slashes will be removed. 2838 * @return string String without the trailing slashes. 2839 */ 2840 function untrailingslashit( $value ) { 2841 return rtrim( $value, '/\\' ); 2842 } 2843 2844 /** 2845 * Navigates through an array, object, or scalar, and removes slashes from the values. 2846 * 2847 * @since 2.0.0 2848 * 2849 * @param mixed $value The value to be stripped. 2850 * @return mixed Stripped value. 2851 */ 2852 function stripslashes_deep( $value ) { 2853 return map_deep( $value, 'stripslashes_from_strings_only' ); 2854 } 2855 2856 /** 2857 * Callback function for `stripslashes_deep()` which strips slashes from strings. 2858 * 2859 * @since 4.4.0 2860 * 2861 * @param mixed $value The array or string to be stripped. 2862 * @return mixed The stripped value. 2863 */ 2864 function stripslashes_from_strings_only( $value ) { 2865 return is_string( $value ) ? stripslashes( $value ) : $value; 2866 } 2867 2868 /** 2869 * Navigates through an array, object, or scalar, and encodes the values to be used in a URL. 2870 * 2871 * @since 2.2.0 2872 * 2873 * @param mixed $value The array or string to be encoded. 2874 * @return mixed The encoded value. 2875 */ 2876 function urlencode_deep( $value ) { 2877 return map_deep( $value, 'urlencode' ); 2878 } 2879 2880 /** 2881 * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL. 2882 * 2883 * @since 3.4.0 2884 * 2885 * @param mixed $value The array or string to be encoded. 2886 * @return mixed The encoded value. 2887 */ 2888 function rawurlencode_deep( $value ) { 2889 return map_deep( $value, 'rawurlencode' ); 2890 } 2891 2892 /** 2893 * Navigates through an array, object, or scalar, and decodes URL-encoded values 2894 * 2895 * @since 4.4.0 2896 * 2897 * @param mixed $value The array or string to be decoded. 2898 * @return mixed The decoded value. 2899 */ 2900 function urldecode_deep( $value ) { 2901 return map_deep( $value, 'urldecode' ); 2902 } 2903 2904 /** 2905 * Obscures email addresses in HTML to prevent spam bots from harvesting them. 2906 * 2907 * Typically this will randomly replace characters from the email address with 2908 * HTML character references; however, when the hex encoding parameter is set, 2909 * some characters will also be represented in their percent-encoded form. 2910 * 2911 * Because this function is randomized, the outputs for any given input may 2912 * differ between calls. This helps diversify the ways the email addresses 2913 * are obscured. 2914 * 2915 * When non-UTF-8 inputs are provided, any spans of invalid UTF-8 bytes will 2916 * be passed through without any obfuscation. 2917 * 2918 * Example: 2919 * 2920 * $email = 'noreply@example.com'; 2921 * $obscured = antispambot( $email ); 2922 * $obscured === 'noreply@example.com'; 2923 * 2924 * // Hex-encoding also obscures characters with percent-encoding. 2925 * $obscured = antispambot( $email, 1 ); 2926 * $obscured === '%6eore%70l%79@%65x%61mple%2e%63%6fm'; 2927 * 2928 * // Non-UTF-8 characters are not obfuscated. "\xFC" is Latin1 "ü". 2929 * $obscured = antispambot( "b\xFCcher@library.de" ); 2930 * $obscured === 'b�cher@library.de'; 2931 * $obscured === "b\xFCcher@library.de" 2932 * 2933 * @since 0.71 2934 * @since 7.1.0 Masquerades multibyte characters. 2935 * 2936 * @param string $email_address Email address. 2937 * @param int $hex_encoding Optional. Set to 1 to enable hex encoding. 2938 * @return string Converted email address. 2939 */ 2940 function antispambot( $email_address, $hex_encoding = 0 ) { 2941 $obfuscated = ''; 2942 $at = 0; 2943 $end = strlen( $email_address ); 2944 $invalid_length = 0; 2945 2946 while ( $at < $end ) { 2947 $was_at = $at; 2948 if ( 2949 0 === _wp_scan_utf8( $email_address, $at, $invalid_length, null, 1 ) && 2950 0 === $invalid_length 2951 ) { 2952 break; 2953 } 2954 2955 $character_length = $at - $was_at; 2956 2957 if ( $character_length > 0 ) { 2958 $character = substr( $email_address, $was_at, $character_length ); 2959 2960 switch ( rand( 0, 1 + $hex_encoding ) ) { 2961 case 0: 2962 $code_point = mb_ord( $character ); 2963 $obfuscated .= "&#{$code_point};"; 2964 break; 2965 2966 case 1: 2967 $obfuscated .= $character; 2968 break; 2969 2970 case 2: 2971 for ( $i = 0; $i < $character_length; $i++ ) { 2972 $hex_value = bin2hex( $character[ $i ] ); 2973 $obfuscated .= "%{$hex_value}"; 2974 } 2975 break; 2976 } 2977 } 2978 2979 if ( 0 !== $invalid_length ) { 2980 $obfuscated .= substr( $email_address, $at, $invalid_length ); 2981 } 2982 2983 $at += $invalid_length; 2984 } 2985 2986 return str_replace( '@', '@', $obfuscated ); 2987 } 2988 2989 /** 2990 * Callback to convert URI match to HTML A element. 2991 * 2992 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). 2993 * 2994 * @since 2.3.2 2995 * @access private 2996 * 2997 * @param array $matches Single Regex Match. 2998 * @return string HTML A element with URI address. 2999 */ 3000 function _make_url_clickable_cb( $matches ) { 3001 $url = $matches[2]; 3002 3003 if ( ')' === $matches[3] && strpos( $url, '(' ) ) { 3004 /* 3005 * If the trailing character is a closing parenthesis, and the URL has an opening parenthesis in it, 3006 * add the closing parenthesis to the URL. Then we can let the parenthesis balancer do its thing below. 3007 */ 3008 $url .= $matches[3]; 3009 $suffix = ''; 3010 } else { 3011 $suffix = $matches[3]; 3012 } 3013 3014 if ( isset( $matches[4] ) && ! empty( $matches[4] ) ) { 3015 $url .= $matches[4]; 3016 } 3017 3018 // Include parentheses in the URL only if paired. 3019 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) { 3020 $suffix = strrchr( $url, ')' ) . $suffix; 3021 $url = substr( $url, 0, strrpos( $url, ')' ) ); 3022 } 3023 3024 $url = esc_url( $url ); 3025 if ( empty( $url ) ) { 3026 return $matches[0]; 3027 } 3028 3029 $rel_attr = _make_clickable_rel_attr( $url ); 3030 3031 return $matches[1] . "<a href=\"{$url}\"{$rel_attr}>{$url}</a>" . $suffix; 3032 } 3033 3034 /** 3035 * Callback to convert URL match to HTML A element. 3036 * 3037 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). 3038 * 3039 * @since 2.3.2 3040 * @access private 3041 * 3042 * @param array $matches Single Regex Match. 3043 * @return string HTML A element with URL address. 3044 */ 3045 function _make_web_ftp_clickable_cb( $matches ) { 3046 $ret = ''; 3047 $dest = $matches[2]; 3048 $dest = 'http://' . $dest; 3049 3050 // Removed trailing [.,;:)] from URL. 3051 $last_char = substr( $dest, -1 ); 3052 if ( in_array( $last_char, array( '.', ',', ';', ':', ')' ), true ) ) { 3053 $ret = $last_char; 3054 $dest = substr( $dest, 0, strlen( $dest ) - 1 ); 3055 } 3056 3057 $dest = esc_url( $dest ); 3058 if ( empty( $dest ) ) { 3059 return $matches[0]; 3060 } 3061 3062 $rel_attr = _make_clickable_rel_attr( $dest ); 3063 3064 return $matches[1] . "<a href=\"{$dest}\"{$rel_attr}>{$dest}</a>{$ret}"; 3065 } 3066 3067 /** 3068 * Callback to convert email address match to HTML A element. 3069 * 3070 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). 3071 * 3072 * @since 2.3.2 3073 * @access private 3074 * 3075 * @param array $matches Single Regex Match. 3076 * @return string HTML A element with email address. 3077 */ 3078 function _make_email_clickable_cb( $matches ) { 3079 $email = $matches[2] . '@' . $matches[3]; 3080 3081 return $matches[1] . "<a href=\"mailto:{$email}\">{$email}</a>"; 3082 } 3083 3084 /** 3085 * Helper function used to build the "rel" attribute for a URL when creating an anchor using make_clickable(). 3086 * 3087 * @since 6.2.0 3088 * 3089 * @param string $url The URL. 3090 * @return string The rel attribute for the anchor or an empty string if no rel attribute should be added. 3091 */ 3092 function _make_clickable_rel_attr( $url ) { 3093 $rel_parts = array(); 3094 $scheme = strtolower( wp_parse_url( $url, PHP_URL_SCHEME ) ); 3095 $nofollow_schemes = array_intersect( wp_allowed_protocols(), array( 'https', 'http' ) ); 3096 3097 // Apply "nofollow" to external links with qualifying URL schemes (mailto:, tel:, etc... shouldn't be followed). 3098 if ( ! wp_is_internal_link( $url ) && in_array( $scheme, $nofollow_schemes, true ) ) { 3099 $rel_parts[] = 'nofollow'; 3100 } 3101 3102 // Apply "ugc" when in comment context. 3103 if ( 'comment_text' === current_filter() ) { 3104 $rel_parts[] = 'ugc'; 3105 } 3106 3107 $rel = implode( ' ', $rel_parts ); 3108 3109 /** 3110 * Filters the rel value that is added to URL matches converted to links. 3111 * 3112 * @since 5.3.0 3113 * 3114 * @param string $rel The rel value. 3115 * @param string $url The matched URL being converted to a link tag. 3116 */ 3117 $rel = apply_filters( 'make_clickable_rel', $rel, $url ); 3118 3119 $rel_attr = $rel ? ' rel="' . esc_attr( $rel ) . '"' : ''; 3120 3121 return $rel_attr; 3122 } 3123 3124 /** 3125 * Converts plaintext URI to HTML links. 3126 * 3127 * Converts URI, www and ftp, and email addresses. Finishes by fixing links 3128 * within links. 3129 * 3130 * @since 0.71 3131 * 3132 * @param string $text Content to convert URIs. 3133 * @return string Content with converted URIs. 3134 */ 3135 function make_clickable( $text ) { 3136 $r = ''; 3137 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Split out HTML tags. 3138 $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>. 3139 foreach ( $textarr as $piece ) { 3140 3141 if ( preg_match( '|^<code[\s>]|i', $piece ) 3142 || preg_match( '|^<pre[\s>]|i', $piece ) 3143 || preg_match( '|^<script[\s>]|i', $piece ) 3144 || preg_match( '|^<style[\s>]|i', $piece ) 3145 ) { 3146 ++$nested_code_pre; 3147 } elseif ( $nested_code_pre 3148 && ( '</code>' === strtolower( $piece ) 3149 || '</pre>' === strtolower( $piece ) 3150 || '</script>' === strtolower( $piece ) 3151 || '</style>' === strtolower( $piece ) 3152 ) 3153 ) { 3154 --$nested_code_pre; 3155 } 3156 3157 if ( $nested_code_pre 3158 || empty( $piece ) 3159 || ( '<' === $piece[0] && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) 3160 ) { 3161 $r .= $piece; 3162 continue; 3163 } 3164 3165 // Long strings might contain expensive edge cases... 3166 if ( 10000 < strlen( $piece ) ) { 3167 // ...break it up. 3168 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing parentheses. 3169 if ( 2101 < strlen( $chunk ) ) { 3170 $r .= $chunk; // Too big, no whitespace: bail. 3171 } else { 3172 $r .= make_clickable( $chunk ); 3173 } 3174 } 3175 } else { 3176 $ret = " $piece "; // Pad with whitespace to simplify the regexes. 3177 3178 $url_clickable = '~ 3179 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation. 3180 ( # 2: URL. 3181 [\\w]{1,20}+:// # Scheme and hier-part prefix. 3182 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long. 3183 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character. 3184 (?: # Unroll the Loop: Only allow punctuation URL character if followed by a non-punctuation URL character. 3185 [\'.,;:!?)] # Punctuation URL character. 3186 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character. 3187 )* 3188 ) 3189 (\)?) # 3: Trailing closing parenthesis (for parenthesis balancing post processing). 3190 (\\.\\w{2,6})? # 4: Allowing file extensions (e.g., .jpg, .png). 3191 ~xS'; 3192 /* 3193 * The regex is a non-anchored pattern and does not have a single fixed starting character. 3194 * Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times. 3195 */ 3196 3197 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret ); 3198 3199 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret ); 3200 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret ); 3201 3202 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding. 3203 $r .= $ret; 3204 } 3205 } 3206 3207 // Cleanup of accidental links within links. 3208 return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', '$1$3</a>', $r ); 3209 } 3210 3211 /** 3212 * Breaks a string into chunks by splitting at whitespace characters. 3213 * 3214 * The length of each returned chunk is as close to the specified length goal as possible, 3215 * with the caveat that each chunk includes its trailing delimiter. 3216 * Chunks longer than the goal are guaranteed to not have any inner whitespace. 3217 * 3218 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly. 3219 * 3220 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters) 3221 * 3222 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) == 3223 * array ( 3224 * 0 => '1234 67890 ', // 11 characters: Perfect split. 3225 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long. 3226 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long. 3227 * 3 => '1234 890 ', // 11 characters: Perfect split. 3228 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long. 3229 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split. 3230 * 6 => ' 45678 ', // 11 characters: Perfect split. 3231 * 7 => '1 3 5 7 90 ', // 11 characters: End of $text. 3232 * ); 3233 * 3234 * @since 3.4.0 3235 * @access private 3236 * 3237 * @param string $text The string to split. 3238 * @param int $goal The desired chunk length. 3239 * @return array Numeric array of chunks. 3240 */ 3241 function _split_str_by_whitespace( $text, $goal ) { 3242 $chunks = array(); 3243 3244 $string_nullspace = strtr( $text, "\r\n\t\v\f ", "\000\000\000\000\000\000" ); 3245 3246 while ( $goal < strlen( $string_nullspace ) ) { 3247 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" ); 3248 3249 if ( false === $pos ) { 3250 $pos = strpos( $string_nullspace, "\000", $goal + 1 ); 3251 if ( false === $pos ) { 3252 break; 3253 } 3254 } 3255 3256 $chunks[] = substr( $text, 0, $pos + 1 ); 3257 $text = substr( $text, $pos + 1 ); 3258 $string_nullspace = substr( $string_nullspace, $pos + 1 ); 3259 } 3260 3261 if ( $text ) { 3262 $chunks[] = $text; 3263 } 3264 3265 return $chunks; 3266 } 3267 3268 /** 3269 * Callback to add a rel attribute to HTML A element. 3270 * 3271 * Will remove already existing string before adding to prevent invalidating (X)HTML. 3272 * 3273 * @since 5.3.0 3274 * 3275 * @param array $matches Single match. 3276 * @param string $rel The rel attribute to add. 3277 * @return string HTML A element with the added rel attribute. 3278 */ 3279 function wp_rel_callback( $matches, $rel ) { 3280 $text = $matches[1]; 3281 $atts = wp_kses_hair( $matches[1], wp_allowed_protocols() ); 3282 3283 if ( ! empty( $atts['href'] ) && wp_is_internal_link( $atts['href']['value'] ) ) { 3284 $rel = trim( str_replace( 'nofollow', '', $rel ) ); 3285 } 3286 3287 if ( ! empty( $atts['rel'] ) ) { 3288 $parts = array_map( 'trim', explode( ' ', $atts['rel']['value'] ) ); 3289 $rel_array = array_map( 'trim', explode( ' ', $rel ) ); 3290 $parts = array_unique( array_merge( $parts, $rel_array ) ); 3291 $rel = implode( ' ', $parts ); 3292 unset( $atts['rel'] ); 3293 3294 $html = ''; 3295 foreach ( $atts as $name => $value ) { 3296 if ( isset( $value['vless'] ) && 'y' === $value['vless'] ) { 3297 $html .= $name . ' '; 3298 } else { 3299 $html .= "{$name}=\"" . esc_attr( $value['value'] ) . '" '; 3300 } 3301 } 3302 $text = trim( $html ); 3303 } 3304 3305 $rel_attr = $rel ? ' rel="' . esc_attr( $rel ) . '"' : ''; 3306 3307 return "<a {$text}{$rel_attr}>"; 3308 } 3309 3310 /** 3311 * Adds `rel="nofollow"` string to all HTML A elements in content. 3312 * 3313 * @since 1.5.0 3314 * 3315 * @param string $text Content that may contain HTML A elements. 3316 * @return string Converted content. 3317 */ 3318 function wp_rel_nofollow( $text ) { 3319 // This is a pre-save filter, so text is already escaped. 3320 $text = stripslashes( $text ); 3321 $text = preg_replace_callback( 3322 '|<a (.+?)>|i', 3323 static function ( $matches ) { 3324 return wp_rel_callback( $matches, 'nofollow' ); 3325 }, 3326 $text 3327 ); 3328 return wp_slash( $text ); 3329 } 3330 3331 /** 3332 * Callback to add `rel="nofollow"` string to HTML A element. 3333 * 3334 * @since 2.3.0 3335 * @deprecated 5.3.0 Use wp_rel_callback() 3336 * 3337 * @param array $matches Single match. 3338 * @return string HTML A Element with `rel="nofollow"`. 3339 */ 3340 function wp_rel_nofollow_callback( $matches ) { 3341 return wp_rel_callback( $matches, 'nofollow' ); 3342 } 3343 3344 /** 3345 * Adds `rel="nofollow ugc"` string to all HTML A elements in content. 3346 * 3347 * @since 5.3.0 3348 * 3349 * @param string $text Content that may contain HTML A elements. 3350 * @return string Converted content. 3351 */ 3352 function wp_rel_ugc( $text ) { 3353 // This is a pre-save filter, so text is already escaped. 3354 $text = stripslashes( $text ); 3355 $text = preg_replace_callback( 3356 '|<a (.+?)>|i', 3357 static function ( $matches ) { 3358 return wp_rel_callback( $matches, 'nofollow ugc' ); 3359 }, 3360 $text 3361 ); 3362 return wp_slash( $text ); 3363 } 3364 3365 /** 3366 * Adds `rel="noopener"` to all HTML A elements that have a target. 3367 * 3368 * @since 5.1.0 3369 * @since 5.6.0 Removed 'noreferrer' relationship. 3370 * @deprecated 6.7.0 3371 * 3372 * @param string $text Content that may contain HTML A elements. 3373 * @return string Converted content. 3374 */ 3375 function wp_targeted_link_rel( $text ) { 3376 _deprecated_function( __FUNCTION__, '6.7.0' ); 3377 3378 // Don't run (more expensive) regex if no links with targets. 3379 if ( false === stripos( $text, 'target' ) || false === stripos( $text, '<a ' ) || is_serialized( $text ) ) { 3380 return $text; 3381 } 3382 3383 $script_and_style_regex = '/<(script|style).*?<\/\\1>/si'; 3384 3385 preg_match_all( $script_and_style_regex, $text, $matches ); 3386 $extra_parts = $matches[0]; 3387 $html_parts = preg_split( $script_and_style_regex, $text ); 3388 3389 foreach ( $html_parts as &$part ) { 3390 $part = preg_replace_callback( '|<a\s([^>]*target\s*=[^>]*)>|i', 'wp_targeted_link_rel_callback', $part ); 3391 } 3392 3393 $text = ''; 3394 for ( $i = 0; $i < count( $html_parts ); $i++ ) { 3395 $text .= $html_parts[ $i ]; 3396 if ( isset( $extra_parts[ $i ] ) ) { 3397 $text .= $extra_parts[ $i ]; 3398 } 3399 } 3400 3401 return $text; 3402 } 3403 3404 /** 3405 * Callback to add `rel="noopener"` string to HTML A element. 3406 * 3407 * Will not duplicate an existing 'noopener' value to avoid invalidating the HTML. 3408 * 3409 * @since 5.1.0 3410 * @since 5.6.0 Removed 'noreferrer' relationship. 3411 * @deprecated 6.7.0 3412 * 3413 * @param array $matches Single match. 3414 * @return string HTML A Element with `rel="noopener"` in addition to any existing values. 3415 */ 3416 function wp_targeted_link_rel_callback( $matches ) { 3417 _deprecated_function( __FUNCTION__, '6.7.0' ); 3418 3419 $link_html = $matches[1]; 3420 $original_link_html = $link_html; 3421 3422 // Consider the HTML escaped if there are no unescaped quotes. 3423 $is_escaped = ! preg_match( '/(^|[^\\\\])[\'"]/', $link_html ); 3424 if ( $is_escaped ) { 3425 // Replace only the quotes so that they are parsable by wp_kses_hair(), leave the rest as is. 3426 $link_html = preg_replace( '/\\\\([\'"])/', '$1', $link_html ); 3427 } 3428 3429 $atts = wp_kses_hair( $link_html, wp_allowed_protocols() ); 3430 3431 /** 3432 * Filters the rel values that are added to links with `target` attribute. 3433 * 3434 * @since 5.1.0 3435 * 3436 * @param string $rel The rel values. 3437 * @param string $link_html The matched content of the link tag including all HTML attributes. 3438 */ 3439 $rel = apply_filters( 'wp_targeted_link_rel', 'noopener', $link_html ); 3440 3441 // Return early if no rel values to be added or if no actual target attribute. 3442 if ( ! $rel || ! isset( $atts['target'] ) ) { 3443 return "<a $original_link_html>"; 3444 } 3445 3446 if ( isset( $atts['rel'] ) ) { 3447 $all_parts = preg_split( '/\s/', "{$atts['rel']['value']} $rel", -1, PREG_SPLIT_NO_EMPTY ); 3448 $rel = implode( ' ', array_unique( $all_parts ) ); 3449 } 3450 3451 $atts['rel']['whole'] = 'rel="' . esc_attr( $rel ) . '"'; 3452 $link_html = implode( ' ', array_column( $atts, 'whole' ) ); 3453 3454 if ( $is_escaped ) { 3455 $link_html = preg_replace( '/[\'"]/', '\\\\$0', $link_html ); 3456 } 3457 3458 return "<a $link_html>"; 3459 } 3460 3461 /** 3462 * Adds all filters modifying the rel attribute of targeted links. 3463 * 3464 * @since 5.1.0 3465 * @deprecated 6.7.0 3466 */ 3467 function wp_init_targeted_link_rel_filters() { 3468 _deprecated_function( __FUNCTION__, '6.7.0' ); 3469 } 3470 3471 /** 3472 * Removes all filters modifying the rel attribute of targeted links. 3473 * 3474 * @since 5.1.0 3475 * @deprecated 6.7.0 3476 */ 3477 function wp_remove_targeted_link_rel_filters() { 3478 _deprecated_function( __FUNCTION__, '6.7.0' ); 3479 } 3480 3481 /** 3482 * Converts one smiley code to the icon graphic file equivalent. 3483 * 3484 * Callback handler for convert_smilies(). 3485 * 3486 * Looks up one smiley code in the $wpsmiliestrans global array and returns an 3487 * `<img>` string for that smiley. 3488 * 3489 * @since 2.8.0 3490 * 3491 * @global array $wpsmiliestrans 3492 * 3493 * @param array $matches Single match. Smiley code to convert to image. 3494 * @return string Image string for smiley. 3495 */ 3496 function translate_smiley( $matches ) { 3497 global $wpsmiliestrans; 3498 3499 if ( 0 === count( $matches ) ) { 3500 return ''; 3501 } 3502 3503 $smiley = trim( reset( $matches ) ); 3504 $img = $wpsmiliestrans[ $smiley ]; 3505 3506 $matches = array(); 3507 $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false; 3508 $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png', 'webp', 'avif' ); 3509 3510 // Don't convert smilies that aren't images - they're probably emoji. 3511 if ( ! in_array( $ext, $image_exts, true ) ) { 3512 return $img; 3513 } 3514 3515 /** 3516 * Filters the Smiley image URL before it's used in the image element. 3517 * 3518 * @since 2.9.0 3519 * 3520 * @param string $smiley_url URL for the smiley image. 3521 * @param string $img Filename for the smiley image. 3522 * @param string $site_url Site URL, as returned by site_url(). 3523 */ 3524 $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() ); 3525 3526 return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) ); 3527 } 3528 3529 /** 3530 * Converts text equivalent of smilies to images. 3531 * 3532 * Will only convert smilies if the option 'use_smilies' is true and the global 3533 * used in the function isn't empty. 3534 * 3535 * @since 0.71 3536 * 3537 * @global string|array $wp_smiliessearch 3538 * 3539 * @param string $text Content to convert smilies from text. 3540 * @return string Converted content with text smilies replaced with images. 3541 */ 3542 function convert_smilies( $text ) { 3543 global $wp_smiliessearch; 3544 3545 if ( ! get_option( 'use_smilies' ) || empty( $wp_smiliessearch ) ) { 3546 // Return default text. 3547 return $text; 3548 } 3549 3550 // HTML loop taken from texturize function, could possible be consolidated. 3551 $textarr = preg_split( '/(<[^>]*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Capture the tags as well as in between. 3552 3553 if ( false === $textarr ) { 3554 // Return default text. 3555 return $text; 3556 } 3557 3558 // Loop stuff. 3559 $stop = count( $textarr ); 3560 $output = ''; 3561 3562 // Ignore processing of specific tags. 3563 $tags_to_ignore = 'code|pre|style|script|textarea'; 3564 $ignore_block_element = ''; 3565 3566 for ( $i = 0; $i < $stop; $i++ ) { 3567 $content = $textarr[ $i ]; 3568 3569 // If we're in an ignore block, wait until we find its closing tag. 3570 if ( '' === $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')[^>]*>/', $content, $matches ) ) { 3571 $ignore_block_element = $matches[1]; 3572 } 3573 3574 // If it's not a tag and not in ignore block. 3575 if ( '' === $ignore_block_element && strlen( $content ) > 0 && '<' !== $content[0] ) { 3576 $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content ); 3577 } 3578 3579 // Did we exit ignore block? 3580 if ( '' !== $ignore_block_element && '</' . $ignore_block_element . '>' === $content ) { 3581 $ignore_block_element = ''; 3582 } 3583 3584 $output .= $content; 3585 } 3586 3587 return $output; 3588 } 3589 3590 /** 3591 * Verifies that an email is valid. 3592 * 3593 * This accepts the addresses that matches the WHATWG specifications, 3594 * i.e. what browsers use for `<input type=email>`. It also accepts some 3595 * additional addresses. 3596 * 3597 * By default this accepts addresses like info@grå.org (also accepted 3598 * by Firefox) `<input type=email>`. You can disable Unicode support by 3599 * using the wp_is_ascii_email filter instead of wp_is_unicode_email, 3600 * which is the default. 3601 * 3602 * @since 0.71 3603 * 3604 * @param string $email Email address to verify. 3605 * @param bool $deprecated Deprecated. 3606 * @return string|false Valid email address on success, false on failure. 3607 */ 3608 function is_email( $email, $deprecated = false ) { 3609 if ( ! empty( $deprecated ) ) { 3610 _deprecated_argument( __FUNCTION__, '3.0.0' ); 3611 } 3612 3613 /** 3614 * Filters whether an email address is valid. 3615 * 3616 * This filter is evaluated under several different contexts, such as 3617 * 'local_invalid_chars', 'domain_no_periods', or no specific context. 3618 * Filters registered on this hook perform the actual validation; the 3619 * default filter is registered in default-filters.php. 3620 * 3621 * @since 2.8.0 3622 * 3623 * @param string|false $is_email The email address if successfully passed the is_email() checks, false otherwise. 3624 * @param string $email The email address being checked. 3625 * @param string|null $context Context under which the email was tested, or null for the initial call. 3626 */ 3627 return apply_filters( 'is_email', false, $email, null ); 3628 } 3629 3630 /** 3631 * Default is_email filter for databases that support Unicode (db charset is utf8mb4). 3632 * 3633 * Validates the email address using {@see WP_Email_Address::from_string()} with Unicode enabled. 3634 * Only acts when $context is null (which it is in the initial validation call); later rescue-context calls are passed through. 3635 * 3636 * @since 7.1.0 3637 * 3638 * @param string|false $value The current filter value. 3639 * @param string $email The email address being checked. 3640 * @param string|null $context Validation context, or null for the initial call. 3641 * @return string|false The email address if valid, false otherwise. 3642 */ 3643 function wp_is_unicode_email( $value, $email, $context ) { 3644 if ( null !== $context ) { 3645 return $value; 3646 } 3647 3648 $result = WP_Email_Address::from_string( $email, 'unicode' ); 3649 return $result ? $result->get_unicode_address() : false; 3650 } 3651 3652 /** 3653 * Default is_email filter for databases that do not support Unicode (db charset is not utf8mb4). 3654 * 3655 * Validates the email address using {@see WP_Email_Address::from_string()} with Unicode disabled. 3656 * Only acts when $context is null (which it is in the initial validation call); later rescue-context calls are passed through. 3657 * 3658 * @since 7.1.0 3659 * 3660 * @param string|false $value The current filter value. 3661 * @param string $email The email address being checked. 3662 * @param string|null $context Validation context, or null for the initial call. 3663 * @return string|false The email address if valid, false otherwise. 3664 */ 3665 function wp_is_ascii_email( $value, $email, $context ) { 3666 if ( null !== $context ) { 3667 return $value; 3668 } 3669 3670 $result = WP_Email_Address::from_string( $email, 'ascii' ); 3671 return $result ? $result->get_unicode_address() : false; 3672 } 3673 3674 /** 3675 * Converts to ASCII from email subjects. 3676 * 3677 * @since 1.2.0 3678 * 3679 * @param string $subject Subject line. 3680 * @return string Converted string to ASCII. 3681 */ 3682 function wp_iso_descrambler( $subject ) { 3683 /* this may only work with iso-8859-1, I'm afraid */ 3684 if ( ! preg_match( '#\=\?(.+)\?Q\?(.+)\?\=#i', $subject, $matches ) ) { 3685 return $subject; 3686 } 3687 3688 $subject = str_replace( '_', ' ', $matches[2] ); 3689 return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject ); 3690 } 3691 3692 /** 3693 * Helper function to convert hex encoded chars to ASCII. 3694 * 3695 * @since 3.1.0 3696 * @access private 3697 * 3698 * @param array $matches The preg_replace_callback matches array. 3699 * @return string Converted chars. 3700 */ 3701 function _wp_iso_convert( $matches ) { 3702 return chr( hexdec( strtolower( $matches[1] ) ) ); 3703 } 3704 3705 /** 3706 * Given a date in the timezone of the site, returns that date in UTC. 3707 * 3708 * Requires and returns a date in the Y-m-d H:i:s format. 3709 * Return format can be overridden using the $format parameter. 3710 * 3711 * @since 1.2.0 3712 * 3713 * @param string $date_string The date to be converted, in the timezone of the site. 3714 * @param string $format The format string for the returned date. Default 'Y-m-d H:i:s'. 3715 * @return string Formatted version of the date, in UTC. 3716 */ 3717 function get_gmt_from_date( $date_string, $format = 'Y-m-d H:i:s' ) { 3718 $datetime = date_create( $date_string, wp_timezone() ); 3719 3720 if ( false === $datetime ) { 3721 return gmdate( $format, 0 ); 3722 } 3723 3724 return $datetime->setTimezone( new DateTimeZone( 'UTC' ) )->format( $format ); 3725 } 3726 3727 /** 3728 * Given a date in UTC or GMT timezone, returns that date in the timezone of the site. 3729 * 3730 * Requires a date in the Y-m-d H:i:s format. 3731 * Default return format of 'Y-m-d H:i:s' can be overridden using the `$format` parameter. 3732 * 3733 * @since 1.2.0 3734 * 3735 * @param string $date_string The date to be converted, in UTC or GMT timezone. 3736 * @param string $format The format string for the returned date. Default 'Y-m-d H:i:s'. 3737 * @return string Formatted version of the date, in the site's timezone. 3738 */ 3739 function get_date_from_gmt( $date_string, $format = 'Y-m-d H:i:s' ) { 3740 $datetime = date_create( $date_string, new DateTimeZone( 'UTC' ) ); 3741 3742 if ( false === $datetime ) { 3743 return gmdate( $format, 0 ); 3744 } 3745 3746 return $datetime->setTimezone( wp_timezone() )->format( $format ); 3747 } 3748 3749 /** 3750 * Given an ISO 8601 timezone, returns its UTC offset in seconds. 3751 * 3752 * @since 1.5.0 3753 * 3754 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'. 3755 * @return int|float The offset in seconds. 3756 */ 3757 function iso8601_timezone_to_offset( $timezone ) { 3758 // $timezone is either 'Z' or '[+|-]hhmm'. 3759 if ( 'Z' === $timezone ) { 3760 $offset = 0; 3761 } else { 3762 $sign = ( str_starts_with( $timezone, '+' ) ) ? 1 : -1; 3763 $hours = (int) substr( $timezone, 1, 2 ); 3764 $minutes = (int) substr( $timezone, 3, 4 ) / 60; 3765 $offset = $sign * HOUR_IN_SECONDS * ( $hours + $minutes ); 3766 } 3767 return $offset; 3768 } 3769 3770 /** 3771 * Given an ISO 8601 (Ymd\TH:i:sO) date, returns a MySQL DateTime (Y-m-d H:i:s) format used by post_date[_gmt]. 3772 * 3773 * @since 1.5.0 3774 * 3775 * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}. 3776 * @param string $timezone Optional. If set to 'gmt' returns the result in UTC. Default 'user'. 3777 * @return string|false The date and time in MySQL DateTime format - Y-m-d H:i:s, or false on failure. 3778 */ 3779 function iso8601_to_datetime( $date_string, $timezone = 'user' ) { 3780 $timezone = strtolower( $timezone ); 3781 $wp_timezone = wp_timezone(); 3782 $datetime = date_create( $date_string, $wp_timezone ); // Timezone is ignored if input has one. 3783 3784 if ( false === $datetime ) { 3785 return false; 3786 } 3787 3788 if ( 'gmt' === $timezone ) { 3789 return $datetime->setTimezone( new DateTimeZone( 'UTC' ) )->format( 'Y-m-d H:i:s' ); 3790 } 3791 3792 if ( 'user' === $timezone ) { 3793 return $datetime->setTimezone( $wp_timezone )->format( 'Y-m-d H:i:s' ); 3794 } 3795 3796 return false; 3797 } 3798 3799 /** 3800 * Sanitizes an email address. 3801 * 3802 * Strips stray whitespace from the input, then strips trailing dots from the domain. 3803 * This is designed to recover from cut/paste mistakes without any risk of transforming 3804 * the input into a different address than the user intended. 3805 * 3806 * Validation and final form are determined by the 'sanitize_email' filter; the default 3807 * filter is registered in default-filters.php and delegates to {@see WP_Email_Address::from_string()}. 3808 * 3809 * @since 1.5.0 3810 * @since 7.1.0 Accepts Unicode email addresses on supporting platforms. 3811 * 3812 * @param string $email Email address to sanitize. 3813 * @return string The sanitized email address, or an empty string if invalid. 3814 */ 3815 function sanitize_email( $email ) { 3816 // Strip surrounding whitespace. 3817 $email = trim( $email ); 3818 3819 // Extract the address from "Display Name <username@domain>" format. 3820 if ( 1 === preg_match( '/<([^>]+)>$/', $email, $matches ) ) { 3821 $email = $matches[1]; 3822 } 3823 3824 /* 3825 * Strip soft hyphens and whitespace adjacent to structural separators (dots and @), 3826 * e.g. copy-paste artifacts like "info@example\u{00AD}.com" or "info@example .com". 3827 * 3828 * In some cases, e.g. autocorrect, some older software has been seen to add the 3829 * space for unrecognized TLDs. This re-joins the parts for proper examination. 3830 */ 3831 $email = preg_replace( '/[\x{00AD}\s]*([.@])[\x{00AD}\s]*/u', '$1', $email ) ?? $email; 3832 3833 // Strip a trailing dot from the domain (e.g. if pasted from the end of a sentence). 3834 if ( str_contains( $email, '@' ) ) { 3835 list( $local, $domain ) = explode( '@', $email, 2 ); 3836 $domain = rtrim( $domain, '.' ); 3837 $email = $local . '@' . $domain; 3838 } 3839 3840 /** 3841 * Filters a sanitized email address. 3842 * 3843 * Filters registered on this hook perform the actual validation and return 3844 * the canonical email string on success or an empty string on failure. 3845 * The default filter is registered in default-filters.php. 3846 * 3847 * @since 2.8.0 3848 * 3849 * @param string $sanitized_email The sanitized email address, or empty string. 3850 * @param string $email The email address as provided to sanitize_email(). 3851 * @param string|null $context Validation context, or null for the initial call. 3852 */ 3853 return apply_filters( 'sanitize_email', '', $email, null ); 3854 } 3855 3856 /** 3857 * Default sanitize_email filter for databases that support Unicode (db charset is utf8mb4). 3858 * 3859 * Returns the canonical address from {@see WP_Email_Address::from_string()} with Unicode 3860 * enabled, or an empty string if the address is invalid. 3861 * 3862 * @since 7.1.0 3863 * 3864 * @param string $value The current filter value. 3865 * @param string $email The email address being sanitized. 3866 * @param string|null $context Sanitization context, always null. 3867 * @return string The canonical email address if valid, empty string otherwise. 3868 */ 3869 function wp_sanitize_unicode_email( $value, $email, $context ) { 3870 $result = WP_Email_Address::from_string( $email, 'unicode' ); 3871 return $result ? $result->get_unicode_address() : ''; 3872 } 3873 3874 /** 3875 * Default sanitize_email filter for databases that do not support Unicode (db charset is not utf8mb4). 3876 * 3877 * Returns the canonical address from {@see WP_Email_Address::from_string()} with Unicode 3878 * disabled, or an empty string if the address is invalid. 3879 * 3880 * @since 7.1.0 3881 * 3882 * @param string $value The current filter value. 3883 * @param string $email The email address being sanitized. 3884 * @param string|null $context Sanitization context, always null. 3885 * @return string The canonical email address if valid, empty string otherwise. 3886 */ 3887 function wp_sanitize_ascii_email( $value, $email, $context ) { 3888 $result = WP_Email_Address::from_string( $email, 'ascii' ); 3889 return $result ? $result->get_unicode_address() : ''; 3890 } 3891 3892 /** 3893 * Determines the difference between two timestamps. 3894 * 3895 * The difference is returned in a human-readable format such as "1 hour", 3896 * "5 minutes", "2 days". 3897 * 3898 * @since 1.5.0 3899 * @since 5.3.0 Added support for showing a difference in seconds. 3900 * 3901 * @param int $from Unix timestamp from which the difference begins. 3902 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set. 3903 * @return string Human-readable time difference. 3904 */ 3905 function human_time_diff( $from, $to = 0 ) { 3906 if ( empty( $to ) ) { 3907 $to = time(); 3908 } 3909 3910 $diff = (int) abs( $to - $from ); 3911 3912 if ( $diff < MINUTE_IN_SECONDS ) { 3913 $secs = $diff; 3914 if ( $secs <= 1 ) { 3915 $secs = 1; 3916 } 3917 /* translators: Time difference between two dates, in seconds. %s: Number of seconds. */ 3918 $since = sprintf( _n( '%s second', '%s seconds', $secs ), $secs ); 3919 } elseif ( $diff < HOUR_IN_SECONDS && $diff >= MINUTE_IN_SECONDS ) { 3920 $mins = round( $diff / MINUTE_IN_SECONDS ); 3921 if ( $mins <= 1 ) { 3922 $mins = 1; 3923 } 3924 /* translators: Time difference between two dates, in minutes. %s: Number of minutes. */ 3925 $since = sprintf( _n( '%s minute', '%s minutes', $mins ), $mins ); 3926 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) { 3927 $hours = round( $diff / HOUR_IN_SECONDS ); 3928 if ( $hours <= 1 ) { 3929 $hours = 1; 3930 } 3931 /* translators: Time difference between two dates, in hours. %s: Number of hours. */ 3932 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours ); 3933 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) { 3934 $days = round( $diff / DAY_IN_SECONDS ); 3935 if ( $days <= 1 ) { 3936 $days = 1; 3937 } 3938 /* translators: Time difference between two dates, in days. %s: Number of days. */ 3939 $since = sprintf( _n( '%s day', '%s days', $days ), $days ); 3940 } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) { 3941 $weeks = round( $diff / WEEK_IN_SECONDS ); 3942 if ( $weeks <= 1 ) { 3943 $weeks = 1; 3944 } 3945 /* translators: Time difference between two dates, in weeks. %s: Number of weeks. */ 3946 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks ); 3947 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) { 3948 $months = round( $diff / MONTH_IN_SECONDS ); 3949 if ( $months <= 1 ) { 3950 $months = 1; 3951 } 3952 /* translators: Time difference between two dates, in months. %s: Number of months. */ 3953 $since = sprintf( _n( '%s month', '%s months', $months ), $months ); 3954 } elseif ( $diff >= YEAR_IN_SECONDS ) { 3955 $years = round( $diff / YEAR_IN_SECONDS ); 3956 if ( $years <= 1 ) { 3957 $years = 1; 3958 } 3959 /* translators: Time difference between two dates, in years. %s: Number of years. */ 3960 $since = sprintf( _n( '%s year', '%s years', $years ), $years ); 3961 } 3962 3963 /** 3964 * Filters the human-readable difference between two timestamps. 3965 * 3966 * @since 4.0.0 3967 * 3968 * @param string $since The difference in human-readable text. 3969 * @param int $diff The difference in seconds. 3970 * @param int $from Unix timestamp from which the difference begins. 3971 * @param int $to Unix timestamp to end the time difference. 3972 */ 3973 return apply_filters( 'human_time_diff', $since, $diff, $from, $to ); 3974 } 3975 3976 /** 3977 * Generates an excerpt from the content, if needed. 3978 * 3979 * Returns a maximum of 55 words with an ellipsis appended if necessary. 3980 * 3981 * The 55-word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter 3982 * The ' […]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter 3983 * 3984 * @since 1.5.0 3985 * @since 5.2.0 Added the `$post` parameter. 3986 * @since 6.3.0 Removes footnotes markup from the excerpt content. 3987 * 3988 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated. 3989 * @param WP_Post|object|int $post Optional. WP_Post instance or Post ID/object. Default null. 3990 * @return string The excerpt. 3991 */ 3992 function wp_trim_excerpt( $text = '', $post = null ) { 3993 $raw_excerpt = $text; 3994 3995 if ( '' === trim( $text ) ) { 3996 $post = get_post( $post ); 3997 $text = get_the_content( '', false, $post ); 3998 3999 $text = strip_shortcodes( $text ); 4000 $text = excerpt_remove_blocks( $text ); 4001 $text = excerpt_remove_footnotes( $text ); 4002 4003 /* 4004 * Temporarily unhook wp_filter_content_tags() since any tags 4005 * within the excerpt are stripped out. Modifying the tags here 4006 * is wasteful and can lead to bugs in the image counting logic. 4007 */ 4008 $filter_image_removed = remove_filter( 'the_content', 'wp_filter_content_tags', 12 ); 4009 4010 /* 4011 * Temporarily unhook do_blocks() since excerpt_remove_blocks( $text ) 4012 * handles block rendering needed for excerpt. 4013 */ 4014 $filter_block_removed = remove_filter( 'the_content', 'do_blocks', 9 ); 4015 4016 /** This filter is documented in wp-includes/post-template.php */ 4017 $text = apply_filters( 'the_content', $text ); 4018 $text = str_replace( ']]>', ']]>', $text ); 4019 4020 // Restore the original filter if removed. 4021 if ( $filter_block_removed ) { 4022 add_filter( 'the_content', 'do_blocks', 9 ); 4023 } 4024 4025 /* 4026 * Only restore the filter callback if it was removed above. The logic 4027 * to unhook and restore only applies on the default priority of 10, 4028 * which is generally used for the filter callback in WordPress core. 4029 */ 4030 if ( $filter_image_removed ) { 4031 add_filter( 'the_content', 'wp_filter_content_tags', 12 ); 4032 } 4033 4034 /* translators: Maximum number of words used in a post excerpt. */ 4035 $excerpt_length = (int) _x( '55', 'excerpt_length' ); 4036 4037 /** 4038 * Filters the maximum number of words in a post excerpt. 4039 * 4040 * @since 2.7.0 4041 * 4042 * @param int $number The maximum number of words. Default 55. 4043 */ 4044 $excerpt_length = (int) apply_filters( 'excerpt_length', $excerpt_length ); 4045 4046 /** 4047 * Filters the string in the "more" link displayed after a trimmed excerpt. 4048 * 4049 * @since 2.9.0 4050 * 4051 * @param string $more_string The string shown within the more link. 4052 */ 4053 $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' ); 4054 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more ); 4055 4056 } 4057 4058 /** 4059 * Filters the trimmed excerpt string. 4060 * 4061 * @since 2.8.0 4062 * 4063 * @param string $text The trimmed text. 4064 * @param string $raw_excerpt The text prior to trimming. 4065 */ 4066 return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt ); 4067 } 4068 4069 /** 4070 * Trims text to a certain number of words. 4071 * 4072 * This function is localized. For languages that count 'words' by the individual 4073 * character (such as East Asian languages), the $num_words argument will apply 4074 * to the number of individual characters. 4075 * 4076 * @since 3.3.0 4077 * 4078 * @param string $text Text to trim. 4079 * @param int $num_words Number of words. Default 55. 4080 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'. 4081 * @return string Trimmed text. 4082 */ 4083 function wp_trim_words( $text, $num_words = 55, $more = null ) { 4084 if ( null === $more ) { 4085 $more = __( '…' ); 4086 } 4087 4088 $original_text = $text; 4089 $text = wp_strip_all_tags( $text ); 4090 $num_words = (int) $num_words; 4091 4092 if ( str_starts_with( wp_get_word_count_type(), 'characters' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) { 4093 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' ); 4094 preg_match_all( '/./u', $text, $words_array ); 4095 $words_array = array_slice( $words_array[0], 0, $num_words + 1 ); 4096 $sep = ''; 4097 } else { 4098 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY ); 4099 $sep = ' '; 4100 } 4101 4102 if ( count( $words_array ) > $num_words ) { 4103 array_pop( $words_array ); 4104 $text = implode( $sep, $words_array ); 4105 $text = $text . $more; 4106 } else { 4107 $text = implode( $sep, $words_array ); 4108 } 4109 4110 /** 4111 * Filters the text content after words have been trimmed. 4112 * 4113 * @since 3.3.0 4114 * 4115 * @param string $text The trimmed text. 4116 * @param int $num_words The number of words to trim the text to. Default 55. 4117 * @param string $more An optional string to append to the end of the trimmed text, e.g. …. 4118 * @param string $original_text The text before it was trimmed. 4119 */ 4120 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text ); 4121 } 4122 4123 /** 4124 * Converts named entities into numbered entities. 4125 * 4126 * @since 1.5.1 4127 * 4128 * @param string $text The text within which entities will be converted. 4129 * @return string Text with converted entities. 4130 */ 4131 function ent2ncr( $text ) { 4132 4133 /** 4134 * Filters text before named entities are converted into numbered entities. 4135 * 4136 * A non-null string must be returned for the filter to be evaluated. 4137 * 4138 * @since 3.3.0 4139 * 4140 * @param string|null $converted_text The text to be converted. Default null. 4141 * @param string $text The text prior to entity conversion. 4142 */ 4143 $filtered = apply_filters( 'pre_ent2ncr', null, $text ); 4144 if ( null !== $filtered ) { 4145 return $filtered; 4146 } 4147 4148 $to_ncr = array( 4149 '"' => '"', 4150 '&' => '&', 4151 '<' => '<', 4152 '>' => '>', 4153 '|' => '|', 4154 ' ' => ' ', 4155 '¡' => '¡', 4156 '¢' => '¢', 4157 '£' => '£', 4158 '¤' => '¤', 4159 '¥' => '¥', 4160 '¦' => '¦', 4161 '&brkbar;' => '¦', 4162 '§' => '§', 4163 '¨' => '¨', 4164 '¨' => '¨', 4165 '©' => '©', 4166 'ª' => 'ª', 4167 '«' => '«', 4168 '¬' => '¬', 4169 '­' => '­', 4170 '®' => '®', 4171 '¯' => '¯', 4172 '&hibar;' => '¯', 4173 '°' => '°', 4174 '±' => '±', 4175 '²' => '²', 4176 '³' => '³', 4177 '´' => '´', 4178 'µ' => 'µ', 4179 '¶' => '¶', 4180 '·' => '·', 4181 '¸' => '¸', 4182 '¹' => '¹', 4183 'º' => 'º', 4184 '»' => '»', 4185 '¼' => '¼', 4186 '½' => '½', 4187 '¾' => '¾', 4188 '¿' => '¿', 4189 'À' => 'À', 4190 'Á' => 'Á', 4191 'Â' => 'Â', 4192 'Ã' => 'Ã', 4193 'Ä' => 'Ä', 4194 'Å' => 'Å', 4195 'Æ' => 'Æ', 4196 'Ç' => 'Ç', 4197 'È' => 'È', 4198 'É' => 'É', 4199 'Ê' => 'Ê', 4200 'Ë' => 'Ë', 4201 'Ì' => 'Ì', 4202 'Í' => 'Í', 4203 'Î' => 'Î', 4204 'Ï' => 'Ï', 4205 'Ð' => 'Ð', 4206 'Ñ' => 'Ñ', 4207 'Ò' => 'Ò', 4208 'Ó' => 'Ó', 4209 'Ô' => 'Ô', 4210 'Õ' => 'Õ', 4211 'Ö' => 'Ö', 4212 '×' => '×', 4213 'Ø' => 'Ø', 4214 'Ù' => 'Ù', 4215 'Ú' => 'Ú', 4216 'Û' => 'Û', 4217 'Ü' => 'Ü', 4218 'Ý' => 'Ý', 4219 'Þ' => 'Þ', 4220 'ß' => 'ß', 4221 'à' => 'à', 4222 'á' => 'á', 4223 'â' => 'â', 4224 'ã' => 'ã', 4225 'ä' => 'ä', 4226 'å' => 'å', 4227 'æ' => 'æ', 4228 'ç' => 'ç', 4229 'è' => 'è', 4230 'é' => 'é', 4231 'ê' => 'ê', 4232 'ë' => 'ë', 4233 'ì' => 'ì', 4234 'í' => 'í', 4235 'î' => 'î', 4236 'ï' => 'ï', 4237 'ð' => 'ð', 4238 'ñ' => 'ñ', 4239 'ò' => 'ò', 4240 'ó' => 'ó', 4241 'ô' => 'ô', 4242 'õ' => 'õ', 4243 'ö' => 'ö', 4244 '÷' => '÷', 4245 'ø' => 'ø', 4246 'ù' => 'ù', 4247 'ú' => 'ú', 4248 'û' => 'û', 4249 'ü' => 'ü', 4250 'ý' => 'ý', 4251 'þ' => 'þ', 4252 'ÿ' => 'ÿ', 4253 'Œ' => 'Œ', 4254 'œ' => 'œ', 4255 'Š' => 'Š', 4256 'š' => 'š', 4257 'Ÿ' => 'Ÿ', 4258 'ƒ' => 'ƒ', 4259 'ˆ' => 'ˆ', 4260 '˜' => '˜', 4261 'Α' => 'Α', 4262 'Β' => 'Β', 4263 'Γ' => 'Γ', 4264 'Δ' => 'Δ', 4265 'Ε' => 'Ε', 4266 'Ζ' => 'Ζ', 4267 'Η' => 'Η', 4268 'Θ' => 'Θ', 4269 'Ι' => 'Ι', 4270 'Κ' => 'Κ', 4271 'Λ' => 'Λ', 4272 'Μ' => 'Μ', 4273 'Ν' => 'Ν', 4274 'Ξ' => 'Ξ', 4275 'Ο' => 'Ο', 4276 'Π' => 'Π', 4277 'Ρ' => 'Ρ', 4278 'Σ' => 'Σ', 4279 'Τ' => 'Τ', 4280 'Υ' => 'Υ', 4281 'Φ' => 'Φ', 4282 'Χ' => 'Χ', 4283 'Ψ' => 'Ψ', 4284 'Ω' => 'Ω', 4285 'α' => 'α', 4286 'β' => 'β', 4287 'γ' => 'γ', 4288 'δ' => 'δ', 4289 'ε' => 'ε', 4290 'ζ' => 'ζ', 4291 'η' => 'η', 4292 'θ' => 'θ', 4293 'ι' => 'ι', 4294 'κ' => 'κ', 4295 'λ' => 'λ', 4296 'μ' => 'μ', 4297 'ν' => 'ν', 4298 'ξ' => 'ξ', 4299 'ο' => 'ο', 4300 'π' => 'π', 4301 'ρ' => 'ρ', 4302 'ς' => 'ς', 4303 'σ' => 'σ', 4304 'τ' => 'τ', 4305 'υ' => 'υ', 4306 'φ' => 'φ', 4307 'χ' => 'χ', 4308 'ψ' => 'ψ', 4309 'ω' => 'ω', 4310 'ϑ' => 'ϑ', 4311 'ϒ' => 'ϒ', 4312 'ϖ' => 'ϖ', 4313 ' ' => ' ', 4314 ' ' => ' ', 4315 ' ' => ' ', 4316 '‌' => '‌', 4317 '‍' => '‍', 4318 '‎' => '‎', 4319 '‏' => '‏', 4320 '–' => '–', 4321 '—' => '—', 4322 '‘' => '‘', 4323 '’' => '’', 4324 '‚' => '‚', 4325 '“' => '“', 4326 '”' => '”', 4327 '„' => '„', 4328 '†' => '†', 4329 '‡' => '‡', 4330 '•' => '•', 4331 '…' => '…', 4332 '‰' => '‰', 4333 '′' => '′', 4334 '″' => '″', 4335 '‹' => '‹', 4336 '›' => '›', 4337 '‾' => '‾', 4338 '⁄' => '⁄', 4339 '€' => '€', 4340 'ℑ' => 'ℑ', 4341 '℘' => '℘', 4342 'ℜ' => 'ℜ', 4343 '™' => '™', 4344 'ℵ' => 'ℵ', 4345 '↵' => '↵', 4346 '⇐' => '⇐', 4347 '⇑' => '⇑', 4348 '⇒' => '⇒', 4349 '⇓' => '⇓', 4350 '⇔' => '⇔', 4351 '∀' => '∀', 4352 '∂' => '∂', 4353 '∃' => '∃', 4354 '∅' => '∅', 4355 '∇' => '∇', 4356 '∈' => '∈', 4357 '∉' => '∉', 4358 '∋' => '∋', 4359 '∏' => '∏', 4360 '∑' => '∑', 4361 '−' => '−', 4362 '∗' => '∗', 4363 '√' => '√', 4364 '∝' => '∝', 4365 '∞' => '∞', 4366 '∠' => '∠', 4367 '∧' => '∧', 4368 '∨' => '∨', 4369 '∩' => '∩', 4370 '∪' => '∪', 4371 '∫' => '∫', 4372 '∴' => '∴', 4373 '∼' => '∼', 4374 '≅' => '≅', 4375 '≈' => '≈', 4376 '≠' => '≠', 4377 '≡' => '≡', 4378 '≤' => '≤', 4379 '≥' => '≥', 4380 '⊂' => '⊂', 4381 '⊃' => '⊃', 4382 '⊄' => '⊄', 4383 '⊆' => '⊆', 4384 '⊇' => '⊇', 4385 '⊕' => '⊕', 4386 '⊗' => '⊗', 4387 '⊥' => '⊥', 4388 '⋅' => '⋅', 4389 '⌈' => '⌈', 4390 '⌉' => '⌉', 4391 '⌊' => '⌊', 4392 '⌋' => '⌋', 4393 '⟨' => '〈', 4394 '⟩' => '〉', 4395 '←' => '←', 4396 '↑' => '↑', 4397 '→' => '→', 4398 '↓' => '↓', 4399 '↔' => '↔', 4400 '◊' => '◊', 4401 '♠' => '♠', 4402 '♣' => '♣', 4403 '♥' => '♥', 4404 '♦' => '♦', 4405 ); 4406 4407 return str_replace( array_keys( $to_ncr ), array_values( $to_ncr ), $text ); 4408 } 4409 4410 /** 4411 * Formats text for the editor. 4412 * 4413 * Generally the browsers treat everything inside a textarea as text, but 4414 * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content. 4415 * 4416 * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the 4417 * filter will be applied to an empty string. 4418 * 4419 * @since 4.3.0 4420 * 4421 * @see _WP_Editors::editor() 4422 * 4423 * @param string $text The text to be formatted. 4424 * @param string $default_editor The default editor for the current user. 4425 * It is usually either 'html' or 'tinymce'. 4426 * @return string The formatted text after filter is applied. 4427 */ 4428 function format_for_editor( $text, $default_editor = null ) { 4429 if ( $text ) { 4430 $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) ); 4431 } 4432 4433 /** 4434 * Filters the text after it is formatted for the editor. 4435 * 4436 * @since 4.3.0 4437 * 4438 * @param string $text The formatted text. 4439 * @param string $default_editor The default editor for the current user. 4440 * It is usually either 'html' or 'tinymce'. 4441 */ 4442 return apply_filters( 'format_for_editor', $text, $default_editor ); 4443 } 4444 4445 /** 4446 * Performs a deep string replace operation to ensure the values in $search are no longer present. 4447 * 4448 * Repeats the replacement operation until it no longer replaces anything to remove "nested" values 4449 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that 4450 * str_replace would return 4451 * 4452 * @since 2.8.1 4453 * @access private 4454 * 4455 * @param string|array $search The value being searched for, otherwise known as the needle. 4456 * An array may be used to designate multiple needles. 4457 * @param string $subject The string being searched and replaced on, otherwise known as the haystack. 4458 * @return string The string with the replaced values. 4459 */ 4460 function _deep_replace( $search, $subject ) { 4461 $subject = (string) $subject; 4462 4463 $count = 1; 4464 while ( $count ) { 4465 $subject = str_replace( $search, '', $subject, $count ); 4466 } 4467 4468 return $subject; 4469 } 4470 4471 /** 4472 * Escapes data for use in a MySQL query. 4473 * 4474 * Usually you should prepare queries using wpdb::prepare(). 4475 * Sometimes, spot-escaping is required or useful. One example 4476 * is preparing an array for use in an IN clause. 4477 * 4478 * NOTE: Since 4.8.3, '%' characters will be replaced with a placeholder string, 4479 * this prevents certain SQLi attacks from taking place. This change in behavior 4480 * may cause issues for code that expects the return value of esc_sql() to be usable 4481 * for other purposes. 4482 * 4483 * @since 2.8.0 4484 * 4485 * @global wpdb $wpdb WordPress database abstraction object. 4486 * 4487 * @param string|array $data Unescaped data. 4488 * @return string|array Escaped data, in the same type as supplied. 4489 */ 4490 function esc_sql( $data ) { 4491 global $wpdb; 4492 return $wpdb->_escape( $data ); 4493 } 4494 4495 /** 4496 * Checks and cleans a URL. 4497 * 4498 * A number of characters are removed from the URL. If the URL is for displaying 4499 * (the default behavior) ampersands are also replaced. The {@see 'clean_url'} filter 4500 * is applied to the returned cleaned URL. 4501 * 4502 * @since 2.8.0 4503 * @since 6.9.0 Prepends `https://` to the URL if it does not already contain a scheme 4504 * and the first item in `$protocols` is 'https'. 4505 * 4506 * @param string $url The URL to be cleaned. 4507 * @param string[] $protocols Optional. An array of acceptable protocols. 4508 * Defaults to return value of wp_allowed_protocols(). 4509 * @param string $_context Private. Use sanitize_url() for database usage. 4510 * @return string The cleaned URL after the {@see 'clean_url'} filter is applied. 4511 * An empty string is returned if `$url` specifies a protocol other than 4512 * those in `$protocols`, or if `$url` contains an empty string. 4513 */ 4514 function esc_url( $url, $protocols = null, $_context = 'display' ) { 4515 $original_url = $url; 4516 4517 if ( '' === $url ) { 4518 return $url; 4519 } 4520 4521 $url = str_replace( ' ', '%20', ltrim( $url ) ); 4522 $url = preg_replace( '|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url ); 4523 4524 if ( '' === $url ) { 4525 return $url; 4526 } 4527 4528 if ( 0 !== stripos( $url, 'mailto:' ) ) { 4529 $strip = array( '%0d', '%0a', '%0D', '%0A' ); 4530 $url = _deep_replace( $strip, $url ); 4531 } 4532 4533 $url = str_replace( ';//', '://', $url ); 4534 /* 4535 * If the URL doesn't appear to contain a scheme, we presume 4536 * it needs http:// prepended (unless it's a relative link 4537 * starting with /, # or ?, or a PHP file). If the first item 4538 * in $protocols is 'https', then https:// is prepended. 4539 */ 4540 if ( ! str_contains( $url, ':' ) && ! in_array( $url[0], array( '/', '#', '?' ), true ) && 4541 ! preg_match( '/^[a-z0-9-]+?\.php/i', $url ) 4542 ) { 4543 $scheme = ( is_array( $protocols ) && 'https' === array_first( $protocols ) ) ? 'https://' : 'http://'; 4544 $url = $scheme . $url; 4545 } 4546 4547 // Replace ampersands and single quotes only when displaying. 4548 if ( 'display' === $_context ) { 4549 $url = wp_kses_normalize_entities( $url ); 4550 $url = str_replace( '&', '&', $url ); 4551 $url = str_replace( "'", ''', $url ); 4552 } 4553 4554 if ( str_contains( $url, '[' ) || str_contains( $url, ']' ) ) { 4555 4556 $parsed = wp_parse_url( $url ); 4557 $front = ''; 4558 4559 if ( isset( $parsed['scheme'] ) ) { 4560 $front .= $parsed['scheme'] . '://'; 4561 } elseif ( '/' === $url[0] ) { 4562 $front .= '//'; 4563 } 4564 4565 if ( isset( $parsed['user'] ) ) { 4566 $front .= $parsed['user']; 4567 } 4568 4569 if ( isset( $parsed['pass'] ) ) { 4570 $front .= ':' . $parsed['pass']; 4571 } 4572 4573 if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) { 4574 $front .= '@'; 4575 } 4576 4577 if ( isset( $parsed['host'] ) ) { 4578 $front .= $parsed['host']; 4579 } 4580 4581 if ( isset( $parsed['port'] ) ) { 4582 $front .= ':' . $parsed['port']; 4583 } 4584 4585 $end_dirty = str_replace( $front, '', $url ); 4586 $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty ); 4587 $url = str_replace( $end_dirty, $end_clean, $url ); 4588 4589 } 4590 4591 if ( '/' === $url[0] ) { 4592 $good_protocol_url = $url; 4593 } else { 4594 if ( ! is_array( $protocols ) ) { 4595 $protocols = wp_allowed_protocols(); 4596 } 4597 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols ); 4598 if ( strtolower( $good_protocol_url ) !== strtolower( $url ) ) { 4599 return ''; 4600 } 4601 } 4602 4603 /** 4604 * Filters a string cleaned and escaped for output as a URL. 4605 * 4606 * @since 2.3.0 4607 * 4608 * @param string $good_protocol_url The cleaned URL to be returned. 4609 * @param string $original_url The URL prior to cleaning. 4610 * @param string $_context If 'display', replace ampersands and single quotes only. 4611 */ 4612 return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context ); 4613 } 4614 4615 /** 4616 * Sanitizes a URL for database or redirect usage. 4617 * 4618 * This function is an alias for sanitize_url(). 4619 * 4620 * @since 2.8.0 4621 * @since 6.1.0 Turned into an alias for sanitize_url(). 4622 * @since 6.9.0 Prepends `https://` to the URL if it does not already contain a scheme 4623 * and the first item in `$protocols` is 'https'. 4624 * 4625 * @see sanitize_url() 4626 * 4627 * @param string $url The URL to be cleaned. 4628 * @param string[] $protocols Optional. An array of acceptable protocols. 4629 * Defaults to return value of wp_allowed_protocols(). 4630 * @return string The cleaned URL after sanitize_url() is run. 4631 */ 4632 function esc_url_raw( $url, $protocols = null ) { 4633 return sanitize_url( $url, $protocols ); 4634 } 4635 4636 /** 4637 * Sanitizes a URL for database or redirect usage. 4638 * 4639 * @since 2.3.1 4640 * @since 2.8.0 Deprecated in favor of esc_url_raw(). 4641 * @since 5.9.0 Restored (un-deprecated). 4642 * @since 6.9.0 Prepends `https://` to the URL if it does not already contain a scheme 4643 * and the first item in `$protocols` is 'https'. 4644 * 4645 * @see esc_url() 4646 * 4647 * @param string $url The URL to be cleaned. 4648 * @param string[] $protocols Optional. An array of acceptable protocols. 4649 * Defaults to return value of wp_allowed_protocols(). 4650 * @return string The cleaned URL after esc_url() is run with the 'db' context. 4651 */ 4652 function sanitize_url( $url, $protocols = null ) { 4653 return esc_url( $url, $protocols, 'db' ); 4654 } 4655 4656 /** 4657 * Converts entities, while preserving already-encoded entities. 4658 * 4659 * @link https://www.php.net/htmlentities Borrowed from the PHP Manual user notes. 4660 * 4661 * @since 1.2.2 4662 * 4663 * @param string $text The text to be converted. 4664 * @return string Converted text. 4665 */ 4666 function htmlentities2( $text ) { 4667 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES ); 4668 4669 $translation_table[ chr( 38 ) ] = '&'; 4670 4671 return preg_replace( '/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/', '&', strtr( $text, $translation_table ) ); 4672 } 4673 4674 /** 4675 * Escapes single quotes, `"`, `<`, `>`, `&`, and fixes line endings. 4676 * 4677 * Escapes text strings for echoing in JS. It is intended to be used for inline JS 4678 * (in a tag attribute, for example `onclick="..."`). Note that the strings have to 4679 * be in single quotes. The {@see 'js_escape'} filter is also applied here. 4680 * 4681 * @since 2.8.0 4682 * 4683 * @param string $text The text to be escaped. 4684 * @return string Escaped text. 4685 */ 4686 function esc_js( $text ) { 4687 $safe_text = wp_check_invalid_utf8( $text ); 4688 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT ); 4689 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) ); 4690 $safe_text = str_replace( "\r", '', $safe_text ); 4691 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) ); 4692 /** 4693 * Filters a string cleaned and escaped for output in JavaScript. 4694 * 4695 * Text passed to esc_js() is stripped of invalid or special characters, 4696 * and properly slashed for output. 4697 * 4698 * @since 2.0.6 4699 * 4700 * @param string $safe_text The text after it has been escaped. 4701 * @param string $text The text prior to being escaped. 4702 */ 4703 return apply_filters( 'js_escape', $safe_text, $text ); 4704 } 4705 4706 /** 4707 * Escaping for HTML blocks. 4708 * 4709 * @since 2.8.0 4710 * 4711 * @param string $text 4712 * @return string Escaped text. 4713 */ 4714 function esc_html( $text ) { 4715 $safe_text = wp_check_invalid_utf8( $text ); 4716 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES ); 4717 /** 4718 * Filters a string cleaned and escaped for output in HTML. 4719 * 4720 * Text passed to esc_html() is stripped of invalid or special characters 4721 * before output. 4722 * 4723 * @since 2.8.0 4724 * 4725 * @param string $safe_text The text after it has been escaped. 4726 * @param string $text The text prior to being escaped. 4727 */ 4728 return apply_filters( 'esc_html', $safe_text, $text ); 4729 } 4730 4731 /** 4732 * Escaping for HTML attributes. 4733 * 4734 * @since 2.8.0 4735 * 4736 * @param string $text 4737 * @return string Escaped text. 4738 */ 4739 function esc_attr( $text ) { 4740 $safe_text = wp_check_invalid_utf8( $text ); 4741 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES ); 4742 /** 4743 * Filters a string cleaned and escaped for output in an HTML attribute. 4744 * 4745 * Text passed to esc_attr() is stripped of invalid or special characters 4746 * before output. 4747 * 4748 * @since 2.0.6 4749 * 4750 * @param string $safe_text The text after it has been escaped. 4751 * @param string $text The text prior to being escaped. 4752 */ 4753 return apply_filters( 'attribute_escape', $safe_text, $text ); 4754 } 4755 4756 /** 4757 * Escaping for textarea values. 4758 * 4759 * @since 3.1.0 4760 * 4761 * @param string $text 4762 * @return string Escaped text. 4763 */ 4764 function esc_textarea( $text ) { 4765 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) ); 4766 /** 4767 * Filters a string cleaned and escaped for output in a textarea element. 4768 * 4769 * @since 3.1.0 4770 * 4771 * @param string $safe_text The text after it has been escaped. 4772 * @param string $text The text prior to being escaped. 4773 */ 4774 return apply_filters( 'esc_textarea', $safe_text, $text ); 4775 } 4776 4777 /** 4778 * Escaping for XML blocks. 4779 * 4780 * @since 5.5.0 4781 * 4782 * @param string $text Text to escape. 4783 * @return string Escaped text. 4784 */ 4785 function esc_xml( $text ) { 4786 $safe_text = wp_check_invalid_utf8( $text ); 4787 4788 $cdata_regex = '\<\!\[CDATA\[.*?\]\]\>'; 4789 $regex = <<<EOF 4790 / 4791 (?=.*?{$cdata_regex}) # lookahead that will match anything followed by a CDATA Section 4792 (?<non_cdata_followed_by_cdata>(.*?)) # the "anything" matched by the lookahead 4793 (?<cdata>({$cdata_regex})) # the CDATA Section matched by the lookahead 4794 4795 | # alternative 4796 4797 (?<non_cdata>(.*)) # non-CDATA Section 4798 /sx 4799 EOF; 4800 4801 $safe_text = (string) preg_replace_callback( 4802 $regex, 4803 static function ( $matches ) { 4804 if ( ! isset( $matches[0] ) ) { 4805 return ''; 4806 } 4807 4808 if ( isset( $matches['non_cdata'] ) ) { 4809 // escape HTML entities in the non-CDATA Section. 4810 return _wp_specialchars( $matches['non_cdata'], ENT_XML1 ); 4811 } 4812 4813 // Return the CDATA Section unchanged, escape HTML entities in the rest. 4814 return _wp_specialchars( $matches['non_cdata_followed_by_cdata'], ENT_XML1 ) . $matches['cdata']; 4815 }, 4816 $safe_text 4817 ); 4818 4819 /** 4820 * Filters a string cleaned and escaped for output in XML. 4821 * 4822 * Text passed to esc_xml() is stripped of invalid or special characters 4823 * before output. HTML named character references are converted to their 4824 * equivalent code points. 4825 * 4826 * @since 5.5.0 4827 * 4828 * @param string $safe_text The text after it has been escaped. 4829 * @param string $text The text prior to being escaped. 4830 */ 4831 return apply_filters( 'esc_xml', $safe_text, $text ); 4832 } 4833 4834 /** 4835 * Escapes an HTML tag name. 4836 * 4837 * @since 2.5.0 4838 * @since 6.5.5 Allow hyphens in tag names (i.e. custom elements). 4839 * 4840 * @param string $tag_name 4841 * @return string Sanitized tag name. 4842 */ 4843 function tag_escape( $tag_name ) { 4844 $safe_tag = strtolower( preg_replace( '/[^a-zA-Z0-9-_:]/', '', $tag_name ) ); 4845 /** 4846 * Filters a string cleaned and escaped for output as an HTML tag. 4847 * 4848 * @since 2.8.0 4849 * 4850 * @param string $safe_tag The tag name after it has been escaped. 4851 * @param string $tag_name The text before it was escaped. 4852 */ 4853 return apply_filters( 'tag_escape', $safe_tag, $tag_name ); 4854 } 4855 4856 /** 4857 * Converts full URL paths to absolute paths. 4858 * 4859 * Removes the http or https protocols and the domain. Keeps the path '/' at the 4860 * beginning, so it isn't a true relative link, but from the web root base. 4861 * 4862 * @since 2.1.0 4863 * @since 4.1.0 Support was added for relative URLs. 4864 * 4865 * @param string $link Full URL path. 4866 * @return string Absolute path. 4867 */ 4868 function wp_make_link_relative( $link ) { 4869 return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link ); 4870 } 4871 4872 /** 4873 * Sanitizes various option values based on the nature of the option. 4874 * 4875 * This is basically a switch statement which will pass $value through a number 4876 * of functions depending on the $option. 4877 * 4878 * @since 2.0.5 4879 * 4880 * @global wpdb $wpdb WordPress database abstraction object. 4881 * 4882 * @param string $option The name of the option. 4883 * @param mixed $value The unsanitized value. 4884 * @return mixed Sanitized value. 4885 */ 4886 function sanitize_option( $option, $value ) { 4887 global $wpdb; 4888 4889 $original_value = $value; 4890 $error = null; 4891 4892 switch ( $option ) { 4893 case 'admin_email': 4894 case 'new_admin_email': 4895 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 4896 if ( is_wp_error( $value ) ) { 4897 $error = $value->get_error_message(); 4898 } else { 4899 $value = sanitize_email( $value ); 4900 if ( ! is_email( $value ) ) { 4901 $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ); 4902 } 4903 } 4904 break; 4905 4906 case 'thumbnail_size_w': 4907 case 'thumbnail_size_h': 4908 case 'medium_size_w': 4909 case 'medium_size_h': 4910 case 'medium_large_size_w': 4911 case 'medium_large_size_h': 4912 case 'large_size_w': 4913 case 'large_size_h': 4914 case 'mailserver_port': 4915 case 'comment_max_links': 4916 case 'page_on_front': 4917 case 'page_for_posts': 4918 case 'rss_excerpt_length': 4919 case 'default_category': 4920 case 'default_email_category': 4921 case 'default_link_category': 4922 case 'close_comments_days_old': 4923 case 'comments_per_page': 4924 case 'thread_comments_depth': 4925 case 'users_can_register': 4926 case 'start_of_week': 4927 case 'site_icon': 4928 case 'fileupload_maxk': 4929 $value = absint( $value ); 4930 break; 4931 4932 case 'posts_per_page': 4933 case 'posts_per_rss': 4934 $value = (int) $value; 4935 if ( empty( $value ) ) { 4936 $value = 1; 4937 } 4938 if ( $value < -1 ) { 4939 $value = abs( $value ); 4940 } 4941 break; 4942 4943 case 'default_ping_status': 4944 case 'default_comment_status': 4945 // Options that if not there have 0 value but need to be something like "closed". 4946 if ( '0' === (string) $value || '' === $value ) { 4947 $value = 'closed'; 4948 } 4949 break; 4950 4951 case 'blogdescription': 4952 case 'blogname': 4953 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 4954 if ( $value !== $original_value ) { 4955 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) ); 4956 } 4957 4958 if ( is_wp_error( $value ) ) { 4959 $error = $value->get_error_message(); 4960 } else { 4961 $value = esc_html( $value ); 4962 } 4963 break; 4964 4965 case 'blog_charset': 4966 if ( is_string( $value ) ) { 4967 $value = preg_replace( '/[^a-zA-Z0-9_-]/', '', $value ); // Strips slashes. 4968 } else { 4969 $value = ''; 4970 } 4971 break; 4972 4973 case 'blog_public': 4974 // This is the value if the settings checkbox is not checked on POST. Don't rely on this. 4975 if ( null === $value ) { 4976 $value = 1; 4977 } else { 4978 $value = (int) $value; 4979 } 4980 break; 4981 4982 case 'date_format': 4983 case 'time_format': 4984 case 'mailserver_url': 4985 case 'mailserver_login': 4986 case 'mailserver_pass': 4987 case 'upload_path': 4988 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 4989 if ( is_wp_error( $value ) ) { 4990 $error = $value->get_error_message(); 4991 } else { 4992 $value = strip_tags( $value ); 4993 $value = wp_kses_data( $value ); 4994 } 4995 break; 4996 4997 case 'ping_sites': 4998 $value = explode( "\n", $value ); 4999 $value = array_filter( array_map( 'trim', $value ) ); 5000 $value = array_filter( array_map( 'sanitize_url', $value ) ); 5001 $value = implode( "\n", $value ); 5002 break; 5003 5004 case 'gmt_offset': 5005 if ( is_numeric( $value ) ) { 5006 $value = preg_replace( '/[^0-9:.-]/', '', $value ); // Strips slashes. 5007 } else { 5008 $value = ''; 5009 } 5010 break; 5011 5012 case 'siteurl': 5013 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5014 if ( is_wp_error( $value ) ) { 5015 $error = $value->get_error_message(); 5016 } else { 5017 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) { 5018 $value = sanitize_url( $value ); 5019 } else { 5020 $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' ); 5021 } 5022 } 5023 break; 5024 5025 case 'home': 5026 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5027 if ( is_wp_error( $value ) ) { 5028 $error = $value->get_error_message(); 5029 } else { 5030 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) { 5031 $value = sanitize_url( $value ); 5032 } else { 5033 $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' ); 5034 } 5035 } 5036 break; 5037 5038 case 'WPLANG': 5039 $allowed = get_available_languages(); 5040 if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) { 5041 $allowed[] = WPLANG; 5042 } 5043 if ( ! in_array( $value, $allowed, true ) && ! empty( $value ) ) { 5044 $value = get_option( $option ); 5045 } 5046 break; 5047 5048 case 'illegal_names': 5049 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5050 if ( is_wp_error( $value ) ) { 5051 $error = $value->get_error_message(); 5052 } else { 5053 if ( ! is_array( $value ) ) { 5054 $value = explode( ' ', $value ); 5055 } 5056 5057 $value = array_values( array_filter( array_map( 'trim', $value ) ) ); 5058 5059 if ( ! $value ) { 5060 $value = ''; 5061 } 5062 } 5063 break; 5064 5065 case 'limited_email_domains': 5066 case 'banned_email_domains': 5067 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5068 if ( is_wp_error( $value ) ) { 5069 $error = $value->get_error_message(); 5070 } else { 5071 if ( ! is_array( $value ) ) { 5072 $value = explode( "\n", $value ); 5073 } 5074 5075 $domains = array_values( array_filter( array_map( 'trim', $value ) ) ); 5076 $value = array(); 5077 5078 foreach ( $domains as $domain ) { 5079 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) { 5080 $value[] = $domain; 5081 } 5082 } 5083 if ( ! $value ) { 5084 $value = ''; 5085 } 5086 } 5087 break; 5088 5089 case 'timezone_string': 5090 $allowed_zones = timezone_identifiers_list( DateTimeZone::ALL_WITH_BC ); 5091 if ( ! in_array( $value, $allowed_zones, true ) && ! empty( $value ) ) { 5092 $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' ); 5093 } 5094 break; 5095 5096 case 'permalink_structure': 5097 case 'category_base': 5098 case 'tag_base': 5099 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5100 if ( is_wp_error( $value ) ) { 5101 $error = $value->get_error_message(); 5102 } else { 5103 $value = sanitize_url( $value ); 5104 $value = str_replace( 'http://', '', $value ); 5105 } 5106 5107 if ( 'permalink_structure' === $option && null === $error 5108 && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value ) 5109 ) { 5110 $error = sprintf( 5111 /* translators: %s: Documentation URL. */ 5112 __( 'A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>' ), 5113 __( 'https://wordpress.org/documentation/article/customize-permalinks/#choosing-your-permalink-structure' ) 5114 ); 5115 } 5116 break; 5117 5118 case 'default_role': 5119 if ( ! get_role( $value ) && get_role( 'subscriber' ) ) { 5120 $value = 'subscriber'; 5121 } 5122 break; 5123 5124 case 'moderation_keys': 5125 case 'disallowed_keys': 5126 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5127 if ( is_wp_error( $value ) ) { 5128 $error = $value->get_error_message(); 5129 } else { 5130 $value = explode( "\n", $value ); 5131 $value = array_filter( array_map( 'trim', $value ) ); 5132 $value = array_unique( $value ); 5133 $value = implode( "\n", $value ); 5134 } 5135 break; 5136 } 5137 5138 if ( null !== $error ) { 5139 if ( '' === $error && is_wp_error( $value ) ) { 5140 /* translators: 1: Option name, 2: Error code. */ 5141 $error = sprintf( __( 'Could not sanitize the %1$s option. Error code: %2$s' ), $option, $value->get_error_code() ); 5142 } 5143 5144 $value = get_option( $option ); 5145 if ( function_exists( 'add_settings_error' ) ) { 5146 add_settings_error( $option, "invalid_{$option}", $error ); 5147 } 5148 } 5149 5150 /** 5151 * Filters an option value following sanitization. 5152 * 5153 * @since 2.3.0 5154 * @since 4.3.0 Added the `$original_value` parameter. 5155 * 5156 * @param mixed $value The sanitized option value. 5157 * @param string $option The option name. 5158 * @param mixed $original_value The original value passed to the function. 5159 */ 5160 return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value ); 5161 } 5162 5163 /** 5164 * Maps a function to all non-iterable elements of an array or an object. 5165 * 5166 * This is similar to `array_walk_recursive()` but acts upon objects too. 5167 * 5168 * @since 4.4.0 5169 * 5170 * @param mixed $value The array, object, or scalar. 5171 * @param callable $callback The function to map onto $value. 5172 * @return mixed The value with the callback applied to all non-arrays and non-objects inside it. 5173 */ 5174 function map_deep( $value, $callback ) { 5175 if ( is_array( $value ) ) { 5176 foreach ( $value as $index => $item ) { 5177 $value[ $index ] = map_deep( $item, $callback ); 5178 } 5179 } elseif ( is_object( $value ) ) { 5180 $object_vars = get_object_vars( $value ); 5181 foreach ( $object_vars as $property_name => $property_value ) { 5182 $value->$property_name = map_deep( $property_value, $callback ); 5183 } 5184 } else { 5185 $value = call_user_func( $callback, $value ); 5186 } 5187 5188 return $value; 5189 } 5190 5191 /** 5192 * Parses a string into variables to be stored in an array. 5193 * 5194 * @since 2.2.1 5195 * 5196 * @param string $input_string The string to be parsed. 5197 * @param array $result Variables will be stored in this array. 5198 */ 5199 function wp_parse_str( $input_string, &$result ) { 5200 parse_str( (string) $input_string, $result ); 5201 5202 /** 5203 * Filters the array of variables derived from a parsed string. 5204 * 5205 * @since 2.2.1 5206 * 5207 * @param array $result The array populated with variables. 5208 */ 5209 $result = apply_filters( 'wp_parse_str', $result ); 5210 } 5211 5212 /** 5213 * Converts lone less than signs. 5214 * 5215 * KSES already converts lone greater than signs. 5216 * 5217 * @since 2.3.0 5218 * 5219 * @param string $content Text to be converted. 5220 * @return string Converted text. 5221 */ 5222 function wp_pre_kses_less_than( $content ) { 5223 return preg_replace_callback( '%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $content ); 5224 } 5225 5226 /** 5227 * Callback function used by preg_replace. 5228 * 5229 * @since 2.3.0 5230 * 5231 * @param string[] $matches Populated by matches to preg_replace. 5232 * @return string The text returned after esc_html if needed. 5233 */ 5234 function wp_pre_kses_less_than_callback( $matches ) { 5235 if ( ! str_contains( $matches[0], '>' ) ) { 5236 return esc_html( $matches[0] ); 5237 } 5238 return $matches[0]; 5239 } 5240 5241 /** 5242 * Removes non-allowable HTML from parsed block attribute values when filtering 5243 * in the post context. 5244 * 5245 * @since 5.3.1 5246 * 5247 * @param string $content Content to be run through KSES. 5248 * @param array[]|string $allowed_html An array of allowed HTML elements 5249 * and attributes, or a context name 5250 * such as 'post'. 5251 * @param string[] $allowed_protocols Array of allowed URL protocols. 5252 * @return string Filtered text to run through KSES. 5253 */ 5254 function wp_pre_kses_block_attributes( $content, $allowed_html, $allowed_protocols ) { 5255 /* 5256 * `filter_block_content` is expected to call `wp_kses`. Temporarily remove 5257 * the filter to avoid recursion. 5258 */ 5259 remove_filter( 'pre_kses', 'wp_pre_kses_block_attributes', 10 ); 5260 $content = filter_block_content( $content, $allowed_html, $allowed_protocols ); 5261 add_filter( 'pre_kses', 'wp_pre_kses_block_attributes', 10, 3 ); 5262 5263 return $content; 5264 } 5265 5266 /** 5267 * WordPress' implementation of PHP sprintf() with filters. 5268 * 5269 * @since 2.5.0 5270 * @since 5.3.0 Formalized the existing and already documented `...$args` parameter 5271 * by adding it to the function signature. 5272 * 5273 * @link https://www.php.net/sprintf 5274 * 5275 * @param string $pattern The string which formatted args are inserted. 5276 * @param mixed ...$args Arguments to be formatted into the $pattern string. 5277 * @return string The formatted string. 5278 */ 5279 function wp_sprintf( $pattern, ...$args ) { 5280 $len = strlen( $pattern ); 5281 $start = 0; 5282 $result = ''; 5283 $arg_index = 0; 5284 5285 while ( $len > $start ) { 5286 // Last character: append and break. 5287 if ( strlen( $pattern ) - 1 === $start ) { 5288 $result .= substr( $pattern, -1 ); 5289 break; 5290 } 5291 5292 // Literal %: append and continue. 5293 if ( '%%' === substr( $pattern, $start, 2 ) ) { 5294 $start += 2; 5295 $result .= '%'; 5296 continue; 5297 } 5298 5299 // Get fragment before next %. 5300 $end = strpos( $pattern, '%', $start + 1 ); 5301 if ( false === $end ) { 5302 $end = $len; 5303 } 5304 $fragment = substr( $pattern, $start, $end - $start ); 5305 5306 // Fragment has a specifier. 5307 if ( '%' === $pattern[ $start ] ) { 5308 // Find numbered arguments or take the next one in order. 5309 if ( preg_match( '/^%(\d+)\$/', $fragment, $matches ) ) { 5310 $index = $matches[1] - 1; // 0-based array vs 1-based sprintf() arguments. 5311 $arg = $args[ $index ] ?? ''; 5312 $fragment = str_replace( "%{$matches[1]}$", '%', $fragment ); 5313 } else { 5314 $arg = $args[ $arg_index ] ?? ''; 5315 ++$arg_index; 5316 } 5317 5318 /** 5319 * Filters a fragment from the pattern passed to wp_sprintf(). 5320 * 5321 * If the fragment is unchanged, then sprintf() will be run on the fragment. 5322 * 5323 * @since 2.5.0 5324 * 5325 * @param string $fragment A fragment from the pattern. 5326 * @param string $arg The argument. 5327 */ 5328 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg ); 5329 5330 if ( $_fragment !== $fragment ) { 5331 $fragment = $_fragment; 5332 } else { 5333 $fragment = sprintf( $fragment, (string) $arg ); 5334 } 5335 } 5336 5337 // Append to result and move to next fragment. 5338 $result .= $fragment; 5339 $start = $end; 5340 } 5341 5342 return $result; 5343 } 5344 5345 /** 5346 * Localizes list items before the rest of the content. 5347 * 5348 * The '%l' must be at the first characters can then contain the rest of the 5349 * content. The list items will have ', ', ', and', and ' and ' added depending 5350 * on the amount of list items in the $args parameter. 5351 * 5352 * @since 2.5.0 5353 * 5354 * @param string $pattern Content containing '%l' at the beginning. 5355 * @param array $args List items to prepend to the content and replace '%l'. 5356 * @return string Localized list items and rest of the content. 5357 */ 5358 function wp_sprintf_l( $pattern, $args ) { 5359 // Not a match. 5360 if ( ! str_starts_with( $pattern, '%l' ) ) { 5361 return $pattern; 5362 } 5363 5364 // Nothing to work with. 5365 if ( empty( $args ) ) { 5366 return ''; 5367 } 5368 5369 /** 5370 * Filters the translated delimiters used by wp_sprintf_l(). 5371 * Placeholders (%s) are included to assist translators and then 5372 * removed before the array of strings reaches the filter. 5373 * 5374 * Please note: Ampersands and entities should be avoided here. 5375 * 5376 * @since 2.5.0 5377 * 5378 * @param array $delimiters An array of translated delimiters. 5379 */ 5380 $l = apply_filters( 5381 'wp_sprintf_l', 5382 array( 5383 /* translators: Used to join items in a list with more than 2 items. */ 5384 'between' => sprintf( __( '%1$s, %2$s' ), '', '' ), 5385 /* translators: Used to join last two items in a list with more than 2 times. */ 5386 'between_last_two' => sprintf( __( '%1$s, and %2$s' ), '', '' ), 5387 /* translators: Used to join items in a list with only 2 items. */ 5388 'between_only_two' => sprintf( __( '%1$s and %2$s' ), '', '' ), 5389 ) 5390 ); 5391 5392 $args = (array) $args; 5393 $result = array_shift( $args ); 5394 if ( 1 === count( $args ) ) { 5395 $result .= $l['between_only_two'] . array_shift( $args ); 5396 } 5397 5398 // Loop when more than two args. 5399 $i = count( $args ); 5400 while ( $i ) { 5401 $arg = array_shift( $args ); 5402 --$i; 5403 if ( 0 === $i ) { 5404 $result .= $l['between_last_two'] . $arg; 5405 } else { 5406 $result .= $l['between'] . $arg; 5407 } 5408 } 5409 5410 return $result . substr( $pattern, 2 ); 5411 } 5412 5413 /** 5414 * Safely extracts not more than the first $count characters from HTML string. 5415 * 5416 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT* 5417 * be counted as one character. For example & will be counted as 4, < as 5418 * 3, etc. 5419 * 5420 * @since 2.5.0 5421 * 5422 * @param string $str String to get the excerpt from. 5423 * @param int $count Maximum number of characters to take. 5424 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string. 5425 * @return string The excerpt. 5426 */ 5427 function wp_html_excerpt( $str, $count, $more = null ) { 5428 if ( null === $more ) { 5429 $more = ''; 5430 } 5431 5432 $str = wp_strip_all_tags( $str, true ); 5433 $excerpt = mb_substr( $str, 0, $count ); 5434 5435 // Remove part of an entity at the end. 5436 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt ); 5437 5438 if ( $str !== $excerpt ) { 5439 $excerpt = trim( $excerpt ) . $more; 5440 } 5441 5442 return $excerpt; 5443 } 5444 5445 /** 5446 * Adds a base URL to relative links in passed content. 5447 * 5448 * By default, this function supports the 'src' and 'href' attributes. 5449 * However, this can be modified via the `$attrs` parameter. 5450 * 5451 * @since 2.7.0 5452 * 5453 * @global string $_links_add_base 5454 * 5455 * @param string $content String to search for links in. 5456 * @param string $base The base URL to prefix to links. 5457 * @param string[] $attrs The attributes which should be processed. 5458 * @return string The processed content. 5459 */ 5460 function links_add_base_url( $content, $base, $attrs = array( 'src', 'href' ) ) { 5461 global $_links_add_base; 5462 $_links_add_base = $base; 5463 $attrs = implode( '|', (array) $attrs ); 5464 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content ); 5465 } 5466 5467 /** 5468 * Callback to add a base URL to relative links in passed content. 5469 * 5470 * @since 2.7.0 5471 * @access private 5472 * 5473 * @global string $_links_add_base 5474 * 5475 * @param string $m The matched link. 5476 * @return string The processed link. 5477 */ 5478 function _links_add_base( $m ) { 5479 global $_links_add_base; 5480 // 1 = attribute name 2 = quotation mark 3 = URL. 5481 return $m[1] . '=' . $m[2] . 5482 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols(), true ) ? 5483 $m[3] : 5484 WP_Http::make_absolute_url( $m[3], $_links_add_base ) 5485 ) 5486 . $m[2]; 5487 } 5488 5489 /** 5490 * Adds a target attribute to all links in passed content. 5491 * 5492 * By default, this function only applies to `<a>` tags. 5493 * However, this can be modified via the `$tags` parameter. 5494 * 5495 * *NOTE:* Any current target attribute will be stripped and replaced. 5496 * 5497 * @since 2.7.0 5498 * 5499 * @global string $_links_add_target 5500 * 5501 * @param string $content String to search for links in. 5502 * @param string $target The target to add to the links. 5503 * @param string[] $tags An array of tags to apply to. 5504 * @return string The processed content. 5505 */ 5506 function links_add_target( $content, $target = '_blank', $tags = array( 'a' ) ) { 5507 global $_links_add_target; 5508 $_links_add_target = $target; 5509 $tags = implode( '|', (array) $tags ); 5510 return preg_replace_callback( "!<($tags)((\s[^>]*)?)>!i", '_links_add_target', $content ); 5511 } 5512 5513 /** 5514 * Callback to add a target attribute to all links in passed content. 5515 * 5516 * @since 2.7.0 5517 * @access private 5518 * 5519 * @global string $_links_add_target 5520 * 5521 * @param string $m The matched link. 5522 * @return string The processed link. 5523 */ 5524 function _links_add_target( $m ) { 5525 global $_links_add_target; 5526 $tag = $m[1]; 5527 $link = preg_replace( '|( target=([\'"])(.*?)\2)|i', '', $m[2] ); 5528 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">'; 5529 } 5530 5531 /** 5532 * Normalizes EOL characters and strips duplicate whitespace. 5533 * 5534 * @since 2.7.0 5535 * 5536 * @param string $str The string to normalize. 5537 * @return string The normalized string. 5538 */ 5539 function normalize_whitespace( $str ) { 5540 $str = trim( $str ); 5541 $str = str_replace( "\r", "\n", $str ); 5542 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str ); 5543 return $str; 5544 } 5545 5546 /** 5547 * Properly strips all HTML tags including 'script' and 'style'. 5548 * 5549 * This differs from strip_tags() because it removes the contents of 5550 * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )` 5551 * will return 'something'. wp_strip_all_tags() will return an empty string. 5552 * 5553 * @since 2.9.0 5554 * 5555 * @param string $text String containing HTML tags 5556 * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars 5557 * @return string The processed string. 5558 */ 5559 function wp_strip_all_tags( $text, $remove_breaks = false ) { 5560 if ( is_null( $text ) ) { 5561 return ''; 5562 } 5563 5564 if ( ! is_scalar( $text ) ) { 5565 /* 5566 * To maintain consistency with pre-PHP 8 error levels, 5567 * wp_trigger_error() is used to trigger an E_USER_WARNING, 5568 * rather than _doing_it_wrong(), which triggers an E_USER_NOTICE. 5569 */ 5570 wp_trigger_error( 5571 '', 5572 sprintf( 5573 /* translators: 1: The function name, 2: The argument number, 3: The argument name, 4: The expected type, 5: The provided type. */ 5574 __( 'Warning: %1$s expects parameter %2$s (%3$s) to be a %4$s, %5$s given.' ), 5575 __FUNCTION__, 5576 '#1', 5577 '$text', 5578 'string', 5579 gettype( $text ) 5580 ), 5581 E_USER_WARNING 5582 ); 5583 5584 return ''; 5585 } 5586 5587 $text = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $text ); 5588 $text = strip_tags( $text ); 5589 5590 if ( $remove_breaks ) { 5591 $text = preg_replace( '/[\r\n\t ]+/', ' ', $text ); 5592 } 5593 5594 return trim( $text ); 5595 } 5596 5597 /** 5598 * Sanitizes a string from user input or from the database. 5599 * 5600 * - Checks for invalid UTF-8, 5601 * - Converts single `<` characters to entities 5602 * - Strips all tags 5603 * - Removes line breaks, tabs, and extra whitespace 5604 * - Strips percent-encoded characters 5605 * 5606 * @since 2.9.0 5607 * 5608 * @see sanitize_textarea_field() 5609 * @see wp_check_invalid_utf8() 5610 * @see wp_strip_all_tags() 5611 * 5612 * @param string $str String to sanitize. 5613 * @return string Sanitized string. 5614 */ 5615 function sanitize_text_field( $str ) { 5616 $filtered = _sanitize_text_fields( $str, false ); 5617 5618 /** 5619 * Filters a sanitized text field string. 5620 * 5621 * @since 2.9.0 5622 * 5623 * @param string $filtered The sanitized string. 5624 * @param string $str The string prior to being sanitized. 5625 */ 5626 return apply_filters( 'sanitize_text_field', $filtered, $str ); 5627 } 5628 5629 /** 5630 * Sanitizes a multiline string from user input or from the database. 5631 * 5632 * The function is like sanitize_text_field(), but preserves 5633 * new lines (\n) and other whitespace, which are legitimate 5634 * input in textarea elements. 5635 * 5636 * @see sanitize_text_field() 5637 * 5638 * @since 4.7.0 5639 * 5640 * @param string $str String to sanitize. 5641 * @return string Sanitized string. 5642 */ 5643 function sanitize_textarea_field( $str ) { 5644 $filtered = _sanitize_text_fields( $str, true ); 5645 5646 /** 5647 * Filters a sanitized textarea field string. 5648 * 5649 * @since 4.7.0 5650 * 5651 * @param string $filtered The sanitized string. 5652 * @param string $str The string prior to being sanitized. 5653 */ 5654 return apply_filters( 'sanitize_textarea_field', $filtered, $str ); 5655 } 5656 5657 /** 5658 * Internal helper function to sanitize a string from user input or from the database. 5659 * 5660 * @since 4.7.0 5661 * @access private 5662 * 5663 * @param string $str String to sanitize. 5664 * @param bool $keep_newlines Optional. Whether to keep newlines. Default: false. 5665 * @return string Sanitized string. 5666 */ 5667 function _sanitize_text_fields( $str, $keep_newlines = false ) { 5668 if ( is_object( $str ) || is_array( $str ) ) { 5669 return ''; 5670 } 5671 5672 $str = (string) $str; 5673 5674 $filtered = wp_check_invalid_utf8( $str ); 5675 5676 if ( str_contains( $filtered, '<' ) ) { 5677 $filtered = wp_pre_kses_less_than( $filtered ); 5678 // This will strip extra whitespace for us. 5679 $filtered = wp_strip_all_tags( $filtered, false ); 5680 5681 /* 5682 * Use HTML entities in a special case to make sure that 5683 * later newline stripping stages cannot lead to a functional tag. 5684 */ 5685 $filtered = str_replace( "<\n", "<\n", $filtered ); 5686 } 5687 5688 if ( ! $keep_newlines ) { 5689 $filtered = preg_replace( '/[\r\n\t ]+/', ' ', $filtered ); 5690 } 5691 $filtered = trim( $filtered ); 5692 5693 // Remove percent-encoded characters. 5694 $found = false; 5695 while ( preg_match( '/%[a-f0-9]{2}/i', $filtered, $match ) ) { 5696 $filtered = str_replace( $match[0], '', $filtered ); 5697 $found = true; 5698 } 5699 5700 if ( $found ) { 5701 // Strip out the whitespace that may now exist after removing percent-encoded characters. 5702 $filtered = trim( preg_replace( '/ +/', ' ', $filtered ) ); 5703 } 5704 5705 return $filtered; 5706 } 5707 5708 /** 5709 * i18n-friendly version of basename(). 5710 * 5711 * @since 3.1.0 5712 * 5713 * @param string $path A path. 5714 * @param string $suffix If the filename ends in suffix this will also be cut off. 5715 * @return string The base name of the given path. 5716 */ 5717 function wp_basename( $path, $suffix = '' ) { 5718 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) ); 5719 } 5720 5721 // phpcs:disable WordPress.WP.CapitalPDangit.MisspelledInComment,WordPress.WP.CapitalPDangit.MisspelledInText,WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid -- 8-) 5722 /** 5723 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence). 5724 * 5725 * Violating our coding standards for a good function name. 5726 * 5727 * @since 3.0.0 5728 * 5729 * @param string $text The text to be modified. 5730 * @return string The modified text. 5731 */ 5732 function capital_P_dangit( $text ) { 5733 // Simple replacement for titles. 5734 $current_filter = current_filter(); 5735 if ( 'the_title' === $current_filter || 'wp_title' === $current_filter ) { 5736 return str_replace( 'Wordpress', 'WordPress', $text ); 5737 } 5738 // Still here? Use the more judicious replacement. 5739 static $dblq = false; 5740 if ( false === $dblq ) { 5741 $dblq = _x( '“', 'opening curly double quote' ); 5742 } 5743 return str_replace( 5744 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ), 5745 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ), 5746 $text 5747 ); 5748 } 5749 // phpcs:enable 5750 5751 /** 5752 * Sanitizes a mime type 5753 * 5754 * @since 3.1.3 5755 * 5756 * @param string $mime_type Mime type. 5757 * @return string Sanitized mime type. 5758 */ 5759 function sanitize_mime_type( $mime_type ) { 5760 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type ); 5761 /** 5762 * Filters a mime type following sanitization. 5763 * 5764 * @since 3.1.3 5765 * 5766 * @param string $sani_mime_type The sanitized mime type. 5767 * @param string $mime_type The mime type prior to sanitization. 5768 */ 5769 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type ); 5770 } 5771 5772 /** 5773 * Sanitizes space or carriage return separated URLs that are used to send trackbacks. 5774 * 5775 * @since 3.4.0 5776 * 5777 * @param string $to_ping Space or carriage return separated URLs 5778 * @return string URLs starting with the http or https protocol, separated by a carriage return. 5779 */ 5780 function sanitize_trackback_urls( $to_ping ) { 5781 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY ); 5782 foreach ( $urls_to_ping as $k => $url ) { 5783 if ( ! preg_match( '#^https?://.#i', $url ) ) { 5784 unset( $urls_to_ping[ $k ] ); 5785 } 5786 } 5787 $urls_to_ping = array_map( 'sanitize_url', $urls_to_ping ); 5788 $urls_to_ping = implode( "\n", $urls_to_ping ); 5789 /** 5790 * Filters a list of trackback URLs following sanitization. 5791 * 5792 * The string returned here consists of a space or carriage return-delimited list 5793 * of trackback URLs. 5794 * 5795 * @since 3.4.0 5796 * 5797 * @param string $urls_to_ping Sanitized space or carriage return separated URLs. 5798 * @param string $to_ping Space or carriage return separated URLs before sanitization. 5799 */ 5800 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping ); 5801 } 5802 5803 /** 5804 * Adds slashes to a string or recursively adds slashes to strings within an array. 5805 * 5806 * This should be used when preparing data for core API that expects slashed data. 5807 * This should not be used to escape data going directly into an SQL query. 5808 * 5809 * @since 3.6.0 5810 * @since 5.5.0 Non-string values are left untouched. 5811 * 5812 * @param string|array $value String or array of data to slash. 5813 * @return string|array Slashed `$value`, in the same type as supplied. 5814 */ 5815 function wp_slash( $value ) { 5816 if ( is_array( $value ) ) { 5817 return array_map( 'wp_slash', $value ); 5818 } 5819 5820 if ( is_string( $value ) ) { 5821 return addslashes( $value ); 5822 } 5823 5824 return $value; 5825 } 5826 5827 /** 5828 * Removes slashes from a string or recursively removes slashes from strings within an array. 5829 * 5830 * This should be used to remove slashes from data passed to core API that 5831 * expects data to be unslashed. 5832 * 5833 * @since 3.6.0 5834 * 5835 * @param string|array $value String or array of data to unslash. 5836 * @return string|array Unslashed `$value`, in the same type as supplied. 5837 */ 5838 function wp_unslash( $value ) { 5839 return stripslashes_deep( $value ); 5840 } 5841 5842 /** 5843 * Extracts and returns the first URL from passed content. 5844 * 5845 * @since 3.6.0 5846 * 5847 * @param string $content A string which might contain an `A` element with a non-empty `href` attribute. 5848 * @return string|false Database-escaped URL via {@see esc_url()} if found, otherwise `false`. 5849 */ 5850 function get_url_in_content( $content ) { 5851 if ( empty( $content ) ) { 5852 return false; 5853 } 5854 5855 $processor = new WP_HTML_Tag_Processor( $content ); 5856 while ( $processor->next_tag( 'A' ) ) { 5857 $href = $processor->get_attribute( 'href' ); 5858 if ( is_string( $href ) && '' !== $href ) { 5859 return sanitize_url( $href ); 5860 } 5861 } 5862 5863 return false; 5864 } 5865 5866 /** 5867 * Returns the regexp for common whitespace characters. 5868 * 5869 * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp. 5870 * This is designed to replace the PCRE \s sequence. In ticket #22692, that 5871 * sequence was found to be unreliable due to random inclusion of the A0 byte. 5872 * 5873 * @since 4.0.0 5874 * 5875 * @return string The spaces regexp. 5876 */ 5877 function wp_spaces_regexp() { 5878 static $spaces = ''; 5879 5880 if ( empty( $spaces ) ) { 5881 /** 5882 * Filters the regexp for common whitespace characters. 5883 * 5884 * This string is substituted for the \s sequence as needed in regular 5885 * expressions. For websites not written in English, different characters 5886 * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0 5887 * sequence may not be in use. 5888 * 5889 * @since 4.0.0 5890 * 5891 * @param string $spaces Regexp pattern for matching common whitespace characters. 5892 */ 5893 $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' ); 5894 } 5895 5896 return $spaces; 5897 } 5898 5899 /** 5900 * Enqueues the important emoji-related styles. 5901 * 5902 * @since 6.4.0 5903 */ 5904 function wp_enqueue_emoji_styles() { 5905 // Back-compat for plugins that disable functionality by unhooking this action. 5906 $action = is_admin() ? 'admin_print_styles' : 'wp_print_styles'; 5907 if ( ! has_action( $action, 'print_emoji_styles' ) ) { 5908 return; 5909 } 5910 remove_action( $action, 'print_emoji_styles' ); 5911 5912 $emoji_styles = ' 5913 img.wp-smiley, img.emoji { 5914 display: inline !important; 5915 border: none !important; 5916 box-shadow: none !important; 5917 height: 1em !important; 5918 width: 1em !important; 5919 margin: 0 0.07em !important; 5920 vertical-align: -0.1em !important; 5921 background: none !important; 5922 padding: 0 !important; 5923 }'; 5924 $handle = 'wp-emoji-styles'; 5925 wp_register_style( $handle, false ); 5926 wp_add_inline_style( $handle, $emoji_styles ); 5927 wp_enqueue_style( $handle ); 5928 } 5929 5930 /** 5931 * Prints the inline Emoji detection script if it is not already printed. 5932 * 5933 * @since 4.2.0 5934 */ 5935 function print_emoji_detection_script(): void { 5936 static $printed = false; 5937 5938 if ( $printed ) { 5939 return; 5940 } 5941 5942 $printed = true; 5943 5944 if ( is_admin() ) { 5945 if ( did_action( 'admin_print_footer_scripts' ) ) { 5946 _print_emoji_detection_script(); 5947 } else { 5948 add_action( 'admin_print_footer_scripts', '_print_emoji_detection_script' ); 5949 } 5950 } else { 5951 if ( did_action( 'wp_print_footer_scripts' ) ) { 5952 _print_emoji_detection_script(); 5953 } else { 5954 add_action( 'wp_print_footer_scripts', '_print_emoji_detection_script' ); 5955 } 5956 } 5957 } 5958 5959 /** 5960 * Prints inline Emoji detection script. 5961 * 5962 * @ignore 5963 * @since 4.6.0 5964 * @access private 5965 */ 5966 function _print_emoji_detection_script() { 5967 $settings = array( 5968 /** 5969 * Filters the URL where emoji png images are hosted. 5970 * 5971 * @since 4.2.0 5972 * 5973 * @param string $url The emoji base URL for png images. 5974 */ 5975 'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/17.0.2/72x72/' ), 5976 5977 /** 5978 * Filters the extension of the emoji png files. 5979 * 5980 * @since 4.2.0 5981 * 5982 * @param string $extension The emoji extension for png files. Default .png. 5983 */ 5984 'ext' => apply_filters( 'emoji_ext', '.png' ), 5985 5986 /** 5987 * Filters the URL where emoji SVG images are hosted. 5988 * 5989 * @since 4.6.0 5990 * 5991 * @param string $url The emoji base URL for svg images. 5992 */ 5993 'svgUrl' => apply_filters( 'emoji_svg_url', 'https://s.w.org/images/core/emoji/17.0.2/svg/' ), 5994 5995 /** 5996 * Filters the extension of the emoji SVG files. 5997 * 5998 * @since 4.6.0 5999 * 6000 * @param string $extension The emoji extension for svg files. Default .svg. 6001 */ 6002 'svgExt' => apply_filters( 'emoji_svg_ext', '.svg' ), 6003 ); 6004 6005 $version = 'ver=' . get_bloginfo( 'version' ); 6006 6007 if ( SCRIPT_DEBUG ) { 6008 $settings['source'] = array( 6009 /** This filter is documented in wp-includes/class-wp-scripts.php */ 6010 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ), 6011 /** This filter is documented in wp-includes/class-wp-scripts.php */ 6012 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ), 6013 ); 6014 } else { 6015 $settings['source'] = array( 6016 /** This filter is documented in wp-includes/class-wp-scripts.php */ 6017 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ), 6018 ); 6019 } 6020 6021 wp_print_inline_script_tag( 6022 wp_json_encode( $settings, JSON_HEX_TAG | JSON_UNESCAPED_SLASHES ), 6023 array( 6024 'id' => 'wp-emoji-settings', 6025 'type' => 'application/json', 6026 ) 6027 ); 6028 6029 $emoji_loader_script_path = '/js/wp-emoji-loader' . wp_scripts_get_suffix() . '.js'; 6030 wp_print_inline_script_tag( 6031 rtrim( file_get_contents( ABSPATH . WPINC . $emoji_loader_script_path ) ) . "\n" . 6032 '//# sourceURL=' . esc_url_raw( includes_url( $emoji_loader_script_path ) ), 6033 array( 6034 'type' => 'module', 6035 ) 6036 ); 6037 } 6038 6039 /** 6040 * Converts emoji characters to their equivalent HTML entity. 6041 * 6042 * This allows us to store emoji in a DB using the utf8 character set. 6043 * 6044 * @since 4.2.0 6045 * 6046 * @param string $content The content to encode. 6047 * @return string The encoded content. 6048 */ 6049 function wp_encode_emoji( $content ) { 6050 $emoji = _wp_emoji_list( 'partials' ); 6051 6052 foreach ( $emoji as $emojum ) { 6053 $emoji_char = html_entity_decode( $emojum ); 6054 if ( str_contains( $content, $emoji_char ) ) { 6055 $content = preg_replace( "/$emoji_char/", $emojum, $content ); 6056 } 6057 } 6058 6059 return $content; 6060 } 6061 6062 /** 6063 * Converts emoji to a static img element. 6064 * 6065 * @since 4.2.0 6066 * 6067 * @param string $text The content to encode. 6068 * @return string The encoded content. 6069 */ 6070 function wp_staticize_emoji( $text ) { 6071 if ( ! str_contains( $text, '&#x' ) ) { 6072 if ( ( function_exists( 'mb_check_encoding' ) && mb_check_encoding( $text, 'ASCII' ) ) || ! preg_match( '/[^\x00-\x7F]/', $text ) ) { 6073 // The text doesn't contain anything that might be emoji, so we can return early. 6074 return $text; 6075 } else { 6076 $encoded_text = wp_encode_emoji( $text ); 6077 if ( $encoded_text === $text ) { 6078 return $encoded_text; 6079 } 6080 6081 $text = $encoded_text; 6082 } 6083 } 6084 6085 $emoji = _wp_emoji_list( 'entities' ); 6086 6087 // Quickly narrow down the list of emoji that might be in the text and need replacing. 6088 $possible_emoji = array(); 6089 foreach ( $emoji as $emojum ) { 6090 if ( str_contains( $text, $emojum ) ) { 6091 $possible_emoji[ $emojum ] = html_entity_decode( $emojum ); 6092 } 6093 } 6094 6095 if ( ! $possible_emoji ) { 6096 return $text; 6097 } 6098 6099 /** This filter is documented in wp-includes/formatting.php */ 6100 $cdn_url = apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/17.0.2/72x72/' ); 6101 6102 /** This filter is documented in wp-includes/formatting.php */ 6103 $ext = apply_filters( 'emoji_ext', '.png' ); 6104 6105 $output = ''; 6106 /* 6107 * HTML loop taken from smiley function, which was taken from texturize function. 6108 * It'll never be consolidated. 6109 * 6110 * First, capture the tags as well as in between. 6111 */ 6112 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); 6113 $stop = count( $textarr ); 6114 6115 // Ignore processing of specific tags. 6116 $tags_to_ignore = 'code|pre|style|script|textarea'; 6117 $ignore_block_element = ''; 6118 6119 for ( $i = 0; $i < $stop; $i++ ) { 6120 $content = $textarr[ $i ]; 6121 6122 // If we're in an ignore block, wait until we find its closing tag. 6123 if ( '' === $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) { 6124 $ignore_block_element = $matches[1]; 6125 } 6126 6127 // If it's not a tag and not in ignore block. 6128 if ( '' === $ignore_block_element && strlen( $content ) > 0 && '<' !== $content[0] && str_contains( $content, '&#x' ) ) { 6129 foreach ( $possible_emoji as $emojum => $emoji_char ) { 6130 if ( ! str_contains( $content, $emojum ) ) { 6131 continue; 6132 } 6133 6134 $file = str_replace( ';&#x', '-', $emojum ); 6135 $file = str_replace( array( '&#x', ';' ), '', $file ); 6136 6137 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $file . $ext, $emoji_char ); 6138 6139 $content = str_replace( $emojum, $entity, $content ); 6140 } 6141 } 6142 6143 // Did we exit ignore block? 6144 if ( '' !== $ignore_block_element && '</' . $ignore_block_element . '>' === $content ) { 6145 $ignore_block_element = ''; 6146 } 6147 6148 $output .= $content; 6149 } 6150 6151 // Finally, remove any stray U+FE0F characters. 6152 $output = str_replace( '️', '', $output ); 6153 6154 return $output; 6155 } 6156 6157 /** 6158 * Converts emoji in emails into static images. 6159 * 6160 * @since 4.2.0 6161 * 6162 * @param array $mail The email data array. 6163 * @return array The email data array, with emoji in the message staticized. 6164 */ 6165 function wp_staticize_emoji_for_email( $mail ) { 6166 if ( ! isset( $mail['message'] ) ) { 6167 return $mail; 6168 } 6169 6170 /* 6171 * We can only transform the emoji into images if it's a `text/html` email. 6172 * To do that, here's a cut down version of the same process that happens 6173 * in wp_mail() - get the `Content-Type` from the headers, if there is one, 6174 * then pass it through the {@see 'wp_mail_content_type'} filter, in case 6175 * a plugin is handling changing the `Content-Type`. 6176 */ 6177 $headers = array(); 6178 if ( isset( $mail['headers'] ) ) { 6179 if ( is_array( $mail['headers'] ) ) { 6180 $headers = $mail['headers']; 6181 } else { 6182 $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) ); 6183 } 6184 } 6185 6186 foreach ( $headers as $header ) { 6187 if ( ! str_contains( $header, ':' ) ) { 6188 continue; 6189 } 6190 6191 // Explode them out. 6192 list( $name, $content ) = explode( ':', trim( $header ), 2 ); 6193 6194 // Cleanup crew. 6195 $name = trim( $name ); 6196 $content = trim( $content ); 6197 6198 if ( 'content-type' === strtolower( $name ) ) { 6199 if ( str_contains( $content, ';' ) ) { 6200 list( $type, $charset ) = explode( ';', $content ); 6201 $content_type = trim( $type ); 6202 } else { 6203 $content_type = trim( $content ); 6204 } 6205 break; 6206 } 6207 } 6208 6209 // Set Content-Type if we don't have a content-type from the input headers. 6210 if ( ! isset( $content_type ) ) { 6211 $content_type = 'text/plain'; 6212 } 6213 6214 /** This filter is documented in wp-includes/pluggable.php */ 6215 $content_type = apply_filters( 'wp_mail_content_type', $content_type ); 6216 6217 if ( 'text/html' === $content_type ) { 6218 $mail['message'] = wp_staticize_emoji( $mail['message'] ); 6219 } 6220 6221 return $mail; 6222 } 6223 6224 /** 6225 * Returns arrays of emoji data. 6226 * 6227 * These arrays are automatically built from the regex in twemoji.js - if they need to be updated, 6228 * you should update the regex there, then run the `npm run grunt precommit:emoji` job. 6229 * 6230 * @since 4.9.0 6231 * @access private 6232 * 6233 * @param string $type Optional. Which array type to return. Accepts 'partials' or 'entities', default 'entities'. 6234 * @return array An array to match all emoji that WordPress recognises. 6235 */ 6236 function _wp_emoji_list( $type = 'entities' ) { 6237 // Do not remove the START/END comments - they're used to find where to insert the arrays. 6238 6239 // START: emoji arrays 6240 $entities = array( '👨🏻‍❤️‍💋‍👨🏻', '👨🏻‍❤️‍💋‍👨🏼', '👨🏻‍❤️‍💋‍👨🏽', '👨🏻‍❤️‍💋‍👨🏾', '👨🏻‍❤️‍💋‍👨🏿', '👨🏼‍❤️‍💋‍👨🏻', '👨🏼‍❤️‍💋‍👨🏼', '👨🏼‍❤️‍💋‍👨🏽', '👨🏼‍❤️‍💋‍👨🏾', '👨🏼‍❤️‍💋‍👨🏿', '👨🏽‍❤️‍💋‍👨🏻', '👨🏽‍❤️‍💋‍👨🏼', '👨🏽‍❤️‍💋‍👨🏽', '👨🏽‍❤️‍💋‍👨🏾', '👨🏽‍❤️‍💋‍👨🏿', '👨🏾‍❤️‍💋‍👨🏻', '👨🏾‍❤️‍💋‍👨🏼', '👨🏾‍❤️‍💋‍👨🏽', '👨🏾‍❤️‍💋‍👨🏾', '👨🏾‍❤️‍💋‍👨🏿', '👨🏿‍❤️‍💋‍👨🏻', '👨🏿‍❤️‍💋‍👨🏼', '👨🏿‍❤️‍💋‍👨🏽', '👨🏿‍❤️‍💋‍👨🏾', '👨🏿‍❤️‍💋‍👨🏿', '👩🏻‍❤️‍💋‍👨🏻', '👩🏻‍❤️‍💋‍👨🏼', '👩🏻‍❤️‍💋‍👨🏽', '👩🏻‍❤️‍💋‍👨🏾', '👩🏻‍❤️‍💋‍👨🏿', '👩🏻‍❤️‍💋‍👩🏻', '👩🏻‍❤️‍💋‍👩🏼', '👩🏻‍❤️‍💋‍👩🏽', '👩🏻‍❤️‍💋‍👩🏾', '👩🏻‍❤️‍💋‍👩🏿', '👩🏼‍❤️‍💋‍👨🏻', '👩🏼‍❤️‍💋‍👨🏼', '👩🏼‍❤️‍💋‍👨🏽', '👩🏼‍❤️‍💋‍👨🏾', '👩🏼‍❤️‍💋‍👨🏿', '👩🏼‍❤️‍💋‍👩🏻', '👩🏼‍❤️‍💋‍👩🏼', '👩🏼‍❤️‍💋‍👩🏽', '👩🏼‍❤️‍💋‍👩🏾', '👩🏼‍❤️‍💋‍👩🏿', '👩🏽‍❤️‍💋‍👨🏻', '👩🏽‍❤️‍💋‍👨🏼', '👩🏽‍❤️‍💋‍👨🏽', '👩🏽‍❤️‍💋‍👨🏾', '👩🏽‍❤️‍💋‍👨🏿', '👩🏽‍❤️‍💋‍👩🏻', '👩🏽‍❤️‍💋‍👩🏼', '👩🏽‍❤️‍💋‍👩🏽', '👩🏽‍❤️‍💋‍👩🏾', '👩🏽‍❤️‍💋‍👩🏿', '👩🏾‍❤️‍💋‍👨🏻', '👩🏾‍❤️‍💋‍👨🏼', '👩🏾‍❤️‍💋‍👨🏽', '👩🏾‍❤️‍💋‍👨🏾', '👩🏾‍❤️‍💋‍👨🏿', '👩🏾‍❤️‍💋‍👩🏻', '👩🏾‍❤️‍💋‍👩🏼', '👩🏾‍❤️‍💋‍👩🏽', '👩🏾‍❤️‍💋‍👩🏾', '👩🏾‍❤️‍💋‍👩🏿', '👩🏿‍❤️‍💋‍👨🏻', '👩🏿‍❤️‍💋‍👨🏼', '👩🏿‍❤️‍💋‍👨🏽', '👩🏿‍❤️‍💋‍👨🏾', '👩🏿‍❤️‍💋‍👨🏿', '👩🏿‍❤️‍💋‍👩🏻', '👩🏿‍❤️‍💋‍👩🏼', '👩🏿‍❤️‍💋‍👩🏽', '👩🏿‍❤️‍💋‍👩🏾', '👩🏿‍❤️‍💋‍👩🏿', '🧑🏻‍❤️‍💋‍🧑🏼', '🧑🏻‍❤️‍💋‍🧑🏽', '🧑🏻‍❤️‍💋‍🧑🏾', '🧑🏻‍❤️‍💋‍🧑🏿', '🧑🏼‍❤️‍💋‍🧑🏻', '🧑🏼‍❤️‍💋‍🧑🏽', '🧑🏼‍❤️‍💋‍🧑🏾', '🧑🏼‍❤️‍💋‍🧑🏿', '🧑🏽‍❤️‍💋‍🧑🏻', '🧑🏽‍❤️‍💋‍🧑🏼', '🧑🏽‍❤️‍💋‍🧑🏾', '🧑🏽‍❤️‍💋‍🧑🏿', '🧑🏾‍❤️‍💋‍🧑🏻', '🧑🏾‍❤️‍💋‍🧑🏼', '🧑🏾‍❤️‍💋‍🧑🏽', '🧑🏾‍❤️‍💋‍🧑🏿', '🧑🏿‍❤️‍💋‍🧑🏻', '🧑🏿‍❤️‍💋‍🧑🏼', '🧑🏿‍❤️‍💋‍🧑🏽', '🧑🏿‍❤️‍💋‍🧑🏾', '👨🏻‍❤️‍👨🏻', '👨🏻‍❤️‍👨🏼', '👨🏻‍❤️‍👨🏽', '👨🏻‍❤️‍👨🏾', '👨🏻‍❤️‍👨🏿', '👨🏼‍❤️‍👨🏻', '👨🏼‍❤️‍👨🏼', '👨🏼‍❤️‍👨🏽', '👨🏼‍❤️‍👨🏾', '👨🏼‍❤️‍👨🏿', '👨🏽‍❤️‍👨🏻', '👨🏽‍❤️‍👨🏼', '👨🏽‍❤️‍👨🏽', '👨🏽‍❤️‍👨🏾', '👨🏽‍❤️‍👨🏿', '👨🏾‍❤️‍👨🏻', '👨🏾‍❤️‍👨🏼', '👨🏾‍❤️‍👨🏽', '👨🏾‍❤️‍👨🏾', '👨🏾‍❤️‍👨🏿', '👨🏿‍❤️‍👨🏻', '👨🏿‍❤️‍👨🏼', '👨🏿‍❤️‍👨🏽', '👨🏿‍❤️‍👨🏾', '👨🏿‍❤️‍👨🏿', '👩🏻‍❤️‍👨🏻', '👩🏻‍❤️‍👨🏼', '👩🏻‍❤️‍👨🏽', '👩🏻‍❤️‍👨🏾', '👩🏻‍❤️‍👨🏿', '👩🏻‍❤️‍👩🏻', '👩🏻‍❤️‍👩🏼', '👩🏻‍❤️‍👩🏽', '👩🏻‍❤️‍👩🏾', '👩🏻‍❤️‍👩🏿', '👩🏼‍❤️‍👨🏻', '👩🏼‍❤️‍👨🏼', '👩🏼‍❤️‍👨🏽', '👩🏼‍❤️‍👨🏾', '👩🏼‍❤️‍👨🏿', '👩🏼‍❤️‍👩🏻', '👩🏼‍❤️‍👩🏼', '👩🏼‍❤️‍👩🏽', '👩🏼‍❤️‍👩🏾', '👩🏼‍❤️‍👩🏿', '👩🏽‍❤️‍👨🏻', '👩🏽‍❤️‍👨🏼', '👩🏽‍❤️‍👨🏽', '👩🏽‍❤️‍👨🏾', '👩🏽‍❤️‍👨🏿', '👩🏽‍❤️‍👩🏻', '👩🏽‍❤️‍👩🏼', '👩🏽‍❤️‍👩🏽', '👩🏽‍❤️‍👩🏾', '👩🏽‍❤️‍👩🏿', '👩🏾‍❤️‍👨🏻', '👩🏾‍❤️‍👨🏼', '👩🏾‍❤️‍👨🏽', '👩🏾‍❤️‍👨🏾', '👩🏾‍❤️‍👨🏿', '👩🏾‍❤️‍👩🏻', '👩🏾‍❤️‍👩🏼', '👩🏾‍❤️‍👩🏽', '👩🏾‍❤️‍👩🏾', '👩🏾‍❤️‍👩🏿', '👩🏿‍❤️‍👨🏻', '👩🏿‍❤️‍👨🏼', '👩🏿‍❤️‍👨🏽', '👩🏿‍❤️‍👨🏾', '👩🏿‍❤️‍👨🏿', '👩🏿‍❤️‍👩🏻', '👩🏿‍❤️‍👩🏼', '👩🏿‍❤️‍👩🏽', '👩🏿‍❤️‍👩🏾', '👩🏿‍❤️‍👩🏿', '🧑🏻‍❤️‍🧑🏼', '🧑🏻‍❤️‍🧑🏽', '🧑🏻‍❤️‍🧑🏾', '🧑🏻‍❤️‍🧑🏿', '🧑🏼‍❤️‍🧑🏻', '🧑🏼‍❤️‍🧑🏽', '🧑🏼‍❤️‍🧑🏾', '🧑🏼‍❤️‍🧑🏿', '🧑🏽‍❤️‍🧑🏻', '🧑🏽‍❤️‍🧑🏼', '🧑🏽‍❤️‍🧑🏾', '🧑🏽‍❤️‍🧑🏿', '🧑🏾‍❤️‍🧑🏻', '🧑🏾‍❤️‍🧑🏼', '🧑🏾‍❤️‍🧑🏽', '🧑🏾‍❤️‍🧑🏿', '🧑🏿‍❤️‍🧑🏻', '🧑🏿‍❤️‍🧑🏼', '🧑🏿‍❤️‍🧑🏽', '🧑🏿‍❤️‍🧑🏾', '👨‍❤️‍💋‍👨', '👩‍❤️‍💋‍👨', '👩‍❤️‍💋‍👩', '🏃🏻‍♀️‍➡️', '🏃🏻‍♂️‍➡️', '🏃🏼‍♀️‍➡️', '🏃🏼‍♂️‍➡️', '🏃🏽‍♀️‍➡️', '🏃🏽‍♂️‍➡️', '🏃🏾‍♀️‍➡️', '🏃🏾‍♂️‍➡️', '🏃🏿‍♀️‍➡️', '🏃🏿‍♂️‍➡️', '🚶🏻‍♀️‍➡️', '🚶🏻‍♂️‍➡️', '🚶🏼‍♀️‍➡️', '🚶🏼‍♂️‍➡️', '🚶🏽‍♀️‍➡️', '🚶🏽‍♂️‍➡️', '🚶🏾‍♀️‍➡️', '🚶🏾‍♂️‍➡️', '🚶🏿‍♀️‍➡️', '🚶🏿‍♂️‍➡️', '🧎🏻‍♀️‍➡️', '🧎🏻‍♂️‍➡️', '🧎🏼‍♀️‍➡️', '🧎🏼‍♂️‍➡️', '🧎🏽‍♀️‍➡️', '🧎🏽‍♂️‍➡️', '🧎🏾‍♀️‍➡️', '🧎🏾‍♂️‍➡️', '🧎🏿‍♀️‍➡️', '🧎🏿‍♂️‍➡️', '🏴󠁧󠁢󠁥󠁮󠁧󠁿', '🏴󠁧󠁢󠁳󠁣󠁴󠁿', '🏴󠁧󠁢󠁷󠁬󠁳󠁿', '👨🏻‍🐰‍👨🏼', '👨🏻‍🐰‍👨🏽', '👨🏻‍🐰‍👨🏾', '👨🏻‍🐰‍👨🏿', '👨🏻‍🤝‍👨🏼', '👨🏻‍🤝‍👨🏽', '👨🏻‍🤝‍👨🏾', '👨🏻‍🤝‍👨🏿', '👨🏻‍🫯‍👨🏼', '👨🏻‍🫯‍👨🏽', '👨🏻‍🫯‍👨🏾', '👨🏻‍🫯‍👨🏿', '👨🏼‍🐰‍👨🏻', '👨🏼‍🐰‍👨🏼', '👨🏼‍🐰‍👨🏽', '👨🏼‍🐰‍👨🏾', '👨🏼‍🐰‍👨🏿', '👨🏼‍🤝‍👨🏻', '👨🏼‍🤝‍👨🏽', '👨🏼‍🤝‍👨🏾', '👨🏼‍🤝‍👨🏿', '👨🏼‍🫯‍👨🏻', '👨🏼‍🫯‍👨🏽', '👨🏼‍🫯‍👨🏾', '👨🏼‍🫯‍👨🏿', '👨🏽‍🐰‍👨🏻', '👨🏽‍🐰‍👨🏼', '👨🏽‍🐰‍👨🏾', '👨🏽‍🐰‍👨🏿', '👨🏽‍🤝‍👨🏻', '👨🏽‍🤝‍👨🏼', '👨🏽‍🤝‍👨🏾', '👨🏽‍🤝‍👨🏿', '👨🏽‍🫯‍👨🏻', '👨🏽‍🫯‍👨🏼', '👨🏽‍🫯‍👨🏾', '👨🏽‍🫯‍👨🏿', '👨🏾‍🐰‍👨🏻', '👨🏾‍🐰‍👨🏼', '👨🏾‍🐰‍👨🏽', '👨🏾‍🐰‍👨🏿', '👨🏾‍🤝‍👨🏻', '👨🏾‍🤝‍👨🏼', '👨🏾‍🤝‍👨🏽', '👨🏾‍🤝‍👨🏿', '👨🏾‍🫯‍👨🏻', '👨🏾‍🫯‍👨🏼', '👨🏾‍🫯‍👨🏽', '👨🏾‍🫯‍👨🏿', '👨🏿‍🐰‍👨🏻', '👨🏿‍🐰‍👨🏼', '👨🏿‍🐰‍👨🏽', '👨🏿‍🐰‍👨🏾', '👨🏿‍🤝‍👨🏻', '👨🏿‍🤝‍👨🏼', '👨🏿‍🤝‍👨🏽', '👨🏿‍🤝‍👨🏾', '👨🏿‍🫯‍👨🏻', '👨🏿‍🫯‍👨🏼', '👨🏿‍🫯‍👨🏽', '👨🏿‍🫯‍👨🏾', '👩🏻‍🐰‍👩🏼', '👩🏻‍🐰‍👩🏽', '👩🏻‍🐰‍👩🏾', '👩🏻‍🐰‍👩🏿', '👩🏻‍🤝‍👨🏼', '👩🏻‍🤝‍👨🏽', '👩🏻‍🤝‍👨🏾', '👩🏻‍🤝‍👨🏿', '👩🏻‍🤝‍👩🏼', '👩🏻‍🤝‍👩🏽', '👩🏻‍🤝‍👩🏾', '👩🏻‍🤝‍👩🏿', '👩🏻‍🫯‍👩🏼', '👩🏻‍🫯‍👩🏽', '👩🏻‍🫯‍👩🏾', '👩🏻‍🫯‍👩🏿', '👩🏼‍🐰‍👩🏻', '👩🏼‍🐰‍👩🏽', '👩🏼‍🐰‍👩🏾', '👩🏼‍🐰‍👩🏿', '👩🏼‍🤝‍👨🏻', '👩🏼‍🤝‍👨🏽', '👩🏼‍🤝‍👨🏾', '👩🏼‍🤝‍👨🏿', '👩🏼‍🤝‍👩🏻', '👩🏼‍🤝‍👩🏽', '👩🏼‍🤝‍👩🏾', '👩🏼‍🤝‍👩🏿', '👩🏼‍🫯‍👩🏻', '👩🏼‍🫯‍👩🏽', '👩🏼‍🫯‍👩🏾', '👩🏼‍🫯‍👩🏿', '👩🏽‍🐰‍👩🏻', '👩🏽‍🐰‍👩🏼', '👩🏽‍🐰‍👩🏾', '👩🏽‍🐰‍👩🏿', '👩🏽‍🤝‍👨🏻', '👩🏽‍🤝‍👨🏼', '👩🏽‍🤝‍👨🏾', '👩🏽‍🤝‍👨🏿', '👩🏽‍🤝‍👩🏻', '👩🏽‍🤝‍👩🏼', '👩🏽‍🤝‍👩🏾', '👩🏽‍🤝‍👩🏿', '👩🏽‍🫯‍👩🏻', '👩🏽‍🫯‍👩🏼', '👩🏽‍🫯‍👩🏾', '👩🏽‍🫯‍👩🏿', '👩🏾‍🐰‍👩🏻', '👩🏾‍🐰‍👩🏼', '👩🏾‍🐰‍👩🏽', '👩🏾‍🐰‍👩🏿', '👩🏾‍🤝‍👨🏻', '👩🏾‍🤝‍👨🏼', '👩🏾‍🤝‍👨🏽', '👩🏾‍🤝‍👨🏿', '👩🏾‍🤝‍👩🏻', '👩🏾‍🤝‍👩🏼', '👩🏾‍🤝‍👩🏽', '👩🏾‍🤝‍👩🏿', '👩🏾‍🫯‍👩🏻', '👩🏾‍🫯‍👩🏼', '👩🏾‍🫯‍👩🏽', '👩🏾‍🫯‍👩🏿', '👩🏿‍🐰‍👩🏻', '👩🏿‍🐰‍👩🏼', '👩🏿‍🐰‍👩🏽', '👩🏿‍🐰‍👩🏾', '👩🏿‍🤝‍👨🏻', '👩🏿‍🤝‍👨🏼', '👩🏿‍🤝‍👨🏽', '👩🏿‍🤝‍👨🏾', '👩🏿‍🤝‍👩🏻', '👩🏿‍🤝‍👩🏼', '👩🏿‍🤝‍👩🏽', '👩🏿‍🤝‍👩🏾', '👩🏿‍🫯‍👩🏻', '👩🏿‍🫯‍👩🏼', '👩🏿‍🫯‍👩🏽', '👩🏿‍🫯‍👩🏾', '🧑🏻‍🐰‍🧑🏼', '🧑🏻‍🐰‍🧑🏽', '🧑🏻‍🐰‍🧑🏾', '🧑🏻‍🐰‍🧑🏿', '🧑🏻‍🤝‍🧑🏻', '🧑🏻‍🤝‍🧑🏼', '🧑🏻‍🤝‍🧑🏽', '🧑🏻‍🤝‍🧑🏾', '🧑🏻‍🤝‍🧑🏿', '🧑🏻‍🫯‍🧑🏼', '🧑🏻‍🫯‍🧑🏽', '🧑🏻‍🫯‍🧑🏾', '🧑🏻‍🫯‍🧑🏿', '🧑🏼‍🐰‍🧑🏻', '🧑🏼‍🐰‍🧑🏽', '🧑🏼‍🐰‍🧑🏾', '🧑🏼‍🐰‍🧑🏿', '🧑🏼‍🤝‍🧑🏻', '🧑🏼‍🤝‍🧑🏼', '🧑🏼‍🤝‍🧑🏽', '🧑🏼‍🤝‍🧑🏾', '🧑🏼‍🤝‍🧑🏿', '🧑🏼‍🫯‍🧑🏻', '🧑🏼‍🫯‍🧑🏽', '🧑🏼‍🫯‍🧑🏾', '🧑🏼‍🫯‍🧑🏿', '🧑🏽‍🐰‍🧑🏻', '🧑🏽‍🐰‍🧑🏼', '🧑🏽‍🐰‍🧑🏾', '🧑🏽‍🐰‍🧑🏿', '🧑🏽‍🤝‍🧑🏻', '🧑🏽‍🤝‍🧑🏼', '🧑🏽‍🤝‍🧑🏽', '🧑🏽‍🤝‍🧑🏾', '🧑🏽‍🤝‍🧑🏿', '🧑🏽‍🫯‍🧑🏻', '🧑🏽‍🫯‍🧑🏼', '🧑🏽‍🫯‍🧑🏾', '🧑🏽‍🫯‍🧑🏿', '🧑🏾‍🐰‍🧑🏻', '🧑🏾‍🐰‍🧑🏼', '🧑🏾‍🐰‍🧑🏽', '🧑🏾‍🐰‍🧑🏿', '🧑🏾‍🤝‍🧑🏻', '🧑🏾‍🤝‍🧑🏼', '🧑🏾‍🤝‍🧑🏽', '🧑🏾‍🤝‍🧑🏾', '🧑🏾‍🤝‍🧑🏿', '🧑🏾‍🫯‍🧑🏻', '🧑🏾‍🫯‍🧑🏼', '🧑🏾‍🫯‍🧑🏽', '🧑🏾‍🫯‍🧑🏿', '🧑🏿‍🐰‍🧑🏻', '🧑🏿‍🐰‍🧑🏼', '🧑🏿‍🐰‍🧑🏽', '🧑🏿‍🐰‍🧑🏾', '🧑🏿‍🤝‍🧑🏻', '🧑🏿‍🤝‍🧑🏼', '🧑🏿‍🤝‍🧑🏽', '🧑🏿‍🤝‍🧑🏾', '🧑🏿‍🤝‍🧑🏿', '🧑🏿‍🫯‍🧑🏻', '🧑🏿‍🫯‍🧑🏼', '🧑🏿‍🫯‍🧑🏽', '🧑🏿‍🫯‍🧑🏾', '👨‍👨‍👦‍👦', '👨‍👨‍👧‍👦', '👨‍👨‍👧‍👧', '👨‍👩‍👦‍👦', '👨‍👩‍👧‍👦', '👨‍👩‍👧‍👧', '👩‍👩‍👦‍👦', '👩‍👩‍👧‍👦', '👩‍👩‍👧‍👧', '🧑‍🧑‍🧒‍🧒', '👨🏻‍🦯‍➡️', '👨🏻‍🦼‍➡️', '👨🏻‍🦽‍➡️', '👨🏼‍🦯‍➡️', '👨🏼‍🦼‍➡️', '👨🏼‍🦽‍➡️', '👨🏽‍🦯‍➡️', '👨🏽‍🦼‍➡️', '👨🏽‍🦽‍➡️', '👨🏾‍🦯‍➡️', '👨🏾‍🦼‍➡️', '👨🏾‍🦽‍➡️', '👨🏿‍🦯‍➡️', '👨🏿‍🦼‍➡️', '👨🏿‍🦽‍➡️', '👩🏻‍🦯‍➡️', '👩🏻‍🦼‍➡️', '👩🏻‍🦽‍➡️', '👩🏼‍🦯‍➡️', '👩🏼‍🦼‍➡️', '👩🏼‍🦽‍➡️', '👩🏽‍🦯‍➡️', '👩🏽‍🦼‍➡️', '👩🏽‍🦽‍➡️', '👩🏾‍🦯‍➡️', '👩🏾‍🦼‍➡️', '👩🏾‍🦽‍➡️', '👩🏿‍🦯‍➡️', '👩🏿‍🦼‍➡️', '👩🏿‍🦽‍➡️', '🧑🏻‍🦯‍➡️', '🧑🏻‍🦼‍➡️', '🧑🏻‍🦽‍➡️', '🧑🏼‍🦯‍➡️', '🧑🏼‍🦼‍➡️', '🧑🏼‍🦽‍➡️', '🧑🏽‍🦯‍➡️', '🧑🏽‍🦼‍➡️', '🧑🏽‍🦽‍➡️', '🧑🏾‍🦯‍➡️', '🧑🏾‍🦼‍➡️', '🧑🏾‍🦽‍➡️', '🧑🏿‍🦯‍➡️', '🧑🏿‍🦼‍➡️', '🧑🏿‍🦽‍➡️', '🏃‍♀️‍➡️', '🏃‍♂️‍➡️', '🚶‍♀️‍➡️', '🚶‍♂️‍➡️', '🧎‍♀️‍➡️', '🧎‍♂️‍➡️', '👨‍🦯‍➡️', '👨‍🦼‍➡️', '👨‍🦽‍➡️', '👨‍❤️‍👨', '👩‍🦯‍➡️', '👩‍🦼‍➡️', '👩‍🦽‍➡️', '👩‍❤️‍👨', '👩‍❤️‍👩', '🧑‍🦯‍➡️', '🧑‍🦼‍➡️', '🧑‍🦽‍➡️', '🫱🏻‍🫲🏼', '🫱🏻‍🫲🏽', '🫱🏻‍🫲🏾', '🫱🏻‍🫲🏿', '🫱🏼‍🫲🏻', '🫱🏼‍🫲🏽', '🫱🏼‍🫲🏾', '🫱🏼‍🫲🏿', '🫱🏽‍🫲🏻', '🫱🏽‍🫲🏼', '🫱🏽‍🫲🏾', '🫱🏽‍🫲🏿', '🫱🏾‍🫲🏻', '🫱🏾‍🫲🏼', '🫱🏾‍🫲🏽', '🫱🏾‍🫲🏿', '🫱🏿‍🫲🏻', '🫱🏿‍🫲🏼', '🫱🏿‍🫲🏽', '🫱🏿‍🫲🏾', '👨‍👦‍👦', '👨‍👧‍👦', '👨‍👧‍👧', '👨‍👨‍👦', '👨‍👨‍👧', '👨‍👩‍👦', '👨‍👩‍👧', '👩‍👦‍👦', '👩‍👧‍👦', '👩‍👧‍👧', '👩‍👩‍👦', '👩‍👩‍👧', '🧑‍🤝‍🧑', '🧑‍🧑‍🧒', '🧑‍🧒‍🧒', '🏃🏻‍♀️', '🏃🏻‍♂️', '🏃🏻‍➡️', '🏃🏼‍♀️', '🏃🏼‍♂️', '🏃🏼‍➡️', '🏃🏽‍♀️', '🏃🏽‍♂️', '🏃🏽‍➡️', '🏃🏾‍♀️', '🏃🏾‍♂️', '🏃🏾‍➡️', '🏃🏿‍♀️', '🏃🏿‍♂️', '🏃🏿‍➡️', '🏄🏻‍♀️', '🏄🏻‍♂️', '🏄🏼‍♀️', '🏄🏼‍♂️', '🏄🏽‍♀️', '🏄🏽‍♂️', '🏄🏾‍♀️', '🏄🏾‍♂️', '🏄🏿‍♀️', '🏄🏿‍♂️', '🏊🏻‍♀️', '🏊🏻‍♂️', '🏊🏼‍♀️', '🏊🏼‍♂️', '🏊🏽‍♀️', '🏊🏽‍♂️', '🏊🏾‍♀️', '🏊🏾‍♂️', '🏊🏿‍♀️', '🏊🏿‍♂️', '🏋🏻‍♀️', '🏋🏻‍♂️', '🏋🏼‍♀️', '🏋🏼‍♂️', '🏋🏽‍♀️', '🏋🏽‍♂️', '🏋🏾‍♀️', '🏋🏾‍♂️', '🏋🏿‍♀️', '🏋🏿‍♂️', '🏌🏻‍♀️', '🏌🏻‍♂️', '🏌🏼‍♀️', '🏌🏼‍♂️', '🏌🏽‍♀️', '🏌🏽‍♂️', '🏌🏾‍♀️', '🏌🏾‍♂️', '🏌🏿‍♀️', '🏌🏿‍♂️', '👨🏻‍⚕️', '👨🏻‍⚖️', '👨🏻‍✈️', '👨🏼‍⚕️', '👨🏼‍⚖️', '👨🏼‍✈️', '👨🏽‍⚕️', '👨🏽‍⚖️', '👨🏽‍✈️', '👨🏾‍⚕️', '👨🏾‍⚖️', '👨🏾‍✈️', '👨🏿‍⚕️', '👨🏿‍⚖️', '👨🏿‍✈️', '👩🏻‍⚕️', '👩🏻‍⚖️', '👩🏻‍✈️', '👩🏼‍⚕️', '👩🏼‍⚖️', '👩🏼‍✈️', '👩🏽‍⚕️', '👩🏽‍⚖️', '👩🏽‍✈️', '👩🏾‍⚕️', '👩🏾‍⚖️', '👩🏾‍✈️', '👩🏿‍⚕️', '👩🏿‍⚖️', '👩🏿‍✈️', '👮🏻‍♀️', '👮🏻‍♂️', '👮🏼‍♀️', '👮🏼‍♂️', '👮🏽‍♀️', '👮🏽‍♂️', '👮🏾‍♀️', '👮🏾‍♂️', '👮🏿‍♀️', '👮🏿‍♂️', '👯🏻‍♀️', '👯🏻‍♂️', '👯🏼‍♀️', '👯🏼‍♂️', '👯🏽‍♀️', '👯🏽‍♂️', '👯🏾‍♀️', '👯🏾‍♂️', '👯🏿‍♀️', '👯🏿‍♂️', '👰🏻‍♀️', '👰🏻‍♂️', '👰🏼‍♀️', '👰🏼‍♂️', '👰🏽‍♀️', '👰🏽‍♂️', '👰🏾‍♀️', '👰🏾‍♂️', '👰🏿‍♀️', '👰🏿‍♂️', '👱🏻‍♀️', '👱🏻‍♂️', '👱🏼‍♀️', '👱🏼‍♂️', '👱🏽‍♀️', '👱🏽‍♂️', '👱🏾‍♀️', '👱🏾‍♂️', '👱🏿‍♀️', '👱🏿‍♂️', '👳🏻‍♀️', '👳🏻‍♂️', '👳🏼‍♀️', '👳🏼‍♂️', '👳🏽‍♀️', '👳🏽‍♂️', '👳🏾‍♀️', '👳🏾‍♂️', '👳🏿‍♀️', '👳🏿‍♂️', '👷🏻‍♀️', '👷🏻‍♂️', '👷🏼‍♀️', '👷🏼‍♂️', '👷🏽‍♀️', '👷🏽‍♂️', '👷🏾‍♀️', '👷🏾‍♂️', '👷🏿‍♀️', '👷🏿‍♂️', '💁🏻‍♀️', '💁🏻‍♂️', '💁🏼‍♀️', '💁🏼‍♂️', '💁🏽‍♀️', '💁🏽‍♂️', '💁🏾‍♀️', '💁🏾‍♂️', '💁🏿‍♀️', '💁🏿‍♂️', '💂🏻‍♀️', '💂🏻‍♂️', '💂🏼‍♀️', '💂🏼‍♂️', '💂🏽‍♀️', '💂🏽‍♂️', '💂🏾‍♀️', '💂🏾‍♂️', '💂🏿‍♀️', '💂🏿‍♂️', '💆🏻‍♀️', '💆🏻‍♂️', '💆🏼‍♀️', '💆🏼‍♂️', '💆🏽‍♀️', '💆🏽‍♂️', '💆🏾‍♀️', '💆🏾‍♂️', '💆🏿‍♀️', '💆🏿‍♂️', '💇🏻‍♀️', '💇🏻‍♂️', '💇🏼‍♀️', '💇🏼‍♂️', '💇🏽‍♀️', '💇🏽‍♂️', '💇🏾‍♀️', '💇🏾‍♂️', '💇🏿‍♀️', '💇🏿‍♂️', '🕴🏻‍♀️', '🕴🏻‍♂️', '🕴🏼‍♀️', '🕴🏼‍♂️', '🕴🏽‍♀️', '🕴🏽‍♂️', '🕴🏾‍♀️', '🕴🏾‍♂️', '🕴🏿‍♀️', '🕴🏿‍♂️', '🕵🏻‍♀️', '🕵🏻‍♂️', '🕵🏼‍♀️', '🕵🏼‍♂️', '🕵🏽‍♀️', '🕵🏽‍♂️', '🕵🏾‍♀️', '🕵🏾‍♂️', '🕵🏿‍♀️', '🕵🏿‍♂️', '🙅🏻‍♀️', '🙅🏻‍♂️', '🙅🏼‍♀️', '🙅🏼‍♂️', '🙅🏽‍♀️', '🙅🏽‍♂️', '🙅🏾‍♀️', '🙅🏾‍♂️', '🙅🏿‍♀️', '🙅🏿‍♂️', '🙆🏻‍♀️', '🙆🏻‍♂️', '🙆🏼‍♀️', '🙆🏼‍♂️', '🙆🏽‍♀️', '🙆🏽‍♂️', '🙆🏾‍♀️', '🙆🏾‍♂️', '🙆🏿‍♀️', '🙆🏿‍♂️', '🙇🏻‍♀️', '🙇🏻‍♂️', '🙇🏼‍♀️', '🙇🏼‍♂️', '🙇🏽‍♀️', '🙇🏽‍♂️', '🙇🏾‍♀️', '🙇🏾‍♂️', '🙇🏿‍♀️', '🙇🏿‍♂️', '🙋🏻‍♀️', '🙋🏻‍♂️', '🙋🏼‍♀️', '🙋🏼‍♂️', '🙋🏽‍♀️', '🙋🏽‍♂️', '🙋🏾‍♀️', '🙋🏾‍♂️', '🙋🏿‍♀️', '🙋🏿‍♂️', '🙍🏻‍♀️', '🙍🏻‍♂️', '🙍🏼‍♀️', '🙍🏼‍♂️', '🙍🏽‍♀️', '🙍🏽‍♂️', '🙍🏾‍♀️', '🙍🏾‍♂️', '🙍🏿‍♀️', '🙍🏿‍♂️', '🙎🏻‍♀️', '🙎🏻‍♂️', '🙎🏼‍♀️', '🙎🏼‍♂️', '🙎🏽‍♀️', '🙎🏽‍♂️', '🙎🏾‍♀️', '🙎🏾‍♂️', '🙎🏿‍♀️', '🙎🏿‍♂️', '🚣🏻‍♀️', '🚣🏻‍♂️', '🚣🏼‍♀️', '🚣🏼‍♂️', '🚣🏽‍♀️', '🚣🏽‍♂️', '🚣🏾‍♀️', '🚣🏾‍♂️', '🚣🏿‍♀️', '🚣🏿‍♂️', '🚴🏻‍♀️', '🚴🏻‍♂️', '🚴🏼‍♀️', '🚴🏼‍♂️', '🚴🏽‍♀️', '🚴🏽‍♂️', '🚴🏾‍♀️', '🚴🏾‍♂️', '🚴🏿‍♀️', '🚴🏿‍♂️', '🚵🏻‍♀️', '🚵🏻‍♂️', '🚵🏼‍♀️', '🚵🏼‍♂️', '🚵🏽‍♀️', '🚵🏽‍♂️', '🚵🏾‍♀️', '🚵🏾‍♂️', '🚵🏿‍♀️', '🚵🏿‍♂️', '🚶🏻‍♀️', '🚶🏻‍♂️', '🚶🏻‍➡️', '🚶🏼‍♀️', '🚶🏼‍♂️', '🚶🏼‍➡️', '🚶🏽‍♀️', '🚶🏽‍♂️', '🚶🏽‍➡️', '🚶🏾‍♀️', '🚶🏾‍♂️', '🚶🏾‍➡️', '🚶🏿‍♀️', '🚶🏿‍♂️', '🚶🏿‍➡️', '🤦🏻‍♀️', '🤦🏻‍♂️', '🤦🏼‍♀️', '🤦🏼‍♂️', '🤦🏽‍♀️', '🤦🏽‍♂️', '🤦🏾‍♀️', '🤦🏾‍♂️', '🤦🏿‍♀️', '🤦🏿‍♂️', '🤵🏻‍♀️', '🤵🏻‍♂️', '🤵🏼‍♀️', '🤵🏼‍♂️', '🤵🏽‍♀️', '🤵🏽‍♂️', '🤵🏾‍♀️', '🤵🏾‍♂️', '🤵🏿‍♀️', '🤵🏿‍♂️', '🤷🏻‍♀️', '🤷🏻‍♂️', '🤷🏼‍♀️', '🤷🏼‍♂️', '🤷🏽‍♀️', '🤷🏽‍♂️', '🤷🏾‍♀️', '🤷🏾‍♂️', '🤷🏿‍♀️', '🤷🏿‍♂️', '🤸🏻‍♀️', '🤸🏻‍♂️', '🤸🏼‍♀️', '🤸🏼‍♂️', '🤸🏽‍♀️', '🤸🏽‍♂️', '🤸🏾‍♀️', '🤸🏾‍♂️', '🤸🏿‍♀️', '🤸🏿‍♂️', '🤹🏻‍♀️', '🤹🏻‍♂️', '🤹🏼‍♀️', '🤹🏼‍♂️', '🤹🏽‍♀️', '🤹🏽‍♂️', '🤹🏾‍♀️', '🤹🏾‍♂️', '🤹🏿‍♀️', '🤹🏿‍♂️', '🤼🏻‍♀️', '🤼🏻‍♂️', '🤼🏼‍♀️', '🤼🏼‍♂️', '🤼🏽‍♀️', '🤼🏽‍♂️', '🤼🏾‍♀️', '🤼🏾‍♂️', '🤼🏿‍♀️', '🤼🏿‍♂️', '🤽🏻‍♀️', '🤽🏻‍♂️', '🤽🏼‍♀️', '🤽🏼‍♂️', '🤽🏽‍♀️', '🤽🏽‍♂️', '🤽🏾‍♀️', '🤽🏾‍♂️', '🤽🏿‍♀️', '🤽🏿‍♂️', '🤾🏻‍♀️', '🤾🏻‍♂️', '🤾🏼‍♀️', '🤾🏼‍♂️', '🤾🏽‍♀️', '🤾🏽‍♂️', '🤾🏾‍♀️', '🤾🏾‍♂️', '🤾🏿‍♀️', '🤾🏿‍♂️', '🦸🏻‍♀️', '🦸🏻‍♂️', '🦸🏼‍♀️', '🦸🏼‍♂️', '🦸🏽‍♀️', '🦸🏽‍♂️', '🦸🏾‍♀️', '🦸🏾‍♂️', '🦸🏿‍♀️', '🦸🏿‍♂️', '🦹🏻‍♀️', '🦹🏻‍♂️', '🦹🏼‍♀️', '🦹🏼‍♂️', '🦹🏽‍♀️', '🦹🏽‍♂️', '🦹🏾‍♀️', '🦹🏾‍♂️', '🦹🏿‍♀️', '🦹🏿‍♂️', '🧍🏻‍♀️', '🧍🏻‍♂️', '🧍🏼‍♀️', '🧍🏼‍♂️', '🧍🏽‍♀️', '🧍🏽‍♂️', '🧍🏾‍♀️', '🧍🏾‍♂️', '🧍🏿‍♀️', '🧍🏿‍♂️', '🧎🏻‍♀️', '🧎🏻‍♂️', '🧎🏻‍➡️', '🧎🏼‍♀️', '🧎🏼‍♂️', '🧎🏼‍➡️', '🧎🏽‍♀️', '🧎🏽‍♂️', '🧎🏽‍➡️', '🧎🏾‍♀️', '🧎🏾‍♂️', '🧎🏾‍➡️', '🧎🏿‍♀️', '🧎🏿‍♂️', '🧎🏿‍➡️', '🧏🏻‍♀️', '🧏🏻‍♂️', '🧏🏼‍♀️', '🧏🏼‍♂️', '🧏🏽‍♀️', '🧏🏽‍♂️', '🧏🏾‍♀️', '🧏🏾‍♂️', '🧏🏿‍♀️', '🧏🏿‍♂️', '🧑🏻‍⚕️', '🧑🏻‍⚖️', '🧑🏻‍✈️', '🧑🏼‍⚕️', '🧑🏼‍⚖️', '🧑🏼‍✈️', '🧑🏽‍⚕️', '🧑🏽‍⚖️', '🧑🏽‍✈️', '🧑🏾‍⚕️', '🧑🏾‍⚖️', '🧑🏾‍✈️', '🧑🏿‍⚕️', '🧑🏿‍⚖️', '🧑🏿‍✈️', '🧔🏻‍♀️', '🧔🏻‍♂️', '🧔🏼‍♀️', '🧔🏼‍♂️', '🧔🏽‍♀️', '🧔🏽‍♂️', '🧔🏾‍♀️', '🧔🏾‍♂️', '🧔🏿‍♀️', '🧔🏿‍♂️', '🧖🏻‍♀️', '🧖🏻‍♂️', '🧖🏼‍♀️', '🧖🏼‍♂️', '🧖🏽‍♀️', '🧖🏽‍♂️', '🧖🏾‍♀️', '🧖🏾‍♂️', '🧖🏿‍♀️', '🧖🏿‍♂️', '🧗🏻‍♀️', '🧗🏻‍♂️', '🧗🏼‍♀️', '🧗🏼‍♂️', '🧗🏽‍♀️', '🧗🏽‍♂️', '🧗🏾‍♀️', '🧗🏾‍♂️', '🧗🏿‍♀️', '🧗🏿‍♂️', '🧘🏻‍♀️', '🧘🏻‍♂️', '🧘🏼‍♀️', '🧘🏼‍♂️', '🧘🏽‍♀️', '🧘🏽‍♂️', '🧘🏾‍♀️', '🧘🏾‍♂️', '🧘🏿‍♀️', '🧘🏿‍♂️', '🧙🏻‍♀️', '🧙🏻‍♂️', '🧙🏼‍♀️', '🧙🏼‍♂️', '🧙🏽‍♀️', '🧙🏽‍♂️', '🧙🏾‍♀️', '🧙🏾‍♂️', '🧙🏿‍♀️', '🧙🏿‍♂️', '🧚🏻‍♀️', '🧚🏻‍♂️', '🧚🏼‍♀️', '🧚🏼‍♂️', '🧚🏽‍♀️', '🧚🏽‍♂️', '🧚🏾‍♀️', '🧚🏾‍♂️', '🧚🏿‍♀️', '🧚🏿‍♂️', '🧛🏻‍♀️', '🧛🏻‍♂️', '🧛🏼‍♀️', '🧛🏼‍♂️', '🧛🏽‍♀️', '🧛🏽‍♂️', '🧛🏾‍♀️', '🧛🏾‍♂️', '🧛🏿‍♀️', '🧛🏿‍♂️', '🧜🏻‍♀️', '🧜🏻‍♂️', '🧜🏼‍♀️', '🧜🏼‍♂️', '🧜🏽‍♀️', '🧜🏽‍♂️', '🧜🏾‍♀️', '🧜🏾‍♂️', '🧜🏿‍♀️', '🧜🏿‍♂️', '🧝🏻‍♀️', '🧝🏻‍♂️', '🧝🏼‍♀️', '🧝🏼‍♂️', '🧝🏽‍♀️', '🧝🏽‍♂️', '🧝🏾‍♀️', '🧝🏾‍♂️', '🧝🏿‍♀️', '🧝🏿‍♂️', '🏋️‍♀️', '🏋️‍♂️', '🏌️‍♀️', '🏌️‍♂️', '🏳️‍⚧️', '🕴️‍♀️', '🕴️‍♂️', '🕵️‍♀️', '🕵️‍♂️', '⛹🏻‍♀️', '⛹🏻‍♂️', '⛹🏼‍♀️', '⛹🏼‍♂️', '⛹🏽‍♀️', '⛹🏽‍♂️', '⛹🏾‍♀️', '⛹🏾‍♂️', '⛹🏿‍♀️', '⛹🏿‍♂️', '⛹️‍♀️', '⛹️‍♂️', '👨🏻‍🌾', '👨🏻‍🍳', '👨🏻‍🍼', '👨🏻‍🎄', '👨🏻‍🎓', '👨🏻‍🎤', '👨🏻‍🎨', '👨🏻‍🏫', '👨🏻‍🏭', '👨🏻‍💻', '👨🏻‍💼', '👨🏻‍🔧', '👨🏻‍🔬', '👨🏻‍🚀', '👨🏻‍🚒', '👨🏻‍🦯', '👨🏻‍🦰', '👨🏻‍🦱', '👨🏻‍🦲', '👨🏻‍🦳', '👨🏻‍🦼', '👨🏻‍🦽', '👨🏼‍🌾', '👨🏼‍🍳', '👨🏼‍🍼', '👨🏼‍🎄', '👨🏼‍🎓', '👨🏼‍🎤', '👨🏼‍🎨', '👨🏼‍🏫', '👨🏼‍🏭', '👨🏼‍💻', '👨🏼‍💼', '👨🏼‍🔧', '👨🏼‍🔬', '👨🏼‍🚀', '👨🏼‍🚒', '👨🏼‍🦯', '👨🏼‍🦰', '👨🏼‍🦱', '👨🏼‍🦲', '👨🏼‍🦳', '👨🏼‍🦼', '👨🏼‍🦽', '👨🏽‍🌾', '👨🏽‍🍳', '👨🏽‍🍼', '👨🏽‍🎄', '👨🏽‍🎓', '👨🏽‍🎤', '👨🏽‍🎨', '👨🏽‍🏫', '👨🏽‍🏭', '👨🏽‍💻', '👨🏽‍💼', '👨🏽‍🔧', '👨🏽‍🔬', '👨🏽‍🚀', '👨🏽‍🚒', '👨🏽‍🦯', '👨🏽‍🦰', '👨🏽‍🦱', '👨🏽‍🦲', '👨🏽‍🦳', '👨🏽‍🦼', '👨🏽‍🦽', '👨🏾‍🌾', '👨🏾‍🍳', '👨🏾‍🍼', '👨🏾‍🎄', '👨🏾‍🎓', '👨🏾‍🎤', '👨🏾‍🎨', '👨🏾‍🏫', '👨🏾‍🏭', '👨🏾‍💻', '👨🏾‍💼', '👨🏾‍🔧', '👨🏾‍🔬', '👨🏾‍🚀', '👨🏾‍🚒', '👨🏾‍🦯', '👨🏾‍🦰', '👨🏾‍🦱', '👨🏾‍🦲', '👨🏾‍🦳', '👨🏾‍🦼', '👨🏾‍🦽', '👨🏿‍🌾', '👨🏿‍🍳', '👨🏿‍🍼', '👨🏿‍🎄', '👨🏿‍🎓', '👨🏿‍🎤', '👨🏿‍🎨', '👨🏿‍🏫', '👨🏿‍🏭', '👨🏿‍💻', '👨🏿‍💼', '👨🏿‍🔧', '👨🏿‍🔬', '👨🏿‍🚀', '👨🏿‍🚒', '👨🏿‍🦯', '👨🏿‍🦰', '👨🏿‍🦱', '👨🏿‍🦲', '👨🏿‍🦳', '👨🏿‍🦼', '👨🏿‍🦽', '👩🏻‍🌾', '👩🏻‍🍳', '👩🏻‍🍼', '👩🏻‍🎄', '👩🏻‍🎓', '👩🏻‍🎤', '👩🏻‍🎨', '👩🏻‍🏫', '👩🏻‍🏭', '👩🏻‍💻', '👩🏻‍💼', '👩🏻‍🔧', '👩🏻‍🔬', '👩🏻‍🚀', '👩🏻‍🚒', '👩🏻‍🦯', '👩🏻‍🦰', '👩🏻‍🦱', '👩🏻‍🦲', '👩🏻‍🦳', '👩🏻‍🦼', '👩🏻‍🦽', '👩🏼‍🌾', '👩🏼‍🍳', '👩🏼‍🍼', '👩🏼‍🎄', '👩🏼‍🎓', '👩🏼‍🎤', '👩🏼‍🎨', '👩🏼‍🏫', '👩🏼‍🏭', '👩🏼‍💻', '👩🏼‍💼', '👩🏼‍🔧', '👩🏼‍🔬', '👩🏼‍🚀', '👩🏼‍🚒', '👩🏼‍🦯', '👩🏼‍🦰', '👩🏼‍🦱', '👩🏼‍🦲', '👩🏼‍🦳', '👩🏼‍🦼', '👩🏼‍🦽', '👩🏽‍🌾', '👩🏽‍🍳', '👩🏽‍🍼', '👩🏽‍🎄', '👩🏽‍🎓', '👩🏽‍🎤', '👩🏽‍🎨', '👩🏽‍🏫', '👩🏽‍🏭', '👩🏽‍💻', '👩🏽‍💼', '👩🏽‍🔧', '👩🏽‍🔬', '👩🏽‍🚀', '👩🏽‍🚒', '👩🏽‍🦯', '👩🏽‍🦰', '👩🏽‍🦱', '👩🏽‍🦲', '👩🏽‍🦳', '👩🏽‍🦼', '👩🏽‍🦽', '👩🏾‍🌾', '👩🏾‍🍳', '👩🏾‍🍼', '👩🏾‍🎄', '👩🏾‍🎓', '👩🏾‍🎤', '👩🏾‍🎨', '👩🏾‍🏫', '👩🏾‍🏭', '👩🏾‍💻', '👩🏾‍💼', '👩🏾‍🔧', '👩🏾‍🔬', '👩🏾‍🚀', '👩🏾‍🚒', '👩🏾‍🦯', '👩🏾‍🦰', '👩🏾‍🦱', '👩🏾‍🦲', '👩🏾‍🦳', '👩🏾‍🦼', '👩🏾‍🦽', '👩🏿‍🌾', '👩🏿‍🍳', '👩🏿‍🍼', '👩🏿‍🎄', '👩🏿‍🎓', '👩🏿‍🎤', '👩🏿‍🎨', '👩🏿‍🏫', '👩🏿‍🏭', '👩🏿‍💻', '👩🏿‍💼', '👩🏿‍🔧', '👩🏿‍🔬', '👩🏿‍🚀', '👩🏿‍🚒', '👩🏿‍🦯', '👩🏿‍🦰', '👩🏿‍🦱', '👩🏿‍🦲', '👩🏿‍🦳', '👩🏿‍🦼', '👩🏿‍🦽', '🧑🏻‍🌾', '🧑🏻‍🍳', '🧑🏻‍🍼', '🧑🏻‍🎄', '🧑🏻‍🎓', '🧑🏻‍🎤', '🧑🏻‍🎨', '🧑🏻‍🏫', '🧑🏻‍🏭', '🧑🏻‍💻', '🧑🏻‍💼', '🧑🏻‍🔧', '🧑🏻‍🔬', '🧑🏻‍🚀', '🧑🏻‍🚒', '🧑🏻‍🦯', '🧑🏻‍🦰', '🧑🏻‍🦱', '🧑🏻‍🦲', '🧑🏻‍🦳', '🧑🏻‍🦼', '🧑🏻‍🦽', '🧑🏻‍🩰', '🧑🏼‍🌾', '🧑🏼‍🍳', '🧑🏼‍🍼', '🧑🏼‍🎄', '🧑🏼‍🎓', '🧑🏼‍🎤', '🧑🏼‍🎨', '🧑🏼‍🏫', '🧑🏼‍🏭', '🧑🏼‍💻', '🧑🏼‍💼', '🧑🏼‍🔧', '🧑🏼‍🔬', '🧑🏼‍🚀', '🧑🏼‍🚒', '🧑🏼‍🦯', '🧑🏼‍🦰', '🧑🏼‍🦱', '🧑🏼‍🦲', '🧑🏼‍🦳', '🧑🏼‍🦼', '🧑🏼‍🦽', '🧑🏼‍🩰', '🧑🏽‍🌾', '🧑🏽‍🍳', '🧑🏽‍🍼', '🧑🏽‍🎄', '🧑🏽‍🎓', '🧑🏽‍🎤', '🧑🏽‍🎨', '🧑🏽‍🏫', '🧑🏽‍🏭', '🧑🏽‍💻', '🧑🏽‍💼', '🧑🏽‍🔧', '🧑🏽‍🔬', '🧑🏽‍🚀', '🧑🏽‍🚒', '🧑🏽‍🦯', '🧑🏽‍🦰', '🧑🏽‍🦱', '🧑🏽‍🦲', '🧑🏽‍🦳', '🧑🏽‍🦼', '🧑🏽‍🦽', '🧑🏽‍🩰', '🧑🏾‍🌾', '🧑🏾‍🍳', '🧑🏾‍🍼', '🧑🏾‍🎄', '🧑🏾‍🎓', '🧑🏾‍🎤', '🧑🏾‍🎨', '🧑🏾‍🏫', '🧑🏾‍🏭', '🧑🏾‍💻', '🧑🏾‍💼', '🧑🏾‍🔧', '🧑🏾‍🔬', '🧑🏾‍🚀', '🧑🏾‍🚒', '🧑🏾‍🦯', '🧑🏾‍🦰', '🧑🏾‍🦱', '🧑🏾‍🦲', '🧑🏾‍🦳', '🧑🏾‍🦼', '🧑🏾‍🦽', '🧑🏾‍🩰', '🧑🏿‍🌾', '🧑🏿‍🍳', '🧑🏿‍🍼', '🧑🏿‍🎄', '🧑🏿‍🎓', '🧑🏿‍🎤', '🧑🏿‍🎨', '🧑🏿‍🏫', '🧑🏿‍🏭', '🧑🏿‍💻', '🧑🏿‍💼', '🧑🏿‍🔧', '🧑🏿‍🔬', '🧑🏿‍🚀', '🧑🏿‍🚒', '🧑🏿‍🦯', '🧑🏿‍🦰', '🧑🏿‍🦱', '🧑🏿‍🦲', '🧑🏿‍🦳', '🧑🏿‍🦼', '🧑🏿‍🦽', '🧑🏿‍🩰', '🏳️‍🌈', '😶‍🌫️', '🏃‍♀️', '🏃‍♂️', '🏃‍➡️', '🏄‍♀️', '🏄‍♂️', '🏊‍♀️', '🏊‍♂️', '🏴‍☠️', '🐻‍❄️', '👨‍⚕️', '👨‍⚖️', '👨‍✈️', '👩‍⚕️', '👩‍⚖️', '👩‍✈️', '👮‍♀️', '👮‍♂️', '👯‍♀️', '👯‍♂️', '👰‍♀️', '👰‍♂️', '👱‍♀️', '👱‍♂️', '👳‍♀️', '👳‍♂️', '👷‍♀️', '👷‍♂️', '💁‍♀️', '💁‍♂️', '💂‍♀️', '💂‍♂️', '💆‍♀️', '💆‍♂️', '💇‍♀️', '💇‍♂️', '🙂‍↔️', '🙂‍↕️', '🙅‍♀️', '🙅‍♂️', '🙆‍♀️', '🙆‍♂️', '🙇‍♀️', '🙇‍♂️', '🙋‍♀️', '🙋‍♂️', '🙍‍♀️', '🙍‍♂️', '🙎‍♀️', '🙎‍♂️', '🚣‍♀️', '🚣‍♂️', '🚴‍♀️', '🚴‍♂️', '🚵‍♀️', '🚵‍♂️', '🚶‍♀️', '🚶‍♂️', '🚶‍➡️', '🤦‍♀️', '🤦‍♂️', '🤵‍♀️', '🤵‍♂️', '🤷‍♀️', '🤷‍♂️', '🤸‍♀️', '🤸‍♂️', '🤹‍♀️', '🤹‍♂️', '🤼‍♀️', '🤼‍♂️', '🤽‍♀️', '🤽‍♂️', '🤾‍♀️', '🤾‍♂️', '🦸‍♀️', '🦸‍♂️', '🦹‍♀️', '🦹‍♂️', '🧍‍♀️', '🧍‍♂️', '🧎‍♀️', '🧎‍♂️', '🧎‍➡️', '🧏‍♀️', '🧏‍♂️', '🧑‍⚕️', '🧑‍⚖️', '🧑‍✈️', '🧔‍♀️', '🧔‍♂️', '🧖‍♀️', '🧖‍♂️', '🧗‍♀️', '🧗‍♂️', '🧘‍♀️', '🧘‍♂️', '🧙‍♀️', '🧙‍♂️', '🧚‍♀️', '🧚‍♂️', '🧛‍♀️', '🧛‍♂️', '🧜‍♀️', '🧜‍♂️', '🧝‍♀️', '🧝‍♂️', '🧞‍♀️', '🧞‍♂️', '🧟‍♀️', '🧟‍♂️', '⛓️‍💥', '❤️‍🔥', '❤️‍🩹', '🍄‍🟫', '🍋‍🟩', '🐕‍🦺', '🐦‍🔥', '👁‍🗨', '👨‍🌾', '👨‍🍳', '👨‍🍼', '👨‍🎄', '👨‍🎓', '👨‍🎤', '👨‍🎨', '👨‍🏫', '👨‍🏭', '👨‍👦', '👨‍👧', '👨‍💻', '👨‍💼', '👨‍🔧', '👨‍🔬', '👨‍🚀', '👨‍🚒', '👨‍🦯', '👨‍🦰', '👨‍🦱', '👨‍🦲', '👨‍🦳', '👨‍🦼', '👨‍🦽', '👩‍🌾', '👩‍🍳', '👩‍🍼', '👩‍🎄', '👩‍🎓', '👩‍🎤', '👩‍🎨', '👩‍🏫', '👩‍🏭', '👩‍👦', '👩‍👧', '👩‍💻', '👩‍💼', '👩‍🔧', '👩‍🔬', '👩‍🚀', '👩‍🚒', '👩‍🦯', '👩‍🦰', '👩‍🦱', '👩‍🦲', '👩‍🦳', '👩‍🦼', '👩‍🦽', '😮‍💨', '😵‍💫', '🧑‍🌾', '🧑‍🍳', '🧑‍🍼', '🧑‍🎄', '🧑‍🎓', '🧑‍🎤', '🧑‍🎨', '🧑‍🏫', '🧑‍🏭', '🧑‍💻', '🧑‍💼', '🧑‍🔧', '🧑‍🔬', '🧑‍🚀', '🧑‍🚒', '🧑‍🦯', '🧑‍🦰', '🧑‍🦱', '🧑‍🦲', '🧑‍🦳', '🧑‍🦼', '🧑‍🦽', '🧑‍🧒', '🧑‍🩰', '🐈‍⬛', '🐦‍⬛', '🇦🇨', '🇦🇩', '🇦🇪', '🇦🇫', '🇦🇬', '🇦🇮', '🇦🇱', '🇦🇲', '🇦🇴', '🇦🇶', '🇦🇷', '🇦🇸', '🇦🇹', '🇦🇺', '🇦🇼', '🇦🇽', '🇦🇿', '🇧🇦', '🇧🇧', '🇧🇩', '🇧🇪', '🇧🇫', '🇧🇬', '🇧🇭', '🇧🇮', '🇧🇯', '🇧🇱', '🇧🇲', '🇧🇳', '🇧🇴', '🇧🇶', '🇧🇷', '🇧🇸', '🇧🇹', '🇧🇻', '🇧🇼', '🇧🇾', '🇧🇿', '🇨🇦', '🇨🇨', '🇨🇩', '🇨🇫', '🇨🇬', '🇨🇭', '🇨🇮', '🇨🇰', '🇨🇱', '🇨🇲', '🇨🇳', '🇨🇴', '🇨🇵', '🇨🇶', '🇨🇷', '🇨🇺', '🇨🇻', '🇨🇼', '🇨🇽', '🇨🇾', '🇨🇿', '🇩🇪', '🇩🇬', '🇩🇯', '🇩🇰', '🇩🇲', '🇩🇴', '🇩🇿', '🇪🇦', '🇪🇨', '🇪🇪', '🇪🇬', '🇪🇭', '🇪🇷', '🇪🇸', '🇪🇹', '🇪🇺', '🇫🇮', '🇫🇯', '🇫🇰', '🇫🇲', '🇫🇴', '🇫🇷', '🇬🇦', '🇬🇧', '🇬🇩', '🇬🇪', '🇬🇫', '🇬🇬', '🇬🇭', '🇬🇮', '🇬🇱', '🇬🇲', '🇬🇳', '🇬🇵', '🇬🇶', '🇬🇷', '🇬🇸', '🇬🇹', '🇬🇺', '🇬🇼', '🇬🇾', '🇭🇰', '🇭🇲', '🇭🇳', '🇭🇷', '🇭🇹', '🇭🇺', '🇮🇨', '🇮🇩', '🇮🇪', '🇮🇱', '🇮🇲', '🇮🇳', '🇮🇴', '🇮🇶', '🇮🇷', '🇮🇸', '🇮🇹', '🇯🇪', '🇯🇲', '🇯🇴', '🇯🇵', '🇰🇪', '🇰🇬', '🇰🇭', '🇰🇮', '🇰🇲', '🇰🇳', '🇰🇵', '🇰🇷', '🇰🇼', '🇰🇾', '🇰🇿', '🇱🇦', '🇱🇧', '🇱🇨', '🇱🇮', '🇱🇰', '🇱🇷', '🇱🇸', '🇱🇹', '🇱🇺', '🇱🇻', '🇱🇾', '🇲🇦', '🇲🇨', '🇲🇩', '🇲🇪', '🇲🇫', '🇲🇬', '🇲🇭', '🇲🇰', '🇲🇱', '🇲🇲', '🇲🇳', '🇲🇴', '🇲🇵', '🇲🇶', '🇲🇷', '🇲🇸', '🇲🇹', '🇲🇺', '🇲🇻', '🇲🇼', '🇲🇽', '🇲🇾', '🇲🇿', '🇳🇦', '🇳🇨', '🇳🇪', '🇳🇫', '🇳🇬', '🇳🇮', '🇳🇱', '🇳🇴', '🇳🇵', '🇳🇷', '🇳🇺', '🇳🇿', '🇴🇲', '🇵🇦', '🇵🇪', '🇵🇫', '🇵🇬', '🇵🇭', '🇵🇰', '🇵🇱', '🇵🇲', '🇵🇳', '🇵🇷', '🇵🇸', '🇵🇹', '🇵🇼', '🇵🇾', '🇶🇦', '🇷🇪', '🇷🇴', '🇷🇸', '🇷🇺', '🇷🇼', '🇸🇦', '🇸🇧', '🇸🇨', '🇸🇩', '🇸🇪', '🇸🇬', '🇸🇭', '🇸🇮', '🇸🇯', '🇸🇰', '🇸🇱', '🇸🇲', '🇸🇳', '🇸🇴', '🇸🇷', '🇸🇸', '🇸🇹', '🇸🇻', '🇸🇽', '🇸🇾', '🇸🇿', '🇹🇦', '🇹🇨', '🇹🇩', '🇹🇫', '🇹🇬', '🇹🇭', '🇹🇯', '🇹🇰', '🇹🇱', '🇹🇲', '🇹🇳', '🇹🇴', '🇹🇷', '🇹🇹', '🇹🇻', '🇹🇼', '🇹🇿', '🇺🇦', '🇺🇬', '🇺🇲', '🇺🇳', '🇺🇸', '🇺🇾', '🇺🇿', '🇻🇦', '🇻🇨', '🇻🇪', '🇻🇬', '🇻🇮', '🇻🇳', '🇻🇺', '🇼🇫', '🇼🇸', '🇽🇰', '🇾🇪', '🇾🇹', '🇿🇦', '🇿🇲', '🇿🇼', '🎅🏻', '🎅🏼', '🎅🏽', '🎅🏾', '🎅🏿', '🏂🏻', '🏂🏼', '🏂🏽', '🏂🏾', '🏂🏿', '🏃🏻', '🏃🏼', '🏃🏽', '🏃🏾', '🏃🏿', '🏄🏻', '🏄🏼', '🏄🏽', '🏄🏾', '🏄🏿', '🏇🏻', '🏇🏼', '🏇🏽', '🏇🏾', '🏇🏿', '🏊🏻', '🏊🏼', '🏊🏽', '🏊🏾', '🏊🏿', '🏋🏻', '🏋🏼', '🏋🏽', '🏋🏾', '🏋🏿', '🏌🏻', '🏌🏼', '🏌🏽', '🏌🏾', '🏌🏿', '👂🏻', '👂🏼', '👂🏽', '👂🏾', '👂🏿', '👃🏻', '👃🏼', '👃🏽', '👃🏾', '👃🏿', '👆🏻', '👆🏼', '👆🏽', '👆🏾', '👆🏿', '👇🏻', '👇🏼', '👇🏽', '👇🏾', '👇🏿', '👈🏻', '👈🏼', '👈🏽', '👈🏾', '👈🏿', '👉🏻', '👉🏼', '👉🏽', '👉🏾', '👉🏿', '👊🏻', '👊🏼', '👊🏽', '👊🏾', '👊🏿', '👋🏻', '👋🏼', '👋🏽', '👋🏾', '👋🏿', '👌🏻', '👌🏼', '👌🏽', '👌🏾', '👌🏿', '👍🏻', '👍🏼', '👍🏽', '👍🏾', '👍🏿', '👎🏻', '👎🏼', '👎🏽', '👎🏾', '👎🏿', '👏🏻', '👏🏼', '👏🏽', '👏🏾', '👏🏿', '👐🏻', '👐🏼', '👐🏽', '👐🏾', '👐🏿', '👦🏻', '👦🏼', '👦🏽', '👦🏾', '👦🏿', '👧🏻', '👧🏼', '👧🏽', '👧🏾', '👧🏿', '👨🏻', '👨🏼', '👨🏽', '👨🏾', '👨🏿', '👩🏻', '👩🏼', '👩🏽', '👩🏾', '👩🏿', '👫🏻', '👫🏼', '👫🏽', '👫🏾', '👫🏿', '👬🏻', '👬🏼', '👬🏽', '👬🏾', '👬🏿', '👭🏻', '👭🏼', '👭🏽', '👭🏾', '👭🏿', '👮🏻', '👮🏼', '👮🏽', '👮🏾', '👮🏿', '👯🏻', '👯🏼', '👯🏽', '👯🏾', '👯🏿', '👰🏻', '👰🏼', '👰🏽', '👰🏾', '👰🏿', '👱🏻', '👱🏼', '👱🏽', '👱🏾', '👱🏿', '👲🏻', '👲🏼', '👲🏽', '👲🏾', '👲🏿', '👳🏻', '👳🏼', '👳🏽', '👳🏾', '👳🏿', '👴🏻', '👴🏼', '👴🏽', '👴🏾', '👴🏿', '👵🏻', '👵🏼', '👵🏽', '👵🏾', '👵🏿', '👶🏻', '👶🏼', '👶🏽', '👶🏾', '👶🏿', '👷🏻', '👷🏼', '👷🏽', '👷🏾', '👷🏿', '👸🏻', '👸🏼', '👸🏽', '👸🏾', '👸🏿', '👼🏻', '👼🏼', '👼🏽', '👼🏾', '👼🏿', '💁🏻', '💁🏼', '💁🏽', '💁🏾', '💁🏿', '💂🏻', '💂🏼', '💂🏽', '💂🏾', '💂🏿', '💃🏻', '💃🏼', '💃🏽', '💃🏾', '💃🏿', '💅🏻', '💅🏼', '💅🏽', '💅🏾', '💅🏿', '💆🏻', '💆🏼', '💆🏽', '💆🏾', '💆🏿', '💇🏻', '💇🏼', '💇🏽', '💇🏾', '💇🏿', '💏🏻', '💏🏼', '💏🏽', '💏🏾', '💏🏿', '💑🏻', '💑🏼', '💑🏽', '💑🏾', '💑🏿', '💪🏻', '💪🏼', '💪🏽', '💪🏾', '💪🏿', '🕴🏻', '🕴🏼', '🕴🏽', '🕴🏾', '🕴🏿', '🕵🏻', '🕵🏼', '🕵🏽', '🕵🏾', '🕵🏿', '🕺🏻', '🕺🏼', '🕺🏽', '🕺🏾', '🕺🏿', '🖐🏻', '🖐🏼', '🖐🏽', '🖐🏾', '🖐🏿', '🖕🏻', '🖕🏼', '🖕🏽', '🖕🏾', '🖕🏿', '🖖🏻', '🖖🏼', '🖖🏽', '🖖🏾', '🖖🏿', '🙅🏻', '🙅🏼', '🙅🏽', '🙅🏾', '🙅🏿', '🙆🏻', '🙆🏼', '🙆🏽', '🙆🏾', '🙆🏿', '🙇🏻', '🙇🏼', '🙇🏽', '🙇🏾', '🙇🏿', '🙋🏻', '🙋🏼', '🙋🏽', '🙋🏾', '🙋🏿', '🙌🏻', '🙌🏼', '🙌🏽', '🙌🏾', '🙌🏿', '🙍🏻', '🙍🏼', '🙍🏽', '🙍🏾', '🙍🏿', '🙎🏻', '🙎🏼', '🙎🏽', '🙎🏾', '🙎🏿', '🙏🏻', '🙏🏼', '🙏🏽', '🙏🏾', '🙏🏿', '🚣🏻', '🚣🏼', '🚣🏽', '🚣🏾', '🚣🏿', '🚴🏻', '🚴🏼', '🚴🏽', '🚴🏾', '🚴🏿', '🚵🏻', '🚵🏼', '🚵🏽', '🚵🏾', '🚵🏿', '🚶🏻', '🚶🏼', '🚶🏽', '🚶🏾', '🚶🏿', '🛀🏻', '🛀🏼', '🛀🏽', '🛀🏾', '🛀🏿', '🛌🏻', '🛌🏼', '🛌🏽', '🛌🏾', '🛌🏿', '🤌🏻', '🤌🏼', '🤌🏽', '🤌🏾', '🤌🏿', '🤏🏻', '🤏🏼', '🤏🏽', '🤏🏾', '🤏🏿', '🤘🏻', '🤘🏼', '🤘🏽', '🤘🏾', '🤘🏿', '🤙🏻', '🤙🏼', '🤙🏽', '🤙🏾', '🤙🏿', '🤚🏻', '🤚🏼', '🤚🏽', '🤚🏾', '🤚🏿', '🤛🏻', '🤛🏼', '🤛🏽', '🤛🏾', '🤛🏿', '🤜🏻', '🤜🏼', '🤜🏽', '🤜🏾', '🤜🏿', '🤝🏻', '🤝🏼', '🤝🏽', '🤝🏾', '🤝🏿', '🤞🏻', '🤞🏼', '🤞🏽', '🤞🏾', '🤞🏿', '🤟🏻', '🤟🏼', '🤟🏽', '🤟🏾', '🤟🏿', '🤦🏻', '🤦🏼', '🤦🏽', '🤦🏾', '🤦🏿', '🤰🏻', '🤰🏼', '🤰🏽', '🤰🏾', '🤰🏿', '🤱🏻', '🤱🏼', '🤱🏽', '🤱🏾', '🤱🏿', '🤲🏻', '🤲🏼', '🤲🏽', '🤲🏾', '🤲🏿', '🤳🏻', '🤳🏼', '🤳🏽', '🤳🏾', '🤳🏿', '🤴🏻', '🤴🏼', '🤴🏽', '🤴🏾', '🤴🏿', '🤵🏻', '🤵🏼', '🤵🏽', '🤵🏾', '🤵🏿', '🤶🏻', '🤶🏼', '🤶🏽', '🤶🏾', '🤶🏿', '🤷🏻', '🤷🏼', '🤷🏽', '🤷🏾', '🤷🏿', '🤸🏻', '🤸🏼', '🤸🏽', '🤸🏾', '🤸🏿', '🤹🏻', '🤹🏼', '🤹🏽', '🤹🏾', '🤹🏿', '🤼🏻', '🤼🏼', '🤼🏽', '🤼🏾', '🤼🏿', '🤽🏻', '🤽🏼', '🤽🏽', '🤽🏾', '🤽🏿', '🤾🏻', '🤾🏼', '🤾🏽', '🤾🏾', '🤾🏿', '🥷🏻', '🥷🏼', '🥷🏽', '🥷🏾', '🥷🏿', '🦵🏻', '🦵🏼', '🦵🏽', '🦵🏾', '🦵🏿', '🦶🏻', '🦶🏼', '🦶🏽', '🦶🏾', '🦶🏿', '🦸🏻', '🦸🏼', '🦸🏽', '🦸🏾', '🦸🏿', '🦹🏻', '🦹🏼', '🦹🏽', '🦹🏾', '🦹🏿', '🦻🏻', '🦻🏼', '🦻🏽', '🦻🏾', '🦻🏿', '🧍🏻', '🧍🏼', '🧍🏽', '🧍🏾', '🧍🏿', '🧎🏻', '🧎🏼', '🧎🏽', '🧎🏾', '🧎🏿', '🧏🏻', '🧏🏼', '🧏🏽', '🧏🏾', '🧏🏿', '🧑🏻', '🧑🏼', '🧑🏽', '🧑🏾', '🧑🏿', '🧒🏻', '🧒🏼', '🧒🏽', '🧒🏾', '🧒🏿', '🧓🏻', '🧓🏼', '🧓🏽', '🧓🏾', '🧓🏿', '🧔🏻', '🧔🏼', '🧔🏽', '🧔🏾', '🧔🏿', '🧕🏻', '🧕🏼', '🧕🏽', '🧕🏾', '🧕🏿', '🧖🏻', '🧖🏼', '🧖🏽', '🧖🏾', '🧖🏿', '🧗🏻', '🧗🏼', '🧗🏽', '🧗🏾', '🧗🏿', '🧘🏻', '🧘🏼', '🧘🏽', '🧘🏾', '🧘🏿', '🧙🏻', '🧙🏼', '🧙🏽', '🧙🏾', '🧙🏿', '🧚🏻', '🧚🏼', '🧚🏽', '🧚🏾', '🧚🏿', '🧛🏻', '🧛🏼', '🧛🏽', '🧛🏾', '🧛🏿', '🧜🏻', '🧜🏼', '🧜🏽', '🧜🏾', '🧜🏿', '🧝🏻', '🧝🏼', '🧝🏽', '🧝🏾', '🧝🏿', '🫃🏻', '🫃🏼', '🫃🏽', '🫃🏾', '🫃🏿', '🫄🏻', '🫄🏼', '🫄🏽', '🫄🏾', '🫄🏿', '🫅🏻', '🫅🏼', '🫅🏽', '🫅🏾', '🫅🏿', '🫰🏻', '🫰🏼', '🫰🏽', '🫰🏾', '🫰🏿', '🫱🏻', '🫱🏼', '🫱🏽', '🫱🏾', '🫱🏿', '🫲🏻', '🫲🏼', '🫲🏽', '🫲🏾', '🫲🏿', '🫳🏻', '🫳🏼', '🫳🏽', '🫳🏾', '🫳🏿', '🫴🏻', '🫴🏼', '🫴🏽', '🫴🏾', '🫴🏿', '🫵🏻', '🫵🏼', '🫵🏽', '🫵🏾', '🫵🏿', '🫶🏻', '🫶🏼', '🫶🏽', '🫶🏾', '🫶🏿', '🫷🏻', '🫷🏼', '🫷🏽', '🫷🏾', '🫷🏿', '🫸🏻', '🫸🏼', '🫸🏽', '🫸🏾', '🫸🏿', '☝🏻', '☝🏼', '☝🏽', '☝🏾', '☝🏿', '⛷🏻', '⛷🏼', '⛷🏽', '⛷🏾', '⛷🏿', '⛹🏻', '⛹🏼', '⛹🏽', '⛹🏾', '⛹🏿', '✊🏻', '✊🏼', '✊🏽', '✊🏾', '✊🏿', '✋🏻', '✋🏼', '✋🏽', '✋🏾', '✋🏿', '✌🏻', '✌🏼', '✌🏽', '✌🏾', '✌🏿', '✍🏻', '✍🏼', '✍🏽', '✍🏾', '✍🏿', '#⃣', '*⃣', '0⃣', '1⃣', '2⃣', '3⃣', '4⃣', '5⃣', '6⃣', '7⃣', '8⃣', '9⃣', '🀄', '🃏', '🅰', '🅱', '🅾', '🅿', '🆎', '🆑', '🆒', '🆓', '🆔', '🆕', '🆖', '🆗', '🆘', '🆙', '🆚', '🇦', '🇧', '🇨', '🇩', '🇪', '🇫', '🇬', '🇭', '🇮', '🇯', '🇰', '🇱', '🇲', '🇳', '🇴', '🇵', '🇶', '🇷', '🇸', '🇹', '🇺', '🇻', '🇼', '🇽', '🇾', '🇿', '🈁', '🈂', '🈚', '🈯', '🈲', '🈳', '🈴', '🈵', '🈶', '🈷', '🈸', '🈹', '🈺', '🉐', '🉑', '🌀', '🌁', '🌂', '🌃', '🌄', '🌅', '🌆', '🌇', '🌈', '🌉', '🌊', '🌋', '🌌', '🌍', '🌎', '🌏', '🌐', '🌑', '🌒', '🌓', '🌔', '🌕', '🌖', '🌗', '🌘', '🌙', '🌚', '🌛', '🌜', '🌝', '🌞', '🌟', '🌠', '🌡', '🌤', '🌥', '🌦', '🌧', '🌨', '🌩', '🌪', '🌫', '🌬', '🌭', '🌮', '🌯', '🌰', '🌱', '🌲', '🌳', '🌴', '🌵', '🌶', '🌷', '🌸', '🌹', '🌺', '🌻', '🌼', '🌽', '🌾', '🌿', '🍀', '🍁', '🍂', '🍃', '🍄', '🍅', '🍆', '🍇', '🍈', '🍉', '🍊', '🍋', '🍌', '🍍', '🍎', '🍏', '🍐', '🍑', '🍒', '🍓', '🍔', '🍕', '🍖', '🍗', '🍘', '🍙', '🍚', '🍛', '🍜', '🍝', '🍞', '🍟', '🍠', '🍡', '🍢', '🍣', '🍤', '🍥', '🍦', '🍧', '🍨', '🍩', '🍪', '🍫', '🍬', '🍭', '🍮', '🍯', '🍰', '🍱', '🍲', '🍳', '🍴', '🍵', '🍶', '🍷', '🍸', '🍹', '🍺', '🍻', '🍼', '🍽', '🍾', '🍿', '🎀', '🎁', '🎂', '🎃', '🎄', '🎅', '🎆', '🎇', '🎈', '🎉', '🎊', '🎋', '🎌', '🎍', '🎎', '🎏', '🎐', '🎑', '🎒', '🎓', '🎖', '🎗', '🎙', '🎚', '🎛', '🎞', '🎟', '🎠', '🎡', '🎢', '🎣', '🎤', '🎥', '🎦', '🎧', '🎨', '🎩', '🎪', '🎫', '🎬', '🎭', '🎮', '🎯', '🎰', '🎱', '🎲', '🎳', '🎴', '🎵', '🎶', '🎷', '🎸', '🎹', '🎺', '🎻', '🎼', '🎽', '🎾', '🎿', '🏀', '🏁', '🏂', '🏃', '🏄', '🏅', '🏆', '🏇', '🏈', '🏉', '🏊', '🏋', '🏌', '🏍', '🏎', '🏏', '🏐', '🏑', '🏒', '🏓', '🏔', '🏕', '🏖', '🏗', '🏘', '🏙', '🏚', '🏛', '🏜', '🏝', '🏞', '🏟', '🏠', '🏡', '🏢', '🏣', '🏤', '🏥', '🏦', '🏧', '🏨', '🏩', '🏪', '🏫', '🏬', '🏭', '🏮', '🏯', '🏰', '🏳', '🏴', '🏵', '🏷', '🏸', '🏹', '🏺', '🏻', '🏼', '🏽', '🏾', '🏿', '🐀', '🐁', '🐂', '🐃', '🐄', '🐅', '🐆', '🐇', '🐈', '🐉', '🐊', '🐋', '🐌', '🐍', '🐎', '🐏', '🐐', '🐑', '🐒', '🐓', '🐔', '🐕', '🐖', '🐗', '🐘', '🐙', '🐚', '🐛', '🐜', '🐝', '🐞', '🐟', '🐠', '🐡', '🐢', '🐣', '🐤', '🐥', '🐦', '🐧', '🐨', '🐩', '🐪', '🐫', '🐬', '🐭', '🐮', '🐯', '🐰', '🐱', '🐲', '🐳', '🐴', '🐵', '🐶', '🐷', '🐸', '🐹', '🐺', '🐻', '🐼', '🐽', '🐾', '🐿', '👀', '👁', '👂', '👃', '👄', '👅', '👆', '👇', '👈', '👉', '👊', '👋', '👌', '👍', '👎', '👏', '👐', '👑', '👒', '👓', '👔', '👕', '👖', '👗', '👘', '👙', '👚', '👛', '👜', '👝', '👞', '👟', '👠', '👡', '👢', '👣', '👤', '👥', '👦', '👧', '👨', '👩', '👪', '👫', '👬', '👭', '👮', '👯', '👰', '👱', '👲', '👳', '👴', '👵', '👶', '👷', '👸', '👹', '👺', '👻', '👼', '👽', '👾', '👿', '💀', '💁', '💂', '💃', '💄', '💅', '💆', '💇', '💈', '💉', '💊', '💋', '💌', '💍', '💎', '💏', '💐', '💑', '💒', '💓', '💔', '💕', '💖', '💗', '💘', '💙', '💚', '💛', '💜', '💝', '💞', '💟', '💠', '💡', '💢', '💣', '💤', '💥', '💦', '💧', '💨', '💩', '💪', '💫', '💬', '💭', '💮', '💯', '💰', '💱', '💲', '💳', '💴', '💵', '💶', '💷', '💸', '💹', '💺', '💻', '💼', '💽', '💾', '💿', '📀', '📁', '📂', '📃', '📄', '📅', '📆', '📇', '📈', '📉', '📊', '📋', '📌', '📍', '📎', '📏', '📐', '📑', '📒', '📓', '📔', '📕', '📖', '📗', '📘', '📙', '📚', '📛', '📜', '📝', '📞', '📟', '📠', '📡', '📢', '📣', '📤', '📥', '📦', '📧', '📨', '📩', '📪', '📫', '📬', '📭', '📮', '📯', '📰', '📱', '📲', '📳', '📴', '📵', '📶', '📷', '📸', '📹', '📺', '📻', '📼', '📽', '📿', '🔀', '🔁', '🔂', '🔃', '🔄', '🔅', '🔆', '🔇', '🔈', '🔉', '🔊', '🔋', '🔌', '🔍', '🔎', '🔏', '🔐', '🔑', '🔒', '🔓', '🔔', '🔕', '🔖', '🔗', '🔘', '🔙', '🔚', '🔛', '🔜', '🔝', '🔞', '🔟', '🔠', '🔡', '🔢', '🔣', '🔤', '🔥', '🔦', '🔧', '🔨', '🔩', '🔪', '🔫', '🔬', '🔭', '🔮', '🔯', '🔰', '🔱', '🔲', '🔳', '🔴', '🔵', '🔶', '🔷', '🔸', '🔹', '🔺', '🔻', '🔼', '🔽', '🕉', '🕊', '🕋', '🕌', '🕍', '🕎', '🕐', '🕑', '🕒', '🕓', '🕔', '🕕', '🕖', '🕗', '🕘', '🕙', '🕚', '🕛', '🕜', '🕝', '🕞', '🕟', '🕠', '🕡', '🕢', '🕣', '🕤', '🕥', '🕦', '🕧', '🕯', '🕰', '🕳', '🕴', '🕵', '🕶', '🕷', '🕸', '🕹', '🕺', '🖇', '🖊', '🖋', '🖌', '🖍', '🖐', '🖕', '🖖', '🖤', '🖥', '🖨', '🖱', '🖲', '🖼', '🗂', '🗃', '🗄', '🗑', '🗒', '🗓', '🗜', '🗝', '🗞', '🗡', '🗣', '🗨', '🗯', '🗳', '🗺', '🗻', '🗼', '🗽', '🗾', '🗿', '😀', '😁', '😂', '😃', '😄', '😅', '😆', '😇', '😈', '😉', '😊', '😋', '😌', '😍', '😎', '😏', '😐', '😑', '😒', '😓', '😔', '😕', '😖', '😗', '😘', '😙', '😚', '😛', '😜', '😝', '😞', '😟', '😠', '😡', '😢', '😣', '😤', '😥', '😦', '😧', '😨', '😩', '😪', '😫', '😬', '😭', '😮', '😯', '😰', '😱', '😲', '😳', '😴', '😵', '😶', '😷', '😸', '😹', '😺', '😻', '😼', '😽', '😾', '😿', '🙀', '🙁', '🙂', '🙃', '🙄', '🙅', '🙆', '🙇', '🙈', '🙉', '🙊', '🙋', '🙌', '🙍', '🙎', '🙏', '🚀', '🚁', '🚂', '🚃', '🚄', '🚅', '🚆', '🚇', '🚈', '🚉', '🚊', '🚋', '🚌', '🚍', '🚎', '🚏', '🚐', '🚑', '🚒', '🚓', '🚔', '🚕', '🚖', '🚗', '🚘', '🚙', '🚚', '🚛', '🚜', '🚝', '🚞', '🚟', '🚠', '🚡', '🚢', '🚣', '🚤', '🚥', '🚦', '🚧', '🚨', '🚩', '🚪', '🚫', '🚬', '🚭', '🚮', '🚯', '🚰', '🚱', '🚲', '🚳', '🚴', '🚵', '🚶', '🚷', '🚸', '🚹', '🚺', '🚻', '🚼', '🚽', '🚾', '🚿', '🛀', '🛁', '🛂', '🛃', '🛄', '🛅', '🛋', '🛌', '🛍', '🛎', '🛏', '🛐', '🛑', '🛒', '🛕', '🛖', '🛗', '🛘', '🛜', '🛝', '🛞', '🛟', '🛠', '🛡', '🛢', '🛣', '🛤', '🛥', '🛩', '🛫', '🛬', '🛰', '🛳', '🛴', '🛵', '🛶', '🛷', '🛸', '🛹', '🛺', '🛻', '🛼', '🟠', '🟡', '🟢', '🟣', '🟤', '🟥', '🟦', '🟧', '🟨', '🟩', '🟪', '🟫', '🟰', '🤌', '🤍', '🤎', '🤏', '🤐', '🤑', '🤒', '🤓', '🤔', '🤕', '🤖', '🤗', '🤘', '🤙', '🤚', '🤛', '🤜', '🤝', '🤞', '🤟', '🤠', '🤡', '🤢', '🤣', '🤤', '🤥', '🤦', '🤧', '🤨', '🤩', '🤪', '🤫', '🤬', '🤭', '🤮', '🤯', '🤰', '🤱', '🤲', '🤳', '🤴', '🤵', '🤶', '🤷', '🤸', '🤹', '🤺', '🤼', '🤽', '🤾', '🤿', '🥀', '🥁', '🥂', '🥃', '🥄', '🥅', '🥇', '🥈', '🥉', '🥊', '🥋', '🥌', '🥍', '🥎', '🥏', '🥐', '🥑', '🥒', '🥓', '🥔', '🥕', '🥖', '🥗', '🥘', '🥙', '🥚', '🥛', '🥜', '🥝', '🥞', '🥟', '🥠', '🥡', '🥢', '🥣', '🥤', '🥥', '🥦', '🥧', '🥨', '🥩', '🥪', '🥫', '🥬', '🥭', '🥮', '🥯', '🥰', '🥱', '🥲', '🥳', '🥴', '🥵', '🥶', '🥷', '🥸', '🥹', '🥺', '🥻', '🥼', '🥽', '🥾', '🥿', '🦀', '🦁', '🦂', '🦃', '🦄', '🦅', '🦆', '🦇', '🦈', '🦉', '🦊', '🦋', '🦌', '🦍', '🦎', '🦏', '🦐', '🦑', '🦒', '🦓', '🦔', '🦕', '🦖', '🦗', '🦘', '🦙', '🦚', '🦛', '🦜', '🦝', '🦞', '🦟', '🦠', '🦡', '🦢', '🦣', '🦤', '🦥', '🦦', '🦧', '🦨', '🦩', '🦪', '🦫', '🦬', '🦭', '🦮', '🦯', '🦰', '🦱', '🦲', '🦳', '🦴', '🦵', '🦶', '🦷', '🦸', '🦹', '🦺', '🦻', '🦼', '🦽', '🦾', '🦿', '🧀', '🧁', '🧂', '🧃', '🧄', '🧅', '🧆', '🧇', '🧈', '🧉', '🧊', '🧋', '🧌', '🧍', '🧎', '🧏', '🧐', '🧑', '🧒', '🧓', '🧔', '🧕', '🧖', '🧗', '🧘', '🧙', '🧚', '🧛', '🧜', '🧝', '🧞', '🧟', '🧠', '🧡', '🧢', '🧣', '🧤', '🧥', '🧦', '🧧', '🧨', '🧩', '🧪', '🧫', '🧬', '🧭', '🧮', '🧯', '🧰', '🧱', '🧲', '🧳', '🧴', '🧵', '🧶', '🧷', '🧸', '🧹', '🧺', '🧻', '🧼', '🧽', '🧾', '🧿', '🩰', '🩱', '🩲', '🩳', '🩴', '🩵', '🩶', '🩷', '🩸', '🩹', '🩺', '🩻', '🩼', '🪀', '🪁', '🪂', '🪃', '🪄', '🪅', '🪆', '🪇', '🪈', '🪉', '🪊', '🪎', '🪏', '🪐', '🪑', '🪒', '🪓', '🪔', '🪕', '🪖', '🪗', '🪘', '🪙', '🪚', '🪛', '🪜', '🪝', '🪞', '🪟', '🪠', '🪡', '🪢', '🪣', '🪤', '🪥', '🪦', '🪧', '🪨', '🪩', '🪪', '🪫', '🪬', '🪭', '🪮', '🪯', '🪰', '🪱', '🪲', '🪳', '🪴', '🪵', '🪶', '🪷', '🪸', '🪹', '🪺', '🪻', '🪼', '🪽', '🪾', '🪿', '🫀', '🫁', '🫂', '🫃', '🫄', '🫅', '🫆', '🫈', '🫍', '🫎', '🫏', '🫐', '🫑', '🫒', '🫓', '🫔', '🫕', '🫖', '🫗', '🫘', '🫙', '🫚', '🫛', '🫜', '🫟', '🫠', '🫡', '🫢', '🫣', '🫤', '🫥', '🫦', '🫧', '🫨', '🫩', '🫪', '🫯', '🫰', '🫱', '🫲', '🫳', '🫴', '🫵', '🫶', '🫷', '🫸', '‼', '⁉', '™', 'ℹ', '↔', '↕', '↖', '↗', '↘', '↙', '↩', '↪', '⌚', '⌛', '⌨', '⏏', '⏩', '⏪', '⏫', '⏬', '⏭', '⏮', '⏯', '⏰', '⏱', '⏲', '⏳', '⏸', '⏹', '⏺', 'Ⓜ', '▪', '▫', '▶', '◀', '◻', '◼', '◽', '◾', '☀', '☁', '☂', '☃', '☄', '☎', '☑', '☔', '☕', '☘', '☝', '☠', '☢', '☣', '☦', '☪', '☮', '☯', '☸', '☹', '☺', '♀', '♂', '♈', '♉', '♊', '♋', '♌', '♍', '♎', '♏', '♐', '♑', '♒', '♓', '♟', '♠', '♣', '♥', '♦', '♨', '♻', '♾', '♿', '⚒', '⚓', '⚔', '⚕', '⚖', '⚗', '⚙', '⚛', '⚜', '⚠', '⚡', '⚧', '⚪', '⚫', '⚰', '⚱', '⚽', '⚾', '⛄', '⛅', '⛈', '⛎', '⛏', '⛑', '⛓', '⛔', '⛩', '⛪', '⛰', '⛱', '⛲', '⛳', '⛴', '⛵', '⛷', '⛸', '⛹', '⛺', '⛽', '✂', '✅', '✈', '✉', '✊', '✋', '✌', '✍', '✏', '✒', '✔', '✖', '✝', '✡', '✨', '✳', '✴', '❄', '❇', '❌', '❎', '❓', '❔', '❕', '❗', '❣', '❤', '➕', '➖', '➗', '➡', '➰', '➿', '⤴', '⤵', '⬅', '⬆', '⬇', '⬛', '⬜', '⭐', '⭕', '〰', '〽', '㊗', '㊙', '' ); 6241 $partials = array( '🀄', '🃏', '🅰', '🅱', '🅾', '🅿', '🆎', '🆑', '🆒', '🆓', '🆔', '🆕', '🆖', '🆗', '🆘', '🆙', '🆚', '🇦', '🇨', '🇩', '🇪', '🇫', '🇬', '🇮', '🇱', '🇲', '🇴', '🇶', '🇷', '🇸', '🇹', '🇺', '🇼', '🇽', '🇿', '🇧', '🇭', '🇯', '🇳', '🇻', '🇾', '🇰', '🇵', '🈁', '🈂', '🈚', '🈯', '🈲', '🈳', '🈴', '🈵', '🈶', '🈷', '🈸', '🈹', '🈺', '🉐', '🉑', '🌀', '🌁', '🌂', '🌃', '🌄', '🌅', '🌆', '🌇', '🌈', '🌉', '🌊', '🌋', '🌌', '🌍', '🌎', '🌏', '🌐', '🌑', '🌒', '🌓', '🌔', '🌕', '🌖', '🌗', '🌘', '🌙', '🌚', '🌛', '🌜', '🌝', '🌞', '🌟', '🌠', '🌡', '🌤', '🌥', '🌦', '🌧', '🌨', '🌩', '🌪', '🌫', '🌬', '🌭', '🌮', '🌯', '🌰', '🌱', '🌲', '🌳', '🌴', '🌵', '🌶', '🌷', '🌸', '🌹', '🌺', '🌻', '🌼', '🌽', '🌾', '🌿', '🍀', '🍁', '🍂', '🍃', '🍄', '‍', '🟫', '🍅', '🍆', '🍇', '🍈', '🍉', '🍊', '🍋', '🟩', '🍌', '🍍', '🍎', '🍏', '🍐', '🍑', '🍒', '🍓', '🍔', '🍕', '🍖', '🍗', '🍘', '🍙', '🍚', '🍛', '🍜', '🍝', '🍞', '🍟', '🍠', '🍡', '🍢', '🍣', '🍤', '🍥', '🍦', '🍧', '🍨', '🍩', '🍪', '🍫', '🍬', '🍭', '🍮', '🍯', '🍰', '🍱', '🍲', '🍳', '🍴', '🍵', '🍶', '🍷', '🍸', '🍹', '🍺', '🍻', '🍼', '🍽', '🍾', '🍿', '🎀', '🎁', '🎂', '🎃', '🎄', '🎅', '🏻', '🏼', '🏽', '🏾', '🏿', '🎆', '🎇', '🎈', '🎉', '🎊', '🎋', '🎌', '🎍', '🎎', '🎏', '🎐', '🎑', '🎒', '🎓', '🎖', '🎗', '🎙', '🎚', '🎛', '🎞', '🎟', '🎠', '🎡', '🎢', '🎣', '🎤', '🎥', '🎦', '🎧', '🎨', '🎩', '🎪', '🎫', '🎬', '🎭', '🎮', '🎯', '🎰', '🎱', '🎲', '🎳', '🎴', '🎵', '🎶', '🎷', '🎸', '🎹', '🎺', '🎻', '🎼', '🎽', '🎾', '🎿', '🏀', '🏁', '🏂', '🏃', '♀', '️', '➡', '♂', '🏄', '🏅', '🏆', '🏇', '🏈', '🏉', '🏊', '🏋', '🏌', '🏍', '🏎', '🏏', '🏐', '🏑', '🏒', '🏓', '🏔', '🏕', '🏖', '🏗', '🏘', '🏙', '🏚', '🏛', '🏜', '🏝', '🏞', '🏟', '🏠', '🏡', '🏢', '🏣', '🏤', '🏥', '🏦', '🏧', '🏨', '🏩', '🏪', '🏫', '🏬', '🏭', '🏮', '🏯', '🏰', '🏳', '⚧', '🏴', '☠', '󠁧', '󠁢', '󠁥', '󠁮', '󠁿', '󠁳', '󠁣', '󠁴', '󠁷', '󠁬', '🏵', '🏷', '🏸', '🏹', '🏺', '🐀', '🐁', '🐂', '🐃', '🐄', '🐅', '🐆', '🐇', '🐈', '⬛', '🐉', '🐊', '🐋', '🐌', '🐍', '🐎', '🐏', '🐐', '🐑', '🐒', '🐓', '🐔', '🐕', '🦺', '🐖', '🐗', '🐘', '🐙', '🐚', '🐛', '🐜', '🐝', '🐞', '🐟', '🐠', '🐡', '🐢', '🐣', '🐤', '🐥', '🐦', '🔥', '🐧', '🐨', '🐩', '🐪', '🐫', '🐬', '🐭', '🐮', '🐯', '🐰', '🐱', '🐲', '🐳', '🐴', '🐵', '🐶', '🐷', '🐸', '🐹', '🐺', '🐻', '❄', '🐼', '🐽', '🐾', '🐿', '👀', '👁', '🗨', '👂', '👃', '👄', '👅', '👆', '👇', '👈', '👉', '👊', '👋', '👌', '👍', '👎', '👏', '👐', '👑', '👒', '👓', '👔', '👕', '👖', '👗', '👘', '👙', '👚', '👛', '👜', '👝', '👞', '👟', '👠', '👡', '👢', '👣', '👤', '👥', '👦', '👧', '👨', '💻', '💼', '🔧', '🔬', '🚀', '🚒', '🤝', '🦯', '🦰', '🦱', '🦲', '🦳', '🦼', '🦽', '🫯', '⚕', '⚖', '✈', '❤', '💋', '👩', '👪', '👫', '👬', '👭', '👮', '👯', '👰', '👱', '👲', '👳', '👴', '👵', '👶', '👷', '👸', '👹', '👺', '👻', '👼', '👽', '👾', '👿', '💀', '💁', '💂', '💃', '💄', '💅', '💆', '💇', '💈', '💉', '💊', '💌', '💍', '💎', '💏', '💐', '💑', '💒', '💓', '💔', '💕', '💖', '💗', '💘', '💙', '💚', '💛', '💜', '💝', '💞', '💟', '💠', '💡', '💢', '💣', '💤', '💥', '💦', '💧', '💨', '💩', '💪', '💫', '💬', '💭', '💮', '💯', '💰', '💱', '💲', '💳', '💴', '💵', '💶', '💷', '💸', '💹', '💺', '💽', '💾', '💿', '📀', '📁', '📂', '📃', '📄', '📅', '📆', '📇', '📈', '📉', '📊', '📋', '📌', '📍', '📎', '📏', '📐', '📑', '📒', '📓', '📔', '📕', '📖', '📗', '📘', '📙', '📚', '📛', '📜', '📝', '📞', '📟', '📠', '📡', '📢', '📣', '📤', '📥', '📦', '📧', '📨', '📩', '📪', '📫', '📬', '📭', '📮', '📯', '📰', '📱', '📲', '📳', '📴', '📵', '📶', '📷', '📸', '📹', '📺', '📻', '📼', '📽', '📿', '🔀', '🔁', '🔂', '🔃', '🔄', '🔅', '🔆', '🔇', '🔈', '🔉', '🔊', '🔋', '🔌', '🔍', '🔎', '🔏', '🔐', '🔑', '🔒', '🔓', '🔔', '🔕', '🔖', '🔗', '🔘', '🔙', '🔚', '🔛', '🔜', '🔝', '🔞', '🔟', '🔠', '🔡', '🔢', '🔣', '🔤', '🔦', '🔨', '🔩', '🔪', '🔫', '🔭', '🔮', '🔯', '🔰', '🔱', '🔲', '🔳', '🔴', '🔵', '🔶', '🔷', '🔸', '🔹', '🔺', '🔻', '🔼', '🔽', '🕉', '🕊', '🕋', '🕌', '🕍', '🕎', '🕐', '🕑', '🕒', '🕓', '🕔', '🕕', '🕖', '🕗', '🕘', '🕙', '🕚', '🕛', '🕜', '🕝', '🕞', '🕟', '🕠', '🕡', '🕢', '🕣', '🕤', '🕥', '🕦', '🕧', '🕯', '🕰', '🕳', '🕴', '🕵', '🕶', '🕷', '🕸', '🕹', '🕺', '🖇', '🖊', '🖋', '🖌', '🖍', '🖐', '🖕', '🖖', '🖤', '🖥', '🖨', '🖱', '🖲', '🖼', '🗂', '🗃', '🗄', '🗑', '🗒', '🗓', '🗜', '🗝', '🗞', '🗡', '🗣', '🗯', '🗳', '🗺', '🗻', '🗼', '🗽', '🗾', '🗿', '😀', '😁', '😂', '😃', '😄', '😅', '😆', '😇', '😈', '😉', '😊', '😋', '😌', '😍', '😎', '😏', '😐', '😑', '😒', '😓', '😔', '😕', '😖', '😗', '😘', '😙', '😚', '😛', '😜', '😝', '😞', '😟', '😠', '😡', '😢', '😣', '😤', '😥', '😦', '😧', '😨', '😩', '😪', '😫', '😬', '😭', '😮', '😯', '😰', '😱', '😲', '😳', '😴', '😵', '😶', '😷', '😸', '😹', '😺', '😻', '😼', '😽', '😾', '😿', '🙀', '🙁', '🙂', '↔', '↕', '🙃', '🙄', '🙅', '🙆', '🙇', '🙈', '🙉', '🙊', '🙋', '🙌', '🙍', '🙎', '🙏', '🚁', '🚂', '🚃', '🚄', '🚅', '🚆', '🚇', '🚈', '🚉', '🚊', '🚋', '🚌', '🚍', '🚎', '🚏', '🚐', '🚑', '🚓', '🚔', '🚕', '🚖', '🚗', '🚘', '🚙', '🚚', '🚛', '🚜', '🚝', '🚞', '🚟', '🚠', '🚡', '🚢', '🚣', '🚤', '🚥', '🚦', '🚧', '🚨', '🚩', '🚪', '🚫', '🚬', '🚭', '🚮', '🚯', '🚰', '🚱', '🚲', '🚳', '🚴', '🚵', '🚶', '🚷', '🚸', '🚹', '🚺', '🚻', '🚼', '🚽', '🚾', '🚿', '🛀', '🛁', '🛂', '🛃', '🛄', '🛅', '🛋', '🛌', '🛍', '🛎', '🛏', '🛐', '🛑', '🛒', '🛕', '🛖', '🛗', '🛘', '🛜', '🛝', '🛞', '🛟', '🛠', '🛡', '🛢', '🛣', '🛤', '🛥', '🛩', '🛫', '🛬', '🛰', '🛳', '🛴', '🛵', '🛶', '🛷', '🛸', '🛹', '🛺', '🛻', '🛼', '🟠', '🟡', '🟢', '🟣', '🟤', '🟥', '🟦', '🟧', '🟨', '🟪', '🟰', '🤌', '🤍', '🤎', '🤏', '🤐', '🤑', '🤒', '🤓', '🤔', '🤕', '🤖', '🤗', '🤘', '🤙', '🤚', '🤛', '🤜', '🤞', '🤟', '🤠', '🤡', '🤢', '🤣', '🤤', '🤥', '🤦', '🤧', '🤨', '🤩', '🤪', '🤫', '🤬', '🤭', '🤮', '🤯', '🤰', '🤱', '🤲', '🤳', '🤴', '🤵', '🤶', '🤷', '🤸', '🤹', '🤺', '🤼', '🤽', '🤾', '🤿', '🥀', '🥁', '🥂', '🥃', '🥄', '🥅', '🥇', '🥈', '🥉', '🥊', '🥋', '🥌', '🥍', '🥎', '🥏', '🥐', '🥑', '🥒', '🥓', '🥔', '🥕', '🥖', '🥗', '🥘', '🥙', '🥚', '🥛', '🥜', '🥝', '🥞', '🥟', '🥠', '🥡', '🥢', '🥣', '🥤', '🥥', '🥦', '🥧', '🥨', '🥩', '🥪', '🥫', '🥬', '🥭', '🥮', '🥯', '🥰', '🥱', '🥲', '🥳', '🥴', '🥵', '🥶', '🥷', '🥸', '🥹', '🥺', '🥻', '🥼', '🥽', '🥾', '🥿', '🦀', '🦁', '🦂', '🦃', '🦄', '🦅', '🦆', '🦇', '🦈', '🦉', '🦊', '🦋', '🦌', '🦍', '🦎', '🦏', '🦐', '🦑', '🦒', '🦓', '🦔', '🦕', '🦖', '🦗', '🦘', '🦙', '🦚', '🦛', '🦜', '🦝', '🦞', '🦟', '🦠', '🦡', '🦢', '🦣', '🦤', '🦥', '🦦', '🦧', '🦨', '🦩', '🦪', '🦫', '🦬', '🦭', '🦮', '🦴', '🦵', '🦶', '🦷', '🦸', '🦹', '🦻', '🦾', '🦿', '🧀', '🧁', '🧂', '🧃', '🧄', '🧅', '🧆', '🧇', '🧈', '🧉', '🧊', '🧋', '🧌', '🧍', '🧎', '🧏', '🧐', '🧑', '🩰', '🧒', '🧓', '🧔', '🧕', '🧖', '🧗', '🧘', '🧙', '🧚', '🧛', '🧜', '🧝', '🧞', '🧟', '🧠', '🧡', '🧢', '🧣', '🧤', '🧥', '🧦', '🧧', '🧨', '🧩', '🧪', '🧫', '🧬', '🧭', '🧮', '🧯', '🧰', '🧱', '🧲', '🧳', '🧴', '🧵', '🧶', '🧷', '🧸', '🧹', '🧺', '🧻', '🧼', '🧽', '🧾', '🧿', '🩱', '🩲', '🩳', '🩴', '🩵', '🩶', '🩷', '🩸', '🩹', '🩺', '🩻', '🩼', '🪀', '🪁', '🪂', '🪃', '🪄', '🪅', '🪆', '🪇', '🪈', '🪉', '🪊', '🪎', '🪏', '🪐', '🪑', '🪒', '🪓', '🪔', '🪕', '🪖', '🪗', '🪘', '🪙', '🪚', '🪛', '🪜', '🪝', '🪞', '🪟', '🪠', '🪡', '🪢', '🪣', '🪤', '🪥', '🪦', '🪧', '🪨', '🪩', '🪪', '🪫', '🪬', '🪭', '🪮', '🪯', '🪰', '🪱', '🪲', '🪳', '🪴', '🪵', '🪶', '🪷', '🪸', '🪹', '🪺', '🪻', '🪼', '🪽', '🪾', '🪿', '🫀', '🫁', '🫂', '🫃', '🫄', '🫅', '🫆', '🫈', '🫍', '🫎', '🫏', '🫐', '🫑', '🫒', '🫓', '🫔', '🫕', '🫖', '🫗', '🫘', '🫙', '🫚', '🫛', '🫜', '🫟', '🫠', '🫡', '🫢', '🫣', '🫤', '🫥', '🫦', '🫧', '🫨', '🫩', '🫪', '🫰', '🫱', '🫲', '🫳', '🫴', '🫵', '🫶', '🫷', '🫸', '‼', '⁉', '™', 'ℹ', '↖', '↗', '↘', '↙', '↩', '↪', '⃣', '⌚', '⌛', '⌨', '⏏', '⏩', '⏪', '⏫', '⏬', '⏭', '⏮', '⏯', '⏰', '⏱', '⏲', '⏳', '⏸', '⏹', '⏺', 'Ⓜ', '▪', '▫', '▶', '◀', '◻', '◼', '◽', '◾', '☀', '☁', '☂', '☃', '☄', '☎', '☑', '☔', '☕', '☘', '☝', '☢', '☣', '☦', '☪', '☮', '☯', '☸', '☹', '☺', '♈', '♉', '♊', '♋', '♌', '♍', '♎', '♏', '♐', '♑', '♒', '♓', '♟', '♠', '♣', '♥', '♦', '♨', '♻', '♾', '♿', '⚒', '⚓', '⚔', '⚗', '⚙', '⚛', '⚜', '⚠', '⚡', '⚪', '⚫', '⚰', '⚱', '⚽', '⚾', '⛄', '⛅', '⛈', '⛎', '⛏', '⛑', '⛓', '⛔', '⛩', '⛪', '⛰', '⛱', '⛲', '⛳', '⛴', '⛵', '⛷', '⛸', '⛹', '⛺', '⛽', '✂', '✅', '✉', '✊', '✋', '✌', '✍', '✏', '✒', '✔', '✖', '✝', '✡', '✨', '✳', '✴', '❇', '❌', '❎', '❓', '❔', '❕', '❗', '❣', '➕', '➖', '➗', '➰', '➿', '⤴', '⤵', '⬅', '⬆', '⬇', '⬜', '⭐', '⭕', '〰', '〽', '㊗', '㊙', '' ); 6242 // END: emoji arrays 6243 6244 if ( 'entities' === $type ) { 6245 return $entities; 6246 } 6247 6248 return $partials; 6249 } 6250 6251 /** 6252 * Shortens a URL, to be used as link text. 6253 * 6254 * @since 1.2.0 6255 * @since 4.4.0 Moved to wp-includes/formatting.php from wp-admin/includes/misc.php and added $length param. 6256 * 6257 * @param string $url URL to shorten. 6258 * @param int $length Optional. Maximum length of the shortened URL. Default 35 characters. 6259 * @return string Shortened URL. 6260 */ 6261 function url_shorten( $url, $length = 35 ) { 6262 $stripped = str_replace( array( 'https://', 'http://', 'www.' ), '', $url ); 6263 $short_url = untrailingslashit( $stripped ); 6264 6265 if ( strlen( $short_url ) > $length ) { 6266 $short_url = substr( $short_url, 0, $length - 3 ) . '…'; 6267 } 6268 return $short_url; 6269 } 6270 6271 /** 6272 * Sanitizes a hex color. 6273 * 6274 * Returns either '', a 3 or 6 digit hex color (with #), or nothing. 6275 * For sanitizing values without a #, see sanitize_hex_color_no_hash(). 6276 * 6277 * @since 3.4.0 6278 * 6279 * @param string $color 6280 * @return string|null The sanitized hex color, or null if invalid. 6281 */ 6282 function sanitize_hex_color( $color ) { 6283 if ( '' === $color ) { 6284 return ''; 6285 } 6286 6287 // 3 or 6 hex digits, or the empty string. 6288 if ( preg_match( '|^#([A-Fa-f0-9]{3}){1,2}$|', $color ) ) { 6289 return $color; 6290 } 6291 return null; 6292 } 6293 6294 /** 6295 * Sanitizes a hex color without a hash. Use sanitize_hex_color() when possible. 6296 * 6297 * Saving hex colors without a hash puts the burden of adding the hash on the 6298 * UI, which makes it difficult to use or upgrade to other color types such as 6299 * rgba, hsl, rgb, and HTML color names. 6300 * 6301 * Returns either '', a 3 or 6 digit hex color (without a #), or null. 6302 * 6303 * @since 3.4.0 6304 * 6305 * @param string $color The color value to sanitize. Can be with or without a #. 6306 * @return string|null The sanitized hex color without the hash prefix, 6307 * empty string if input is empty, or null if invalid. 6308 */ 6309 function sanitize_hex_color_no_hash( $color ) { 6310 $color = ltrim( $color, '#' ); 6311 6312 if ( '' === $color ) { 6313 return ''; 6314 } 6315 6316 return sanitize_hex_color( '#' . $color ) ? $color : null; 6317 } 6318 6319 /** 6320 * Ensures that any hex color is properly hashed. 6321 * Otherwise, returns value untouched. 6322 * 6323 * This method should only be necessary if using sanitize_hex_color_no_hash(). 6324 * 6325 * @since 3.4.0 6326 * 6327 * @param string $color The color value to add the hash prefix to. Can be with or without a #. 6328 * @return string The color with the hash prefix if it's a valid hex color, 6329 * otherwise the original value. 6330 */ 6331 function maybe_hash_hex_color( $color ) { 6332 $unhashed = sanitize_hex_color_no_hash( $color ); 6333 if ( $unhashed ) { 6334 return '#' . $unhashed; 6335 } 6336 6337 return $color; 6338 }
title
Description
Body
title
Description
Body
title
Description
Body
title
Body
| Generated : Mon Jun 29 08:20:12 2026 | Cross-referenced by PHPXref |