| [ 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 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 * Determines if a given byte string represents a valid UTF-8 encoding. 922 * 923 * Note that it’s unlikely for non-UTF-8 data to validate as UTF-8, but 924 * it is still possible. Many texts are simultaneously valid UTF-8, 925 * valid US-ASCII, and valid ISO-8859-1 (`latin1`). 926 * 927 * Example: 928 * 929 * true === wp_is_valid_utf8( '' ); 930 * true === wp_is_valid_utf8( 'just a test' ); 931 * true === wp_is_valid_utf8( "\xE2\x9C\x8F" ); // Pencil, U+270F. 932 * true === wp_is_valid_utf8( "\u{270F}" ); // Pencil, U+270F. 933 * true === wp_is_valid_utf8( '✏' ); // Pencil, U+270F. 934 * 935 * false === wp_is_valid_utf8( "just \xC0 test" ); // Invalid bytes. 936 * false === wp_is_valid_utf8( "\xE2\x9C" ); // Invalid/incomplete sequences. 937 * false === wp_is_valid_utf8( "\xC1\xBF" ); // Overlong sequences. 938 * false === wp_is_valid_utf8( "\xED\xB0\x80" ); // Surrogate halves. 939 * false === wp_is_valid_utf8( "B\xFCch" ); // ISO-8859-1 high-bytes. 940 * // E.g. The “ü” in ISO-8859-1 is a single byte 0xFC, 941 * // but in UTF-8 is the two-byte sequence 0xC3 0xBC. 942 * 943 * A “valid” string consists of “well-formed UTF-8 code unit sequence[s],” meaning 944 * that the bytes conform to the UTF-8 encoding scheme, all characters use the minimal 945 * byte sequence required by UTF-8, and that no sequence encodes a UTF-16 surrogate 946 * code point or any character above the representable range. 947 * 948 * @see https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/#G32860 949 * 950 * @see _wp_is_valid_utf8_fallback 951 * 952 * @since 6.9.0 953 * 954 * @param string $bytes String which might contain text encoded as UTF-8. 955 * @return bool Whether the provided bytes can decode as valid UTF-8. 956 */ 957 function wp_is_valid_utf8( string $bytes ): bool { 958 /* 959 * Since PHP 8.3.0 the UTF-8 validity is cached internally 960 * on string objects, making this a direct property lookup. 961 * 962 * This is to be preferred exclusively once PHP 8.3.0 is 963 * the minimum supported version, because even when the 964 * status isn’t cached, it uses highly-optimized code to 965 * validate the byte stream. 966 */ 967 return function_exists( 'mb_check_encoding' ) 968 ? mb_check_encoding( $bytes, 'UTF-8' ) 969 : _wp_is_valid_utf8_fallback( $bytes ); 970 } 971 972 /** 973 * Fallback mechanism for safely validating UTF-8 bytes. 974 * 975 * By implementing a raw method here the code will behave in the same way on 976 * all installed systems, regardless of what extensions are installed. 977 * 978 * @see wp_is_valid_utf8 979 * 980 * @since 6.9.0 981 * @access private 982 * 983 * @param string $bytes String which might contain text encoded as UTF-8. 984 * @return bool Whether the provided bytes can decode as valid UTF-8. 985 */ 986 function _wp_is_valid_utf8_fallback( string $bytes ): bool { 987 $end = strlen( $bytes ); 988 989 for ( $i = 0; $i < $end; $i++ ) { 990 /* 991 * Quickly skip past US-ASCII bytes, all of which are valid UTF-8. 992 * 993 * This optimization step improves the speed from 10x to 100x 994 * depending on whether the JIT has optimized the function. 995 */ 996 $i += strspn( 997 $bytes, 998 "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" . 999 "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" . 1000 " !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f", 1001 $i 1002 ); 1003 if ( $i >= $end ) { 1004 break; 1005 } 1006 1007 /** 1008 * The above fast-track handled all single-byte UTF-8 characters. What 1009 * follows MUST be a multibyte sequence otherwise there’s invalid UTF-8. 1010 * 1011 * Therefore everything past here is checking those multibyte sequences. 1012 * Because it’s possible that there are truncated characters, the use of 1013 * the null-coalescing operator with "\xC0" is a convenience for skipping 1014 * length checks on every continuation bytes. This works because 0xC0 is 1015 * always invalid in a UTF-8 string, meaning that if the string has been 1016 * truncated, it will find 0xC0 and reject as invalid UTF-8. 1017 * 1018 * > [The following table] lists all of the byte sequences that are well-formed 1019 * > in UTF-8. A range of byte values such as A0..BF indicates that any byte 1020 * > from A0 to BF (inclusive) is well-formed in that position. Any byte value 1021 * > outside of the ranges listed is ill-formed. 1022 * 1023 * > Table 3-7. Well-Formed UTF-8 Byte Sequences 1024 * ╭─────────────────────┬────────────┬──────────────┬─────────────┬──────────────╮ 1025 * │ Code Points │ First Byte │ Second Byte │ Third Byte │ Fourth Byte │ 1026 * ├─────────────────────┼────────────┼──────────────┼─────────────┼──────────────┤ 1027 * │ U+0000..U+007F │ 00..7F │ │ │ │ 1028 * │ U+0080..U+07FF │ C2..DF │ 80..BF │ │ │ 1029 * │ U+0800..U+0FFF │ E0 │ A0..BF │ 80..BF │ │ 1030 * │ U+1000..U+CFFF │ E1..EC │ 80..BF │ 80..BF │ │ 1031 * │ U+D000..U+D7FF │ ED │ 80..9F │ 80..BF │ │ 1032 * │ U+E000..U+FFFF │ EE..EF │ 80..BF │ 80..BF │ │ 1033 * │ U+10000..U+3FFFF │ F0 │ 90..BF │ 80..BF │ 80..BF │ 1034 * │ U+40000..U+FFFFF │ F1..F3 │ 80..BF │ 80..BF │ 80..BF │ 1035 * │ U+100000..U+10FFFF │ F4 │ 80..8F │ 80..BF │ 80..BF │ 1036 * ╰─────────────────────┴────────────┴──────────────┴─────────────┴──────────────╯ 1037 * 1038 * Notice that all valid third and forth bytes are in the range 80..BF. This 1039 * validator takes advantage of that to only check the range of those bytes once. 1040 * 1041 * @see https://lemire.me/blog/2018/05/09/how-quickly-can-you-check-that-a-string-is-valid-unicode-utf-8/ 1042 * @see https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/#G27506 1043 */ 1044 1045 $b1 = ord( $bytes[ $i ] ); 1046 $b2 = ord( $bytes[ $i + 1 ] ?? "\xC0" ); 1047 1048 // Valid two-byte code points. 1049 1050 if ( $b1 >= 0xC2 && $b1 <= 0xDF && $b2 >= 0x80 && $b2 <= 0xBF ) { 1051 $i++; 1052 continue; 1053 } 1054 1055 $b3 = ord( $bytes[ $i + 2 ] ?? "\xC0" ); 1056 1057 // Valid three-byte code points. 1058 1059 if ( $b3 < 0x80 || $b3 > 0xBF ) { 1060 return false; 1061 } 1062 1063 if ( 1064 ( 0xE0 === $b1 && $b2 >= 0xA0 && $b2 <= 0xBF ) || 1065 ( $b1 >= 0xE1 && $b1 <= 0xEC && $b2 >= 0x80 && $b2 <= 0xBF ) || 1066 ( 0xED === $b1 && $b2 >= 0x80 && $b2 <= 0x9F ) || 1067 ( $b1 >= 0xEE && $b1 <= 0xEF && $b2 >= 0x80 && $b2 <= 0xBF ) 1068 ) { 1069 $i += 2; 1070 continue; 1071 } 1072 1073 $b4 = ord( $bytes[ $i + 3 ] ?? "\xC0" ); 1074 1075 // Valid four-byte code points. 1076 1077 if ( $b4 < 0x80 || $b4 > 0xBF ) { 1078 return false; 1079 } 1080 1081 if ( 1082 ( 0xF0 === $b1 && $b2 >= 0x90 && $b2 <= 0xBF ) || 1083 ( $b1 >= 0xF1 && $b1 <= 0xF3 && $b2 >= 0x80 && $b2 <= 0xBF ) || 1084 ( 0xF4 === $b1 && $b2 >= 0x80 && $b2 <= 0x8F ) 1085 ) { 1086 $i += 3; 1087 continue; 1088 } 1089 1090 // Any other sequence is invalid. 1091 return false; 1092 } 1093 1094 // Reaching the end implies validating every byte. 1095 return true; 1096 } 1097 1098 /** 1099 * Converts a number of special characters into their HTML entities. 1100 * 1101 * Specifically deals with: `&`, `<`, `>`, `"`, and `'`. 1102 * 1103 * `$quote_style` can be set to ENT_COMPAT to encode `"` to 1104 * `"`, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded. 1105 * 1106 * @since 1.2.2 1107 * @since 5.5.0 `$quote_style` also accepts `ENT_XML1`. 1108 * @access private 1109 * 1110 * @param string $text The text which is to be encoded. 1111 * @param int|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT, 1112 * both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. 1113 * Converts single and double quotes, as well as converting HTML 1114 * named entities (that are not also XML named entities) to their 1115 * code points if set to ENT_XML1. Also compatible with old values; 1116 * converting single quotes if set to 'single', 1117 * double if set to 'double' or both if otherwise set. 1118 * Default is ENT_NOQUOTES. 1119 * @param false|string $charset Optional. The character encoding of the string. Default false. 1120 * @param bool $double_encode Optional. Whether to encode existing HTML entities. Default false. 1121 * @return string The encoded text with HTML entities. 1122 */ 1123 function _wp_specialchars( $text, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) { 1124 $text = (string) $text; 1125 1126 if ( 0 === strlen( $text ) ) { 1127 return ''; 1128 } 1129 1130 // Don't bother if there are no specialchars - saves some processing. 1131 if ( ! preg_match( '/[&<>"\']/', $text ) ) { 1132 return $text; 1133 } 1134 1135 // Account for the previous behavior of the function when the $quote_style is not an accepted value. 1136 if ( empty( $quote_style ) ) { 1137 $quote_style = ENT_NOQUOTES; 1138 } elseif ( ENT_XML1 === $quote_style ) { 1139 $quote_style = ENT_QUOTES | ENT_XML1; 1140 } elseif ( ! in_array( $quote_style, array( ENT_NOQUOTES, ENT_COMPAT, ENT_QUOTES, 'single', 'double' ), true ) ) { 1141 $quote_style = ENT_QUOTES; 1142 } 1143 1144 $charset = _canonical_charset( $charset ? $charset : get_option( 'blog_charset' ) ); 1145 1146 $_quote_style = $quote_style; 1147 1148 if ( 'double' === $quote_style ) { 1149 $quote_style = ENT_COMPAT; 1150 $_quote_style = ENT_COMPAT; 1151 } elseif ( 'single' === $quote_style ) { 1152 $quote_style = ENT_NOQUOTES; 1153 } 1154 1155 if ( ! $double_encode ) { 1156 /* 1157 * Guarantee every &entity; is valid, convert &garbage; into &garbage; 1158 * This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable. 1159 */ 1160 $text = wp_kses_normalize_entities( $text, ( $quote_style & ENT_XML1 ) ? 'xml' : 'html' ); 1161 } 1162 1163 $text = htmlspecialchars( $text, $quote_style, $charset, $double_encode ); 1164 1165 // Back-compat. 1166 if ( 'single' === $_quote_style ) { 1167 $text = str_replace( "'", ''', $text ); 1168 } 1169 1170 return $text; 1171 } 1172 1173 /** 1174 * Converts a number of HTML entities into their special characters. 1175 * 1176 * Specifically deals with: `&`, `<`, `>`, `"`, and `'`. 1177 * 1178 * `$quote_style` can be set to ENT_COMPAT to decode `"` entities, 1179 * or ENT_QUOTES to do both `"` and `'`. Default is ENT_NOQUOTES where no quotes are decoded. 1180 * 1181 * @since 2.8.0 1182 * 1183 * @param string $text The text which is to be decoded. 1184 * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT, 1185 * both single and double if set to ENT_QUOTES or 1186 * none if set to ENT_NOQUOTES. 1187 * Also compatible with old _wp_specialchars() values; 1188 * converting single quotes if set to 'single', 1189 * double if set to 'double' or both if otherwise set. 1190 * Default is ENT_NOQUOTES. 1191 * @return string The decoded text without HTML entities. 1192 */ 1193 function wp_specialchars_decode( $text, $quote_style = ENT_NOQUOTES ) { 1194 $text = (string) $text; 1195 1196 if ( 0 === strlen( $text ) ) { 1197 return ''; 1198 } 1199 1200 // Don't bother if there are no entities - saves a lot of processing. 1201 if ( ! str_contains( $text, '&' ) ) { 1202 return $text; 1203 } 1204 1205 // Match the previous behavior of _wp_specialchars() when the $quote_style is not an accepted value. 1206 if ( empty( $quote_style ) ) { 1207 $quote_style = ENT_NOQUOTES; 1208 } elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) { 1209 $quote_style = ENT_QUOTES; 1210 } 1211 1212 // More complete than get_html_translation_table( HTML_SPECIALCHARS ). 1213 $single = array( 1214 ''' => '\'', 1215 ''' => '\'', 1216 ); 1217 $single_preg = array( 1218 '/�*39;/' => ''', 1219 '/�*27;/i' => ''', 1220 ); 1221 $double = array( 1222 '"' => '"', 1223 '"' => '"', 1224 '"' => '"', 1225 ); 1226 $double_preg = array( 1227 '/�*34;/' => '"', 1228 '/�*22;/i' => '"', 1229 ); 1230 $others = array( 1231 '<' => '<', 1232 '<' => '<', 1233 '>' => '>', 1234 '>' => '>', 1235 '&' => '&', 1236 '&' => '&', 1237 '&' => '&', 1238 ); 1239 $others_preg = array( 1240 '/�*60;/' => '<', 1241 '/�*62;/' => '>', 1242 '/�*38;/' => '&', 1243 '/�*26;/i' => '&', 1244 ); 1245 1246 if ( ENT_QUOTES === $quote_style ) { 1247 $translation = array_merge( $single, $double, $others ); 1248 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg ); 1249 } elseif ( ENT_COMPAT === $quote_style || 'double' === $quote_style ) { 1250 $translation = array_merge( $double, $others ); 1251 $translation_preg = array_merge( $double_preg, $others_preg ); 1252 } elseif ( 'single' === $quote_style ) { 1253 $translation = array_merge( $single, $others ); 1254 $translation_preg = array_merge( $single_preg, $others_preg ); 1255 } elseif ( ENT_NOQUOTES === $quote_style ) { 1256 $translation = $others; 1257 $translation_preg = $others_preg; 1258 } 1259 1260 // Remove zero padding on numeric entities. 1261 $text = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $text ); 1262 1263 // Replace characters according to translation table. 1264 return strtr( $text, $translation ); 1265 } 1266 1267 /** 1268 * Checks for invalid UTF8 in a string. 1269 * 1270 * @since 2.8.0 1271 * 1272 * @param string $text The text which is to be checked. 1273 * @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default false. 1274 * @return string The checked text. 1275 */ 1276 function wp_check_invalid_utf8( $text, $strip = false ) { 1277 $text = (string) $text; 1278 1279 if ( 0 === strlen( $text ) ) { 1280 return ''; 1281 } 1282 1283 // Store the site charset as a static to avoid multiple calls to get_option(). 1284 static $is_utf8 = null; 1285 if ( ! isset( $is_utf8 ) ) { 1286 $is_utf8 = is_utf8_charset(); 1287 } 1288 if ( ! $is_utf8 ) { 1289 return $text; 1290 } 1291 1292 // Check for support for utf8 in the installed PCRE library once and store the result in a static. 1293 static $utf8_pcre = null; 1294 if ( ! isset( $utf8_pcre ) ) { 1295 // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged 1296 $utf8_pcre = @preg_match( '/^./u', 'a' ); 1297 } 1298 // We can't demand utf8 in the PCRE installation, so just return the string in those cases. 1299 if ( ! $utf8_pcre ) { 1300 return $text; 1301 } 1302 1303 // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged -- preg_match fails when it encounters invalid UTF8 in $text. 1304 if ( 1 === @preg_match( '/^./us', $text ) ) { 1305 return $text; 1306 } 1307 1308 // Attempt to strip the bad chars if requested (not recommended). 1309 if ( $strip && function_exists( 'iconv' ) ) { 1310 return iconv( 'utf-8', 'utf-8', $text ); 1311 } 1312 1313 return ''; 1314 } 1315 1316 /** 1317 * Encodes the Unicode values to be used in the URI. 1318 * 1319 * @since 1.5.0 1320 * @since 5.8.3 Added the `encode_ascii_characters` parameter. 1321 * 1322 * @param string $utf8_string String to encode. 1323 * @param int $length Max length of the string. 1324 * @param bool $encode_ascii_characters Whether to encode ascii characters such as < " ' 1325 * @return string String with Unicode encoded for URI. 1326 */ 1327 function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters = false ) { 1328 $unicode = ''; 1329 $values = array(); 1330 $num_octets = 1; 1331 $unicode_length = 0; 1332 1333 mbstring_binary_safe_encoding(); 1334 $string_length = strlen( $utf8_string ); 1335 reset_mbstring_encoding(); 1336 1337 for ( $i = 0; $i < $string_length; $i++ ) { 1338 1339 $value = ord( $utf8_string[ $i ] ); 1340 1341 if ( $value < 128 ) { 1342 $char = chr( $value ); 1343 $encoded_char = $encode_ascii_characters ? rawurlencode( $char ) : $char; 1344 $encoded_char_length = strlen( $encoded_char ); 1345 if ( $length && ( $unicode_length + $encoded_char_length ) > $length ) { 1346 break; 1347 } 1348 $unicode .= $encoded_char; 1349 $unicode_length += $encoded_char_length; 1350 } else { 1351 if ( count( $values ) === 0 ) { 1352 if ( $value < 224 ) { 1353 $num_octets = 2; 1354 } elseif ( $value < 240 ) { 1355 $num_octets = 3; 1356 } else { 1357 $num_octets = 4; 1358 } 1359 } 1360 1361 $values[] = $value; 1362 1363 if ( $length && ( $unicode_length + ( $num_octets * 3 ) ) > $length ) { 1364 break; 1365 } 1366 if ( count( $values ) === $num_octets ) { 1367 for ( $j = 0; $j < $num_octets; $j++ ) { 1368 $unicode .= '%' . dechex( $values[ $j ] ); 1369 } 1370 1371 $unicode_length += $num_octets * 3; 1372 1373 $values = array(); 1374 $num_octets = 1; 1375 } 1376 } 1377 } 1378 1379 return $unicode; 1380 } 1381 1382 /** 1383 * Converts all accent characters to ASCII characters. 1384 * 1385 * If there are no accent characters, then the string given is just returned. 1386 * 1387 * **Accent characters converted:** 1388 * 1389 * Currency signs: 1390 * 1391 * | Code | Glyph | Replacement | Description | 1392 * | -------- | ----- | ----------- | ------------------- | 1393 * | U+00A3 | £ | (empty) | British Pound sign | 1394 * | U+20AC | € | E | Euro sign | 1395 * 1396 * Decompositions for Latin-1 Supplement: 1397 * 1398 * | Code | Glyph | Replacement | Description | 1399 * | ------- | ----- | ----------- | -------------------------------------- | 1400 * | U+00AA | ª | a | Feminine ordinal indicator | 1401 * | U+00BA | º | o | Masculine ordinal indicator | 1402 * | U+00C0 | À | A | Latin capital letter A with grave | 1403 * | U+00C1 | Á | A | Latin capital letter A with acute | 1404 * | U+00C2 |  | A | Latin capital letter A with circumflex | 1405 * | U+00C3 | à | A | Latin capital letter A with tilde | 1406 * | U+00C4 | Ä | A | Latin capital letter A with diaeresis | 1407 * | U+00C5 | Å | A | Latin capital letter A with ring above | 1408 * | U+00C6 | Æ | AE | Latin capital letter AE | 1409 * | U+00C7 | Ç | C | Latin capital letter C with cedilla | 1410 * | U+00C8 | È | E | Latin capital letter E with grave | 1411 * | U+00C9 | É | E | Latin capital letter E with acute | 1412 * | U+00CA | Ê | E | Latin capital letter E with circumflex | 1413 * | U+00CB | Ë | E | Latin capital letter E with diaeresis | 1414 * | U+00CC | Ì | I | Latin capital letter I with grave | 1415 * | U+00CD | Í | I | Latin capital letter I with acute | 1416 * | U+00CE | Î | I | Latin capital letter I with circumflex | 1417 * | U+00CF | Ï | I | Latin capital letter I with diaeresis | 1418 * | U+00D0 | Ð | D | Latin capital letter Eth | 1419 * | U+00D1 | Ñ | N | Latin capital letter N with tilde | 1420 * | U+00D2 | Ò | O | Latin capital letter O with grave | 1421 * | U+00D3 | Ó | O | Latin capital letter O with acute | 1422 * | U+00D4 | Ô | O | Latin capital letter O with circumflex | 1423 * | U+00D5 | Õ | O | Latin capital letter O with tilde | 1424 * | U+00D6 | Ö | O | Latin capital letter O with diaeresis | 1425 * | U+00D8 | Ø | O | Latin capital letter O with stroke | 1426 * | U+00D9 | Ù | U | Latin capital letter U with grave | 1427 * | U+00DA | Ú | U | Latin capital letter U with acute | 1428 * | U+00DB | Û | U | Latin capital letter U with circumflex | 1429 * | U+00DC | Ü | U | Latin capital letter U with diaeresis | 1430 * | U+00DD | Ý | Y | Latin capital letter Y with acute | 1431 * | U+00DE | Þ | TH | Latin capital letter Thorn | 1432 * | U+00DF | ß | s | Latin small letter sharp s | 1433 * | U+00E0 | à | a | Latin small letter a with grave | 1434 * | U+00E1 | á | a | Latin small letter a with acute | 1435 * | U+00E2 | â | a | Latin small letter a with circumflex | 1436 * | U+00E3 | ã | a | Latin small letter a with tilde | 1437 * | U+00E4 | ä | a | Latin small letter a with diaeresis | 1438 * | U+00E5 | å | a | Latin small letter a with ring above | 1439 * | U+00E6 | æ | ae | Latin small letter ae | 1440 * | U+00E7 | ç | c | Latin small letter c with cedilla | 1441 * | U+00E8 | è | e | Latin small letter e with grave | 1442 * | U+00E9 | é | e | Latin small letter e with acute | 1443 * | U+00EA | ê | e | Latin small letter e with circumflex | 1444 * | U+00EB | ë | e | Latin small letter e with diaeresis | 1445 * | U+00EC | ì | i | Latin small letter i with grave | 1446 * | U+00ED | í | i | Latin small letter i with acute | 1447 * | U+00EE | î | i | Latin small letter i with circumflex | 1448 * | U+00EF | ï | i | Latin small letter i with diaeresis | 1449 * | U+00F0 | ð | d | Latin small letter Eth | 1450 * | U+00F1 | ñ | n | Latin small letter n with tilde | 1451 * | U+00F2 | ò | o | Latin small letter o with grave | 1452 * | U+00F3 | ó | o | Latin small letter o with acute | 1453 * | U+00F4 | ô | o | Latin small letter o with circumflex | 1454 * | U+00F5 | õ | o | Latin small letter o with tilde | 1455 * | U+00F6 | ö | o | Latin small letter o with diaeresis | 1456 * | U+00F8 | ø | o | Latin small letter o with stroke | 1457 * | U+00F9 | ù | u | Latin small letter u with grave | 1458 * | U+00FA | ú | u | Latin small letter u with acute | 1459 * | U+00FB | û | u | Latin small letter u with circumflex | 1460 * | U+00FC | ü | u | Latin small letter u with diaeresis | 1461 * | U+00FD | ý | y | Latin small letter y with acute | 1462 * | U+00FE | þ | th | Latin small letter Thorn | 1463 * | U+00FF | ÿ | y | Latin small letter y with diaeresis | 1464 * 1465 * Decompositions for Latin Extended-A: 1466 * 1467 * | Code | Glyph | Replacement | Description | 1468 * | ------- | ----- | ----------- | ------------------------------------------------- | 1469 * | U+0100 | Ā | A | Latin capital letter A with macron | 1470 * | U+0101 | ā | a | Latin small letter a with macron | 1471 * | U+0102 | Ă | A | Latin capital letter A with breve | 1472 * | U+0103 | ă | a | Latin small letter a with breve | 1473 * | U+0104 | Ą | A | Latin capital letter A with ogonek | 1474 * | U+0105 | ą | a | Latin small letter a with ogonek | 1475 * | U+01006 | Ć | C | Latin capital letter C with acute | 1476 * | U+0107 | ć | c | Latin small letter c with acute | 1477 * | U+0108 | Ĉ | C | Latin capital letter C with circumflex | 1478 * | U+0109 | ĉ | c | Latin small letter c with circumflex | 1479 * | U+010A | Ċ | C | Latin capital letter C with dot above | 1480 * | U+010B | ċ | c | Latin small letter c with dot above | 1481 * | U+010C | Č | C | Latin capital letter C with caron | 1482 * | U+010D | č | c | Latin small letter c with caron | 1483 * | U+010E | Ď | D | Latin capital letter D with caron | 1484 * | U+010F | ď | d | Latin small letter d with caron | 1485 * | U+0110 | Đ | D | Latin capital letter D with stroke | 1486 * | U+0111 | đ | d | Latin small letter d with stroke | 1487 * | U+0112 | Ē | E | Latin capital letter E with macron | 1488 * | U+0113 | ē | e | Latin small letter e with macron | 1489 * | U+0114 | Ĕ | E | Latin capital letter E with breve | 1490 * | U+0115 | ĕ | e | Latin small letter e with breve | 1491 * | U+0116 | Ė | E | Latin capital letter E with dot above | 1492 * | U+0117 | ė | e | Latin small letter e with dot above | 1493 * | U+0118 | Ę | E | Latin capital letter E with ogonek | 1494 * | U+0119 | ę | e | Latin small letter e with ogonek | 1495 * | U+011A | Ě | E | Latin capital letter E with caron | 1496 * | U+011B | ě | e | Latin small letter e with caron | 1497 * | U+011C | Ĝ | G | Latin capital letter G with circumflex | 1498 * | U+011D | ĝ | g | Latin small letter g with circumflex | 1499 * | U+011E | Ğ | G | Latin capital letter G with breve | 1500 * | U+011F | ğ | g | Latin small letter g with breve | 1501 * | U+0120 | Ġ | G | Latin capital letter G with dot above | 1502 * | U+0121 | ġ | g | Latin small letter g with dot above | 1503 * | U+0122 | Ģ | G | Latin capital letter G with cedilla | 1504 * | U+0123 | ģ | g | Latin small letter g with cedilla | 1505 * | U+0124 | Ĥ | H | Latin capital letter H with circumflex | 1506 * | U+0125 | ĥ | h | Latin small letter h with circumflex | 1507 * | U+0126 | Ħ | H | Latin capital letter H with stroke | 1508 * | U+0127 | ħ | h | Latin small letter h with stroke | 1509 * | U+0128 | Ĩ | I | Latin capital letter I with tilde | 1510 * | U+0129 | ĩ | i | Latin small letter i with tilde | 1511 * | U+012A | Ī | I | Latin capital letter I with macron | 1512 * | U+012B | ī | i | Latin small letter i with macron | 1513 * | U+012C | Ĭ | I | Latin capital letter I with breve | 1514 * | U+012D | ĭ | i | Latin small letter i with breve | 1515 * | U+012E | Į | I | Latin capital letter I with ogonek | 1516 * | U+012F | į | i | Latin small letter i with ogonek | 1517 * | U+0130 | İ | I | Latin capital letter I with dot above | 1518 * | U+0131 | ı | i | Latin small letter dotless i | 1519 * | U+0132 | IJ | IJ | Latin capital ligature IJ | 1520 * | U+0133 | ij | ij | Latin small ligature ij | 1521 * | U+0134 | Ĵ | J | Latin capital letter J with circumflex | 1522 * | U+0135 | ĵ | j | Latin small letter j with circumflex | 1523 * | U+0136 | Ķ | K | Latin capital letter K with cedilla | 1524 * | U+0137 | ķ | k | Latin small letter k with cedilla | 1525 * | U+0138 | ĸ | k | Latin small letter Kra | 1526 * | U+0139 | Ĺ | L | Latin capital letter L with acute | 1527 * | U+013A | ĺ | l | Latin small letter l with acute | 1528 * | U+013B | Ļ | L | Latin capital letter L with cedilla | 1529 * | U+013C | ļ | l | Latin small letter l with cedilla | 1530 * | U+013D | Ľ | L | Latin capital letter L with caron | 1531 * | U+013E | ľ | l | Latin small letter l with caron | 1532 * | U+013F | Ŀ | L | Latin capital letter L with middle dot | 1533 * | U+0140 | ŀ | l | Latin small letter l with middle dot | 1534 * | U+0141 | Ł | L | Latin capital letter L with stroke | 1535 * | U+0142 | ł | l | Latin small letter l with stroke | 1536 * | U+0143 | Ń | N | Latin capital letter N with acute | 1537 * | U+0144 | ń | n | Latin small letter N with acute | 1538 * | U+0145 | Ņ | N | Latin capital letter N with cedilla | 1539 * | U+0146 | ņ | n | Latin small letter n with cedilla | 1540 * | U+0147 | Ň | N | Latin capital letter N with caron | 1541 * | U+0148 | ň | n | Latin small letter n with caron | 1542 * | U+0149 | ʼn | n | Latin small letter n preceded by apostrophe | 1543 * | U+014A | Ŋ | N | Latin capital letter Eng | 1544 * | U+014B | ŋ | n | Latin small letter Eng | 1545 * | U+014C | Ō | O | Latin capital letter O with macron | 1546 * | U+014D | ō | o | Latin small letter o with macron | 1547 * | U+014E | Ŏ | O | Latin capital letter O with breve | 1548 * | U+014F | ŏ | o | Latin small letter o with breve | 1549 * | U+0150 | Ő | O | Latin capital letter O with double acute | 1550 * | U+0151 | ő | o | Latin small letter o with double acute | 1551 * | U+0152 | Œ | OE | Latin capital ligature OE | 1552 * | U+0153 | œ | oe | Latin small ligature oe | 1553 * | U+0154 | Ŕ | R | Latin capital letter R with acute | 1554 * | U+0155 | ŕ | r | Latin small letter r with acute | 1555 * | U+0156 | Ŗ | R | Latin capital letter R with cedilla | 1556 * | U+0157 | ŗ | r | Latin small letter r with cedilla | 1557 * | U+0158 | Ř | R | Latin capital letter R with caron | 1558 * | U+0159 | ř | r | Latin small letter r with caron | 1559 * | U+015A | Ś | S | Latin capital letter S with acute | 1560 * | U+015B | ś | s | Latin small letter s with acute | 1561 * | U+015C | Ŝ | S | Latin capital letter S with circumflex | 1562 * | U+015D | ŝ | s | Latin small letter s with circumflex | 1563 * | U+015E | Ş | S | Latin capital letter S with cedilla | 1564 * | U+015F | ş | s | Latin small letter s with cedilla | 1565 * | U+0160 | Š | S | Latin capital letter S with caron | 1566 * | U+0161 | š | s | Latin small letter s with caron | 1567 * | U+0162 | Ţ | T | Latin capital letter T with cedilla | 1568 * | U+0163 | ţ | t | Latin small letter t with cedilla | 1569 * | U+0164 | Ť | T | Latin capital letter T with caron | 1570 * | U+0165 | ť | t | Latin small letter t with caron | 1571 * | U+0166 | Ŧ | T | Latin capital letter T with stroke | 1572 * | U+0167 | ŧ | t | Latin small letter t with stroke | 1573 * | U+0168 | Ũ | U | Latin capital letter U with tilde | 1574 * | U+0169 | ũ | u | Latin small letter u with tilde | 1575 * | U+016A | Ū | U | Latin capital letter U with macron | 1576 * | U+016B | ū | u | Latin small letter u with macron | 1577 * | U+016C | Ŭ | U | Latin capital letter U with breve | 1578 * | U+016D | ŭ | u | Latin small letter u with breve | 1579 * | U+016E | Ů | U | Latin capital letter U with ring above | 1580 * | U+016F | ů | u | Latin small letter u with ring above | 1581 * | U+0170 | Ű | U | Latin capital letter U with double acute | 1582 * | U+0171 | ű | u | Latin small letter u with double acute | 1583 * | U+0172 | Ų | U | Latin capital letter U with ogonek | 1584 * | U+0173 | ų | u | Latin small letter u with ogonek | 1585 * | U+0174 | Ŵ | W | Latin capital letter W with circumflex | 1586 * | U+0175 | ŵ | w | Latin small letter w with circumflex | 1587 * | U+0176 | Ŷ | Y | Latin capital letter Y with circumflex | 1588 * | U+0177 | ŷ | y | Latin small letter y with circumflex | 1589 * | U+0178 | Ÿ | Y | Latin capital letter Y with diaeresis | 1590 * | U+0179 | Ź | Z | Latin capital letter Z with acute | 1591 * | U+017A | ź | z | Latin small letter z with acute | 1592 * | U+017B | Ż | Z | Latin capital letter Z with dot above | 1593 * | U+017C | ż | z | Latin small letter z with dot above | 1594 * | U+017D | Ž | Z | Latin capital letter Z with caron | 1595 * | U+017E | ž | z | Latin small letter z with caron | 1596 * | U+017F | ſ | s | Latin small letter long s | 1597 * | U+01A0 | Ơ | O | Latin capital letter O with horn | 1598 * | U+01A1 | ơ | o | Latin small letter o with horn | 1599 * | U+01AF | Ư | U | Latin capital letter U with horn | 1600 * | U+01B0 | ư | u | Latin small letter u with horn | 1601 * | U+01CD | Ǎ | A | Latin capital letter A with caron | 1602 * | U+01CE | ǎ | a | Latin small letter a with caron | 1603 * | U+01CF | Ǐ | I | Latin capital letter I with caron | 1604 * | U+01D0 | ǐ | i | Latin small letter i with caron | 1605 * | U+01D1 | Ǒ | O | Latin capital letter O with caron | 1606 * | U+01D2 | ǒ | o | Latin small letter o with caron | 1607 * | U+01D3 | Ǔ | U | Latin capital letter U with caron | 1608 * | U+01D4 | ǔ | u | Latin small letter u with caron | 1609 * | U+01D5 | Ǖ | U | Latin capital letter U with diaeresis and macron | 1610 * | U+01D6 | ǖ | u | Latin small letter u with diaeresis and macron | 1611 * | U+01D7 | Ǘ | U | Latin capital letter U with diaeresis and acute | 1612 * | U+01D8 | ǘ | u | Latin small letter u with diaeresis and acute | 1613 * | U+01D9 | Ǚ | U | Latin capital letter U with diaeresis and caron | 1614 * | U+01DA | ǚ | u | Latin small letter u with diaeresis and caron | 1615 * | U+01DB | Ǜ | U | Latin capital letter U with diaeresis and grave | 1616 * | U+01DC | ǜ | u | Latin small letter u with diaeresis and grave | 1617 * 1618 * Decompositions for Latin Extended-B: 1619 * 1620 * | Code | Glyph | Replacement | Description | 1621 * | -------- | ----- | ----------- | ----------------------------------------- | 1622 * | U+018F | Ə | E | Latin capital letter Ə | 1623 * | U+0259 | ǝ | e | Latin small letter ǝ | 1624 * | U+0218 | Ș | S | Latin capital letter S with comma below | 1625 * | U+0219 | ș | s | Latin small letter s with comma below | 1626 * | U+021A | Ț | T | Latin capital letter T with comma below | 1627 * | U+021B | ț | t | Latin small letter t with comma below | 1628 * 1629 * Vowels with diacritic (Chinese, Hanyu Pinyin): 1630 * 1631 * | Code | Glyph | Replacement | Description | 1632 * | -------- | ----- | ----------- | ----------------------------------------------------- | 1633 * | U+0251 | ɑ | a | Latin small letter alpha | 1634 * | U+1EA0 | Ạ | A | Latin capital letter A with dot below | 1635 * | U+1EA1 | ạ | a | Latin small letter a with dot below | 1636 * | U+1EA2 | Ả | A | Latin capital letter A with hook above | 1637 * | U+1EA3 | ả | a | Latin small letter a with hook above | 1638 * | U+1EA4 | Ấ | A | Latin capital letter A with circumflex and acute | 1639 * | U+1EA5 | ấ | a | Latin small letter a with circumflex and acute | 1640 * | U+1EA6 | Ầ | A | Latin capital letter A with circumflex and grave | 1641 * | U+1EA7 | ầ | a | Latin small letter a with circumflex and grave | 1642 * | U+1EA8 | Ẩ | A | Latin capital letter A with circumflex and hook above | 1643 * | U+1EA9 | ẩ | a | Latin small letter a with circumflex and hook above | 1644 * | U+1EAA | Ẫ | A | Latin capital letter A with circumflex and tilde | 1645 * | U+1EAB | ẫ | a | Latin small letter a with circumflex and tilde | 1646 * | U+1EA6 | Ậ | A | Latin capital letter A with circumflex and dot below | 1647 * | U+1EAD | ậ | a | Latin small letter a with circumflex and dot below | 1648 * | U+1EAE | Ắ | A | Latin capital letter A with breve and acute | 1649 * | U+1EAF | ắ | a | Latin small letter a with breve and acute | 1650 * | U+1EB0 | Ằ | A | Latin capital letter A with breve and grave | 1651 * | U+1EB1 | ằ | a | Latin small letter a with breve and grave | 1652 * | U+1EB2 | Ẳ | A | Latin capital letter A with breve and hook above | 1653 * | U+1EB3 | ẳ | a | Latin small letter a with breve and hook above | 1654 * | U+1EB4 | Ẵ | A | Latin capital letter A with breve and tilde | 1655 * | U+1EB5 | ẵ | a | Latin small letter a with breve and tilde | 1656 * | U+1EB6 | Ặ | A | Latin capital letter A with breve and dot below | 1657 * | U+1EB7 | ặ | a | Latin small letter a with breve and dot below | 1658 * | U+1EB8 | Ẹ | E | Latin capital letter E with dot below | 1659 * | U+1EB9 | ẹ | e | Latin small letter e with dot below | 1660 * | U+1EBA | Ẻ | E | Latin capital letter E with hook above | 1661 * | U+1EBB | ẻ | e | Latin small letter e with hook above | 1662 * | U+1EBC | Ẽ | E | Latin capital letter E with tilde | 1663 * | U+1EBD | ẽ | e | Latin small letter e with tilde | 1664 * | U+1EBE | Ế | E | Latin capital letter E with circumflex and acute | 1665 * | U+1EBF | ế | e | Latin small letter e with circumflex and acute | 1666 * | U+1EC0 | Ề | E | Latin capital letter E with circumflex and grave | 1667 * | U+1EC1 | ề | e | Latin small letter e with circumflex and grave | 1668 * | U+1EC2 | Ể | E | Latin capital letter E with circumflex and hook above | 1669 * | U+1EC3 | ể | e | Latin small letter e with circumflex and hook above | 1670 * | U+1EC4 | Ễ | E | Latin capital letter E with circumflex and tilde | 1671 * | U+1EC5 | ễ | e | Latin small letter e with circumflex and tilde | 1672 * | U+1EC6 | Ệ | E | Latin capital letter E with circumflex and dot below | 1673 * | U+1EC7 | ệ | e | Latin small letter e with circumflex and dot below | 1674 * | U+1EC8 | Ỉ | I | Latin capital letter I with hook above | 1675 * | U+1EC9 | ỉ | i | Latin small letter i with hook above | 1676 * | U+1ECA | Ị | I | Latin capital letter I with dot below | 1677 * | U+1ECB | ị | i | Latin small letter i with dot below | 1678 * | U+1ECC | Ọ | O | Latin capital letter O with dot below | 1679 * | U+1ECD | ọ | o | Latin small letter o with dot below | 1680 * | U+1ECE | Ỏ | O | Latin capital letter O with hook above | 1681 * | U+1ECF | ỏ | o | Latin small letter o with hook above | 1682 * | U+1ED0 | Ố | O | Latin capital letter O with circumflex and acute | 1683 * | U+1ED1 | ố | o | Latin small letter o with circumflex and acute | 1684 * | U+1ED2 | Ồ | O | Latin capital letter O with circumflex and grave | 1685 * | U+1ED3 | ồ | o | Latin small letter o with circumflex and grave | 1686 * | U+1ED4 | Ổ | O | Latin capital letter O with circumflex and hook above | 1687 * | U+1ED5 | ổ | o | Latin small letter o with circumflex and hook above | 1688 * | U+1ED6 | Ỗ | O | Latin capital letter O with circumflex and tilde | 1689 * | U+1ED7 | ỗ | o | Latin small letter o with circumflex and tilde | 1690 * | U+1ED8 | Ộ | O | Latin capital letter O with circumflex and dot below | 1691 * | U+1ED9 | ộ | o | Latin small letter o with circumflex and dot below | 1692 * | U+1EDA | Ớ | O | Latin capital letter O with horn and acute | 1693 * | U+1EDB | ớ | o | Latin small letter o with horn and acute | 1694 * | U+1EDC | Ờ | O | Latin capital letter O with horn and grave | 1695 * | U+1EDD | ờ | o | Latin small letter o with horn and grave | 1696 * | U+1EDE | Ở | O | Latin capital letter O with horn and hook above | 1697 * | U+1EDF | ở | o | Latin small letter o with horn and hook above | 1698 * | U+1EE0 | Ỡ | O | Latin capital letter O with horn and tilde | 1699 * | U+1EE1 | ỡ | o | Latin small letter o with horn and tilde | 1700 * | U+1EE2 | Ợ | O | Latin capital letter O with horn and dot below | 1701 * | U+1EE3 | ợ | o | Latin small letter o with horn and dot below | 1702 * | U+1EE4 | Ụ | U | Latin capital letter U with dot below | 1703 * | U+1EE5 | ụ | u | Latin small letter u with dot below | 1704 * | U+1EE6 | Ủ | U | Latin capital letter U with hook above | 1705 * | U+1EE7 | ủ | u | Latin small letter u with hook above | 1706 * | U+1EE8 | Ứ | U | Latin capital letter U with horn and acute | 1707 * | U+1EE9 | ứ | u | Latin small letter u with horn and acute | 1708 * | U+1EEA | Ừ | U | Latin capital letter U with horn and grave | 1709 * | U+1EEB | ừ | u | Latin small letter u with horn and grave | 1710 * | U+1EEC | Ử | U | Latin capital letter U with horn and hook above | 1711 * | U+1EED | ử | u | Latin small letter u with horn and hook above | 1712 * | U+1EEE | Ữ | U | Latin capital letter U with horn and tilde | 1713 * | U+1EEF | ữ | u | Latin small letter u with horn and tilde | 1714 * | U+1EF0 | Ự | U | Latin capital letter U with horn and dot below | 1715 * | U+1EF1 | ự | u | Latin small letter u with horn and dot below | 1716 * | U+1EF2 | Ỳ | Y | Latin capital letter Y with grave | 1717 * | U+1EF3 | ỳ | y | Latin small letter y with grave | 1718 * | U+1EF4 | Ỵ | Y | Latin capital letter Y with dot below | 1719 * | U+1EF5 | ỵ | y | Latin small letter y with dot below | 1720 * | U+1EF6 | Ỷ | Y | Latin capital letter Y with hook above | 1721 * | U+1EF7 | ỷ | y | Latin small letter y with hook above | 1722 * | U+1EF8 | Ỹ | Y | Latin capital letter Y with tilde | 1723 * | U+1EF9 | ỹ | y | Latin small letter y with tilde | 1724 * 1725 * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`), 1726 * German (Switzerland) informal (`de_CH_informal`), and German (Austria) (`de_AT`) locales: 1727 * 1728 * | Code | Glyph | Replacement | Description | 1729 * | -------- | ----- | ----------- | --------------------------------------- | 1730 * | U+00C4 | Ä | Ae | Latin capital letter A with diaeresis | 1731 * | U+00E4 | ä | ae | Latin small letter a with diaeresis | 1732 * | U+00D6 | Ö | Oe | Latin capital letter O with diaeresis | 1733 * | U+00F6 | ö | oe | Latin small letter o with diaeresis | 1734 * | U+00DC | Ü | Ue | Latin capital letter U with diaeresis | 1735 * | U+00FC | ü | ue | Latin small letter u with diaeresis | 1736 * | U+00DF | ß | ss | Latin small letter sharp s | 1737 * 1738 * Danish (`da_DK`) locale: 1739 * 1740 * | Code | Glyph | Replacement | Description | 1741 * | -------- | ----- | ----------- | --------------------------------------- | 1742 * | U+00C6 | Æ | Ae | Latin capital letter AE | 1743 * | U+00E6 | æ | ae | Latin small letter ae | 1744 * | U+00D8 | Ø | Oe | Latin capital letter O with stroke | 1745 * | U+00F8 | ø | oe | Latin small letter o with stroke | 1746 * | U+00C5 | Å | Aa | Latin capital letter A with ring above | 1747 * | U+00E5 | å | aa | Latin small letter a with ring above | 1748 * 1749 * Catalan (`ca`) locale: 1750 * 1751 * | Code | Glyph | Replacement | Description | 1752 * | -------- | ----- | ----------- | --------------------------------------- | 1753 * | U+00B7 | l·l | ll | Flown dot (between two Ls) | 1754 * 1755 * Serbian (`sr_RS`) and Bosnian (`bs_BA`) locales: 1756 * 1757 * | Code | Glyph | Replacement | Description | 1758 * | -------- | ----- | ----------- | --------------------------------------- | 1759 * | U+0110 | Đ | DJ | Latin capital letter D with stroke | 1760 * | U+0111 | đ | dj | Latin small letter d with stroke | 1761 * 1762 * @since 1.2.1 1763 * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`. 1764 * @since 4.7.0 Added locale support for `sr_RS`. 1765 * @since 4.8.0 Added locale support for `bs_BA`. 1766 * @since 5.7.0 Added locale support for `de_AT`. 1767 * @since 6.0.0 Added the `$locale` parameter. 1768 * @since 6.1.0 Added Unicode NFC encoding normalization support. 1769 * 1770 * @param string $text Text that might have accent characters. 1771 * @param string $locale Optional. The locale to use for accent removal. Some character 1772 * replacements depend on the locale being used (e.g. 'de_DE'). 1773 * Defaults to the current locale. 1774 * @return string Filtered string with replaced "nice" characters. 1775 */ 1776 function remove_accents( $text, $locale = '' ) { 1777 if ( ! preg_match( '/[\x80-\xff]/', $text ) ) { 1778 return $text; 1779 } 1780 1781 if ( wp_is_valid_utf8( $text ) ) { 1782 1783 /* 1784 * Unicode sequence normalization from NFD (Normalization Form Decomposed) 1785 * to NFC (Normalization Form [Pre]Composed), the encoding used in this function. 1786 */ 1787 if ( function_exists( 'normalizer_is_normalized' ) 1788 && function_exists( 'normalizer_normalize' ) 1789 ) { 1790 if ( ! normalizer_is_normalized( $text ) ) { 1791 $text = normalizer_normalize( $text ); 1792 } 1793 } 1794 1795 $chars = array( 1796 // Decompositions for Latin-1 Supplement. 1797 'ª' => 'a', 1798 'º' => 'o', 1799 'À' => 'A', 1800 'Á' => 'A', 1801 'Â' => 'A', 1802 'Ã' => 'A', 1803 'Ä' => 'A', 1804 'Å' => 'A', 1805 'Æ' => 'AE', 1806 'Ç' => 'C', 1807 'È' => 'E', 1808 'É' => 'E', 1809 'Ê' => 'E', 1810 'Ë' => 'E', 1811 'Ì' => 'I', 1812 'Í' => 'I', 1813 'Î' => 'I', 1814 'Ï' => 'I', 1815 'Ð' => 'D', 1816 'Ñ' => 'N', 1817 'Ò' => 'O', 1818 'Ó' => 'O', 1819 'Ô' => 'O', 1820 'Õ' => 'O', 1821 'Ö' => 'O', 1822 'Ù' => 'U', 1823 'Ú' => 'U', 1824 'Û' => 'U', 1825 'Ü' => 'U', 1826 'Ý' => 'Y', 1827 'Þ' => 'TH', 1828 'ß' => 's', 1829 'à' => 'a', 1830 'á' => 'a', 1831 'â' => 'a', 1832 'ã' => 'a', 1833 'ä' => 'a', 1834 'å' => 'a', 1835 'æ' => 'ae', 1836 'ç' => 'c', 1837 'è' => 'e', 1838 'é' => 'e', 1839 'ê' => 'e', 1840 'ë' => 'e', 1841 'ì' => 'i', 1842 'í' => 'i', 1843 'î' => 'i', 1844 'ï' => 'i', 1845 'ð' => 'd', 1846 'ñ' => 'n', 1847 'ò' => 'o', 1848 'ó' => 'o', 1849 'ô' => 'o', 1850 'õ' => 'o', 1851 'ö' => 'o', 1852 'ø' => 'o', 1853 'ù' => 'u', 1854 'ú' => 'u', 1855 'û' => 'u', 1856 'ü' => 'u', 1857 'ý' => 'y', 1858 'þ' => 'th', 1859 'ÿ' => 'y', 1860 'Ø' => 'O', 1861 // Decompositions for Latin Extended-A. 1862 'Ā' => 'A', 1863 'ā' => 'a', 1864 'Ă' => 'A', 1865 'ă' => 'a', 1866 'Ą' => 'A', 1867 'ą' => 'a', 1868 'Ć' => 'C', 1869 'ć' => 'c', 1870 'Ĉ' => 'C', 1871 'ĉ' => 'c', 1872 'Ċ' => 'C', 1873 'ċ' => 'c', 1874 'Č' => 'C', 1875 'č' => 'c', 1876 'Ď' => 'D', 1877 'ď' => 'd', 1878 'Đ' => 'D', 1879 'đ' => 'd', 1880 'Ē' => 'E', 1881 'ē' => 'e', 1882 'Ĕ' => 'E', 1883 'ĕ' => 'e', 1884 'Ė' => 'E', 1885 'ė' => 'e', 1886 'Ę' => 'E', 1887 'ę' => 'e', 1888 'Ě' => 'E', 1889 'ě' => 'e', 1890 'Ĝ' => 'G', 1891 'ĝ' => 'g', 1892 'Ğ' => 'G', 1893 'ğ' => 'g', 1894 'Ġ' => 'G', 1895 'ġ' => 'g', 1896 'Ģ' => 'G', 1897 'ģ' => 'g', 1898 'Ĥ' => 'H', 1899 'ĥ' => 'h', 1900 'Ħ' => 'H', 1901 'ħ' => 'h', 1902 'Ĩ' => 'I', 1903 'ĩ' => 'i', 1904 'Ī' => 'I', 1905 'ī' => 'i', 1906 'Ĭ' => 'I', 1907 'ĭ' => 'i', 1908 'Į' => 'I', 1909 'į' => 'i', 1910 'İ' => 'I', 1911 'ı' => 'i', 1912 'IJ' => 'IJ', 1913 'ij' => 'ij', 1914 'Ĵ' => 'J', 1915 'ĵ' => 'j', 1916 'Ķ' => 'K', 1917 'ķ' => 'k', 1918 'ĸ' => 'k', 1919 'Ĺ' => 'L', 1920 'ĺ' => 'l', 1921 'Ļ' => 'L', 1922 'ļ' => 'l', 1923 'Ľ' => 'L', 1924 'ľ' => 'l', 1925 'Ŀ' => 'L', 1926 'ŀ' => 'l', 1927 'Ł' => 'L', 1928 'ł' => 'l', 1929 'Ń' => 'N', 1930 'ń' => 'n', 1931 'Ņ' => 'N', 1932 'ņ' => 'n', 1933 'Ň' => 'N', 1934 'ň' => 'n', 1935 'ʼn' => 'n', 1936 'Ŋ' => 'N', 1937 'ŋ' => 'n', 1938 'Ō' => 'O', 1939 'ō' => 'o', 1940 'Ŏ' => 'O', 1941 'ŏ' => 'o', 1942 'Ő' => 'O', 1943 'ő' => 'o', 1944 'Œ' => 'OE', 1945 'œ' => 'oe', 1946 'Ŕ' => 'R', 1947 'ŕ' => 'r', 1948 'Ŗ' => 'R', 1949 'ŗ' => 'r', 1950 'Ř' => 'R', 1951 'ř' => 'r', 1952 'Ś' => 'S', 1953 'ś' => 's', 1954 'Ŝ' => 'S', 1955 'ŝ' => 's', 1956 'Ş' => 'S', 1957 'ş' => 's', 1958 'Š' => 'S', 1959 'š' => 's', 1960 'Ţ' => 'T', 1961 'ţ' => 't', 1962 'Ť' => 'T', 1963 'ť' => 't', 1964 'Ŧ' => 'T', 1965 'ŧ' => 't', 1966 'Ũ' => 'U', 1967 'ũ' => 'u', 1968 'Ū' => 'U', 1969 'ū' => 'u', 1970 'Ŭ' => 'U', 1971 'ŭ' => 'u', 1972 'Ů' => 'U', 1973 'ů' => 'u', 1974 'Ű' => 'U', 1975 'ű' => 'u', 1976 'Ų' => 'U', 1977 'ų' => 'u', 1978 'Ŵ' => 'W', 1979 'ŵ' => 'w', 1980 'Ŷ' => 'Y', 1981 'ŷ' => 'y', 1982 'Ÿ' => 'Y', 1983 'Ź' => 'Z', 1984 'ź' => 'z', 1985 'Ż' => 'Z', 1986 'ż' => 'z', 1987 'Ž' => 'Z', 1988 'ž' => 'z', 1989 'ſ' => 's', 1990 // Decompositions for Latin Extended-B. 1991 'Ə' => 'E', 1992 'ǝ' => 'e', 1993 'Ș' => 'S', 1994 'ș' => 's', 1995 'Ț' => 'T', 1996 'ț' => 't', 1997 // Euro sign. 1998 '€' => 'E', 1999 // GBP (Pound) sign. 2000 '£' => '', 2001 // Vowels with diacritic (Vietnamese). Unmarked. 2002 'Ơ' => 'O', 2003 'ơ' => 'o', 2004 'Ư' => 'U', 2005 'ư' => 'u', 2006 // Grave accent. 2007 'Ầ' => 'A', 2008 'ầ' => 'a', 2009 'Ằ' => 'A', 2010 'ằ' => 'a', 2011 'Ề' => 'E', 2012 'ề' => 'e', 2013 'Ồ' => 'O', 2014 'ồ' => 'o', 2015 'Ờ' => 'O', 2016 'ờ' => 'o', 2017 'Ừ' => 'U', 2018 'ừ' => 'u', 2019 'Ỳ' => 'Y', 2020 'ỳ' => 'y', 2021 // Hook. 2022 'Ả' => 'A', 2023 'ả' => 'a', 2024 'Ẩ' => 'A', 2025 'ẩ' => 'a', 2026 'Ẳ' => 'A', 2027 'ẳ' => 'a', 2028 'Ẻ' => 'E', 2029 'ẻ' => 'e', 2030 'Ể' => 'E', 2031 'ể' => 'e', 2032 'Ỉ' => 'I', 2033 'ỉ' => 'i', 2034 'Ỏ' => 'O', 2035 'ỏ' => 'o', 2036 'Ổ' => 'O', 2037 'ổ' => 'o', 2038 'Ở' => 'O', 2039 'ở' => 'o', 2040 'Ủ' => 'U', 2041 'ủ' => 'u', 2042 'Ử' => 'U', 2043 'ử' => 'u', 2044 'Ỷ' => 'Y', 2045 'ỷ' => 'y', 2046 // Tilde. 2047 'Ẫ' => 'A', 2048 'ẫ' => 'a', 2049 'Ẵ' => 'A', 2050 'ẵ' => 'a', 2051 'Ẽ' => 'E', 2052 'ẽ' => 'e', 2053 'Ễ' => 'E', 2054 'ễ' => 'e', 2055 'Ỗ' => 'O', 2056 'ỗ' => 'o', 2057 'Ỡ' => 'O', 2058 'ỡ' => 'o', 2059 'Ữ' => 'U', 2060 'ữ' => 'u', 2061 'Ỹ' => 'Y', 2062 'ỹ' => 'y', 2063 // Acute accent. 2064 'Ấ' => 'A', 2065 'ấ' => 'a', 2066 'Ắ' => 'A', 2067 'ắ' => 'a', 2068 'Ế' => 'E', 2069 'ế' => 'e', 2070 'Ố' => 'O', 2071 'ố' => 'o', 2072 'Ớ' => 'O', 2073 'ớ' => 'o', 2074 'Ứ' => 'U', 2075 'ứ' => 'u', 2076 // Dot below. 2077 'Ạ' => 'A', 2078 'ạ' => 'a', 2079 'Ậ' => 'A', 2080 'ậ' => 'a', 2081 'Ặ' => 'A', 2082 'ặ' => 'a', 2083 'Ẹ' => 'E', 2084 'ẹ' => 'e', 2085 'Ệ' => 'E', 2086 'ệ' => 'e', 2087 'Ị' => 'I', 2088 'ị' => 'i', 2089 'Ọ' => 'O', 2090 'ọ' => 'o', 2091 'Ộ' => 'O', 2092 'ộ' => 'o', 2093 'Ợ' => 'O', 2094 'ợ' => 'o', 2095 'Ụ' => 'U', 2096 'ụ' => 'u', 2097 'Ự' => 'U', 2098 'ự' => 'u', 2099 'Ỵ' => 'Y', 2100 'ỵ' => 'y', 2101 // Vowels with diacritic (Chinese, Hanyu Pinyin). 2102 'ɑ' => 'a', 2103 // Macron. 2104 'Ǖ' => 'U', 2105 'ǖ' => 'u', 2106 // Acute accent. 2107 'Ǘ' => 'U', 2108 'ǘ' => 'u', 2109 // Caron. 2110 'Ǎ' => 'A', 2111 'ǎ' => 'a', 2112 'Ǐ' => 'I', 2113 'ǐ' => 'i', 2114 'Ǒ' => 'O', 2115 'ǒ' => 'o', 2116 'Ǔ' => 'U', 2117 'ǔ' => 'u', 2118 'Ǚ' => 'U', 2119 'ǚ' => 'u', 2120 // Grave accent. 2121 'Ǜ' => 'U', 2122 'ǜ' => 'u', 2123 ); 2124 2125 // Used for locale-specific rules. 2126 if ( empty( $locale ) ) { 2127 $locale = get_locale(); 2128 } 2129 2130 /* 2131 * German has various locales (de_DE, de_CH, de_AT, ...) with formal and informal variants. 2132 * There is no 3-letter locale like 'def', so checking for 'de' instead of 'de_' is safe, 2133 * since 'de' itself would be a valid locale too. 2134 */ 2135 if ( str_starts_with( $locale, 'de' ) ) { 2136 $chars['Ä'] = 'Ae'; 2137 $chars['ä'] = 'ae'; 2138 $chars['Ö'] = 'Oe'; 2139 $chars['ö'] = 'oe'; 2140 $chars['Ü'] = 'Ue'; 2141 $chars['ü'] = 'ue'; 2142 $chars['ß'] = 'ss'; 2143 } elseif ( 'da_DK' === $locale ) { 2144 $chars['Æ'] = 'Ae'; 2145 $chars['æ'] = 'ae'; 2146 $chars['Ø'] = 'Oe'; 2147 $chars['ø'] = 'oe'; 2148 $chars['Å'] = 'Aa'; 2149 $chars['å'] = 'aa'; 2150 } elseif ( 'ca' === $locale ) { 2151 $chars['l·l'] = 'll'; 2152 } elseif ( 'sr_RS' === $locale || 'bs_BA' === $locale ) { 2153 $chars['Đ'] = 'DJ'; 2154 $chars['đ'] = 'dj'; 2155 } 2156 2157 $text = strtr( $text, $chars ); 2158 } else { 2159 $chars = array(); 2160 // Assume ISO-8859-1 if not UTF-8. 2161 $chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e" 2162 . "\x9f\xa2\xa5\xb5\xc0\xc1\xc2" 2163 . "\xc3\xc4\xc5\xc7\xc8\xc9\xca" 2164 . "\xcb\xcc\xcd\xce\xcf\xd1\xd2" 2165 . "\xd3\xd4\xd5\xd6\xd8\xd9\xda" 2166 . "\xdb\xdc\xdd\xe0\xe1\xe2\xe3" 2167 . "\xe4\xe5\xe7\xe8\xe9\xea\xeb" 2168 . "\xec\xed\xee\xef\xf1\xf2\xf3" 2169 . "\xf4\xf5\xf6\xf8\xf9\xfa\xfb" 2170 . "\xfc\xfd\xff"; 2171 2172 $chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy'; 2173 2174 $text = strtr( $text, $chars['in'], $chars['out'] ); 2175 $double_chars = array(); 2176 $double_chars['in'] = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" ); 2177 $double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' ); 2178 $text = str_replace( $double_chars['in'], $double_chars['out'], $text ); 2179 } 2180 2181 return $text; 2182 } 2183 2184 /** 2185 * Sanitizes a filename, replacing whitespace with dashes. 2186 * 2187 * Removes special characters that are illegal in filenames on certain 2188 * operating systems and special characters requiring special escaping 2189 * to manipulate at the command line. Replaces spaces and consecutive 2190 * dashes with a single dash. Trims period, dash and underscore from beginning 2191 * and end of filename. It is not guaranteed that this function will return a 2192 * filename that is allowed to be uploaded. 2193 * 2194 * @since 2.1.0 2195 * 2196 * @param string $filename The filename to be sanitized. 2197 * @return string The sanitized filename. 2198 */ 2199 function sanitize_file_name( $filename ) { 2200 $filename_raw = $filename; 2201 $filename = remove_accents( $filename ); 2202 2203 $special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '|', '~', '`', '!', '{', '}', '%', '+', '’', '«', '»', '”', '“', chr( 0 ) ); 2204 2205 if ( ! wp_is_valid_utf8( $filename ) ) { 2206 $_ext = pathinfo( $filename, PATHINFO_EXTENSION ); 2207 $_name = pathinfo( $filename, PATHINFO_FILENAME ); 2208 $filename = sanitize_title_with_dashes( $_name ) . '.' . $_ext; 2209 } 2210 2211 if ( _wp_can_use_pcre_u() ) { 2212 /** 2213 * Replace all whitespace characters with a basic space (U+0020). 2214 * 2215 * The “Zs” in the pattern selects characters in the `Space_Separator` 2216 * category, which is what Unicode considers space characters. 2217 * 2218 * @see https://www.unicode.org/reports/tr44/#General_Category_Values 2219 * @see https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-6/#G17548 2220 * @see https://www.php.net/manual/en/regexp.reference.unicode.php 2221 */ 2222 $filename = preg_replace( '#\p{Zs}#siu', ' ', $filename ); 2223 } 2224 2225 /** 2226 * Filters the list of characters to remove from a filename. 2227 * 2228 * @since 2.8.0 2229 * 2230 * @param string[] $special_chars Array of characters to remove. 2231 * @param string $filename_raw The original filename to be sanitized. 2232 */ 2233 $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw ); 2234 2235 $filename = str_replace( $special_chars, '', $filename ); 2236 $filename = str_replace( array( '%20', '+' ), '-', $filename ); 2237 $filename = preg_replace( '/\.{2,}/', '.', $filename ); 2238 $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename ); 2239 $filename = trim( $filename, '.-_' ); 2240 2241 if ( ! str_contains( $filename, '.' ) ) { 2242 $mime_types = wp_get_mime_types(); 2243 $filetype = wp_check_filetype( 'test.' . $filename, $mime_types ); 2244 if ( $filetype['ext'] === $filename ) { 2245 $filename = 'unnamed-file.' . $filetype['ext']; 2246 } 2247 } 2248 2249 // Split the filename into a base and extension[s]. 2250 $parts = explode( '.', $filename ); 2251 2252 // Return if only one extension. 2253 if ( count( $parts ) <= 2 ) { 2254 /** This filter is documented in wp-includes/formatting.php */ 2255 return apply_filters( 'sanitize_file_name', $filename, $filename_raw ); 2256 } 2257 2258 // Process multiple extensions. 2259 $filename = array_shift( $parts ); 2260 $extension = array_pop( $parts ); 2261 $mimes = get_allowed_mime_types(); 2262 2263 /* 2264 * Loop over any intermediate extensions. Postfix them with a trailing underscore 2265 * if they are a 2 - 5 character long alpha string not in the allowed extension list. 2266 */ 2267 foreach ( (array) $parts as $part ) { 2268 $filename .= '.' . $part; 2269 2270 if ( preg_match( '/^[a-zA-Z]{2,5}\d?$/', $part ) ) { 2271 $allowed = false; 2272 foreach ( $mimes as $ext_preg => $mime_match ) { 2273 $ext_preg = '!^(' . $ext_preg . ')$!i'; 2274 if ( preg_match( $ext_preg, $part ) ) { 2275 $allowed = true; 2276 break; 2277 } 2278 } 2279 if ( ! $allowed ) { 2280 $filename .= '_'; 2281 } 2282 } 2283 } 2284 2285 $filename .= '.' . $extension; 2286 2287 /** 2288 * Filters a sanitized filename string. 2289 * 2290 * @since 2.8.0 2291 * 2292 * @param string $filename Sanitized filename. 2293 * @param string $filename_raw The filename prior to sanitization. 2294 */ 2295 return apply_filters( 'sanitize_file_name', $filename, $filename_raw ); 2296 } 2297 2298 /** 2299 * Sanitizes a username, stripping out unsafe characters. 2300 * 2301 * Removes tags, percent-encoded characters, HTML entities, and if strict is enabled, 2302 * will only keep alphanumeric, _, space, ., -, @. After sanitizing, it passes the username, 2303 * raw username (the username in the parameter), and the value of $strict as parameters 2304 * for the {@see 'sanitize_user'} filter. 2305 * 2306 * @since 2.0.0 2307 * 2308 * @param string $username The username to be sanitized. 2309 * @param bool $strict Optional. If set to true, limits $username to specific characters. 2310 * Default false. 2311 * @return string The sanitized username, after passing through filters. 2312 */ 2313 function sanitize_user( $username, $strict = false ) { 2314 $raw_username = $username; 2315 $username = wp_strip_all_tags( $username ); 2316 $username = remove_accents( $username ); 2317 // Remove percent-encoded characters. 2318 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username ); 2319 // Remove HTML entities. 2320 $username = preg_replace( '/&.+?;/', '', $username ); 2321 2322 // If strict, reduce to ASCII for max portability. 2323 if ( $strict ) { 2324 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username ); 2325 } 2326 2327 $username = trim( $username ); 2328 // Consolidate contiguous whitespace. 2329 $username = preg_replace( '|\s+|', ' ', $username ); 2330 2331 /** 2332 * Filters a sanitized username string. 2333 * 2334 * @since 2.0.1 2335 * 2336 * @param string $username Sanitized username. 2337 * @param string $raw_username The username prior to sanitization. 2338 * @param bool $strict Whether to limit the sanitization to specific characters. 2339 */ 2340 return apply_filters( 'sanitize_user', $username, $raw_username, $strict ); 2341 } 2342 2343 /** 2344 * Sanitizes a string key. 2345 * 2346 * Keys are used as internal identifiers. Lowercase alphanumeric characters, 2347 * dashes, and underscores are allowed. 2348 * 2349 * @since 3.0.0 2350 * 2351 * @param string $key String key. 2352 * @return string Sanitized key. 2353 */ 2354 function sanitize_key( $key ) { 2355 $sanitized_key = ''; 2356 2357 if ( is_scalar( $key ) ) { 2358 $sanitized_key = strtolower( $key ); 2359 $sanitized_key = preg_replace( '/[^a-z0-9_\-]/', '', $sanitized_key ); 2360 } 2361 2362 /** 2363 * Filters a sanitized key string. 2364 * 2365 * @since 3.0.0 2366 * 2367 * @param string $sanitized_key Sanitized key. 2368 * @param string $key The key prior to sanitization. 2369 */ 2370 return apply_filters( 'sanitize_key', $sanitized_key, $key ); 2371 } 2372 2373 /** 2374 * Sanitizes a string into a slug, which can be used in URLs or HTML attributes. 2375 * 2376 * By default, converts accent characters to ASCII characters and further 2377 * limits the output to alphanumeric characters, underscore (_) and dash (-) 2378 * through the {@see 'sanitize_title'} filter. 2379 * 2380 * If `$title` is empty and `$fallback_title` is set, the latter will be used. 2381 * 2382 * @since 1.0.0 2383 * 2384 * @param string $title The string to be sanitized. 2385 * @param string $fallback_title Optional. A title to use if $title is empty. Default empty. 2386 * @param string $context Optional. The operation for which the string is sanitized. 2387 * When set to 'save', the string runs through remove_accents(). 2388 * Default 'save'. 2389 * @return string The sanitized string. 2390 */ 2391 function sanitize_title( $title, $fallback_title = '', $context = 'save' ) { 2392 $raw_title = $title; 2393 2394 if ( 'save' === $context ) { 2395 $title = remove_accents( $title ); 2396 } 2397 2398 /** 2399 * Filters a sanitized title string. 2400 * 2401 * @since 1.2.0 2402 * 2403 * @param string $title Sanitized title. 2404 * @param string $raw_title The title prior to sanitization. 2405 * @param string $context The context for which the title is being sanitized. 2406 */ 2407 $title = apply_filters( 'sanitize_title', $title, $raw_title, $context ); 2408 2409 if ( '' === $title || false === $title ) { 2410 $title = $fallback_title; 2411 } 2412 2413 return $title; 2414 } 2415 2416 /** 2417 * Sanitizes a title with the 'query' context. 2418 * 2419 * Used for querying the database for a value from URL. 2420 * 2421 * @since 3.1.0 2422 * 2423 * @param string $title The string to be sanitized. 2424 * @return string The sanitized string. 2425 */ 2426 function sanitize_title_for_query( $title ) { 2427 return sanitize_title( $title, '', 'query' ); 2428 } 2429 2430 /** 2431 * Sanitizes a title, replacing whitespace and a few other characters with dashes. 2432 * 2433 * Limits the output to alphanumeric characters, underscore (_) and dash (-). 2434 * Whitespace becomes a dash. 2435 * 2436 * @since 1.2.0 2437 * 2438 * @param string $title The title to be sanitized. 2439 * @param string $raw_title Optional. Not used. Default empty. 2440 * @param string $context Optional. The operation for which the string is sanitized. 2441 * When set to 'save', additional entities are converted to hyphens 2442 * or stripped entirely. Default 'display'. 2443 * @return string The sanitized title. 2444 */ 2445 function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) { 2446 $title = strip_tags( $title ); 2447 // Preserve escaped octets. 2448 $title = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title ); 2449 // Remove percent signs that are not part of an octet. 2450 $title = str_replace( '%', '', $title ); 2451 // Restore octets. 2452 $title = preg_replace( '|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title ); 2453 2454 if ( wp_is_valid_utf8( $title ) ) { 2455 if ( function_exists( 'mb_strtolower' ) ) { 2456 $title = mb_strtolower( $title, 'UTF-8' ); 2457 } 2458 $title = utf8_uri_encode( $title, 200 ); 2459 } 2460 2461 $title = strtolower( $title ); 2462 2463 if ( 'save' === $context ) { 2464 // Convert  , &ndash, and &mdash to hyphens. 2465 $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title ); 2466 // Convert  , &ndash, and &mdash HTML entities to hyphens. 2467 $title = str_replace( array( ' ', ' ', '–', '–', '—', '—' ), '-', $title ); 2468 // Convert forward slash to hyphen. 2469 $title = str_replace( '/', '-', $title ); 2470 2471 // Strip these characters entirely. 2472 $title = str_replace( 2473 array( 2474 // Soft hyphens. 2475 '%c2%ad', 2476 // ¡ and ¿. 2477 '%c2%a1', 2478 '%c2%bf', 2479 // Angle quotes. 2480 '%c2%ab', 2481 '%c2%bb', 2482 '%e2%80%b9', 2483 '%e2%80%ba', 2484 // Curly quotes. 2485 '%e2%80%98', 2486 '%e2%80%99', 2487 '%e2%80%9c', 2488 '%e2%80%9d', 2489 '%e2%80%9a', 2490 '%e2%80%9b', 2491 '%e2%80%9e', 2492 '%e2%80%9f', 2493 // Bullet. 2494 '%e2%80%a2', 2495 // ©, ®, °, &hellip, and &trade. 2496 '%c2%a9', 2497 '%c2%ae', 2498 '%c2%b0', 2499 '%e2%80%a6', 2500 '%e2%84%a2', 2501 // Acute accents. 2502 '%c2%b4', 2503 '%cb%8a', 2504 '%cc%81', 2505 '%cd%81', 2506 // Grave accent, macron, caron. 2507 '%cc%80', 2508 '%cc%84', 2509 '%cc%8c', 2510 // Non-visible characters that display without a width. 2511 '%e2%80%8b', // Zero width space. 2512 '%e2%80%8c', // Zero width non-joiner. 2513 '%e2%80%8d', // Zero width joiner. 2514 '%e2%80%8e', // Left-to-right mark. 2515 '%e2%80%8f', // Right-to-left mark. 2516 '%e2%80%aa', // Left-to-right embedding. 2517 '%e2%80%ab', // Right-to-left embedding. 2518 '%e2%80%ac', // Pop directional formatting. 2519 '%e2%80%ad', // Left-to-right override. 2520 '%e2%80%ae', // Right-to-left override. 2521 '%ef%bb%bf', // Byte order mark. 2522 '%ef%bf%bc', // Object replacement character. 2523 ), 2524 '', 2525 $title 2526 ); 2527 2528 // Convert non-visible characters that display with a width to hyphen. 2529 $title = str_replace( 2530 array( 2531 '%e2%80%80', // En quad. 2532 '%e2%80%81', // Em quad. 2533 '%e2%80%82', // En space. 2534 '%e2%80%83', // Em space. 2535 '%e2%80%84', // Three-per-em space. 2536 '%e2%80%85', // Four-per-em space. 2537 '%e2%80%86', // Six-per-em space. 2538 '%e2%80%87', // Figure space. 2539 '%e2%80%88', // Punctuation space. 2540 '%e2%80%89', // Thin space. 2541 '%e2%80%8a', // Hair space. 2542 '%e2%80%a8', // Line separator. 2543 '%e2%80%a9', // Paragraph separator. 2544 '%e2%80%af', // Narrow no-break space. 2545 ), 2546 '-', 2547 $title 2548 ); 2549 2550 // Convert × to 'x'. 2551 $title = str_replace( '%c3%97', 'x', $title ); 2552 } 2553 2554 // Remove HTML entities. 2555 $title = preg_replace( '/&.+?;/', '', $title ); 2556 $title = str_replace( '.', '-', $title ); 2557 2558 $title = preg_replace( '/[^%a-z0-9 _-]/', '', $title ); 2559 $title = preg_replace( '/\s+/', '-', $title ); 2560 $title = preg_replace( '|-+|', '-', $title ); 2561 $title = trim( $title, '-' ); 2562 2563 return $title; 2564 } 2565 2566 /** 2567 * Ensures a string is a valid SQL 'order by' clause. 2568 * 2569 * Accepts one or more columns, with or without a sort order (ASC / DESC). 2570 * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc. 2571 * 2572 * Also accepts 'RAND()'. 2573 * 2574 * @since 2.5.1 2575 * 2576 * @param string $orderby Order by clause to be validated. 2577 * @return string|false Returns $orderby if valid, false otherwise. 2578 */ 2579 function sanitize_sql_orderby( $orderby ) { 2580 if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) { 2581 return $orderby; 2582 } 2583 return false; 2584 } 2585 2586 /** 2587 * Sanitizes an HTML classname to ensure it only contains valid characters. 2588 * 2589 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty 2590 * string then it will return the alternative value supplied. 2591 * 2592 * @todo Expand to support the full range of CDATA that a class attribute can contain. 2593 * 2594 * @since 2.8.0 2595 * 2596 * @param string $classname The classname to be sanitized. 2597 * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string. 2598 * Default empty string. 2599 * @return string The sanitized value. 2600 */ 2601 function sanitize_html_class( $classname, $fallback = '' ) { 2602 // Strip out any percent-encoded characters. 2603 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $classname ); 2604 2605 // Limit to A-Z, a-z, 0-9, '_', '-'. 2606 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized ); 2607 2608 if ( '' === $sanitized && $fallback ) { 2609 return sanitize_html_class( $fallback ); 2610 } 2611 /** 2612 * Filters a sanitized HTML class string. 2613 * 2614 * @since 2.8.0 2615 * 2616 * @param string $sanitized The sanitized HTML class. 2617 * @param string $classname HTML class before sanitization. 2618 * @param string $fallback The fallback string. 2619 */ 2620 return apply_filters( 'sanitize_html_class', $sanitized, $classname, $fallback ); 2621 } 2622 2623 /** 2624 * Strips out all characters not allowed in a locale name. 2625 * 2626 * @since 6.2.1 2627 * 2628 * @param string $locale_name The locale name to be sanitized. 2629 * @return string The sanitized value. 2630 */ 2631 function sanitize_locale_name( $locale_name ) { 2632 // Limit to A-Z, a-z, 0-9, '_', '-'. 2633 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $locale_name ); 2634 2635 /** 2636 * Filters a sanitized locale name string. 2637 * 2638 * @since 6.2.1 2639 * 2640 * @param string $sanitized The sanitized locale name. 2641 * @param string $locale_name The locale name before sanitization. 2642 */ 2643 return apply_filters( 'sanitize_locale_name', $sanitized, $locale_name ); 2644 } 2645 2646 /** 2647 * Converts lone & characters into `&` (a.k.a. `&`) 2648 * 2649 * @since 0.71 2650 * 2651 * @param string $content String of characters to be converted. 2652 * @param string $deprecated Not used. 2653 * @return string Converted string. 2654 */ 2655 function convert_chars( $content, $deprecated = '' ) { 2656 if ( ! empty( $deprecated ) ) { 2657 _deprecated_argument( __FUNCTION__, '0.71' ); 2658 } 2659 2660 if ( str_contains( $content, '&' ) ) { 2661 $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content ); 2662 } 2663 2664 return $content; 2665 } 2666 2667 /** 2668 * Converts invalid Unicode references range to valid range. 2669 * 2670 * @since 4.3.0 2671 * 2672 * @param string $content String with entities that need converting. 2673 * @return string Converted string. 2674 */ 2675 function convert_invalid_entities( $content ) { 2676 $wp_htmltranswinuni = array( 2677 '€' => '€', // The Euro sign. 2678 '' => '', 2679 '‚' => '‚', // These are Windows CP1252 specific characters. 2680 'ƒ' => 'ƒ', // They would look weird on non-Windows browsers. 2681 '„' => '„', 2682 '…' => '…', 2683 '†' => '†', 2684 '‡' => '‡', 2685 'ˆ' => 'ˆ', 2686 '‰' => '‰', 2687 'Š' => 'Š', 2688 '‹' => '‹', 2689 'Œ' => 'Œ', 2690 '' => '', 2691 'Ž' => 'Ž', 2692 '' => '', 2693 '' => '', 2694 '‘' => '‘', 2695 '’' => '’', 2696 '“' => '“', 2697 '”' => '”', 2698 '•' => '•', 2699 '–' => '–', 2700 '—' => '—', 2701 '˜' => '˜', 2702 '™' => '™', 2703 'š' => 'š', 2704 '›' => '›', 2705 'œ' => 'œ', 2706 '' => '', 2707 'ž' => 'ž', 2708 'Ÿ' => 'Ÿ', 2709 ); 2710 2711 if ( str_contains( $content, '' ) ) { 2712 $content = strtr( $content, $wp_htmltranswinuni ); 2713 } 2714 2715 return $content; 2716 } 2717 2718 /** 2719 * Balances tags if forced to, or if the 'use_balanceTags' option is set to true. 2720 * 2721 * @since 0.71 2722 * 2723 * @param string $text Text to be balanced. 2724 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false. 2725 * @return string Balanced text. 2726 */ 2727 function balanceTags( $text, $force = false ) { // phpcs:ignore WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid 2728 if ( $force || (int) get_option( 'use_balanceTags' ) === 1 ) { 2729 return force_balance_tags( $text ); 2730 } else { 2731 return $text; 2732 } 2733 } 2734 2735 /** 2736 * Balances tags of string using a modified stack. 2737 * 2738 * {@internal Modified by Scott Reilly (coffee2code) 02 Aug 2004 2739 * 1.1 Fixed handling of append/stack pop order of end text 2740 * Added Cleaning Hooks 2741 * 1.0 First Version} 2742 * 2743 * @since 2.0.4 2744 * @since 5.3.0 Improve accuracy and add support for custom element tags. 2745 * 2746 * @author Leonard Lin <leonard@acm.org> 2747 * @license GPL 2748 * @copyright November 4, 2001 2749 * @version 1.1 2750 * @todo Make better - change loop condition to $text in 1.2 2751 * 2752 * @param string $text Text to be balanced. 2753 * @return string Balanced text. 2754 */ 2755 function force_balance_tags( $text ) { 2756 $tagstack = array(); 2757 $stacksize = 0; 2758 $tagqueue = ''; 2759 $newtext = ''; 2760 // Known single-entity/self-closing tags. 2761 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source', 'track', 'wbr' ); 2762 // Tags that can be immediately nested within themselves. 2763 $nestable_tags = array( 'article', 'aside', 'blockquote', 'details', 'div', 'figure', 'object', 'q', 'section', 'span' ); 2764 2765 // WP bug fix for comments - in case you REALLY meant to type '< !--'. 2766 $text = str_replace( '< !--', '< !--', $text ); 2767 // WP bug fix for LOVE <3 (and other situations with '<' before a number). 2768 $text = preg_replace( '#<([0-9]{1})#', '<$1', $text ); 2769 2770 /** 2771 * Matches supported tags. 2772 * 2773 * To get the pattern as a string without the comments paste into a PHP 2774 * REPL like `php -a`. 2775 * 2776 * @see https://html.spec.whatwg.org/#elements-2 2777 * @see https://html.spec.whatwg.org/multipage/custom-elements.html#valid-custom-element-name 2778 * 2779 * @example 2780 * ~# php -a 2781 * php > $s = [paste copied contents of expression below including parentheses]; 2782 * php > echo $s; 2783 */ 2784 $tag_pattern = ( 2785 '#<' . // Start with an opening bracket. 2786 '(/?)' . // Group 1 - If it's a closing tag it'll have a leading slash. 2787 '(' . // Group 2 - Tag name. 2788 // Custom element tags have more lenient rules than HTML tag names. 2789 '(?:[a-z](?:[a-z0-9._]*)-(?:[a-z0-9._-]+)+)' . 2790 '|' . 2791 // Traditional tag rules approximate HTML tag names. 2792 '(?:[\w:]+)' . 2793 ')' . 2794 '(?:' . 2795 // We either immediately close the tag with its '>' and have nothing here. 2796 '\s*' . 2797 '(/?)' . // Group 3 - "attributes" for empty tag. 2798 '|' . 2799 // Or we must start with space characters to separate the tag name from the attributes (or whitespace). 2800 '(\s+)' . // Group 4 - Pre-attribute whitespace. 2801 '([^>]*)' . // Group 5 - Attributes. 2802 ')' . 2803 '>#' // End with a closing bracket. 2804 ); 2805 2806 while ( preg_match( $tag_pattern, $text, $regex ) ) { 2807 $full_match = $regex[0]; 2808 $has_leading_slash = ! empty( $regex[1] ); 2809 $tag_name = $regex[2]; 2810 $tag = strtolower( $tag_name ); 2811 $is_single_tag = in_array( $tag, $single_tags, true ); 2812 $pre_attribute_ws = isset( $regex[4] ) ? $regex[4] : ''; 2813 $attributes = trim( isset( $regex[5] ) ? $regex[5] : $regex[3] ); 2814 $has_self_closer = str_ends_with( $attributes, '/' ); 2815 2816 $newtext .= $tagqueue; 2817 2818 $i = strpos( $text, $full_match ); 2819 $l = strlen( $full_match ); 2820 2821 // Clear the shifter. 2822 $tagqueue = ''; 2823 if ( $has_leading_slash ) { // End tag. 2824 // If too many closing tags. 2825 if ( $stacksize <= 0 ) { 2826 $tag = ''; 2827 // Or close to be safe $tag = '/' . $tag. 2828 2829 // If stacktop value = tag close value, then pop. 2830 } elseif ( $tagstack[ $stacksize - 1 ] === $tag ) { // Found closing tag. 2831 $tag = '</' . $tag . '>'; // Close tag. 2832 array_pop( $tagstack ); 2833 --$stacksize; 2834 } else { // Closing tag not at top, search for it. 2835 for ( $j = $stacksize - 1; $j >= 0; $j-- ) { 2836 if ( $tagstack[ $j ] === $tag ) { 2837 // Add tag to tagqueue. 2838 for ( $k = $stacksize - 1; $k >= $j; $k-- ) { 2839 $tagqueue .= '</' . array_pop( $tagstack ) . '>'; 2840 --$stacksize; 2841 } 2842 break; 2843 } 2844 } 2845 $tag = ''; 2846 } 2847 } else { // Begin tag. 2848 if ( $has_self_closer ) { 2849 /* 2850 * If it presents itself as a self-closing tag, but it isn't a known single-entity self-closing tag, 2851 * then don't let it be treated as such and immediately close it with a closing tag. 2852 * The tag will encapsulate no text as a result. 2853 */ 2854 if ( ! $is_single_tag ) { 2855 $attributes = trim( substr( $attributes, 0, -1 ) ) . "></$tag"; 2856 } 2857 } elseif ( $is_single_tag ) { 2858 // Else if it's a known single-entity tag but it doesn't close itself, do so. 2859 $pre_attribute_ws = ' '; 2860 $attributes .= '/'; 2861 } else { 2862 /* 2863 * It's not a single-entity tag. 2864 * If the top of the stack is the same as the tag we want to push, close previous tag. 2865 */ 2866 if ( $stacksize > 0 && ! in_array( $tag, $nestable_tags, true ) && $tagstack[ $stacksize - 1 ] === $tag ) { 2867 $tagqueue = '</' . array_pop( $tagstack ) . '>'; 2868 --$stacksize; 2869 } 2870 $stacksize = array_push( $tagstack, $tag ); 2871 } 2872 2873 // Attributes. 2874 if ( $has_self_closer && $is_single_tag ) { 2875 // We need some space - avoid <br/> and prefer <br />. 2876 $pre_attribute_ws = ' '; 2877 } 2878 2879 $tag = '<' . $tag . $pre_attribute_ws . $attributes . '>'; 2880 // If already queuing a close tag, then put this tag on too. 2881 if ( ! empty( $tagqueue ) ) { 2882 $tagqueue .= $tag; 2883 $tag = ''; 2884 } 2885 } 2886 $newtext .= substr( $text, 0, $i ) . $tag; 2887 $text = substr( $text, $i + $l ); 2888 } 2889 2890 // Clear tag queue. 2891 $newtext .= $tagqueue; 2892 2893 // Add remaining text. 2894 $newtext .= $text; 2895 2896 while ( $x = array_pop( $tagstack ) ) { 2897 $newtext .= '</' . $x . '>'; // Add remaining tags to close. 2898 } 2899 2900 // WP fix for the bug with HTML comments. 2901 $newtext = str_replace( '< !--', '<!--', $newtext ); 2902 $newtext = str_replace( '< !--', '< !--', $newtext ); 2903 2904 return $newtext; 2905 } 2906 2907 /** 2908 * Acts on text which is about to be edited. 2909 * 2910 * The $content is run through esc_textarea(), which uses htmlspecialchars() 2911 * to convert special characters to HTML entities. If `$richedit` is set to true, 2912 * it is simply a holder for the {@see 'format_to_edit'} filter. 2913 * 2914 * @since 0.71 2915 * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity. 2916 * 2917 * @param string $content The text about to be edited. 2918 * @param bool $rich_text Optional. Whether `$content` should be considered rich text, 2919 * in which case it would not be passed through esc_textarea(). 2920 * Default false. 2921 * @return string The text after the filter (and possibly htmlspecialchars()) has been run. 2922 */ 2923 function format_to_edit( $content, $rich_text = false ) { 2924 /** 2925 * Filters the text to be formatted for editing. 2926 * 2927 * @since 1.2.0 2928 * 2929 * @param string $content The text, prior to formatting for editing. 2930 */ 2931 $content = apply_filters( 'format_to_edit', $content ); 2932 if ( ! $rich_text ) { 2933 $content = esc_textarea( $content ); 2934 } 2935 return $content; 2936 } 2937 2938 /** 2939 * Add leading zeros when necessary. 2940 * 2941 * If you set the threshold to '4' and the number is '10', then you will get 2942 * back '0010'. If you set the threshold to '4' and the number is '5000', then you 2943 * will get back '5000'. 2944 * 2945 * Uses sprintf to append the amount of zeros based on the $threshold parameter 2946 * and the size of the number. If the number is large enough, then no zeros will 2947 * be appended. 2948 * 2949 * @since 0.71 2950 * 2951 * @param int $number Number to append zeros to if not greater than threshold. 2952 * @param int $threshold Digit places number needs to be to not have zeros added. 2953 * @return string Adds leading zeros to number if needed. 2954 */ 2955 function zeroise( $number, $threshold ) { 2956 return sprintf( '%0' . $threshold . 's', $number ); 2957 } 2958 2959 /** 2960 * Adds backslashes before letters and before a number at the start of a string. 2961 * 2962 * @since 0.71 2963 * 2964 * @param string $value Value to which backslashes will be added. 2965 * @return string String with backslashes inserted. 2966 */ 2967 function backslashit( $value ) { 2968 if ( isset( $value[0] ) && $value[0] >= '0' && $value[0] <= '9' ) { 2969 $value = '\\\\' . $value; 2970 } 2971 return addcslashes( $value, 'A..Za..z' ); 2972 } 2973 2974 /** 2975 * Appends a trailing slash. 2976 * 2977 * Will remove trailing forward and backslashes if it exists already before adding 2978 * a trailing forward slash. This prevents double slashing a string or path. 2979 * 2980 * The primary use of this is for paths and thus should be used for paths. It is 2981 * not restricted to paths and offers no specific path support. 2982 * 2983 * @since 1.2.0 2984 * 2985 * @param string $value Value to which trailing slash will be added. 2986 * @return string String with trailing slash added. 2987 */ 2988 function trailingslashit( $value ) { 2989 return untrailingslashit( $value ) . '/'; 2990 } 2991 2992 /** 2993 * Removes trailing forward slashes and backslashes if they exist. 2994 * 2995 * The primary use of this is for paths and thus should be used for paths. It is 2996 * not restricted to paths and offers no specific path support. 2997 * 2998 * @since 2.2.0 2999 * 3000 * @param string $value Value from which trailing slashes will be removed. 3001 * @return string String without the trailing slashes. 3002 */ 3003 function untrailingslashit( $value ) { 3004 return rtrim( $value, '/\\' ); 3005 } 3006 3007 /** 3008 * Adds slashes to a string or recursively adds slashes to strings within an array. 3009 * 3010 * @since 0.71 3011 * 3012 * @param string|array $gpc String or array of data to slash. 3013 * @return string|array Slashed `$gpc`. 3014 */ 3015 function addslashes_gpc( $gpc ) { 3016 return wp_slash( $gpc ); 3017 } 3018 3019 /** 3020 * Navigates through an array, object, or scalar, and removes slashes from the values. 3021 * 3022 * @since 2.0.0 3023 * 3024 * @param mixed $value The value to be stripped. 3025 * @return mixed Stripped value. 3026 */ 3027 function stripslashes_deep( $value ) { 3028 return map_deep( $value, 'stripslashes_from_strings_only' ); 3029 } 3030 3031 /** 3032 * Callback function for `stripslashes_deep()` which strips slashes from strings. 3033 * 3034 * @since 4.4.0 3035 * 3036 * @param mixed $value The array or string to be stripped. 3037 * @return mixed The stripped value. 3038 */ 3039 function stripslashes_from_strings_only( $value ) { 3040 return is_string( $value ) ? stripslashes( $value ) : $value; 3041 } 3042 3043 /** 3044 * Navigates through an array, object, or scalar, and encodes the values to be used in a URL. 3045 * 3046 * @since 2.2.0 3047 * 3048 * @param mixed $value The array or string to be encoded. 3049 * @return mixed The encoded value. 3050 */ 3051 function urlencode_deep( $value ) { 3052 return map_deep( $value, 'urlencode' ); 3053 } 3054 3055 /** 3056 * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL. 3057 * 3058 * @since 3.4.0 3059 * 3060 * @param mixed $value The array or string to be encoded. 3061 * @return mixed The encoded value. 3062 */ 3063 function rawurlencode_deep( $value ) { 3064 return map_deep( $value, 'rawurlencode' ); 3065 } 3066 3067 /** 3068 * Navigates through an array, object, or scalar, and decodes URL-encoded values 3069 * 3070 * @since 4.4.0 3071 * 3072 * @param mixed $value The array or string to be decoded. 3073 * @return mixed The decoded value. 3074 */ 3075 function urldecode_deep( $value ) { 3076 return map_deep( $value, 'urldecode' ); 3077 } 3078 3079 /** 3080 * Converts email addresses characters to HTML entities to block spam bots. 3081 * 3082 * @since 0.71 3083 * 3084 * @param string $email_address Email address. 3085 * @param int $hex_encoding Optional. Set to 1 to enable hex encoding. 3086 * @return string Converted email address. 3087 */ 3088 function antispambot( $email_address, $hex_encoding = 0 ) { 3089 $email_no_spam_address = ''; 3090 3091 for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) { 3092 $j = rand( 0, 1 + $hex_encoding ); 3093 3094 if ( 0 === $j ) { 3095 $email_no_spam_address .= '&#' . ord( $email_address[ $i ] ) . ';'; 3096 } elseif ( 1 === $j ) { 3097 $email_no_spam_address .= $email_address[ $i ]; 3098 } elseif ( 2 === $j ) { 3099 $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[ $i ] ) ), 2 ); 3100 } 3101 } 3102 3103 return str_replace( '@', '@', $email_no_spam_address ); 3104 } 3105 3106 /** 3107 * Callback to convert URI match to HTML A element. 3108 * 3109 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). 3110 * 3111 * @since 2.3.2 3112 * @access private 3113 * 3114 * @param array $matches Single Regex Match. 3115 * @return string HTML A element with URI address. 3116 */ 3117 function _make_url_clickable_cb( $matches ) { 3118 $url = $matches[2]; 3119 3120 if ( ')' === $matches[3] && strpos( $url, '(' ) ) { 3121 /* 3122 * If the trailing character is a closing parenthesis, and the URL has an opening parenthesis in it, 3123 * add the closing parenthesis to the URL. Then we can let the parenthesis balancer do its thing below. 3124 */ 3125 $url .= $matches[3]; 3126 $suffix = ''; 3127 } else { 3128 $suffix = $matches[3]; 3129 } 3130 3131 if ( isset( $matches[4] ) && ! empty( $matches[4] ) ) { 3132 $url .= $matches[4]; 3133 } 3134 3135 // Include parentheses in the URL only if paired. 3136 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) { 3137 $suffix = strrchr( $url, ')' ) . $suffix; 3138 $url = substr( $url, 0, strrpos( $url, ')' ) ); 3139 } 3140 3141 $url = esc_url( $url ); 3142 if ( empty( $url ) ) { 3143 return $matches[0]; 3144 } 3145 3146 $rel_attr = _make_clickable_rel_attr( $url ); 3147 3148 return $matches[1] . "<a href=\"{$url}\"{$rel_attr}>{$url}</a>" . $suffix; 3149 } 3150 3151 /** 3152 * Callback to convert URL match to HTML A element. 3153 * 3154 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). 3155 * 3156 * @since 2.3.2 3157 * @access private 3158 * 3159 * @param array $matches Single Regex Match. 3160 * @return string HTML A element with URL address. 3161 */ 3162 function _make_web_ftp_clickable_cb( $matches ) { 3163 $ret = ''; 3164 $dest = $matches[2]; 3165 $dest = 'http://' . $dest; 3166 3167 // Removed trailing [.,;:)] from URL. 3168 $last_char = substr( $dest, -1 ); 3169 if ( in_array( $last_char, array( '.', ',', ';', ':', ')' ), true ) === true ) { 3170 $ret = $last_char; 3171 $dest = substr( $dest, 0, strlen( $dest ) - 1 ); 3172 } 3173 3174 $dest = esc_url( $dest ); 3175 if ( empty( $dest ) ) { 3176 return $matches[0]; 3177 } 3178 3179 $rel_attr = _make_clickable_rel_attr( $dest ); 3180 3181 return $matches[1] . "<a href=\"{$dest}\"{$rel_attr}>{$dest}</a>{$ret}"; 3182 } 3183 3184 /** 3185 * Callback to convert email address match to HTML A element. 3186 * 3187 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable(). 3188 * 3189 * @since 2.3.2 3190 * @access private 3191 * 3192 * @param array $matches Single Regex Match. 3193 * @return string HTML A element with email address. 3194 */ 3195 function _make_email_clickable_cb( $matches ) { 3196 $email = $matches[2] . '@' . $matches[3]; 3197 3198 return $matches[1] . "<a href=\"mailto:{$email}\">{$email}</a>"; 3199 } 3200 3201 /** 3202 * Helper function used to build the "rel" attribute for a URL when creating an anchor using make_clickable(). 3203 * 3204 * @since 6.2.0 3205 * 3206 * @param string $url The URL. 3207 * @return string The rel attribute for the anchor or an empty string if no rel attribute should be added. 3208 */ 3209 function _make_clickable_rel_attr( $url ) { 3210 $rel_parts = array(); 3211 $scheme = strtolower( wp_parse_url( $url, PHP_URL_SCHEME ) ); 3212 $nofollow_schemes = array_intersect( wp_allowed_protocols(), array( 'https', 'http' ) ); 3213 3214 // Apply "nofollow" to external links with qualifying URL schemes (mailto:, tel:, etc... shouldn't be followed). 3215 if ( ! wp_is_internal_link( $url ) && in_array( $scheme, $nofollow_schemes, true ) ) { 3216 $rel_parts[] = 'nofollow'; 3217 } 3218 3219 // Apply "ugc" when in comment context. 3220 if ( 'comment_text' === current_filter() ) { 3221 $rel_parts[] = 'ugc'; 3222 } 3223 3224 $rel = implode( ' ', $rel_parts ); 3225 3226 /** 3227 * Filters the rel value that is added to URL matches converted to links. 3228 * 3229 * @since 5.3.0 3230 * 3231 * @param string $rel The rel value. 3232 * @param string $url The matched URL being converted to a link tag. 3233 */ 3234 $rel = apply_filters( 'make_clickable_rel', $rel, $url ); 3235 3236 $rel_attr = $rel ? ' rel="' . esc_attr( $rel ) . '"' : ''; 3237 3238 return $rel_attr; 3239 } 3240 3241 /** 3242 * Converts plaintext URI to HTML links. 3243 * 3244 * Converts URI, www and ftp, and email addresses. Finishes by fixing links 3245 * within links. 3246 * 3247 * @since 0.71 3248 * 3249 * @param string $text Content to convert URIs. 3250 * @return string Content with converted URIs. 3251 */ 3252 function make_clickable( $text ) { 3253 $r = ''; 3254 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Split out HTML tags. 3255 $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>. 3256 foreach ( $textarr as $piece ) { 3257 3258 if ( preg_match( '|^<code[\s>]|i', $piece ) 3259 || preg_match( '|^<pre[\s>]|i', $piece ) 3260 || preg_match( '|^<script[\s>]|i', $piece ) 3261 || preg_match( '|^<style[\s>]|i', $piece ) 3262 ) { 3263 ++$nested_code_pre; 3264 } elseif ( $nested_code_pre 3265 && ( '</code>' === strtolower( $piece ) 3266 || '</pre>' === strtolower( $piece ) 3267 || '</script>' === strtolower( $piece ) 3268 || '</style>' === strtolower( $piece ) 3269 ) 3270 ) { 3271 --$nested_code_pre; 3272 } 3273 3274 if ( $nested_code_pre 3275 || empty( $piece ) 3276 || ( '<' === $piece[0] && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) 3277 ) { 3278 $r .= $piece; 3279 continue; 3280 } 3281 3282 // Long strings might contain expensive edge cases... 3283 if ( 10000 < strlen( $piece ) ) { 3284 // ...break it up. 3285 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing parentheses. 3286 if ( 2101 < strlen( $chunk ) ) { 3287 $r .= $chunk; // Too big, no whitespace: bail. 3288 } else { 3289 $r .= make_clickable( $chunk ); 3290 } 3291 } 3292 } else { 3293 $ret = " $piece "; // Pad with whitespace to simplify the regexes. 3294 3295 $url_clickable = '~ 3296 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation. 3297 ( # 2: URL. 3298 [\\w]{1,20}+:// # Scheme and hier-part prefix. 3299 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long. 3300 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character. 3301 (?: # Unroll the Loop: Only allow punctuation URL character if followed by a non-punctuation URL character. 3302 [\'.,;:!?)] # Punctuation URL character. 3303 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character. 3304 )* 3305 ) 3306 (\)?) # 3: Trailing closing parenthesis (for parenthesis balancing post processing). 3307 (\\.\\w{2,6})? # 4: Allowing file extensions (e.g., .jpg, .png). 3308 ~xS'; 3309 /* 3310 * The regex is a non-anchored pattern and does not have a single fixed starting character. 3311 * Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times. 3312 */ 3313 3314 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret ); 3315 3316 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret ); 3317 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret ); 3318 3319 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding. 3320 $r .= $ret; 3321 } 3322 } 3323 3324 // Cleanup of accidental links within links. 3325 return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', '$1$3</a>', $r ); 3326 } 3327 3328 /** 3329 * Breaks a string into chunks by splitting at whitespace characters. 3330 * 3331 * The length of each returned chunk is as close to the specified length goal as possible, 3332 * with the caveat that each chunk includes its trailing delimiter. 3333 * Chunks longer than the goal are guaranteed to not have any inner whitespace. 3334 * 3335 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly. 3336 * 3337 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters) 3338 * 3339 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) == 3340 * array ( 3341 * 0 => '1234 67890 ', // 11 characters: Perfect split. 3342 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long. 3343 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long. 3344 * 3 => '1234 890 ', // 11 characters: Perfect split. 3345 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long. 3346 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split. 3347 * 6 => ' 45678 ', // 11 characters: Perfect split. 3348 * 7 => '1 3 5 7 90 ', // 11 characters: End of $text. 3349 * ); 3350 * 3351 * @since 3.4.0 3352 * @access private 3353 * 3354 * @param string $text The string to split. 3355 * @param int $goal The desired chunk length. 3356 * @return array Numeric array of chunks. 3357 */ 3358 function _split_str_by_whitespace( $text, $goal ) { 3359 $chunks = array(); 3360 3361 $string_nullspace = strtr( $text, "\r\n\t\v\f ", "\000\000\000\000\000\000" ); 3362 3363 while ( $goal < strlen( $string_nullspace ) ) { 3364 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" ); 3365 3366 if ( false === $pos ) { 3367 $pos = strpos( $string_nullspace, "\000", $goal + 1 ); 3368 if ( false === $pos ) { 3369 break; 3370 } 3371 } 3372 3373 $chunks[] = substr( $text, 0, $pos + 1 ); 3374 $text = substr( $text, $pos + 1 ); 3375 $string_nullspace = substr( $string_nullspace, $pos + 1 ); 3376 } 3377 3378 if ( $text ) { 3379 $chunks[] = $text; 3380 } 3381 3382 return $chunks; 3383 } 3384 3385 /** 3386 * Callback to add a rel attribute to HTML A element. 3387 * 3388 * Will remove already existing string before adding to prevent invalidating (X)HTML. 3389 * 3390 * @since 5.3.0 3391 * 3392 * @param array $matches Single match. 3393 * @param string $rel The rel attribute to add. 3394 * @return string HTML A element with the added rel attribute. 3395 */ 3396 function wp_rel_callback( $matches, $rel ) { 3397 $text = $matches[1]; 3398 $atts = wp_kses_hair( $matches[1], wp_allowed_protocols() ); 3399 3400 if ( ! empty( $atts['href'] ) && wp_is_internal_link( $atts['href']['value'] ) ) { 3401 $rel = trim( str_replace( 'nofollow', '', $rel ) ); 3402 } 3403 3404 if ( ! empty( $atts['rel'] ) ) { 3405 $parts = array_map( 'trim', explode( ' ', $atts['rel']['value'] ) ); 3406 $rel_array = array_map( 'trim', explode( ' ', $rel ) ); 3407 $parts = array_unique( array_merge( $parts, $rel_array ) ); 3408 $rel = implode( ' ', $parts ); 3409 unset( $atts['rel'] ); 3410 3411 $html = ''; 3412 foreach ( $atts as $name => $value ) { 3413 if ( isset( $value['vless'] ) && 'y' === $value['vless'] ) { 3414 $html .= $name . ' '; 3415 } else { 3416 $html .= "{$name}=\"" . esc_attr( $value['value'] ) . '" '; 3417 } 3418 } 3419 $text = trim( $html ); 3420 } 3421 3422 $rel_attr = $rel ? ' rel="' . esc_attr( $rel ) . '"' : ''; 3423 3424 return "<a {$text}{$rel_attr}>"; 3425 } 3426 3427 /** 3428 * Adds `rel="nofollow"` string to all HTML A elements in content. 3429 * 3430 * @since 1.5.0 3431 * 3432 * @param string $text Content that may contain HTML A elements. 3433 * @return string Converted content. 3434 */ 3435 function wp_rel_nofollow( $text ) { 3436 // This is a pre-save filter, so text is already escaped. 3437 $text = stripslashes( $text ); 3438 $text = preg_replace_callback( 3439 '|<a (.+?)>|i', 3440 static function ( $matches ) { 3441 return wp_rel_callback( $matches, 'nofollow' ); 3442 }, 3443 $text 3444 ); 3445 return wp_slash( $text ); 3446 } 3447 3448 /** 3449 * Callback to add `rel="nofollow"` string to HTML A element. 3450 * 3451 * @since 2.3.0 3452 * @deprecated 5.3.0 Use wp_rel_callback() 3453 * 3454 * @param array $matches Single match. 3455 * @return string HTML A Element with `rel="nofollow"`. 3456 */ 3457 function wp_rel_nofollow_callback( $matches ) { 3458 return wp_rel_callback( $matches, 'nofollow' ); 3459 } 3460 3461 /** 3462 * Adds `rel="nofollow ugc"` string to all HTML A elements in content. 3463 * 3464 * @since 5.3.0 3465 * 3466 * @param string $text Content that may contain HTML A elements. 3467 * @return string Converted content. 3468 */ 3469 function wp_rel_ugc( $text ) { 3470 // This is a pre-save filter, so text is already escaped. 3471 $text = stripslashes( $text ); 3472 $text = preg_replace_callback( 3473 '|<a (.+?)>|i', 3474 static function ( $matches ) { 3475 return wp_rel_callback( $matches, 'nofollow ugc' ); 3476 }, 3477 $text 3478 ); 3479 return wp_slash( $text ); 3480 } 3481 3482 /** 3483 * Adds `rel="noopener"` to all HTML A elements that have a target. 3484 * 3485 * @since 5.1.0 3486 * @since 5.6.0 Removed 'noreferrer' relationship. 3487 * @deprecated 6.7.0 3488 * 3489 * @param string $text Content that may contain HTML A elements. 3490 * @return string Converted content. 3491 */ 3492 function wp_targeted_link_rel( $text ) { 3493 _deprecated_function( __FUNCTION__, '6.7.0' ); 3494 3495 // Don't run (more expensive) regex if no links with targets. 3496 if ( stripos( $text, 'target' ) === false || stripos( $text, '<a ' ) === false || is_serialized( $text ) ) { 3497 return $text; 3498 } 3499 3500 $script_and_style_regex = '/<(script|style).*?<\/\\1>/si'; 3501 3502 preg_match_all( $script_and_style_regex, $text, $matches ); 3503 $extra_parts = $matches[0]; 3504 $html_parts = preg_split( $script_and_style_regex, $text ); 3505 3506 foreach ( $html_parts as &$part ) { 3507 $part = preg_replace_callback( '|<a\s([^>]*target\s*=[^>]*)>|i', 'wp_targeted_link_rel_callback', $part ); 3508 } 3509 3510 $text = ''; 3511 for ( $i = 0; $i < count( $html_parts ); $i++ ) { 3512 $text .= $html_parts[ $i ]; 3513 if ( isset( $extra_parts[ $i ] ) ) { 3514 $text .= $extra_parts[ $i ]; 3515 } 3516 } 3517 3518 return $text; 3519 } 3520 3521 /** 3522 * Callback to add `rel="noopener"` string to HTML A element. 3523 * 3524 * Will not duplicate an existing 'noopener' value to avoid invalidating the HTML. 3525 * 3526 * @since 5.1.0 3527 * @since 5.6.0 Removed 'noreferrer' relationship. 3528 * @deprecated 6.7.0 3529 * 3530 * @param array $matches Single match. 3531 * @return string HTML A Element with `rel="noopener"` in addition to any existing values. 3532 */ 3533 function wp_targeted_link_rel_callback( $matches ) { 3534 _deprecated_function( __FUNCTION__, '6.7.0' ); 3535 3536 $link_html = $matches[1]; 3537 $original_link_html = $link_html; 3538 3539 // Consider the HTML escaped if there are no unescaped quotes. 3540 $is_escaped = ! preg_match( '/(^|[^\\\\])[\'"]/', $link_html ); 3541 if ( $is_escaped ) { 3542 // Replace only the quotes so that they are parsable by wp_kses_hair(), leave the rest as is. 3543 $link_html = preg_replace( '/\\\\([\'"])/', '$1', $link_html ); 3544 } 3545 3546 $atts = wp_kses_hair( $link_html, wp_allowed_protocols() ); 3547 3548 /** 3549 * Filters the rel values that are added to links with `target` attribute. 3550 * 3551 * @since 5.1.0 3552 * 3553 * @param string $rel The rel values. 3554 * @param string $link_html The matched content of the link tag including all HTML attributes. 3555 */ 3556 $rel = apply_filters( 'wp_targeted_link_rel', 'noopener', $link_html ); 3557 3558 // Return early if no rel values to be added or if no actual target attribute. 3559 if ( ! $rel || ! isset( $atts['target'] ) ) { 3560 return "<a $original_link_html>"; 3561 } 3562 3563 if ( isset( $atts['rel'] ) ) { 3564 $all_parts = preg_split( '/\s/', "{$atts['rel']['value']} $rel", -1, PREG_SPLIT_NO_EMPTY ); 3565 $rel = implode( ' ', array_unique( $all_parts ) ); 3566 } 3567 3568 $atts['rel']['whole'] = 'rel="' . esc_attr( $rel ) . '"'; 3569 $link_html = implode( ' ', array_column( $atts, 'whole' ) ); 3570 3571 if ( $is_escaped ) { 3572 $link_html = preg_replace( '/[\'"]/', '\\\\$0', $link_html ); 3573 } 3574 3575 return "<a $link_html>"; 3576 } 3577 3578 /** 3579 * Adds all filters modifying the rel attribute of targeted links. 3580 * 3581 * @since 5.1.0 3582 * @deprecated 6.7.0 3583 */ 3584 function wp_init_targeted_link_rel_filters() { 3585 _deprecated_function( __FUNCTION__, '6.7.0' ); 3586 } 3587 3588 /** 3589 * Removes all filters modifying the rel attribute of targeted links. 3590 * 3591 * @since 5.1.0 3592 * @deprecated 6.7.0 3593 */ 3594 function wp_remove_targeted_link_rel_filters() { 3595 _deprecated_function( __FUNCTION__, '6.7.0' ); 3596 } 3597 3598 /** 3599 * Converts one smiley code to the icon graphic file equivalent. 3600 * 3601 * Callback handler for convert_smilies(). 3602 * 3603 * Looks up one smiley code in the $wpsmiliestrans global array and returns an 3604 * `<img>` string for that smiley. 3605 * 3606 * @since 2.8.0 3607 * 3608 * @global array $wpsmiliestrans 3609 * 3610 * @param array $matches Single match. Smiley code to convert to image. 3611 * @return string Image string for smiley. 3612 */ 3613 function translate_smiley( $matches ) { 3614 global $wpsmiliestrans; 3615 3616 if ( count( $matches ) === 0 ) { 3617 return ''; 3618 } 3619 3620 $smiley = trim( reset( $matches ) ); 3621 $img = $wpsmiliestrans[ $smiley ]; 3622 3623 $matches = array(); 3624 $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false; 3625 $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png', 'webp', 'avif' ); 3626 3627 // Don't convert smilies that aren't images - they're probably emoji. 3628 if ( ! in_array( $ext, $image_exts, true ) ) { 3629 return $img; 3630 } 3631 3632 /** 3633 * Filters the Smiley image URL before it's used in the image element. 3634 * 3635 * @since 2.9.0 3636 * 3637 * @param string $smiley_url URL for the smiley image. 3638 * @param string $img Filename for the smiley image. 3639 * @param string $site_url Site URL, as returned by site_url(). 3640 */ 3641 $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() ); 3642 3643 return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) ); 3644 } 3645 3646 /** 3647 * Converts text equivalent of smilies to images. 3648 * 3649 * Will only convert smilies if the option 'use_smilies' is true and the global 3650 * used in the function isn't empty. 3651 * 3652 * @since 0.71 3653 * 3654 * @global string|array $wp_smiliessearch 3655 * 3656 * @param string $text Content to convert smilies from text. 3657 * @return string Converted content with text smilies replaced with images. 3658 */ 3659 function convert_smilies( $text ) { 3660 global $wp_smiliessearch; 3661 3662 if ( ! get_option( 'use_smilies' ) || empty( $wp_smiliessearch ) ) { 3663 // Return default text. 3664 return $text; 3665 } 3666 3667 // HTML loop taken from texturize function, could possible be consolidated. 3668 $textarr = preg_split( '/(<[^>]*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Capture the tags as well as in between. 3669 3670 if ( false === $textarr ) { 3671 // Return default text. 3672 return $text; 3673 } 3674 3675 // Loop stuff. 3676 $stop = count( $textarr ); 3677 $output = ''; 3678 3679 // Ignore processing of specific tags. 3680 $tags_to_ignore = 'code|pre|style|script|textarea'; 3681 $ignore_block_element = ''; 3682 3683 for ( $i = 0; $i < $stop; $i++ ) { 3684 $content = $textarr[ $i ]; 3685 3686 // If we're in an ignore block, wait until we find its closing tag. 3687 if ( '' === $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')[^>]*>/', $content, $matches ) ) { 3688 $ignore_block_element = $matches[1]; 3689 } 3690 3691 // If it's not a tag and not in ignore block. 3692 if ( '' === $ignore_block_element && strlen( $content ) > 0 && '<' !== $content[0] ) { 3693 $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content ); 3694 } 3695 3696 // Did we exit ignore block? 3697 if ( '' !== $ignore_block_element && '</' . $ignore_block_element . '>' === $content ) { 3698 $ignore_block_element = ''; 3699 } 3700 3701 $output .= $content; 3702 } 3703 3704 return $output; 3705 } 3706 3707 /** 3708 * Verifies that an email is valid. 3709 * 3710 * Does not grok i18n domains. Not RFC compliant. 3711 * 3712 * @since 0.71 3713 * 3714 * @param string $email Email address to verify. 3715 * @param bool $deprecated Deprecated. 3716 * @return string|false Valid email address on success, false on failure. 3717 */ 3718 function is_email( $email, $deprecated = false ) { 3719 if ( ! empty( $deprecated ) ) { 3720 _deprecated_argument( __FUNCTION__, '3.0.0' ); 3721 } 3722 3723 // Test for the minimum length the email can be. 3724 if ( strlen( $email ) < 6 ) { 3725 /** 3726 * Filters whether an email address is valid. 3727 * 3728 * This filter is evaluated under several different contexts, such as 'email_too_short', 3729 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits', 3730 * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context. 3731 * 3732 * @since 2.8.0 3733 * 3734 * @param string|false $is_email The email address if successfully passed the is_email() checks, false otherwise. 3735 * @param string $email The email address being checked. 3736 * @param string $context Context under which the email was tested. 3737 */ 3738 return apply_filters( 'is_email', false, $email, 'email_too_short' ); 3739 } 3740 3741 // Test for an @ character after the first position. 3742 if ( strpos( $email, '@', 1 ) === false ) { 3743 /** This filter is documented in wp-includes/formatting.php */ 3744 return apply_filters( 'is_email', false, $email, 'email_no_at' ); 3745 } 3746 3747 // Split out the local and domain parts. 3748 list( $local, $domain ) = explode( '@', $email, 2 ); 3749 3750 /* 3751 * LOCAL PART 3752 * Test for invalid characters. 3753 */ 3754 if ( ! preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) { 3755 /** This filter is documented in wp-includes/formatting.php */ 3756 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' ); 3757 } 3758 3759 /* 3760 * DOMAIN PART 3761 * Test for sequences of periods. 3762 */ 3763 if ( preg_match( '/\.{2,}/', $domain ) ) { 3764 /** This filter is documented in wp-includes/formatting.php */ 3765 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' ); 3766 } 3767 3768 // Test for leading and trailing periods and whitespace. 3769 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) { 3770 /** This filter is documented in wp-includes/formatting.php */ 3771 return apply_filters( 'is_email', false, $email, 'domain_period_limits' ); 3772 } 3773 3774 // Split the domain into subs. 3775 $subs = explode( '.', $domain ); 3776 3777 // Assume the domain will have at least two subs. 3778 if ( 2 > count( $subs ) ) { 3779 /** This filter is documented in wp-includes/formatting.php */ 3780 return apply_filters( 'is_email', false, $email, 'domain_no_periods' ); 3781 } 3782 3783 // Loop through each sub. 3784 foreach ( $subs as $sub ) { 3785 // Test for leading and trailing hyphens and whitespace. 3786 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) { 3787 /** This filter is documented in wp-includes/formatting.php */ 3788 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' ); 3789 } 3790 3791 // Test for invalid characters. 3792 if ( ! preg_match( '/^[a-z0-9-]+$/i', $sub ) ) { 3793 /** This filter is documented in wp-includes/formatting.php */ 3794 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' ); 3795 } 3796 } 3797 3798 // Congratulations, your email made it! 3799 /** This filter is documented in wp-includes/formatting.php */ 3800 return apply_filters( 'is_email', $email, $email, null ); 3801 } 3802 3803 /** 3804 * Converts to ASCII from email subjects. 3805 * 3806 * @since 1.2.0 3807 * 3808 * @param string $subject Subject line. 3809 * @return string Converted string to ASCII. 3810 */ 3811 function wp_iso_descrambler( $subject ) { 3812 /* this may only work with iso-8859-1, I'm afraid */ 3813 if ( ! preg_match( '#\=\?(.+)\?Q\?(.+)\?\=#i', $subject, $matches ) ) { 3814 return $subject; 3815 } 3816 3817 $subject = str_replace( '_', ' ', $matches[2] ); 3818 return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject ); 3819 } 3820 3821 /** 3822 * Helper function to convert hex encoded chars to ASCII. 3823 * 3824 * @since 3.1.0 3825 * @access private 3826 * 3827 * @param array $matches The preg_replace_callback matches array. 3828 * @return string Converted chars. 3829 */ 3830 function _wp_iso_convert( $matches ) { 3831 return chr( hexdec( strtolower( $matches[1] ) ) ); 3832 } 3833 3834 /** 3835 * Given a date in the timezone of the site, returns that date in UTC. 3836 * 3837 * Requires and returns a date in the Y-m-d H:i:s format. 3838 * Return format can be overridden using the $format parameter. 3839 * 3840 * @since 1.2.0 3841 * 3842 * @param string $date_string The date to be converted, in the timezone of the site. 3843 * @param string $format The format string for the returned date. Default 'Y-m-d H:i:s'. 3844 * @return string Formatted version of the date, in UTC. 3845 */ 3846 function get_gmt_from_date( $date_string, $format = 'Y-m-d H:i:s' ) { 3847 $datetime = date_create( $date_string, wp_timezone() ); 3848 3849 if ( false === $datetime ) { 3850 return gmdate( $format, 0 ); 3851 } 3852 3853 return $datetime->setTimezone( new DateTimeZone( 'UTC' ) )->format( $format ); 3854 } 3855 3856 /** 3857 * Given a date in UTC or GMT timezone, returns that date in the timezone of the site. 3858 * 3859 * Requires a date in the Y-m-d H:i:s format. 3860 * Default return format of 'Y-m-d H:i:s' can be overridden using the `$format` parameter. 3861 * 3862 * @since 1.2.0 3863 * 3864 * @param string $date_string The date to be converted, in UTC or GMT timezone. 3865 * @param string $format The format string for the returned date. Default 'Y-m-d H:i:s'. 3866 * @return string Formatted version of the date, in the site's timezone. 3867 */ 3868 function get_date_from_gmt( $date_string, $format = 'Y-m-d H:i:s' ) { 3869 $datetime = date_create( $date_string, new DateTimeZone( 'UTC' ) ); 3870 3871 if ( false === $datetime ) { 3872 return gmdate( $format, 0 ); 3873 } 3874 3875 return $datetime->setTimezone( wp_timezone() )->format( $format ); 3876 } 3877 3878 /** 3879 * Given an ISO 8601 timezone, returns its UTC offset in seconds. 3880 * 3881 * @since 1.5.0 3882 * 3883 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'. 3884 * @return int|float The offset in seconds. 3885 */ 3886 function iso8601_timezone_to_offset( $timezone ) { 3887 // $timezone is either 'Z' or '[+|-]hhmm'. 3888 if ( 'Z' === $timezone ) { 3889 $offset = 0; 3890 } else { 3891 $sign = ( str_starts_with( $timezone, '+' ) ) ? 1 : -1; 3892 $hours = (int) substr( $timezone, 1, 2 ); 3893 $minutes = (int) substr( $timezone, 3, 4 ) / 60; 3894 $offset = $sign * HOUR_IN_SECONDS * ( $hours + $minutes ); 3895 } 3896 return $offset; 3897 } 3898 3899 /** 3900 * 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]. 3901 * 3902 * @since 1.5.0 3903 * 3904 * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}. 3905 * @param string $timezone Optional. If set to 'gmt' returns the result in UTC. Default 'user'. 3906 * @return string|false The date and time in MySQL DateTime format - Y-m-d H:i:s, or false on failure. 3907 */ 3908 function iso8601_to_datetime( $date_string, $timezone = 'user' ) { 3909 $timezone = strtolower( $timezone ); 3910 $wp_timezone = wp_timezone(); 3911 $datetime = date_create( $date_string, $wp_timezone ); // Timezone is ignored if input has one. 3912 3913 if ( false === $datetime ) { 3914 return false; 3915 } 3916 3917 if ( 'gmt' === $timezone ) { 3918 return $datetime->setTimezone( new DateTimeZone( 'UTC' ) )->format( 'Y-m-d H:i:s' ); 3919 } 3920 3921 if ( 'user' === $timezone ) { 3922 return $datetime->setTimezone( $wp_timezone )->format( 'Y-m-d H:i:s' ); 3923 } 3924 3925 return false; 3926 } 3927 3928 /** 3929 * Strips out all characters that are not allowable in an email. 3930 * 3931 * @since 1.5.0 3932 * 3933 * @param string $email Email address to filter. 3934 * @return string Filtered email address. 3935 */ 3936 function sanitize_email( $email ) { 3937 // Test for the minimum length the email can be. 3938 if ( strlen( $email ) < 6 ) { 3939 /** 3940 * Filters a sanitized email address. 3941 * 3942 * This filter is evaluated under several contexts, including 'email_too_short', 3943 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits', 3944 * 'domain_no_periods', 'domain_no_valid_subs', or no context. 3945 * 3946 * @since 2.8.0 3947 * 3948 * @param string $sanitized_email The sanitized email address. 3949 * @param string $email The email address, as provided to sanitize_email(). 3950 * @param string|null $message A message to pass to the user. null if email is sanitized. 3951 */ 3952 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' ); 3953 } 3954 3955 // Test for an @ character after the first position. 3956 if ( strpos( $email, '@', 1 ) === false ) { 3957 /** This filter is documented in wp-includes/formatting.php */ 3958 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' ); 3959 } 3960 3961 // Split out the local and domain parts. 3962 list( $local, $domain ) = explode( '@', $email, 2 ); 3963 3964 /* 3965 * LOCAL PART 3966 * Test for invalid characters. 3967 */ 3968 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local ); 3969 if ( '' === $local ) { 3970 /** This filter is documented in wp-includes/formatting.php */ 3971 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' ); 3972 } 3973 3974 /* 3975 * DOMAIN PART 3976 * Test for sequences of periods. 3977 */ 3978 $domain = preg_replace( '/\.{2,}/', '', $domain ); 3979 if ( '' === $domain ) { 3980 /** This filter is documented in wp-includes/formatting.php */ 3981 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' ); 3982 } 3983 3984 // Test for leading and trailing periods and whitespace. 3985 $domain = trim( $domain, " \t\n\r\0\x0B." ); 3986 if ( '' === $domain ) { 3987 /** This filter is documented in wp-includes/formatting.php */ 3988 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' ); 3989 } 3990 3991 // Split the domain into subs. 3992 $subs = explode( '.', $domain ); 3993 3994 // Assume the domain will have at least two subs. 3995 if ( 2 > count( $subs ) ) { 3996 /** This filter is documented in wp-includes/formatting.php */ 3997 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' ); 3998 } 3999 4000 // Create an array that will contain valid subs. 4001 $new_subs = array(); 4002 4003 // Loop through each sub. 4004 foreach ( $subs as $sub ) { 4005 // Test for leading and trailing hyphens. 4006 $sub = trim( $sub, " \t\n\r\0\x0B-" ); 4007 4008 // Test for invalid characters. 4009 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub ); 4010 4011 // If there's anything left, add it to the valid subs. 4012 if ( '' !== $sub ) { 4013 $new_subs[] = $sub; 4014 } 4015 } 4016 4017 // If there aren't 2 or more valid subs. 4018 if ( 2 > count( $new_subs ) ) { 4019 /** This filter is documented in wp-includes/formatting.php */ 4020 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' ); 4021 } 4022 4023 // Join valid subs into the new domain. 4024 $domain = implode( '.', $new_subs ); 4025 4026 // Put the email back together. 4027 $sanitized_email = $local . '@' . $domain; 4028 4029 // Congratulations, your email made it! 4030 /** This filter is documented in wp-includes/formatting.php */ 4031 return apply_filters( 'sanitize_email', $sanitized_email, $email, null ); 4032 } 4033 4034 /** 4035 * Determines the difference between two timestamps. 4036 * 4037 * The difference is returned in a human-readable format such as "1 hour", 4038 * "5 minutes", "2 days". 4039 * 4040 * @since 1.5.0 4041 * @since 5.3.0 Added support for showing a difference in seconds. 4042 * 4043 * @param int $from Unix timestamp from which the difference begins. 4044 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set. 4045 * @return string Human-readable time difference. 4046 */ 4047 function human_time_diff( $from, $to = 0 ) { 4048 if ( empty( $to ) ) { 4049 $to = time(); 4050 } 4051 4052 $diff = (int) abs( $to - $from ); 4053 4054 if ( $diff < MINUTE_IN_SECONDS ) { 4055 $secs = $diff; 4056 if ( $secs <= 1 ) { 4057 $secs = 1; 4058 } 4059 /* translators: Time difference between two dates, in seconds. %s: Number of seconds. */ 4060 $since = sprintf( _n( '%s second', '%s seconds', $secs ), $secs ); 4061 } elseif ( $diff < HOUR_IN_SECONDS && $diff >= MINUTE_IN_SECONDS ) { 4062 $mins = round( $diff / MINUTE_IN_SECONDS ); 4063 if ( $mins <= 1 ) { 4064 $mins = 1; 4065 } 4066 /* translators: Time difference between two dates, in minutes. %s: Number of minutes. */ 4067 $since = sprintf( _n( '%s minute', '%s minutes', $mins ), $mins ); 4068 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) { 4069 $hours = round( $diff / HOUR_IN_SECONDS ); 4070 if ( $hours <= 1 ) { 4071 $hours = 1; 4072 } 4073 /* translators: Time difference between two dates, in hours. %s: Number of hours. */ 4074 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours ); 4075 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) { 4076 $days = round( $diff / DAY_IN_SECONDS ); 4077 if ( $days <= 1 ) { 4078 $days = 1; 4079 } 4080 /* translators: Time difference between two dates, in days. %s: Number of days. */ 4081 $since = sprintf( _n( '%s day', '%s days', $days ), $days ); 4082 } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) { 4083 $weeks = round( $diff / WEEK_IN_SECONDS ); 4084 if ( $weeks <= 1 ) { 4085 $weeks = 1; 4086 } 4087 /* translators: Time difference between two dates, in weeks. %s: Number of weeks. */ 4088 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks ); 4089 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) { 4090 $months = round( $diff / MONTH_IN_SECONDS ); 4091 if ( $months <= 1 ) { 4092 $months = 1; 4093 } 4094 /* translators: Time difference between two dates, in months. %s: Number of months. */ 4095 $since = sprintf( _n( '%s month', '%s months', $months ), $months ); 4096 } elseif ( $diff >= YEAR_IN_SECONDS ) { 4097 $years = round( $diff / YEAR_IN_SECONDS ); 4098 if ( $years <= 1 ) { 4099 $years = 1; 4100 } 4101 /* translators: Time difference between two dates, in years. %s: Number of years. */ 4102 $since = sprintf( _n( '%s year', '%s years', $years ), $years ); 4103 } 4104 4105 /** 4106 * Filters the human-readable difference between two timestamps. 4107 * 4108 * @since 4.0.0 4109 * 4110 * @param string $since The difference in human-readable text. 4111 * @param int $diff The difference in seconds. 4112 * @param int $from Unix timestamp from which the difference begins. 4113 * @param int $to Unix timestamp to end the time difference. 4114 */ 4115 return apply_filters( 'human_time_diff', $since, $diff, $from, $to ); 4116 } 4117 4118 /** 4119 * Generates an excerpt from the content, if needed. 4120 * 4121 * Returns a maximum of 55 words with an ellipsis appended if necessary. 4122 * 4123 * The 55-word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter 4124 * The ' […]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter 4125 * 4126 * @since 1.5.0 4127 * @since 5.2.0 Added the `$post` parameter. 4128 * @since 6.3.0 Removes footnotes markup from the excerpt content. 4129 * 4130 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated. 4131 * @param WP_Post|object|int $post Optional. WP_Post instance or Post ID/object. Default null. 4132 * @return string The excerpt. 4133 */ 4134 function wp_trim_excerpt( $text = '', $post = null ) { 4135 $raw_excerpt = $text; 4136 4137 if ( '' === trim( $text ) ) { 4138 $post = get_post( $post ); 4139 $text = get_the_content( '', false, $post ); 4140 4141 $text = strip_shortcodes( $text ); 4142 $text = excerpt_remove_blocks( $text ); 4143 $text = excerpt_remove_footnotes( $text ); 4144 4145 /* 4146 * Temporarily unhook wp_filter_content_tags() since any tags 4147 * within the excerpt are stripped out. Modifying the tags here 4148 * is wasteful and can lead to bugs in the image counting logic. 4149 */ 4150 $filter_image_removed = remove_filter( 'the_content', 'wp_filter_content_tags', 12 ); 4151 4152 /* 4153 * Temporarily unhook do_blocks() since excerpt_remove_blocks( $text ) 4154 * handles block rendering needed for excerpt. 4155 */ 4156 $filter_block_removed = remove_filter( 'the_content', 'do_blocks', 9 ); 4157 4158 /** This filter is documented in wp-includes/post-template.php */ 4159 $text = apply_filters( 'the_content', $text ); 4160 $text = str_replace( ']]>', ']]>', $text ); 4161 4162 // Restore the original filter if removed. 4163 if ( $filter_block_removed ) { 4164 add_filter( 'the_content', 'do_blocks', 9 ); 4165 } 4166 4167 /* 4168 * Only restore the filter callback if it was removed above. The logic 4169 * to unhook and restore only applies on the default priority of 10, 4170 * which is generally used for the filter callback in WordPress core. 4171 */ 4172 if ( $filter_image_removed ) { 4173 add_filter( 'the_content', 'wp_filter_content_tags', 12 ); 4174 } 4175 4176 /* translators: Maximum number of words used in a post excerpt. */ 4177 $excerpt_length = (int) _x( '55', 'excerpt_length' ); 4178 4179 /** 4180 * Filters the maximum number of words in a post excerpt. 4181 * 4182 * @since 2.7.0 4183 * 4184 * @param int $number The maximum number of words. Default 55. 4185 */ 4186 $excerpt_length = (int) apply_filters( 'excerpt_length', $excerpt_length ); 4187 4188 /** 4189 * Filters the string in the "more" link displayed after a trimmed excerpt. 4190 * 4191 * @since 2.9.0 4192 * 4193 * @param string $more_string The string shown within the more link. 4194 */ 4195 $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' ); 4196 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more ); 4197 4198 } 4199 4200 /** 4201 * Filters the trimmed excerpt string. 4202 * 4203 * @since 2.8.0 4204 * 4205 * @param string $text The trimmed text. 4206 * @param string $raw_excerpt The text prior to trimming. 4207 */ 4208 return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt ); 4209 } 4210 4211 /** 4212 * Trims text to a certain number of words. 4213 * 4214 * This function is localized. For languages that count 'words' by the individual 4215 * character (such as East Asian languages), the $num_words argument will apply 4216 * to the number of individual characters. 4217 * 4218 * @since 3.3.0 4219 * 4220 * @param string $text Text to trim. 4221 * @param int $num_words Number of words. Default 55. 4222 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'. 4223 * @return string Trimmed text. 4224 */ 4225 function wp_trim_words( $text, $num_words = 55, $more = null ) { 4226 if ( null === $more ) { 4227 $more = __( '…' ); 4228 } 4229 4230 $original_text = $text; 4231 $text = wp_strip_all_tags( $text ); 4232 $num_words = (int) $num_words; 4233 4234 if ( str_starts_with( wp_get_word_count_type(), 'characters' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) { 4235 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' ); 4236 preg_match_all( '/./u', $text, $words_array ); 4237 $words_array = array_slice( $words_array[0], 0, $num_words + 1 ); 4238 $sep = ''; 4239 } else { 4240 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY ); 4241 $sep = ' '; 4242 } 4243 4244 if ( count( $words_array ) > $num_words ) { 4245 array_pop( $words_array ); 4246 $text = implode( $sep, $words_array ); 4247 $text = $text . $more; 4248 } else { 4249 $text = implode( $sep, $words_array ); 4250 } 4251 4252 /** 4253 * Filters the text content after words have been trimmed. 4254 * 4255 * @since 3.3.0 4256 * 4257 * @param string $text The trimmed text. 4258 * @param int $num_words The number of words to trim the text to. Default 55. 4259 * @param string $more An optional string to append to the end of the trimmed text, e.g. …. 4260 * @param string $original_text The text before it was trimmed. 4261 */ 4262 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text ); 4263 } 4264 4265 /** 4266 * Converts named entities into numbered entities. 4267 * 4268 * @since 1.5.1 4269 * 4270 * @param string $text The text within which entities will be converted. 4271 * @return string Text with converted entities. 4272 */ 4273 function ent2ncr( $text ) { 4274 4275 /** 4276 * Filters text before named entities are converted into numbered entities. 4277 * 4278 * A non-null string must be returned for the filter to be evaluated. 4279 * 4280 * @since 3.3.0 4281 * 4282 * @param string|null $converted_text The text to be converted. Default null. 4283 * @param string $text The text prior to entity conversion. 4284 */ 4285 $filtered = apply_filters( 'pre_ent2ncr', null, $text ); 4286 if ( null !== $filtered ) { 4287 return $filtered; 4288 } 4289 4290 $to_ncr = array( 4291 '"' => '"', 4292 '&' => '&', 4293 '<' => '<', 4294 '>' => '>', 4295 '|' => '|', 4296 ' ' => ' ', 4297 '¡' => '¡', 4298 '¢' => '¢', 4299 '£' => '£', 4300 '¤' => '¤', 4301 '¥' => '¥', 4302 '¦' => '¦', 4303 '&brkbar;' => '¦', 4304 '§' => '§', 4305 '¨' => '¨', 4306 '¨' => '¨', 4307 '©' => '©', 4308 'ª' => 'ª', 4309 '«' => '«', 4310 '¬' => '¬', 4311 '­' => '­', 4312 '®' => '®', 4313 '¯' => '¯', 4314 '&hibar;' => '¯', 4315 '°' => '°', 4316 '±' => '±', 4317 '²' => '²', 4318 '³' => '³', 4319 '´' => '´', 4320 'µ' => 'µ', 4321 '¶' => '¶', 4322 '·' => '·', 4323 '¸' => '¸', 4324 '¹' => '¹', 4325 'º' => 'º', 4326 '»' => '»', 4327 '¼' => '¼', 4328 '½' => '½', 4329 '¾' => '¾', 4330 '¿' => '¿', 4331 'À' => 'À', 4332 'Á' => 'Á', 4333 'Â' => 'Â', 4334 'Ã' => 'Ã', 4335 'Ä' => 'Ä', 4336 'Å' => 'Å', 4337 'Æ' => 'Æ', 4338 'Ç' => 'Ç', 4339 'È' => 'È', 4340 'É' => 'É', 4341 'Ê' => 'Ê', 4342 'Ë' => 'Ë', 4343 'Ì' => 'Ì', 4344 'Í' => 'Í', 4345 'Î' => 'Î', 4346 'Ï' => 'Ï', 4347 'Ð' => 'Ð', 4348 'Ñ' => 'Ñ', 4349 'Ò' => 'Ò', 4350 'Ó' => 'Ó', 4351 'Ô' => 'Ô', 4352 'Õ' => 'Õ', 4353 'Ö' => 'Ö', 4354 '×' => '×', 4355 'Ø' => 'Ø', 4356 'Ù' => 'Ù', 4357 'Ú' => 'Ú', 4358 'Û' => 'Û', 4359 'Ü' => 'Ü', 4360 'Ý' => 'Ý', 4361 'Þ' => 'Þ', 4362 'ß' => 'ß', 4363 'à' => 'à', 4364 'á' => 'á', 4365 'â' => 'â', 4366 'ã' => 'ã', 4367 'ä' => 'ä', 4368 'å' => 'å', 4369 'æ' => 'æ', 4370 'ç' => 'ç', 4371 'è' => 'è', 4372 'é' => 'é', 4373 'ê' => 'ê', 4374 'ë' => 'ë', 4375 'ì' => 'ì', 4376 'í' => 'í', 4377 'î' => 'î', 4378 'ï' => 'ï', 4379 'ð' => 'ð', 4380 'ñ' => 'ñ', 4381 'ò' => 'ò', 4382 'ó' => 'ó', 4383 'ô' => 'ô', 4384 'õ' => 'õ', 4385 'ö' => 'ö', 4386 '÷' => '÷', 4387 'ø' => 'ø', 4388 'ù' => 'ù', 4389 'ú' => 'ú', 4390 'û' => 'û', 4391 'ü' => 'ü', 4392 'ý' => 'ý', 4393 'þ' => 'þ', 4394 'ÿ' => 'ÿ', 4395 'Œ' => 'Œ', 4396 'œ' => 'œ', 4397 'Š' => 'Š', 4398 'š' => 'š', 4399 'Ÿ' => 'Ÿ', 4400 'ƒ' => 'ƒ', 4401 'ˆ' => 'ˆ', 4402 '˜' => '˜', 4403 'Α' => 'Α', 4404 'Β' => 'Β', 4405 'Γ' => 'Γ', 4406 'Δ' => 'Δ', 4407 'Ε' => 'Ε', 4408 'Ζ' => 'Ζ', 4409 'Η' => 'Η', 4410 'Θ' => 'Θ', 4411 'Ι' => 'Ι', 4412 'Κ' => 'Κ', 4413 'Λ' => 'Λ', 4414 'Μ' => 'Μ', 4415 'Ν' => 'Ν', 4416 'Ξ' => 'Ξ', 4417 'Ο' => 'Ο', 4418 'Π' => 'Π', 4419 'Ρ' => 'Ρ', 4420 'Σ' => 'Σ', 4421 'Τ' => 'Τ', 4422 'Υ' => 'Υ', 4423 'Φ' => 'Φ', 4424 'Χ' => 'Χ', 4425 'Ψ' => 'Ψ', 4426 'Ω' => 'Ω', 4427 'α' => 'α', 4428 'β' => 'β', 4429 'γ' => 'γ', 4430 'δ' => 'δ', 4431 'ε' => 'ε', 4432 'ζ' => 'ζ', 4433 'η' => 'η', 4434 'θ' => 'θ', 4435 'ι' => 'ι', 4436 'κ' => 'κ', 4437 'λ' => 'λ', 4438 'μ' => 'μ', 4439 'ν' => 'ν', 4440 'ξ' => 'ξ', 4441 'ο' => 'ο', 4442 'π' => 'π', 4443 'ρ' => 'ρ', 4444 'ς' => 'ς', 4445 'σ' => 'σ', 4446 'τ' => 'τ', 4447 'υ' => 'υ', 4448 'φ' => 'φ', 4449 'χ' => 'χ', 4450 'ψ' => 'ψ', 4451 'ω' => 'ω', 4452 'ϑ' => 'ϑ', 4453 'ϒ' => 'ϒ', 4454 'ϖ' => 'ϖ', 4455 ' ' => ' ', 4456 ' ' => ' ', 4457 ' ' => ' ', 4458 '‌' => '‌', 4459 '‍' => '‍', 4460 '‎' => '‎', 4461 '‏' => '‏', 4462 '–' => '–', 4463 '—' => '—', 4464 '‘' => '‘', 4465 '’' => '’', 4466 '‚' => '‚', 4467 '“' => '“', 4468 '”' => '”', 4469 '„' => '„', 4470 '†' => '†', 4471 '‡' => '‡', 4472 '•' => '•', 4473 '…' => '…', 4474 '‰' => '‰', 4475 '′' => '′', 4476 '″' => '″', 4477 '‹' => '‹', 4478 '›' => '›', 4479 '‾' => '‾', 4480 '⁄' => '⁄', 4481 '€' => '€', 4482 'ℑ' => 'ℑ', 4483 '℘' => '℘', 4484 'ℜ' => 'ℜ', 4485 '™' => '™', 4486 'ℵ' => 'ℵ', 4487 '↵' => '↵', 4488 '⇐' => '⇐', 4489 '⇑' => '⇑', 4490 '⇒' => '⇒', 4491 '⇓' => '⇓', 4492 '⇔' => '⇔', 4493 '∀' => '∀', 4494 '∂' => '∂', 4495 '∃' => '∃', 4496 '∅' => '∅', 4497 '∇' => '∇', 4498 '∈' => '∈', 4499 '∉' => '∉', 4500 '∋' => '∋', 4501 '∏' => '∏', 4502 '∑' => '∑', 4503 '−' => '−', 4504 '∗' => '∗', 4505 '√' => '√', 4506 '∝' => '∝', 4507 '∞' => '∞', 4508 '∠' => '∠', 4509 '∧' => '∧', 4510 '∨' => '∨', 4511 '∩' => '∩', 4512 '∪' => '∪', 4513 '∫' => '∫', 4514 '∴' => '∴', 4515 '∼' => '∼', 4516 '≅' => '≅', 4517 '≈' => '≈', 4518 '≠' => '≠', 4519 '≡' => '≡', 4520 '≤' => '≤', 4521 '≥' => '≥', 4522 '⊂' => '⊂', 4523 '⊃' => '⊃', 4524 '⊄' => '⊄', 4525 '⊆' => '⊆', 4526 '⊇' => '⊇', 4527 '⊕' => '⊕', 4528 '⊗' => '⊗', 4529 '⊥' => '⊥', 4530 '⋅' => '⋅', 4531 '⌈' => '⌈', 4532 '⌉' => '⌉', 4533 '⌊' => '⌊', 4534 '⌋' => '⌋', 4535 '⟨' => '〈', 4536 '⟩' => '〉', 4537 '←' => '←', 4538 '↑' => '↑', 4539 '→' => '→', 4540 '↓' => '↓', 4541 '↔' => '↔', 4542 '◊' => '◊', 4543 '♠' => '♠', 4544 '♣' => '♣', 4545 '♥' => '♥', 4546 '♦' => '♦', 4547 ); 4548 4549 return str_replace( array_keys( $to_ncr ), array_values( $to_ncr ), $text ); 4550 } 4551 4552 /** 4553 * Formats text for the editor. 4554 * 4555 * Generally the browsers treat everything inside a textarea as text, but 4556 * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content. 4557 * 4558 * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the 4559 * filter will be applied to an empty string. 4560 * 4561 * @since 4.3.0 4562 * 4563 * @see _WP_Editors::editor() 4564 * 4565 * @param string $text The text to be formatted. 4566 * @param string $default_editor The default editor for the current user. 4567 * It is usually either 'html' or 'tinymce'. 4568 * @return string The formatted text after filter is applied. 4569 */ 4570 function format_for_editor( $text, $default_editor = null ) { 4571 if ( $text ) { 4572 $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) ); 4573 } 4574 4575 /** 4576 * Filters the text after it is formatted for the editor. 4577 * 4578 * @since 4.3.0 4579 * 4580 * @param string $text The formatted text. 4581 * @param string $default_editor The default editor for the current user. 4582 * It is usually either 'html' or 'tinymce'. 4583 */ 4584 return apply_filters( 'format_for_editor', $text, $default_editor ); 4585 } 4586 4587 /** 4588 * Performs a deep string replace operation to ensure the values in $search are no longer present. 4589 * 4590 * Repeats the replacement operation until it no longer replaces anything to remove "nested" values 4591 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that 4592 * str_replace would return 4593 * 4594 * @since 2.8.1 4595 * @access private 4596 * 4597 * @param string|array $search The value being searched for, otherwise known as the needle. 4598 * An array may be used to designate multiple needles. 4599 * @param string $subject The string being searched and replaced on, otherwise known as the haystack. 4600 * @return string The string with the replaced values. 4601 */ 4602 function _deep_replace( $search, $subject ) { 4603 $subject = (string) $subject; 4604 4605 $count = 1; 4606 while ( $count ) { 4607 $subject = str_replace( $search, '', $subject, $count ); 4608 } 4609 4610 return $subject; 4611 } 4612 4613 /** 4614 * Escapes data for use in a MySQL query. 4615 * 4616 * Usually you should prepare queries using wpdb::prepare(). 4617 * Sometimes, spot-escaping is required or useful. One example 4618 * is preparing an array for use in an IN clause. 4619 * 4620 * NOTE: Since 4.8.3, '%' characters will be replaced with a placeholder string, 4621 * this prevents certain SQLi attacks from taking place. This change in behavior 4622 * may cause issues for code that expects the return value of esc_sql() to be usable 4623 * for other purposes. 4624 * 4625 * @since 2.8.0 4626 * 4627 * @global wpdb $wpdb WordPress database abstraction object. 4628 * 4629 * @param string|array $data Unescaped data. 4630 * @return string|array Escaped data, in the same type as supplied. 4631 */ 4632 function esc_sql( $data ) { 4633 global $wpdb; 4634 return $wpdb->_escape( $data ); 4635 } 4636 4637 /** 4638 * Checks and cleans a URL. 4639 * 4640 * A number of characters are removed from the URL. If the URL is for displaying 4641 * (the default behavior) ampersands are also replaced. The {@see 'clean_url'} filter 4642 * is applied to the returned cleaned URL. 4643 * 4644 * @since 2.8.0 4645 * 4646 * @param string $url The URL to be cleaned. 4647 * @param string[] $protocols Optional. An array of acceptable protocols. 4648 * Defaults to return value of wp_allowed_protocols(). 4649 * @param string $_context Private. Use sanitize_url() for database usage. 4650 * @return string The cleaned URL after the {@see 'clean_url'} filter is applied. 4651 * An empty string is returned if `$url` specifies a protocol other than 4652 * those in `$protocols`, or if `$url` contains an empty string. 4653 */ 4654 function esc_url( $url, $protocols = null, $_context = 'display' ) { 4655 $original_url = $url; 4656 4657 if ( '' === $url ) { 4658 return $url; 4659 } 4660 4661 $url = str_replace( ' ', '%20', ltrim( $url ) ); 4662 $url = preg_replace( '|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url ); 4663 4664 if ( '' === $url ) { 4665 return $url; 4666 } 4667 4668 if ( 0 !== stripos( $url, 'mailto:' ) ) { 4669 $strip = array( '%0d', '%0a', '%0D', '%0A' ); 4670 $url = _deep_replace( $strip, $url ); 4671 } 4672 4673 $url = str_replace( ';//', '://', $url ); 4674 /* 4675 * If the URL doesn't appear to contain a scheme, we presume 4676 * it needs http:// prepended (unless it's a relative link 4677 * starting with /, # or ?, or a PHP file). 4678 */ 4679 if ( ! str_contains( $url, ':' ) && ! in_array( $url[0], array( '/', '#', '?' ), true ) && 4680 ! preg_match( '/^[a-z0-9-]+?\.php/i', $url ) 4681 ) { 4682 $url = 'http://' . $url; 4683 } 4684 4685 // Replace ampersands and single quotes only when displaying. 4686 if ( 'display' === $_context ) { 4687 $url = wp_kses_normalize_entities( $url ); 4688 $url = str_replace( '&', '&', $url ); 4689 $url = str_replace( "'", ''', $url ); 4690 } 4691 4692 if ( str_contains( $url, '[' ) || str_contains( $url, ']' ) ) { 4693 4694 $parsed = wp_parse_url( $url ); 4695 $front = ''; 4696 4697 if ( isset( $parsed['scheme'] ) ) { 4698 $front .= $parsed['scheme'] . '://'; 4699 } elseif ( '/' === $url[0] ) { 4700 $front .= '//'; 4701 } 4702 4703 if ( isset( $parsed['user'] ) ) { 4704 $front .= $parsed['user']; 4705 } 4706 4707 if ( isset( $parsed['pass'] ) ) { 4708 $front .= ':' . $parsed['pass']; 4709 } 4710 4711 if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) { 4712 $front .= '@'; 4713 } 4714 4715 if ( isset( $parsed['host'] ) ) { 4716 $front .= $parsed['host']; 4717 } 4718 4719 if ( isset( $parsed['port'] ) ) { 4720 $front .= ':' . $parsed['port']; 4721 } 4722 4723 $end_dirty = str_replace( $front, '', $url ); 4724 $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty ); 4725 $url = str_replace( $end_dirty, $end_clean, $url ); 4726 4727 } 4728 4729 if ( '/' === $url[0] ) { 4730 $good_protocol_url = $url; 4731 } else { 4732 if ( ! is_array( $protocols ) ) { 4733 $protocols = wp_allowed_protocols(); 4734 } 4735 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols ); 4736 if ( strtolower( $good_protocol_url ) !== strtolower( $url ) ) { 4737 return ''; 4738 } 4739 } 4740 4741 /** 4742 * Filters a string cleaned and escaped for output as a URL. 4743 * 4744 * @since 2.3.0 4745 * 4746 * @param string $good_protocol_url The cleaned URL to be returned. 4747 * @param string $original_url The URL prior to cleaning. 4748 * @param string $_context If 'display', replace ampersands and single quotes only. 4749 */ 4750 return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context ); 4751 } 4752 4753 /** 4754 * Sanitizes a URL for database or redirect usage. 4755 * 4756 * This function is an alias for sanitize_url(). 4757 * 4758 * @since 2.8.0 4759 * @since 6.1.0 Turned into an alias for sanitize_url(). 4760 * 4761 * @see sanitize_url() 4762 * 4763 * @param string $url The URL to be cleaned. 4764 * @param string[] $protocols Optional. An array of acceptable protocols. 4765 * Defaults to return value of wp_allowed_protocols(). 4766 * @return string The cleaned URL after sanitize_url() is run. 4767 */ 4768 function esc_url_raw( $url, $protocols = null ) { 4769 return sanitize_url( $url, $protocols ); 4770 } 4771 4772 /** 4773 * Sanitizes a URL for database or redirect usage. 4774 * 4775 * @since 2.3.1 4776 * @since 2.8.0 Deprecated in favor of esc_url_raw(). 4777 * @since 5.9.0 Restored (un-deprecated). 4778 * 4779 * @see esc_url() 4780 * 4781 * @param string $url The URL to be cleaned. 4782 * @param string[] $protocols Optional. An array of acceptable protocols. 4783 * Defaults to return value of wp_allowed_protocols(). 4784 * @return string The cleaned URL after esc_url() is run with the 'db' context. 4785 */ 4786 function sanitize_url( $url, $protocols = null ) { 4787 return esc_url( $url, $protocols, 'db' ); 4788 } 4789 4790 /** 4791 * Converts entities, while preserving already-encoded entities. 4792 * 4793 * @link https://www.php.net/htmlentities Borrowed from the PHP Manual user notes. 4794 * 4795 * @since 1.2.2 4796 * 4797 * @param string $text The text to be converted. 4798 * @return string Converted text. 4799 */ 4800 function htmlentities2( $text ) { 4801 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES ); 4802 4803 $translation_table[ chr( 38 ) ] = '&'; 4804 4805 return preg_replace( '/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/', '&', strtr( $text, $translation_table ) ); 4806 } 4807 4808 /** 4809 * Escapes single quotes, `"`, `<`, `>`, `&`, and fixes line endings. 4810 * 4811 * Escapes text strings for echoing in JS. It is intended to be used for inline JS 4812 * (in a tag attribute, for example `onclick="..."`). Note that the strings have to 4813 * be in single quotes. The {@see 'js_escape'} filter is also applied here. 4814 * 4815 * @since 2.8.0 4816 * 4817 * @param string $text The text to be escaped. 4818 * @return string Escaped text. 4819 */ 4820 function esc_js( $text ) { 4821 $safe_text = wp_check_invalid_utf8( $text ); 4822 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT ); 4823 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) ); 4824 $safe_text = str_replace( "\r", '', $safe_text ); 4825 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) ); 4826 /** 4827 * Filters a string cleaned and escaped for output in JavaScript. 4828 * 4829 * Text passed to esc_js() is stripped of invalid or special characters, 4830 * and properly slashed for output. 4831 * 4832 * @since 2.0.6 4833 * 4834 * @param string $safe_text The text after it has been escaped. 4835 * @param string $text The text prior to being escaped. 4836 */ 4837 return apply_filters( 'js_escape', $safe_text, $text ); 4838 } 4839 4840 /** 4841 * Escaping for HTML blocks. 4842 * 4843 * @since 2.8.0 4844 * 4845 * @param string $text 4846 * @return string 4847 */ 4848 function esc_html( $text ) { 4849 $safe_text = wp_check_invalid_utf8( $text ); 4850 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES ); 4851 /** 4852 * Filters a string cleaned and escaped for output in HTML. 4853 * 4854 * Text passed to esc_html() is stripped of invalid or special characters 4855 * before output. 4856 * 4857 * @since 2.8.0 4858 * 4859 * @param string $safe_text The text after it has been escaped. 4860 * @param string $text The text prior to being escaped. 4861 */ 4862 return apply_filters( 'esc_html', $safe_text, $text ); 4863 } 4864 4865 /** 4866 * Escaping for HTML attributes. 4867 * 4868 * @since 2.8.0 4869 * 4870 * @param string $text 4871 * @return string 4872 */ 4873 function esc_attr( $text ) { 4874 $safe_text = wp_check_invalid_utf8( $text ); 4875 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES ); 4876 /** 4877 * Filters a string cleaned and escaped for output in an HTML attribute. 4878 * 4879 * Text passed to esc_attr() is stripped of invalid or special characters 4880 * before output. 4881 * 4882 * @since 2.0.6 4883 * 4884 * @param string $safe_text The text after it has been escaped. 4885 * @param string $text The text prior to being escaped. 4886 */ 4887 return apply_filters( 'attribute_escape', $safe_text, $text ); 4888 } 4889 4890 /** 4891 * Escaping for textarea values. 4892 * 4893 * @since 3.1.0 4894 * 4895 * @param string $text 4896 * @return string 4897 */ 4898 function esc_textarea( $text ) { 4899 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) ); 4900 /** 4901 * Filters a string cleaned and escaped for output in a textarea element. 4902 * 4903 * @since 3.1.0 4904 * 4905 * @param string $safe_text The text after it has been escaped. 4906 * @param string $text The text prior to being escaped. 4907 */ 4908 return apply_filters( 'esc_textarea', $safe_text, $text ); 4909 } 4910 4911 /** 4912 * Escaping for XML blocks. 4913 * 4914 * @since 5.5.0 4915 * 4916 * @param string $text Text to escape. 4917 * @return string Escaped text. 4918 */ 4919 function esc_xml( $text ) { 4920 $safe_text = wp_check_invalid_utf8( $text ); 4921 4922 $cdata_regex = '\<\!\[CDATA\[.*?\]\]\>'; 4923 $regex = <<<EOF 4924 / 4925 (?=.*?{$cdata_regex}) # lookahead that will match anything followed by a CDATA Section 4926 (?<non_cdata_followed_by_cdata>(.*?)) # the "anything" matched by the lookahead 4927 (?<cdata>({$cdata_regex})) # the CDATA Section matched by the lookahead 4928 4929 | # alternative 4930 4931 (?<non_cdata>(.*)) # non-CDATA Section 4932 /sx 4933 EOF; 4934 4935 $safe_text = (string) preg_replace_callback( 4936 $regex, 4937 static function ( $matches ) { 4938 if ( ! isset( $matches[0] ) ) { 4939 return ''; 4940 } 4941 4942 if ( isset( $matches['non_cdata'] ) ) { 4943 // escape HTML entities in the non-CDATA Section. 4944 return _wp_specialchars( $matches['non_cdata'], ENT_XML1 ); 4945 } 4946 4947 // Return the CDATA Section unchanged, escape HTML entities in the rest. 4948 return _wp_specialchars( $matches['non_cdata_followed_by_cdata'], ENT_XML1 ) . $matches['cdata']; 4949 }, 4950 $safe_text 4951 ); 4952 4953 /** 4954 * Filters a string cleaned and escaped for output in XML. 4955 * 4956 * Text passed to esc_xml() is stripped of invalid or special characters 4957 * before output. HTML named character references are converted to their 4958 * equivalent code points. 4959 * 4960 * @since 5.5.0 4961 * 4962 * @param string $safe_text The text after it has been escaped. 4963 * @param string $text The text prior to being escaped. 4964 */ 4965 return apply_filters( 'esc_xml', $safe_text, $text ); 4966 } 4967 4968 /** 4969 * Escapes an HTML tag name. 4970 * 4971 * @since 2.5.0 4972 * @since 6.5.5 Allow hyphens in tag names (i.e. custom elements). 4973 * 4974 * @param string $tag_name 4975 * @return string 4976 */ 4977 function tag_escape( $tag_name ) { 4978 $safe_tag = strtolower( preg_replace( '/[^a-zA-Z0-9-_:]/', '', $tag_name ) ); 4979 /** 4980 * Filters a string cleaned and escaped for output as an HTML tag. 4981 * 4982 * @since 2.8.0 4983 * 4984 * @param string $safe_tag The tag name after it has been escaped. 4985 * @param string $tag_name The text before it was escaped. 4986 */ 4987 return apply_filters( 'tag_escape', $safe_tag, $tag_name ); 4988 } 4989 4990 /** 4991 * Converts full URL paths to absolute paths. 4992 * 4993 * Removes the http or https protocols and the domain. Keeps the path '/' at the 4994 * beginning, so it isn't a true relative link, but from the web root base. 4995 * 4996 * @since 2.1.0 4997 * @since 4.1.0 Support was added for relative URLs. 4998 * 4999 * @param string $link Full URL path. 5000 * @return string Absolute path. 5001 */ 5002 function wp_make_link_relative( $link ) { 5003 return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link ); 5004 } 5005 5006 /** 5007 * Sanitizes various option values based on the nature of the option. 5008 * 5009 * This is basically a switch statement which will pass $value through a number 5010 * of functions depending on the $option. 5011 * 5012 * @since 2.0.5 5013 * 5014 * @global wpdb $wpdb WordPress database abstraction object. 5015 * 5016 * @param string $option The name of the option. 5017 * @param mixed $value The unsanitized value. 5018 * @return mixed Sanitized value. 5019 */ 5020 function sanitize_option( $option, $value ) { 5021 global $wpdb; 5022 5023 $original_value = $value; 5024 $error = null; 5025 5026 switch ( $option ) { 5027 case 'admin_email': 5028 case 'new_admin_email': 5029 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5030 if ( is_wp_error( $value ) ) { 5031 $error = $value->get_error_message(); 5032 } else { 5033 $value = sanitize_email( $value ); 5034 if ( ! is_email( $value ) ) { 5035 $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ); 5036 } 5037 } 5038 break; 5039 5040 case 'thumbnail_size_w': 5041 case 'thumbnail_size_h': 5042 case 'medium_size_w': 5043 case 'medium_size_h': 5044 case 'medium_large_size_w': 5045 case 'medium_large_size_h': 5046 case 'large_size_w': 5047 case 'large_size_h': 5048 case 'mailserver_port': 5049 case 'comment_max_links': 5050 case 'page_on_front': 5051 case 'page_for_posts': 5052 case 'rss_excerpt_length': 5053 case 'default_category': 5054 case 'default_email_category': 5055 case 'default_link_category': 5056 case 'close_comments_days_old': 5057 case 'comments_per_page': 5058 case 'thread_comments_depth': 5059 case 'users_can_register': 5060 case 'start_of_week': 5061 case 'site_icon': 5062 case 'fileupload_maxk': 5063 $value = absint( $value ); 5064 break; 5065 5066 case 'posts_per_page': 5067 case 'posts_per_rss': 5068 $value = (int) $value; 5069 if ( empty( $value ) ) { 5070 $value = 1; 5071 } 5072 if ( $value < -1 ) { 5073 $value = abs( $value ); 5074 } 5075 break; 5076 5077 case 'default_ping_status': 5078 case 'default_comment_status': 5079 // Options that if not there have 0 value but need to be something like "closed". 5080 if ( '0' === (string) $value || '' === $value ) { 5081 $value = 'closed'; 5082 } 5083 break; 5084 5085 case 'blogdescription': 5086 case 'blogname': 5087 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5088 if ( $value !== $original_value ) { 5089 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) ); 5090 } 5091 5092 if ( is_wp_error( $value ) ) { 5093 $error = $value->get_error_message(); 5094 } else { 5095 $value = esc_html( $value ); 5096 } 5097 break; 5098 5099 case 'blog_charset': 5100 if ( is_string( $value ) ) { 5101 $value = preg_replace( '/[^a-zA-Z0-9_-]/', '', $value ); // Strips slashes. 5102 } else { 5103 $value = ''; 5104 } 5105 break; 5106 5107 case 'blog_public': 5108 // This is the value if the settings checkbox is not checked on POST. Don't rely on this. 5109 if ( null === $value ) { 5110 $value = 1; 5111 } else { 5112 $value = (int) $value; 5113 } 5114 break; 5115 5116 case 'date_format': 5117 case 'time_format': 5118 case 'mailserver_url': 5119 case 'mailserver_login': 5120 case 'mailserver_pass': 5121 case 'upload_path': 5122 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5123 if ( is_wp_error( $value ) ) { 5124 $error = $value->get_error_message(); 5125 } else { 5126 $value = strip_tags( $value ); 5127 $value = wp_kses_data( $value ); 5128 } 5129 break; 5130 5131 case 'ping_sites': 5132 $value = explode( "\n", $value ); 5133 $value = array_filter( array_map( 'trim', $value ) ); 5134 $value = array_filter( array_map( 'sanitize_url', $value ) ); 5135 $value = implode( "\n", $value ); 5136 break; 5137 5138 case 'gmt_offset': 5139 if ( is_numeric( $value ) ) { 5140 $value = preg_replace( '/[^0-9:.-]/', '', $value ); // Strips slashes. 5141 } else { 5142 $value = ''; 5143 } 5144 break; 5145 5146 case 'siteurl': 5147 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5148 if ( is_wp_error( $value ) ) { 5149 $error = $value->get_error_message(); 5150 } else { 5151 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) { 5152 $value = sanitize_url( $value ); 5153 } else { 5154 $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' ); 5155 } 5156 } 5157 break; 5158 5159 case 'home': 5160 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5161 if ( is_wp_error( $value ) ) { 5162 $error = $value->get_error_message(); 5163 } else { 5164 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) { 5165 $value = sanitize_url( $value ); 5166 } else { 5167 $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' ); 5168 } 5169 } 5170 break; 5171 5172 case 'WPLANG': 5173 $allowed = get_available_languages(); 5174 if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) { 5175 $allowed[] = WPLANG; 5176 } 5177 if ( ! in_array( $value, $allowed, true ) && ! empty( $value ) ) { 5178 $value = get_option( $option ); 5179 } 5180 break; 5181 5182 case 'illegal_names': 5183 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5184 if ( is_wp_error( $value ) ) { 5185 $error = $value->get_error_message(); 5186 } else { 5187 if ( ! is_array( $value ) ) { 5188 $value = explode( ' ', $value ); 5189 } 5190 5191 $value = array_values( array_filter( array_map( 'trim', $value ) ) ); 5192 5193 if ( ! $value ) { 5194 $value = ''; 5195 } 5196 } 5197 break; 5198 5199 case 'limited_email_domains': 5200 case 'banned_email_domains': 5201 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5202 if ( is_wp_error( $value ) ) { 5203 $error = $value->get_error_message(); 5204 } else { 5205 if ( ! is_array( $value ) ) { 5206 $value = explode( "\n", $value ); 5207 } 5208 5209 $domains = array_values( array_filter( array_map( 'trim', $value ) ) ); 5210 $value = array(); 5211 5212 foreach ( $domains as $domain ) { 5213 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) { 5214 $value[] = $domain; 5215 } 5216 } 5217 if ( ! $value ) { 5218 $value = ''; 5219 } 5220 } 5221 break; 5222 5223 case 'timezone_string': 5224 $allowed_zones = timezone_identifiers_list( DateTimeZone::ALL_WITH_BC ); 5225 if ( ! in_array( $value, $allowed_zones, true ) && ! empty( $value ) ) { 5226 $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' ); 5227 } 5228 break; 5229 5230 case 'permalink_structure': 5231 case 'category_base': 5232 case 'tag_base': 5233 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5234 if ( is_wp_error( $value ) ) { 5235 $error = $value->get_error_message(); 5236 } else { 5237 $value = sanitize_url( $value ); 5238 $value = str_replace( 'http://', '', $value ); 5239 } 5240 5241 if ( 'permalink_structure' === $option && null === $error 5242 && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value ) 5243 ) { 5244 $error = sprintf( 5245 /* translators: %s: Documentation URL. */ 5246 __( 'A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>' ), 5247 __( 'https://wordpress.org/documentation/article/customize-permalinks/#choosing-your-permalink-structure' ) 5248 ); 5249 } 5250 break; 5251 5252 case 'default_role': 5253 if ( ! get_role( $value ) && get_role( 'subscriber' ) ) { 5254 $value = 'subscriber'; 5255 } 5256 break; 5257 5258 case 'moderation_keys': 5259 case 'disallowed_keys': 5260 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value ); 5261 if ( is_wp_error( $value ) ) { 5262 $error = $value->get_error_message(); 5263 } else { 5264 $value = explode( "\n", $value ); 5265 $value = array_filter( array_map( 'trim', $value ) ); 5266 $value = array_unique( $value ); 5267 $value = implode( "\n", $value ); 5268 } 5269 break; 5270 } 5271 5272 if ( null !== $error ) { 5273 if ( '' === $error && is_wp_error( $value ) ) { 5274 /* translators: 1: Option name, 2: Error code. */ 5275 $error = sprintf( __( 'Could not sanitize the %1$s option. Error code: %2$s' ), $option, $value->get_error_code() ); 5276 } 5277 5278 $value = get_option( $option ); 5279 if ( function_exists( 'add_settings_error' ) ) { 5280 add_settings_error( $option, "invalid_{$option}", $error ); 5281 } 5282 } 5283 5284 /** 5285 * Filters an option value following sanitization. 5286 * 5287 * @since 2.3.0 5288 * @since 4.3.0 Added the `$original_value` parameter. 5289 * 5290 * @param mixed $value The sanitized option value. 5291 * @param string $option The option name. 5292 * @param mixed $original_value The original value passed to the function. 5293 */ 5294 return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value ); 5295 } 5296 5297 /** 5298 * Maps a function to all non-iterable elements of an array or an object. 5299 * 5300 * This is similar to `array_walk_recursive()` but acts upon objects too. 5301 * 5302 * @since 4.4.0 5303 * 5304 * @param mixed $value The array, object, or scalar. 5305 * @param callable $callback The function to map onto $value. 5306 * @return mixed The value with the callback applied to all non-arrays and non-objects inside it. 5307 */ 5308 function map_deep( $value, $callback ) { 5309 if ( is_array( $value ) ) { 5310 foreach ( $value as $index => $item ) { 5311 $value[ $index ] = map_deep( $item, $callback ); 5312 } 5313 } elseif ( is_object( $value ) ) { 5314 $object_vars = get_object_vars( $value ); 5315 foreach ( $object_vars as $property_name => $property_value ) { 5316 $value->$property_name = map_deep( $property_value, $callback ); 5317 } 5318 } else { 5319 $value = call_user_func( $callback, $value ); 5320 } 5321 5322 return $value; 5323 } 5324 5325 /** 5326 * Parses a string into variables to be stored in an array. 5327 * 5328 * @since 2.2.1 5329 * 5330 * @param string $input_string The string to be parsed. 5331 * @param array $result Variables will be stored in this array. 5332 */ 5333 function wp_parse_str( $input_string, &$result ) { 5334 parse_str( (string) $input_string, $result ); 5335 5336 /** 5337 * Filters the array of variables derived from a parsed string. 5338 * 5339 * @since 2.2.1 5340 * 5341 * @param array $result The array populated with variables. 5342 */ 5343 $result = apply_filters( 'wp_parse_str', $result ); 5344 } 5345 5346 /** 5347 * Converts lone less than signs. 5348 * 5349 * KSES already converts lone greater than signs. 5350 * 5351 * @since 2.3.0 5352 * 5353 * @param string $content Text to be converted. 5354 * @return string Converted text. 5355 */ 5356 function wp_pre_kses_less_than( $content ) { 5357 return preg_replace_callback( '%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $content ); 5358 } 5359 5360 /** 5361 * Callback function used by preg_replace. 5362 * 5363 * @since 2.3.0 5364 * 5365 * @param string[] $matches Populated by matches to preg_replace. 5366 * @return string The text returned after esc_html if needed. 5367 */ 5368 function wp_pre_kses_less_than_callback( $matches ) { 5369 if ( ! str_contains( $matches[0], '>' ) ) { 5370 return esc_html( $matches[0] ); 5371 } 5372 return $matches[0]; 5373 } 5374 5375 /** 5376 * Removes non-allowable HTML from parsed block attribute values when filtering 5377 * in the post context. 5378 * 5379 * @since 5.3.1 5380 * 5381 * @param string $content Content to be run through KSES. 5382 * @param array[]|string $allowed_html An array of allowed HTML elements 5383 * and attributes, or a context name 5384 * such as 'post'. 5385 * @param string[] $allowed_protocols Array of allowed URL protocols. 5386 * @return string Filtered text to run through KSES. 5387 */ 5388 function wp_pre_kses_block_attributes( $content, $allowed_html, $allowed_protocols ) { 5389 /* 5390 * `filter_block_content` is expected to call `wp_kses`. Temporarily remove 5391 * the filter to avoid recursion. 5392 */ 5393 remove_filter( 'pre_kses', 'wp_pre_kses_block_attributes', 10 ); 5394 $content = filter_block_content( $content, $allowed_html, $allowed_protocols ); 5395 add_filter( 'pre_kses', 'wp_pre_kses_block_attributes', 10, 3 ); 5396 5397 return $content; 5398 } 5399 5400 /** 5401 * WordPress' implementation of PHP sprintf() with filters. 5402 * 5403 * @since 2.5.0 5404 * @since 5.3.0 Formalized the existing and already documented `...$args` parameter 5405 * by adding it to the function signature. 5406 * 5407 * @link https://www.php.net/sprintf 5408 * 5409 * @param string $pattern The string which formatted args are inserted. 5410 * @param mixed ...$args Arguments to be formatted into the $pattern string. 5411 * @return string The formatted string. 5412 */ 5413 function wp_sprintf( $pattern, ...$args ) { 5414 $len = strlen( $pattern ); 5415 $start = 0; 5416 $result = ''; 5417 $arg_index = 0; 5418 5419 while ( $len > $start ) { 5420 // Last character: append and break. 5421 if ( strlen( $pattern ) - 1 === $start ) { 5422 $result .= substr( $pattern, -1 ); 5423 break; 5424 } 5425 5426 // Literal %: append and continue. 5427 if ( '%%' === substr( $pattern, $start, 2 ) ) { 5428 $start += 2; 5429 $result .= '%'; 5430 continue; 5431 } 5432 5433 // Get fragment before next %. 5434 $end = strpos( $pattern, '%', $start + 1 ); 5435 if ( false === $end ) { 5436 $end = $len; 5437 } 5438 $fragment = substr( $pattern, $start, $end - $start ); 5439 5440 // Fragment has a specifier. 5441 if ( '%' === $pattern[ $start ] ) { 5442 // Find numbered arguments or take the next one in order. 5443 if ( preg_match( '/^%(\d+)\$/', $fragment, $matches ) ) { 5444 $index = $matches[1] - 1; // 0-based array vs 1-based sprintf() arguments. 5445 $arg = isset( $args[ $index ] ) ? $args[ $index ] : ''; 5446 $fragment = str_replace( "%{$matches[1]}$", '%', $fragment ); 5447 } else { 5448 $arg = isset( $args[ $arg_index ] ) ? $args[ $arg_index ] : ''; 5449 ++$arg_index; 5450 } 5451 5452 /** 5453 * Filters a fragment from the pattern passed to wp_sprintf(). 5454 * 5455 * If the fragment is unchanged, then sprintf() will be run on the fragment. 5456 * 5457 * @since 2.5.0 5458 * 5459 * @param string $fragment A fragment from the pattern. 5460 * @param string $arg The argument. 5461 */ 5462 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg ); 5463 5464 if ( $_fragment !== $fragment ) { 5465 $fragment = $_fragment; 5466 } else { 5467 $fragment = sprintf( $fragment, (string) $arg ); 5468 } 5469 } 5470 5471 // Append to result and move to next fragment. 5472 $result .= $fragment; 5473 $start = $end; 5474 } 5475 5476 return $result; 5477 } 5478 5479 /** 5480 * Localizes list items before the rest of the content. 5481 * 5482 * The '%l' must be at the first characters can then contain the rest of the 5483 * content. The list items will have ', ', ', and', and ' and ' added depending 5484 * on the amount of list items in the $args parameter. 5485 * 5486 * @since 2.5.0 5487 * 5488 * @param string $pattern Content containing '%l' at the beginning. 5489 * @param array $args List items to prepend to the content and replace '%l'. 5490 * @return string Localized list items and rest of the content. 5491 */ 5492 function wp_sprintf_l( $pattern, $args ) { 5493 // Not a match. 5494 if ( ! str_starts_with( $pattern, '%l' ) ) { 5495 return $pattern; 5496 } 5497 5498 // Nothing to work with. 5499 if ( empty( $args ) ) { 5500 return ''; 5501 } 5502 5503 /** 5504 * Filters the translated delimiters used by wp_sprintf_l(). 5505 * Placeholders (%s) are included to assist translators and then 5506 * removed before the array of strings reaches the filter. 5507 * 5508 * Please note: Ampersands and entities should be avoided here. 5509 * 5510 * @since 2.5.0 5511 * 5512 * @param array $delimiters An array of translated delimiters. 5513 */ 5514 $l = apply_filters( 5515 'wp_sprintf_l', 5516 array( 5517 /* translators: Used to join items in a list with more than 2 items. */ 5518 'between' => sprintf( __( '%1$s, %2$s' ), '', '' ), 5519 /* translators: Used to join last two items in a list with more than 2 times. */ 5520 'between_last_two' => sprintf( __( '%1$s, and %2$s' ), '', '' ), 5521 /* translators: Used to join items in a list with only 2 items. */ 5522 'between_only_two' => sprintf( __( '%1$s and %2$s' ), '', '' ), 5523 ) 5524 ); 5525 5526 $args = (array) $args; 5527 $result = array_shift( $args ); 5528 if ( count( $args ) === 1 ) { 5529 $result .= $l['between_only_two'] . array_shift( $args ); 5530 } 5531 5532 // Loop when more than two args. 5533 $i = count( $args ); 5534 while ( $i ) { 5535 $arg = array_shift( $args ); 5536 --$i; 5537 if ( 0 === $i ) { 5538 $result .= $l['between_last_two'] . $arg; 5539 } else { 5540 $result .= $l['between'] . $arg; 5541 } 5542 } 5543 5544 return $result . substr( $pattern, 2 ); 5545 } 5546 5547 /** 5548 * Safely extracts not more than the first $count characters from HTML string. 5549 * 5550 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT* 5551 * be counted as one character. For example & will be counted as 4, < as 5552 * 3, etc. 5553 * 5554 * @since 2.5.0 5555 * 5556 * @param string $str String to get the excerpt from. 5557 * @param int $count Maximum number of characters to take. 5558 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string. 5559 * @return string The excerpt. 5560 */ 5561 function wp_html_excerpt( $str, $count, $more = null ) { 5562 if ( null === $more ) { 5563 $more = ''; 5564 } 5565 5566 $str = wp_strip_all_tags( $str, true ); 5567 $excerpt = mb_substr( $str, 0, $count ); 5568 5569 // Remove part of an entity at the end. 5570 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt ); 5571 5572 if ( $str !== $excerpt ) { 5573 $excerpt = trim( $excerpt ) . $more; 5574 } 5575 5576 return $excerpt; 5577 } 5578 5579 /** 5580 * Adds a base URL to relative links in passed content. 5581 * 5582 * By default, this function supports the 'src' and 'href' attributes. 5583 * However, this can be modified via the `$attrs` parameter. 5584 * 5585 * @since 2.7.0 5586 * 5587 * @global string $_links_add_base 5588 * 5589 * @param string $content String to search for links in. 5590 * @param string $base The base URL to prefix to links. 5591 * @param string[] $attrs The attributes which should be processed. 5592 * @return string The processed content. 5593 */ 5594 function links_add_base_url( $content, $base, $attrs = array( 'src', 'href' ) ) { 5595 global $_links_add_base; 5596 $_links_add_base = $base; 5597 $attrs = implode( '|', (array) $attrs ); 5598 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content ); 5599 } 5600 5601 /** 5602 * Callback to add a base URL to relative links in passed content. 5603 * 5604 * @since 2.7.0 5605 * @access private 5606 * 5607 * @global string $_links_add_base 5608 * 5609 * @param string $m The matched link. 5610 * @return string The processed link. 5611 */ 5612 function _links_add_base( $m ) { 5613 global $_links_add_base; 5614 // 1 = attribute name 2 = quotation mark 3 = URL. 5615 return $m[1] . '=' . $m[2] . 5616 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols(), true ) ? 5617 $m[3] : 5618 WP_Http::make_absolute_url( $m[3], $_links_add_base ) 5619 ) 5620 . $m[2]; 5621 } 5622 5623 /** 5624 * Adds a target attribute to all links in passed content. 5625 * 5626 * By default, this function only applies to `<a>` tags. 5627 * However, this can be modified via the `$tags` parameter. 5628 * 5629 * *NOTE:* Any current target attribute will be stripped and replaced. 5630 * 5631 * @since 2.7.0 5632 * 5633 * @global string $_links_add_target 5634 * 5635 * @param string $content String to search for links in. 5636 * @param string $target The target to add to the links. 5637 * @param string[] $tags An array of tags to apply to. 5638 * @return string The processed content. 5639 */ 5640 function links_add_target( $content, $target = '_blank', $tags = array( 'a' ) ) { 5641 global $_links_add_target; 5642 $_links_add_target = $target; 5643 $tags = implode( '|', (array) $tags ); 5644 return preg_replace_callback( "!<($tags)((\s[^>]*)?)>!i", '_links_add_target', $content ); 5645 } 5646 5647 /** 5648 * Callback to add a target attribute to all links in passed content. 5649 * 5650 * @since 2.7.0 5651 * @access private 5652 * 5653 * @global string $_links_add_target 5654 * 5655 * @param string $m The matched link. 5656 * @return string The processed link. 5657 */ 5658 function _links_add_target( $m ) { 5659 global $_links_add_target; 5660 $tag = $m[1]; 5661 $link = preg_replace( '|( target=([\'"])(.*?)\2)|i', '', $m[2] ); 5662 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">'; 5663 } 5664 5665 /** 5666 * Normalizes EOL characters and strips duplicate whitespace. 5667 * 5668 * @since 2.7.0 5669 * 5670 * @param string $str The string to normalize. 5671 * @return string The normalized string. 5672 */ 5673 function normalize_whitespace( $str ) { 5674 $str = trim( $str ); 5675 $str = str_replace( "\r", "\n", $str ); 5676 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str ); 5677 return $str; 5678 } 5679 5680 /** 5681 * Properly strips all HTML tags including 'script' and 'style'. 5682 * 5683 * This differs from strip_tags() because it removes the contents of 5684 * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )` 5685 * will return 'something'. wp_strip_all_tags() will return an empty string. 5686 * 5687 * @since 2.9.0 5688 * 5689 * @param string $text String containing HTML tags 5690 * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars 5691 * @return string The processed string. 5692 */ 5693 function wp_strip_all_tags( $text, $remove_breaks = false ) { 5694 if ( is_null( $text ) ) { 5695 return ''; 5696 } 5697 5698 if ( ! is_scalar( $text ) ) { 5699 /* 5700 * To maintain consistency with pre-PHP 8 error levels, 5701 * wp_trigger_error() is used to trigger an E_USER_WARNING, 5702 * rather than _doing_it_wrong(), which triggers an E_USER_NOTICE. 5703 */ 5704 wp_trigger_error( 5705 '', 5706 sprintf( 5707 /* translators: 1: The function name, 2: The argument number, 3: The argument name, 4: The expected type, 5: The provided type. */ 5708 __( 'Warning: %1$s expects parameter %2$s (%3$s) to be a %4$s, %5$s given.' ), 5709 __FUNCTION__, 5710 '#1', 5711 '$text', 5712 'string', 5713 gettype( $text ) 5714 ), 5715 E_USER_WARNING 5716 ); 5717 5718 return ''; 5719 } 5720 5721 $text = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $text ); 5722 $text = strip_tags( $text ); 5723 5724 if ( $remove_breaks ) { 5725 $text = preg_replace( '/[\r\n\t ]+/', ' ', $text ); 5726 } 5727 5728 return trim( $text ); 5729 } 5730 5731 /** 5732 * Sanitizes a string from user input or from the database. 5733 * 5734 * - Checks for invalid UTF-8, 5735 * - Converts single `<` characters to entities 5736 * - Strips all tags 5737 * - Removes line breaks, tabs, and extra whitespace 5738 * - Strips percent-encoded characters 5739 * 5740 * @since 2.9.0 5741 * 5742 * @see sanitize_textarea_field() 5743 * @see wp_check_invalid_utf8() 5744 * @see wp_strip_all_tags() 5745 * 5746 * @param string $str String to sanitize. 5747 * @return string Sanitized string. 5748 */ 5749 function sanitize_text_field( $str ) { 5750 $filtered = _sanitize_text_fields( $str, false ); 5751 5752 /** 5753 * Filters a sanitized text field string. 5754 * 5755 * @since 2.9.0 5756 * 5757 * @param string $filtered The sanitized string. 5758 * @param string $str The string prior to being sanitized. 5759 */ 5760 return apply_filters( 'sanitize_text_field', $filtered, $str ); 5761 } 5762 5763 /** 5764 * Sanitizes a multiline string from user input or from the database. 5765 * 5766 * The function is like sanitize_text_field(), but preserves 5767 * new lines (\n) and other whitespace, which are legitimate 5768 * input in textarea elements. 5769 * 5770 * @see sanitize_text_field() 5771 * 5772 * @since 4.7.0 5773 * 5774 * @param string $str String to sanitize. 5775 * @return string Sanitized string. 5776 */ 5777 function sanitize_textarea_field( $str ) { 5778 $filtered = _sanitize_text_fields( $str, true ); 5779 5780 /** 5781 * Filters a sanitized textarea field string. 5782 * 5783 * @since 4.7.0 5784 * 5785 * @param string $filtered The sanitized string. 5786 * @param string $str The string prior to being sanitized. 5787 */ 5788 return apply_filters( 'sanitize_textarea_field', $filtered, $str ); 5789 } 5790 5791 /** 5792 * Internal helper function to sanitize a string from user input or from the database. 5793 * 5794 * @since 4.7.0 5795 * @access private 5796 * 5797 * @param string $str String to sanitize. 5798 * @param bool $keep_newlines Optional. Whether to keep newlines. Default: false. 5799 * @return string Sanitized string. 5800 */ 5801 function _sanitize_text_fields( $str, $keep_newlines = false ) { 5802 if ( is_object( $str ) || is_array( $str ) ) { 5803 return ''; 5804 } 5805 5806 $str = (string) $str; 5807 5808 $filtered = wp_check_invalid_utf8( $str ); 5809 5810 if ( str_contains( $filtered, '<' ) ) { 5811 $filtered = wp_pre_kses_less_than( $filtered ); 5812 // This will strip extra whitespace for us. 5813 $filtered = wp_strip_all_tags( $filtered, false ); 5814 5815 /* 5816 * Use HTML entities in a special case to make sure that 5817 * later newline stripping stages cannot lead to a functional tag. 5818 */ 5819 $filtered = str_replace( "<\n", "<\n", $filtered ); 5820 } 5821 5822 if ( ! $keep_newlines ) { 5823 $filtered = preg_replace( '/[\r\n\t ]+/', ' ', $filtered ); 5824 } 5825 $filtered = trim( $filtered ); 5826 5827 // Remove percent-encoded characters. 5828 $found = false; 5829 while ( preg_match( '/%[a-f0-9]{2}/i', $filtered, $match ) ) { 5830 $filtered = str_replace( $match[0], '', $filtered ); 5831 $found = true; 5832 } 5833 5834 if ( $found ) { 5835 // Strip out the whitespace that may now exist after removing percent-encoded characters. 5836 $filtered = trim( preg_replace( '/ +/', ' ', $filtered ) ); 5837 } 5838 5839 return $filtered; 5840 } 5841 5842 /** 5843 * i18n-friendly version of basename(). 5844 * 5845 * @since 3.1.0 5846 * 5847 * @param string $path A path. 5848 * @param string $suffix If the filename ends in suffix this will also be cut off. 5849 * @return string 5850 */ 5851 function wp_basename( $path, $suffix = '' ) { 5852 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) ); 5853 } 5854 5855 // phpcs:disable WordPress.WP.CapitalPDangit.MisspelledInComment,WordPress.WP.CapitalPDangit.MisspelledInText,WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid -- 8-) 5856 /** 5857 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence). 5858 * 5859 * Violating our coding standards for a good function name. 5860 * 5861 * @since 3.0.0 5862 * 5863 * @param string $text The text to be modified. 5864 * @return string The modified text. 5865 */ 5866 function capital_P_dangit( $text ) { 5867 // Simple replacement for titles. 5868 $current_filter = current_filter(); 5869 if ( 'the_title' === $current_filter || 'wp_title' === $current_filter ) { 5870 return str_replace( 'Wordpress', 'WordPress', $text ); 5871 } 5872 // Still here? Use the more judicious replacement. 5873 static $dblq = false; 5874 if ( false === $dblq ) { 5875 $dblq = _x( '“', 'opening curly double quote' ); 5876 } 5877 return str_replace( 5878 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ), 5879 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ), 5880 $text 5881 ); 5882 } 5883 // phpcs:enable 5884 5885 /** 5886 * Sanitizes a mime type 5887 * 5888 * @since 3.1.3 5889 * 5890 * @param string $mime_type Mime type. 5891 * @return string Sanitized mime type. 5892 */ 5893 function sanitize_mime_type( $mime_type ) { 5894 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type ); 5895 /** 5896 * Filters a mime type following sanitization. 5897 * 5898 * @since 3.1.3 5899 * 5900 * @param string $sani_mime_type The sanitized mime type. 5901 * @param string $mime_type The mime type prior to sanitization. 5902 */ 5903 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type ); 5904 } 5905 5906 /** 5907 * Sanitizes space or carriage return separated URLs that are used to send trackbacks. 5908 * 5909 * @since 3.4.0 5910 * 5911 * @param string $to_ping Space or carriage return separated URLs 5912 * @return string URLs starting with the http or https protocol, separated by a carriage return. 5913 */ 5914 function sanitize_trackback_urls( $to_ping ) { 5915 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY ); 5916 foreach ( $urls_to_ping as $k => $url ) { 5917 if ( ! preg_match( '#^https?://.#i', $url ) ) { 5918 unset( $urls_to_ping[ $k ] ); 5919 } 5920 } 5921 $urls_to_ping = array_map( 'sanitize_url', $urls_to_ping ); 5922 $urls_to_ping = implode( "\n", $urls_to_ping ); 5923 /** 5924 * Filters a list of trackback URLs following sanitization. 5925 * 5926 * The string returned here consists of a space or carriage return-delimited list 5927 * of trackback URLs. 5928 * 5929 * @since 3.4.0 5930 * 5931 * @param string $urls_to_ping Sanitized space or carriage return separated URLs. 5932 * @param string $to_ping Space or carriage return separated URLs before sanitization. 5933 */ 5934 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping ); 5935 } 5936 5937 /** 5938 * Adds slashes to a string or recursively adds slashes to strings within an array. 5939 * 5940 * This should be used when preparing data for core API that expects slashed data. 5941 * This should not be used to escape data going directly into an SQL query. 5942 * 5943 * @since 3.6.0 5944 * @since 5.5.0 Non-string values are left untouched. 5945 * 5946 * @param string|array $value String or array of data to slash. 5947 * @return string|array Slashed `$value`, in the same type as supplied. 5948 */ 5949 function wp_slash( $value ) { 5950 if ( is_array( $value ) ) { 5951 $value = array_map( 'wp_slash', $value ); 5952 } 5953 5954 if ( is_string( $value ) ) { 5955 return addslashes( $value ); 5956 } 5957 5958 return $value; 5959 } 5960 5961 /** 5962 * Removes slashes from a string or recursively removes slashes from strings within an array. 5963 * 5964 * This should be used to remove slashes from data passed to core API that 5965 * expects data to be unslashed. 5966 * 5967 * @since 3.6.0 5968 * 5969 * @param string|array $value String or array of data to unslash. 5970 * @return string|array Unslashed `$value`, in the same type as supplied. 5971 */ 5972 function wp_unslash( $value ) { 5973 return stripslashes_deep( $value ); 5974 } 5975 5976 /** 5977 * Extracts and returns the first URL from passed content. 5978 * 5979 * @since 3.6.0 5980 * 5981 * @param string $content A string which might contain an `A` element with a non-empty `href` attribute. 5982 * @return string|false Database-escaped URL via {@see esc_url()} if found, otherwise `false`. 5983 */ 5984 function get_url_in_content( $content ) { 5985 if ( empty( $content ) ) { 5986 return false; 5987 } 5988 5989 $processor = new WP_HTML_Tag_Processor( $content ); 5990 while ( $processor->next_tag( 'A' ) ) { 5991 $href = $processor->get_attribute( 'href' ); 5992 if ( is_string( $href ) && ! empty( $href ) ) { 5993 return sanitize_url( $href ); 5994 } 5995 } 5996 5997 return false; 5998 } 5999 6000 /** 6001 * Returns the regexp for common whitespace characters. 6002 * 6003 * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp. 6004 * This is designed to replace the PCRE \s sequence. In ticket #22692, that 6005 * sequence was found to be unreliable due to random inclusion of the A0 byte. 6006 * 6007 * @since 4.0.0 6008 * 6009 * @return string The spaces regexp. 6010 */ 6011 function wp_spaces_regexp() { 6012 static $spaces = ''; 6013 6014 if ( empty( $spaces ) ) { 6015 /** 6016 * Filters the regexp for common whitespace characters. 6017 * 6018 * This string is substituted for the \s sequence as needed in regular 6019 * expressions. For websites not written in English, different characters 6020 * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0 6021 * sequence may not be in use. 6022 * 6023 * @since 4.0.0 6024 * 6025 * @param string $spaces Regexp pattern for matching common whitespace characters. 6026 */ 6027 $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' ); 6028 } 6029 6030 return $spaces; 6031 } 6032 6033 /** 6034 * Enqueues the important emoji-related styles. 6035 * 6036 * @since 6.4.0 6037 */ 6038 function wp_enqueue_emoji_styles() { 6039 // Back-compat for plugins that disable functionality by unhooking this action. 6040 $action = is_admin() ? 'admin_print_styles' : 'wp_print_styles'; 6041 if ( ! has_action( $action, 'print_emoji_styles' ) ) { 6042 return; 6043 } 6044 remove_action( $action, 'print_emoji_styles' ); 6045 6046 $emoji_styles = ' 6047 img.wp-smiley, img.emoji { 6048 display: inline !important; 6049 border: none !important; 6050 box-shadow: none !important; 6051 height: 1em !important; 6052 width: 1em !important; 6053 margin: 0 0.07em !important; 6054 vertical-align: -0.1em !important; 6055 background: none !important; 6056 padding: 0 !important; 6057 }'; 6058 $handle = 'wp-emoji-styles'; 6059 wp_register_style( $handle, false ); 6060 wp_add_inline_style( $handle, $emoji_styles ); 6061 wp_enqueue_style( $handle ); 6062 } 6063 6064 /** 6065 * Prints the inline Emoji detection script if it is not already printed. 6066 * 6067 * @since 4.2.0 6068 */ 6069 function print_emoji_detection_script() { 6070 static $printed = false; 6071 6072 if ( $printed ) { 6073 return; 6074 } 6075 6076 $printed = true; 6077 6078 _print_emoji_detection_script(); 6079 } 6080 6081 /** 6082 * Prints inline Emoji detection script. 6083 * 6084 * @ignore 6085 * @since 4.6.0 6086 * @access private 6087 */ 6088 function _print_emoji_detection_script() { 6089 $settings = array( 6090 /** 6091 * Filters the URL where emoji png images are hosted. 6092 * 6093 * @since 4.2.0 6094 * 6095 * @param string $url The emoji base URL for png images. 6096 */ 6097 'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/16.0.1/72x72/' ), 6098 6099 /** 6100 * Filters the extension of the emoji png files. 6101 * 6102 * @since 4.2.0 6103 * 6104 * @param string $extension The emoji extension for png files. Default .png. 6105 */ 6106 'ext' => apply_filters( 'emoji_ext', '.png' ), 6107 6108 /** 6109 * Filters the URL where emoji SVG images are hosted. 6110 * 6111 * @since 4.6.0 6112 * 6113 * @param string $url The emoji base URL for svg images. 6114 */ 6115 'svgUrl' => apply_filters( 'emoji_svg_url', 'https://s.w.org/images/core/emoji/16.0.1/svg/' ), 6116 6117 /** 6118 * Filters the extension of the emoji SVG files. 6119 * 6120 * @since 4.6.0 6121 * 6122 * @param string $extension The emoji extension for svg files. Default .svg. 6123 */ 6124 'svgExt' => apply_filters( 'emoji_svg_ext', '.svg' ), 6125 ); 6126 6127 $version = 'ver=' . get_bloginfo( 'version' ); 6128 6129 if ( SCRIPT_DEBUG ) { 6130 $settings['source'] = array( 6131 /** This filter is documented in wp-includes/class-wp-scripts.php */ 6132 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ), 6133 /** This filter is documented in wp-includes/class-wp-scripts.php */ 6134 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ), 6135 ); 6136 } else { 6137 $settings['source'] = array( 6138 /** This filter is documented in wp-includes/class-wp-scripts.php */ 6139 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ), 6140 ); 6141 } 6142 6143 wp_print_inline_script_tag( 6144 sprintf( 'window._wpemojiSettings = %s;', wp_json_encode( $settings ) ) . "\n" . 6145 file_get_contents( ABSPATH . WPINC . '/js/wp-emoji-loader' . wp_scripts_get_suffix() . '.js' ) 6146 ); 6147 } 6148 6149 /** 6150 * Converts emoji characters to their equivalent HTML entity. 6151 * 6152 * This allows us to store emoji in a DB using the utf8 character set. 6153 * 6154 * @since 4.2.0 6155 * 6156 * @param string $content The content to encode. 6157 * @return string The encoded content. 6158 */ 6159 function wp_encode_emoji( $content ) { 6160 $emoji = _wp_emoji_list( 'partials' ); 6161 6162 foreach ( $emoji as $emojum ) { 6163 $emoji_char = html_entity_decode( $emojum ); 6164 if ( str_contains( $content, $emoji_char ) ) { 6165 $content = preg_replace( "/$emoji_char/", $emojum, $content ); 6166 } 6167 } 6168 6169 return $content; 6170 } 6171 6172 /** 6173 * Converts emoji to a static img element. 6174 * 6175 * @since 4.2.0 6176 * 6177 * @param string $text The content to encode. 6178 * @return string The encoded content. 6179 */ 6180 function wp_staticize_emoji( $text ) { 6181 if ( ! str_contains( $text, '&#x' ) ) { 6182 if ( ( function_exists( 'mb_check_encoding' ) && mb_check_encoding( $text, 'ASCII' ) ) || ! preg_match( '/[^\x00-\x7F]/', $text ) ) { 6183 // The text doesn't contain anything that might be emoji, so we can return early. 6184 return $text; 6185 } else { 6186 $encoded_text = wp_encode_emoji( $text ); 6187 if ( $encoded_text === $text ) { 6188 return $encoded_text; 6189 } 6190 6191 $text = $encoded_text; 6192 } 6193 } 6194 6195 $emoji = _wp_emoji_list( 'entities' ); 6196 6197 // Quickly narrow down the list of emoji that might be in the text and need replacing. 6198 $possible_emoji = array(); 6199 foreach ( $emoji as $emojum ) { 6200 if ( str_contains( $text, $emojum ) ) { 6201 $possible_emoji[ $emojum ] = html_entity_decode( $emojum ); 6202 } 6203 } 6204 6205 if ( ! $possible_emoji ) { 6206 return $text; 6207 } 6208 6209 /** This filter is documented in wp-includes/formatting.php */ 6210 $cdn_url = apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/16.0.1/72x72/' ); 6211 6212 /** This filter is documented in wp-includes/formatting.php */ 6213 $ext = apply_filters( 'emoji_ext', '.png' ); 6214 6215 $output = ''; 6216 /* 6217 * HTML loop taken from smiley function, which was taken from texturize function. 6218 * It'll never be consolidated. 6219 * 6220 * First, capture the tags as well as in between. 6221 */ 6222 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); 6223 $stop = count( $textarr ); 6224 6225 // Ignore processing of specific tags. 6226 $tags_to_ignore = 'code|pre|style|script|textarea'; 6227 $ignore_block_element = ''; 6228 6229 for ( $i = 0; $i < $stop; $i++ ) { 6230 $content = $textarr[ $i ]; 6231 6232 // If we're in an ignore block, wait until we find its closing tag. 6233 if ( '' === $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) { 6234 $ignore_block_element = $matches[1]; 6235 } 6236 6237 // If it's not a tag and not in ignore block. 6238 if ( '' === $ignore_block_element && strlen( $content ) > 0 && '<' !== $content[0] && str_contains( $content, '&#x' ) ) { 6239 foreach ( $possible_emoji as $emojum => $emoji_char ) { 6240 if ( ! str_contains( $content, $emojum ) ) { 6241 continue; 6242 } 6243 6244 $file = str_replace( ';&#x', '-', $emojum ); 6245 $file = str_replace( array( '&#x', ';' ), '', $file ); 6246 6247 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $file . $ext, $emoji_char ); 6248 6249 $content = str_replace( $emojum, $entity, $content ); 6250 } 6251 } 6252 6253 // Did we exit ignore block? 6254 if ( '' !== $ignore_block_element && '</' . $ignore_block_element . '>' === $content ) { 6255 $ignore_block_element = ''; 6256 } 6257 6258 $output .= $content; 6259 } 6260 6261 // Finally, remove any stray U+FE0F characters. 6262 $output = str_replace( '️', '', $output ); 6263 6264 return $output; 6265 } 6266 6267 /** 6268 * Converts emoji in emails into static images. 6269 * 6270 * @since 4.2.0 6271 * 6272 * @param array $mail The email data array. 6273 * @return array The email data array, with emoji in the message staticized. 6274 */ 6275 function wp_staticize_emoji_for_email( $mail ) { 6276 if ( ! isset( $mail['message'] ) ) { 6277 return $mail; 6278 } 6279 6280 /* 6281 * We can only transform the emoji into images if it's a `text/html` email. 6282 * To do that, here's a cut down version of the same process that happens 6283 * in wp_mail() - get the `Content-Type` from the headers, if there is one, 6284 * then pass it through the {@see 'wp_mail_content_type'} filter, in case 6285 * a plugin is handling changing the `Content-Type`. 6286 */ 6287 $headers = array(); 6288 if ( isset( $mail['headers'] ) ) { 6289 if ( is_array( $mail['headers'] ) ) { 6290 $headers = $mail['headers']; 6291 } else { 6292 $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) ); 6293 } 6294 } 6295 6296 foreach ( $headers as $header ) { 6297 if ( ! str_contains( $header, ':' ) ) { 6298 continue; 6299 } 6300 6301 // Explode them out. 6302 list( $name, $content ) = explode( ':', trim( $header ), 2 ); 6303 6304 // Cleanup crew. 6305 $name = trim( $name ); 6306 $content = trim( $content ); 6307 6308 if ( 'content-type' === strtolower( $name ) ) { 6309 if ( str_contains( $content, ';' ) ) { 6310 list( $type, $charset ) = explode( ';', $content ); 6311 $content_type = trim( $type ); 6312 } else { 6313 $content_type = trim( $content ); 6314 } 6315 break; 6316 } 6317 } 6318 6319 // Set Content-Type if we don't have a content-type from the input headers. 6320 if ( ! isset( $content_type ) ) { 6321 $content_type = 'text/plain'; 6322 } 6323 6324 /** This filter is documented in wp-includes/pluggable.php */ 6325 $content_type = apply_filters( 'wp_mail_content_type', $content_type ); 6326 6327 if ( 'text/html' === $content_type ) { 6328 $mail['message'] = wp_staticize_emoji( $mail['message'] ); 6329 } 6330 6331 return $mail; 6332 } 6333 6334 /** 6335 * Returns arrays of emoji data. 6336 * 6337 * These arrays are automatically built from the regex in twemoji.js - if they need to be updated, 6338 * you should update the regex there, then run the `npm run grunt precommit:emoji` job. 6339 * 6340 * @since 4.9.0 6341 * @access private 6342 * 6343 * @param string $type Optional. Which array type to return. Accepts 'partials' or 'entities', default 'entities'. 6344 * @return array An array to match all emoji that WordPress recognises. 6345 */ 6346 function _wp_emoji_list( $type = 'entities' ) { 6347 // Do not remove the START/END comments - they're used to find where to insert the arrays. 6348 6349 // START: emoji arrays 6350 $entities = array( '👨🏻‍❤️‍💋‍👨🏻', '👨🏻‍❤️‍💋‍👨🏼', '👨🏻‍❤️‍💋‍👨🏽', '👨🏻‍❤️‍💋‍👨🏾', '👨🏻‍❤️‍💋‍👨🏿', '👨🏼‍❤️‍💋‍👨🏻', '👨🏼‍❤️‍💋‍👨🏼', '👨🏼‍❤️‍💋‍👨🏽', '👨🏼‍❤️‍💋‍👨🏾', '👨🏼‍❤️‍💋‍👨🏿', '👨🏽‍❤️‍💋‍👨🏻', '👨🏽‍❤️‍💋‍👨🏼', '👨🏽‍❤️‍💋‍👨🏽', '👨🏽‍❤️‍💋‍👨🏾', '👨🏽‍❤️‍💋‍👨🏿', '👨🏾‍❤️‍💋‍👨🏻', '👨🏾‍❤️‍💋‍👨🏼', '👨🏾‍❤️‍💋‍👨🏽', '👨🏾‍❤️‍💋‍👨🏾', '👨🏾‍❤️‍💋‍👨🏿', '👨🏿‍❤️‍💋‍👨🏻', '👨🏿‍❤️‍💋‍👨🏼', '👨🏿‍❤️‍💋‍👨🏽', '👨🏿‍❤️‍💋‍👨🏾', '👨🏿‍❤️‍💋‍👨🏿', '👩🏻‍❤️‍💋‍👨🏻', '👩🏻‍❤️‍💋‍👨🏼', '👩🏻‍❤️‍💋‍👨🏽', '👩🏻‍❤️‍💋‍👨🏾', '👩🏻‍❤️‍💋‍👨🏿', '👩🏻‍❤️‍💋‍👩🏻', '👩🏻‍❤️‍💋‍👩🏼', '👩🏻‍❤️‍💋‍👩🏽', '👩🏻‍❤️‍💋‍👩🏾', '👩🏻‍❤️‍💋‍👩🏿', '👩🏼‍❤️‍💋‍👨🏻', '👩🏼‍❤️‍💋‍👨🏼', '👩🏼‍❤️‍💋‍👨🏽', '👩🏼‍❤️‍💋‍👨🏾', '👩🏼‍❤️‍💋‍👨🏿', '👩🏼‍❤️‍💋‍👩🏻', '👩🏼‍❤️‍💋‍👩🏼', '👩🏼‍❤️‍💋‍👩🏽', '👩🏼‍❤️‍💋‍👩🏾', '👩🏼‍❤️‍💋‍👩🏿', '👩🏽‍❤️‍💋‍👨🏻', '👩🏽‍❤️‍💋‍👨🏼', '👩🏽‍❤️‍💋‍👨🏽', '👩🏽‍❤️‍💋‍👨🏾', '👩🏽‍❤️‍💋‍👨🏿', '👩🏽‍❤️‍💋‍👩🏻', '👩🏽‍❤️‍💋‍👩🏼', '👩🏽‍❤️‍💋‍👩🏽', '👩🏽‍❤️‍💋‍👩🏾', '👩🏽‍❤️‍💋‍👩🏿', '👩🏾‍❤️‍💋‍👨🏻', '👩🏾‍❤️‍💋‍👨🏼', '👩🏾‍❤️‍💋‍👨🏽', '👩🏾‍❤️‍💋‍👨🏾', '👩🏾‍❤️‍💋‍👨🏿', '👩🏾‍❤️‍💋‍👩🏻', '👩🏾‍❤️‍💋‍👩🏼', '👩🏾‍❤️‍💋‍👩🏽', '👩🏾‍❤️‍💋‍👩🏾', '👩🏾‍❤️‍💋‍👩🏿', '👩🏿‍❤️‍💋‍👨🏻', '👩🏿‍❤️‍💋‍👨🏼', '👩🏿‍❤️‍💋‍👨🏽', '👩🏿‍❤️‍💋‍👨🏾', '👩🏿‍❤️‍💋‍👨🏿', '👩🏿‍❤️‍💋‍👩🏻', '👩🏿‍❤️‍💋‍👩🏼', '👩🏿‍❤️‍💋‍👩🏽', '👩🏿‍❤️‍💋‍👩🏾', '👩🏿‍❤️‍💋‍👩🏿', '🧑🏻‍❤️‍💋‍🧑🏼', '🧑🏻‍❤️‍💋‍🧑🏽', '🧑🏻‍❤️‍💋‍🧑🏾', '🧑🏻‍❤️‍💋‍🧑🏿', '🧑🏼‍❤️‍💋‍🧑🏻', '🧑🏼‍❤️‍💋‍🧑🏽', '🧑🏼‍❤️‍💋‍🧑🏾', '🧑🏼‍❤️‍💋‍🧑🏿', '🧑🏽‍❤️‍💋‍🧑🏻', '🧑🏽‍❤️‍💋‍🧑🏼', '🧑🏽‍❤️‍💋‍🧑🏾', '🧑🏽‍❤️‍💋‍🧑🏿', '🧑🏾‍❤️‍💋‍🧑🏻', '🧑🏾‍❤️‍💋‍🧑🏼', '🧑🏾‍❤️‍💋‍🧑🏽', '🧑🏾‍❤️‍💋‍🧑🏿', '🧑🏿‍❤️‍💋‍🧑🏻', '🧑🏿‍❤️‍💋‍🧑🏼', '🧑🏿‍❤️‍💋‍🧑🏽', '🧑🏿‍❤️‍💋‍🧑🏾', '👨🏻‍❤️‍👨🏻', '👨🏻‍❤️‍👨🏼', '👨🏻‍❤️‍👨🏽', '👨🏻‍❤️‍👨🏾', '👨🏻‍❤️‍👨🏿', '👨🏼‍❤️‍👨🏻', '👨🏼‍❤️‍👨🏼', '👨🏼‍❤️‍👨🏽', '👨🏼‍❤️‍👨🏾', '👨🏼‍❤️‍👨🏿', '👨🏽‍❤️‍👨🏻', '👨🏽‍❤️‍👨🏼', '👨🏽‍❤️‍👨🏽', '👨🏽‍❤️‍👨🏾', '👨🏽‍❤️‍👨🏿', '👨🏾‍❤️‍👨🏻', '👨🏾‍❤️‍👨🏼', '👨🏾‍❤️‍👨🏽', '👨🏾‍❤️‍👨🏾', '👨🏾‍❤️‍👨🏿', '👨🏿‍❤️‍👨🏻', '👨🏿‍❤️‍👨🏼', '👨🏿‍❤️‍👨🏽', '👨🏿‍❤️‍👨🏾', '👨🏿‍❤️‍👨🏿', '👩🏻‍❤️‍👨🏻', '👩🏻‍❤️‍👨🏼', '👩🏻‍❤️‍👨🏽', '👩🏻‍❤️‍👨🏾', '👩🏻‍❤️‍👨🏿', '👩🏻‍❤️‍👩🏻', '👩🏻‍❤️‍👩🏼', '👩🏻‍❤️‍👩🏽', '👩🏻‍❤️‍👩🏾', '👩🏻‍❤️‍👩🏿', '👩🏼‍❤️‍👨🏻', '👩🏼‍❤️‍👨🏼', '👩🏼‍❤️‍👨🏽', '👩🏼‍❤️‍👨🏾', '👩🏼‍❤️‍👨🏿', '👩🏼‍❤️‍👩🏻', '👩🏼‍❤️‍👩🏼', '👩🏼‍❤️‍👩🏽', '👩🏼‍❤️‍👩🏾', '👩🏼‍❤️‍👩🏿', '👩🏽‍❤️‍👨🏻', '👩🏽‍❤️‍👨🏼', '👩🏽‍❤️‍👨🏽', '👩🏽‍❤️‍👨🏾', '👩🏽‍❤️‍👨🏿', '👩🏽‍❤️‍👩🏻', '👩🏽‍❤️‍👩🏼', '👩🏽‍❤️‍👩🏽', '👩🏽‍❤️‍👩🏾', '👩🏽‍❤️‍👩🏿', '👩🏾‍❤️‍👨🏻', '👩🏾‍❤️‍👨🏼', '👩🏾‍❤️‍👨🏽', '👩🏾‍❤️‍👨🏾', '👩🏾‍❤️‍👨🏿', '👩🏾‍❤️‍👩🏻', '👩🏾‍❤️‍👩🏼', '👩🏾‍❤️‍👩🏽', '👩🏾‍❤️‍👩🏾', '👩🏾‍❤️‍👩🏿', '👩🏿‍❤️‍👨🏻', '👩🏿‍❤️‍👨🏼', '👩🏿‍❤️‍👨🏽', '👩🏿‍❤️‍👨🏾', '👩🏿‍❤️‍👨🏿', '👩🏿‍❤️‍👩🏻', '👩🏿‍❤️‍👩🏼', '👩🏿‍❤️‍👩🏽', '👩🏿‍❤️‍👩🏾', '👩🏿‍❤️‍👩🏿', '🧑🏻‍❤️‍🧑🏼', '🧑🏻‍❤️‍🧑🏽', '🧑🏻‍❤️‍🧑🏾', '🧑🏻‍❤️‍🧑🏿', '🧑🏼‍❤️‍🧑🏻', '🧑🏼‍❤️‍🧑🏽', '🧑🏼‍❤️‍🧑🏾', '🧑🏼‍❤️‍🧑🏿', '🧑🏽‍❤️‍🧑🏻', '🧑🏽‍❤️‍🧑🏼', '🧑🏽‍❤️‍🧑🏾', '🧑🏽‍❤️‍🧑🏿', '🧑🏾‍❤️‍🧑🏻', '🧑🏾‍❤️‍🧑🏼', '🧑🏾‍❤️‍🧑🏽', '🧑🏾‍❤️‍🧑🏿', '🧑🏿‍❤️‍🧑🏻', '🧑🏿‍❤️‍🧑🏼', '🧑🏿‍❤️‍🧑🏽', '🧑🏿‍❤️‍🧑🏾', '👨‍❤️‍💋‍👨', '👩‍❤️‍💋‍👨', '👩‍❤️‍💋‍👩', '🏃🏻‍♀️‍➡️', '🏃🏻‍♂️‍➡️', '🏃🏼‍♀️‍➡️', '🏃🏼‍♂️‍➡️', '🏃🏽‍♀️‍➡️', '🏃🏽‍♂️‍➡️', '🏃🏾‍♀️‍➡️', '🏃🏾‍♂️‍➡️', '🏃🏿‍♀️‍➡️', '🏃🏿‍♂️‍➡️', '🚶🏻‍♀️‍➡️', '🚶🏻‍♂️‍➡️', '🚶🏼‍♀️‍➡️', '🚶🏼‍♂️‍➡️', '🚶🏽‍♀️‍➡️', '🚶🏽‍♂️‍➡️', '🚶🏾‍♀️‍➡️', '🚶🏾‍♂️‍➡️', '🚶🏿‍♀️‍➡️', '🚶🏿‍♂️‍➡️', '🧎🏻‍♀️‍➡️', '🧎🏻‍♂️‍➡️', '🧎🏼‍♀️‍➡️', '🧎🏼‍♂️‍➡️', '🧎🏽‍♀️‍➡️', '🧎🏽‍♂️‍➡️', '🧎🏾‍♀️‍➡️', '🧎🏾‍♂️‍➡️', '🧎🏿‍♀️‍➡️', '🧎🏿‍♂️‍➡️', '🏴󠁧󠁢󠁥󠁮󠁧󠁿', '🏴󠁧󠁢󠁳󠁣󠁴󠁿', '🏴󠁧󠁢󠁷󠁬󠁳󠁿', '👨🏻‍🤝‍👨🏼', '👨🏻‍🤝‍👨🏽', '👨🏻‍🤝‍👨🏾', '👨🏻‍🤝‍👨🏿', '👨🏼‍🤝‍👨🏻', '👨🏼‍🤝‍👨🏽', '👨🏼‍🤝‍👨🏾', '👨🏼‍🤝‍👨🏿', '👨🏽‍🤝‍👨🏻', '👨🏽‍🤝‍👨🏼', '👨🏽‍🤝‍👨🏾', '👨🏽‍🤝‍👨🏿', '👨🏾‍🤝‍👨🏻', '👨🏾‍🤝‍👨🏼', '👨🏾‍🤝‍👨🏽', '👨🏾‍🤝‍👨🏿', '👨🏿‍🤝‍👨🏻', '👨🏿‍🤝‍👨🏼', '👨🏿‍🤝‍👨🏽', '👨🏿‍🤝‍👨🏾', '👩🏻‍🤝‍👨🏼', '👩🏻‍🤝‍👨🏽', '👩🏻‍🤝‍👨🏾', '👩🏻‍🤝‍👨🏿', '👩🏻‍🤝‍👩🏼', '👩🏻‍🤝‍👩🏽', '👩🏻‍🤝‍👩🏾', '👩🏻‍🤝‍👩🏿', '👩🏼‍🤝‍👨🏻', '👩🏼‍🤝‍👨🏽', '👩🏼‍🤝‍👨🏾', '👩🏼‍🤝‍👨🏿', '👩🏼‍🤝‍👩🏻', '👩🏼‍🤝‍👩🏽', '👩🏼‍🤝‍👩🏾', '👩🏼‍🤝‍👩🏿', '👩🏽‍🤝‍👨🏻', '👩🏽‍🤝‍👨🏼', '👩🏽‍🤝‍👨🏾', '👩🏽‍🤝‍👨🏿', '👩🏽‍🤝‍👩🏻', '👩🏽‍🤝‍👩🏼', '👩🏽‍🤝‍👩🏾', '👩🏽‍🤝‍👩🏿', '👩🏾‍🤝‍👨🏻', '👩🏾‍🤝‍👨🏼', '👩🏾‍🤝‍👨🏽', '👩🏾‍🤝‍👨🏿', '👩🏾‍🤝‍👩🏻', '👩🏾‍🤝‍👩🏼', '👩🏾‍🤝‍👩🏽', '👩🏾‍🤝‍👩🏿', '👩🏿‍🤝‍👨🏻', '👩🏿‍🤝‍👨🏼', '👩🏿‍🤝‍👨🏽', '👩🏿‍🤝‍👨🏾', '👩🏿‍🤝‍👩🏻', '👩🏿‍🤝‍👩🏼', '👩🏿‍🤝‍👩🏽', '👩🏿‍🤝‍👩🏾', '🧑🏻‍🤝‍🧑🏻', '🧑🏻‍🤝‍🧑🏼', '🧑🏻‍🤝‍🧑🏽', '🧑🏻‍🤝‍🧑🏾', '🧑🏻‍🤝‍🧑🏿', '🧑🏼‍🤝‍🧑🏻', '🧑🏼‍🤝‍🧑🏼', '🧑🏼‍🤝‍🧑🏽', '🧑🏼‍🤝‍🧑🏾', '🧑🏼‍🤝‍🧑🏿', '🧑🏽‍🤝‍🧑🏻', '🧑🏽‍🤝‍🧑🏼', '🧑🏽‍🤝‍🧑🏽', '🧑🏽‍🤝‍🧑🏾', '🧑🏽‍🤝‍🧑🏿', '🧑🏾‍🤝‍🧑🏻', '🧑🏾‍🤝‍🧑🏼', '🧑🏾‍🤝‍🧑🏽', '🧑🏾‍🤝‍🧑🏾', '🧑🏾‍🤝‍🧑🏿', '🧑🏿‍🤝‍🧑🏻', '🧑🏿‍🤝‍🧑🏼', '🧑🏿‍🤝‍🧑🏽', '🧑🏿‍🤝‍🧑🏾', '🧑🏿‍🤝‍🧑🏿', '👨‍👨‍👦‍👦', '👨‍👨‍👧‍👦', '👨‍👨‍👧‍👧', '👨‍👩‍👦‍👦', '👨‍👩‍👧‍👦', '👨‍👩‍👧‍👧', '👩‍👩‍👦‍👦', '👩‍👩‍👧‍👦', '👩‍👩‍👧‍👧', '🧑‍🧑‍🧒‍🧒', '👨🏻‍🦯‍➡️', '👨🏻‍🦼‍➡️', '👨🏻‍🦽‍➡️', '👨🏼‍🦯‍➡️', '👨🏼‍🦼‍➡️', '👨🏼‍🦽‍➡️', '👨🏽‍🦯‍➡️', '👨🏽‍🦼‍➡️', '👨🏽‍🦽‍➡️', '👨🏾‍🦯‍➡️', '👨🏾‍🦼‍➡️', '👨🏾‍🦽‍➡️', '👨🏿‍🦯‍➡️', '👨🏿‍🦼‍➡️', '👨🏿‍🦽‍➡️', '👩🏻‍🦯‍➡️', '👩🏻‍🦼‍➡️', '👩🏻‍🦽‍➡️', '👩🏼‍🦯‍➡️', '👩🏼‍🦼‍➡️', '👩🏼‍🦽‍➡️', '👩🏽‍🦯‍➡️', '👩🏽‍🦼‍➡️', '👩🏽‍🦽‍➡️', '👩🏾‍🦯‍➡️', '👩🏾‍🦼‍➡️', '👩🏾‍🦽‍➡️', '👩🏿‍🦯‍➡️', '👩🏿‍🦼‍➡️', '👩🏿‍🦽‍➡️', '🧑🏻‍🦯‍➡️', '🧑🏻‍🦼‍➡️', '🧑🏻‍🦽‍➡️', '🧑🏼‍🦯‍➡️', '🧑🏼‍🦼‍➡️', '🧑🏼‍🦽‍➡️', '🧑🏽‍🦯‍➡️', '🧑🏽‍🦼‍➡️', '🧑🏽‍🦽‍➡️', '🧑🏾‍🦯‍➡️', '🧑🏾‍🦼‍➡️', '🧑🏾‍🦽‍➡️', '🧑🏿‍🦯‍➡️', '🧑🏿‍🦼‍➡️', '🧑🏿‍🦽‍➡️', '🏃‍♀️‍➡️', '🏃‍♂️‍➡️', '🚶‍♀️‍➡️', '🚶‍♂️‍➡️', '🧎‍♀️‍➡️', '🧎‍♂️‍➡️', '👨‍🦯‍➡️', '👨‍🦼‍➡️', '👨‍🦽‍➡️', '👨‍❤️‍👨', '👩‍🦯‍➡️', '👩‍🦼‍➡️', '👩‍🦽‍➡️', '👩‍❤️‍👨', '👩‍❤️‍👩', '🧑‍🦯‍➡️', '🧑‍🦼‍➡️', '🧑‍🦽‍➡️', '🫱🏻‍🫲🏼', '🫱🏻‍🫲🏽', '🫱🏻‍🫲🏾', '🫱🏻‍🫲🏿', '🫱🏼‍🫲🏻', '🫱🏼‍🫲🏽', '🫱🏼‍🫲🏾', '🫱🏼‍🫲🏿', '🫱🏽‍🫲🏻', '🫱🏽‍🫲🏼', '🫱🏽‍🫲🏾', '🫱🏽‍🫲🏿', '🫱🏾‍🫲🏻', '🫱🏾‍🫲🏼', '🫱🏾‍🫲🏽', '🫱🏾‍🫲🏿', '🫱🏿‍🫲🏻', '🫱🏿‍🫲🏼', '🫱🏿‍🫲🏽', '🫱🏿‍🫲🏾', '👨‍👦‍👦', '👨‍👧‍👦', '👨‍👧‍👧', '👨‍👨‍👦', '👨‍👨‍👧', '👨‍👩‍👦', '👨‍👩‍👧', '👩‍👦‍👦', '👩‍👧‍👦', '👩‍👧‍👧', '👩‍👩‍👦', '👩‍👩‍👧', '🧑‍🤝‍🧑', '🧑‍🧑‍🧒', '🧑‍🧒‍🧒', '🏃🏻‍♀️', '🏃🏻‍♂️', '🏃🏻‍➡️', '🏃🏼‍♀️', '🏃🏼‍♂️', '🏃🏼‍➡️', '🏃🏽‍♀️', '🏃🏽‍♂️', '🏃🏽‍➡️', '🏃🏾‍♀️', '🏃🏾‍♂️', '🏃🏾‍➡️', '🏃🏿‍♀️', '🏃🏿‍♂️', '🏃🏿‍➡️', '🏄🏻‍♀️', '🏄🏻‍♂️', '🏄🏼‍♀️', '🏄🏼‍♂️', '🏄🏽‍♀️', '🏄🏽‍♂️', '🏄🏾‍♀️', '🏄🏾‍♂️', '🏄🏿‍♀️', '🏄🏿‍♂️', '🏊🏻‍♀️', '🏊🏻‍♂️', '🏊🏼‍♀️', '🏊🏼‍♂️', '🏊🏽‍♀️', '🏊🏽‍♂️', '🏊🏾‍♀️', '🏊🏾‍♂️', '🏊🏿‍♀️', '🏊🏿‍♂️', '🏋🏻‍♀️', '🏋🏻‍♂️', '🏋🏼‍♀️', '🏋🏼‍♂️', '🏋🏽‍♀️', '🏋🏽‍♂️', '🏋🏾‍♀️', '🏋🏾‍♂️', '🏋🏿‍♀️', '🏋🏿‍♂️', '🏌🏻‍♀️', '🏌🏻‍♂️', '🏌🏼‍♀️', '🏌🏼‍♂️', '🏌🏽‍♀️', '🏌🏽‍♂️', '🏌🏾‍♀️', '🏌🏾‍♂️', '🏌🏿‍♀️', '🏌🏿‍♂️', '👨🏻‍⚕️', '👨🏻‍⚖️', '👨🏻‍✈️', '👨🏼‍⚕️', '👨🏼‍⚖️', '👨🏼‍✈️', '👨🏽‍⚕️', '👨🏽‍⚖️', '👨🏽‍✈️', '👨🏾‍⚕️', '👨🏾‍⚖️', '👨🏾‍✈️', '👨🏿‍⚕️', '👨🏿‍⚖️', '👨🏿‍✈️', '👩🏻‍⚕️', '👩🏻‍⚖️', '👩🏻‍✈️', '👩🏼‍⚕️', '👩🏼‍⚖️', '👩🏼‍✈️', '👩🏽‍⚕️', '👩🏽‍⚖️', '👩🏽‍✈️', '👩🏾‍⚕️', '👩🏾‍⚖️', '👩🏾‍✈️', '👩🏿‍⚕️', '👩🏿‍⚖️', '👩🏿‍✈️', '👮🏻‍♀️', '👮🏻‍♂️', '👮🏼‍♀️', '👮🏼‍♂️', '👮🏽‍♀️', '👮🏽‍♂️', '👮🏾‍♀️', '👮🏾‍♂️', '👮🏿‍♀️', '👮🏿‍♂️', '👰🏻‍♀️', '👰🏻‍♂️', '👰🏼‍♀️', '👰🏼‍♂️', '👰🏽‍♀️', '👰🏽‍♂️', '👰🏾‍♀️', '👰🏾‍♂️', '👰🏿‍♀️', '👰🏿‍♂️', '👱🏻‍♀️', '👱🏻‍♂️', '👱🏼‍♀️', '👱🏼‍♂️', '👱🏽‍♀️', '👱🏽‍♂️', '👱🏾‍♀️', '👱🏾‍♂️', '👱🏿‍♀️', '👱🏿‍♂️', '👳🏻‍♀️', '👳🏻‍♂️', '👳🏼‍♀️', '👳🏼‍♂️', '👳🏽‍♀️', '👳🏽‍♂️', '👳🏾‍♀️', '👳🏾‍♂️', '👳🏿‍♀️', '👳🏿‍♂️', '👷🏻‍♀️', '👷🏻‍♂️', '👷🏼‍♀️', '👷🏼‍♂️', '👷🏽‍♀️', '👷🏽‍♂️', '👷🏾‍♀️', '👷🏾‍♂️', '👷🏿‍♀️', '👷🏿‍♂️', '💁🏻‍♀️', '💁🏻‍♂️', '💁🏼‍♀️', '💁🏼‍♂️', '💁🏽‍♀️', '💁🏽‍♂️', '💁🏾‍♀️', '💁🏾‍♂️', '💁🏿‍♀️', '💁🏿‍♂️', '💂🏻‍♀️', '💂🏻‍♂️', '💂🏼‍♀️', '💂🏼‍♂️', '💂🏽‍♀️', '💂🏽‍♂️', '💂🏾‍♀️', '💂🏾‍♂️', '💂🏿‍♀️', '💂🏿‍♂️', '💆🏻‍♀️', '💆🏻‍♂️', '💆🏼‍♀️', '💆🏼‍♂️', '💆🏽‍♀️', '💆🏽‍♂️', '💆🏾‍♀️', '💆🏾‍♂️', '💆🏿‍♀️', '💆🏿‍♂️', '💇🏻‍♀️', '💇🏻‍♂️', '💇🏼‍♀️', '💇🏼‍♂️', '💇🏽‍♀️', '💇🏽‍♂️', '💇🏾‍♀️', '💇🏾‍♂️', '💇🏿‍♀️', '💇🏿‍♂️', '🕴🏻‍♀️', '🕴🏻‍♂️', '🕴🏼‍♀️', '🕴🏼‍♂️', '🕴🏽‍♀️', '🕴🏽‍♂️', '🕴🏾‍♀️', '🕴🏾‍♂️', '🕴🏿‍♀️', '🕴🏿‍♂️', '🕵🏻‍♀️', '🕵🏻‍♂️', '🕵🏼‍♀️', '🕵🏼‍♂️', '🕵🏽‍♀️', '🕵🏽‍♂️', '🕵🏾‍♀️', '🕵🏾‍♂️', '🕵🏿‍♀️', '🕵🏿‍♂️', '🙅🏻‍♀️', '🙅🏻‍♂️', '🙅🏼‍♀️', '🙅🏼‍♂️', '🙅🏽‍♀️', '🙅🏽‍♂️', '🙅🏾‍♀️', '🙅🏾‍♂️', '🙅🏿‍♀️', '🙅🏿‍♂️', '🙆🏻‍♀️', '🙆🏻‍♂️', '🙆🏼‍♀️', '🙆🏼‍♂️', '🙆🏽‍♀️', '🙆🏽‍♂️', '🙆🏾‍♀️', '🙆🏾‍♂️', '🙆🏿‍♀️', '🙆🏿‍♂️', '🙇🏻‍♀️', '🙇🏻‍♂️', '🙇🏼‍♀️', '🙇🏼‍♂️', '🙇🏽‍♀️', '🙇🏽‍♂️', '🙇🏾‍♀️', '🙇🏾‍♂️', '🙇🏿‍♀️', '🙇🏿‍♂️', '🙋🏻‍♀️', '🙋🏻‍♂️', '🙋🏼‍♀️', '🙋🏼‍♂️', '🙋🏽‍♀️', '🙋🏽‍♂️', '🙋🏾‍♀️', '🙋🏾‍♂️', '🙋🏿‍♀️', '🙋🏿‍♂️', '🙍🏻‍♀️', '🙍🏻‍♂️', '🙍🏼‍♀️', '🙍🏼‍♂️', '🙍🏽‍♀️', '🙍🏽‍♂️', '🙍🏾‍♀️', '🙍🏾‍♂️', '🙍🏿‍♀️', '🙍🏿‍♂️', '🙎🏻‍♀️', '🙎🏻‍♂️', '🙎🏼‍♀️', '🙎🏼‍♂️', '🙎🏽‍♀️', '🙎🏽‍♂️', '🙎🏾‍♀️', '🙎🏾‍♂️', '🙎🏿‍♀️', '🙎🏿‍♂️', '🚣🏻‍♀️', '🚣🏻‍♂️', '🚣🏼‍♀️', '🚣🏼‍♂️', '🚣🏽‍♀️', '🚣🏽‍♂️', '🚣🏾‍♀️', '🚣🏾‍♂️', '🚣🏿‍♀️', '🚣🏿‍♂️', '🚴🏻‍♀️', '🚴🏻‍♂️', '🚴🏼‍♀️', '🚴🏼‍♂️', '🚴🏽‍♀️', '🚴🏽‍♂️', '🚴🏾‍♀️', '🚴🏾‍♂️', '🚴🏿‍♀️', '🚴🏿‍♂️', '🚵🏻‍♀️', '🚵🏻‍♂️', '🚵🏼‍♀️', '🚵🏼‍♂️', '🚵🏽‍♀️', '🚵🏽‍♂️', '🚵🏾‍♀️', '🚵🏾‍♂️', '🚵🏿‍♀️', '🚵🏿‍♂️', '🚶🏻‍♀️', '🚶🏻‍♂️', '🚶🏻‍➡️', '🚶🏼‍♀️', '🚶🏼‍♂️', '🚶🏼‍➡️', '🚶🏽‍♀️', '🚶🏽‍♂️', '🚶🏽‍➡️', '🚶🏾‍♀️', '🚶🏾‍♂️', '🚶🏾‍➡️', '🚶🏿‍♀️', '🚶🏿‍♂️', '🚶🏿‍➡️', '🤦🏻‍♀️', '🤦🏻‍♂️', '🤦🏼‍♀️', '🤦🏼‍♂️', '🤦🏽‍♀️', '🤦🏽‍♂️', '🤦🏾‍♀️', '🤦🏾‍♂️', '🤦🏿‍♀️', '🤦🏿‍♂️', '🤵🏻‍♀️', '🤵🏻‍♂️', '🤵🏼‍♀️', '🤵🏼‍♂️', '🤵🏽‍♀️', '🤵🏽‍♂️', '🤵🏾‍♀️', '🤵🏾‍♂️', '🤵🏿‍♀️', '🤵🏿‍♂️', '🤷🏻‍♀️', '🤷🏻‍♂️', '🤷🏼‍♀️', '🤷🏼‍♂️', '🤷🏽‍♀️', '🤷🏽‍♂️', '🤷🏾‍♀️', '🤷🏾‍♂️', '🤷🏿‍♀️', '🤷🏿‍♂️', '🤸🏻‍♀️', '🤸🏻‍♂️', '🤸🏼‍♀️', '🤸🏼‍♂️', '🤸🏽‍♀️', '🤸🏽‍♂️', '🤸🏾‍♀️', '🤸🏾‍♂️', '🤸🏿‍♀️', '🤸🏿‍♂️', '🤹🏻‍♀️', '🤹🏻‍♂️', '🤹🏼‍♀️', '🤹🏼‍♂️', '🤹🏽‍♀️', '🤹🏽‍♂️', '🤹🏾‍♀️', '🤹🏾‍♂️', '🤹🏿‍♀️', '🤹🏿‍♂️', '🤽🏻‍♀️', '🤽🏻‍♂️', '🤽🏼‍♀️', '🤽🏼‍♂️', '🤽🏽‍♀️', '🤽🏽‍♂️', '🤽🏾‍♀️', '🤽🏾‍♂️', '🤽🏿‍♀️', '🤽🏿‍♂️', '🤾🏻‍♀️', '🤾🏻‍♂️', '🤾🏼‍♀️', '🤾🏼‍♂️', '🤾🏽‍♀️', '🤾🏽‍♂️', '🤾🏾‍♀️', '🤾🏾‍♂️', '🤾🏿‍♀️', '🤾🏿‍♂️', '🦸🏻‍♀️', '🦸🏻‍♂️', '🦸🏼‍♀️', '🦸🏼‍♂️', '🦸🏽‍♀️', '🦸🏽‍♂️', '🦸🏾‍♀️', '🦸🏾‍♂️', '🦸🏿‍♀️', '🦸🏿‍♂️', '🦹🏻‍♀️', '🦹🏻‍♂️', '🦹🏼‍♀️', '🦹🏼‍♂️', '🦹🏽‍♀️', '🦹🏽‍♂️', '🦹🏾‍♀️', '🦹🏾‍♂️', '🦹🏿‍♀️', '🦹🏿‍♂️', '🧍🏻‍♀️', '🧍🏻‍♂️', '🧍🏼‍♀️', '🧍🏼‍♂️', '🧍🏽‍♀️', '🧍🏽‍♂️', '🧍🏾‍♀️', '🧍🏾‍♂️', '🧍🏿‍♀️', '🧍🏿‍♂️', '🧎🏻‍♀️', '🧎🏻‍♂️', '🧎🏻‍➡️', '🧎🏼‍♀️', '🧎🏼‍♂️', '🧎🏼‍➡️', '🧎🏽‍♀️', '🧎🏽‍♂️', '🧎🏽‍➡️', '🧎🏾‍♀️', '🧎🏾‍♂️', '🧎🏾‍➡️', '🧎🏿‍♀️', '🧎🏿‍♂️', '🧎🏿‍➡️', '🧏🏻‍♀️', '🧏🏻‍♂️', '🧏🏼‍♀️', '🧏🏼‍♂️', '🧏🏽‍♀️', '🧏🏽‍♂️', '🧏🏾‍♀️', '🧏🏾‍♂️', '🧏🏿‍♀️', '🧏🏿‍♂️', '🧑🏻‍⚕️', '🧑🏻‍⚖️', '🧑🏻‍✈️', '🧑🏼‍⚕️', '🧑🏼‍⚖️', '🧑🏼‍✈️', '🧑🏽‍⚕️', '🧑🏽‍⚖️', '🧑🏽‍✈️', '🧑🏾‍⚕️', '🧑🏾‍⚖️', '🧑🏾‍✈️', '🧑🏿‍⚕️', '🧑🏿‍⚖️', '🧑🏿‍✈️', '🧔🏻‍♀️', '🧔🏻‍♂️', '🧔🏼‍♀️', '🧔🏼‍♂️', '🧔🏽‍♀️', '🧔🏽‍♂️', '🧔🏾‍♀️', '🧔🏾‍♂️', '🧔🏿‍♀️', '🧔🏿‍♂️', '🧖🏻‍♀️', '🧖🏻‍♂️', '🧖🏼‍♀️', '🧖🏼‍♂️', '🧖🏽‍♀️', '🧖🏽‍♂️', '🧖🏾‍♀️', '🧖🏾‍♂️', '🧖🏿‍♀️', '🧖🏿‍♂️', '🧗🏻‍♀️', '🧗🏻‍♂️', '🧗🏼‍♀️', '🧗🏼‍♂️', '🧗🏽‍♀️', '🧗🏽‍♂️', '🧗🏾‍♀️', '🧗🏾‍♂️', '🧗🏿‍♀️', '🧗🏿‍♂️', '🧘🏻‍♀️', '🧘🏻‍♂️', '🧘🏼‍♀️', '🧘🏼‍♂️', '🧘🏽‍♀️', '🧘🏽‍♂️', '🧘🏾‍♀️', '🧘🏾‍♂️', '🧘🏿‍♀️', '🧘🏿‍♂️', '🧙🏻‍♀️', '🧙🏻‍♂️', '🧙🏼‍♀️', '🧙🏼‍♂️', '🧙🏽‍♀️', '🧙🏽‍♂️', '🧙🏾‍♀️', '🧙🏾‍♂️', '🧙🏿‍♀️', '🧙🏿‍♂️', '🧚🏻‍♀️', '🧚🏻‍♂️', '🧚🏼‍♀️', '🧚🏼‍♂️', '🧚🏽‍♀️', '🧚🏽‍♂️', '🧚🏾‍♀️', '🧚🏾‍♂️', '🧚🏿‍♀️', '🧚🏿‍♂️', '🧛🏻‍♀️', '🧛🏻‍♂️', '🧛🏼‍♀️', '🧛🏼‍♂️', '🧛🏽‍♀️', '🧛🏽‍♂️', '🧛🏾‍♀️', '🧛🏾‍♂️', '🧛🏿‍♀️', '🧛🏿‍♂️', '🧜🏻‍♀️', '🧜🏻‍♂️', '🧜🏼‍♀️', '🧜🏼‍♂️', '🧜🏽‍♀️', '🧜🏽‍♂️', '🧜🏾‍♀️', '🧜🏾‍♂️', '🧜🏿‍♀️', '🧜🏿‍♂️', '🧝🏻‍♀️', '🧝🏻‍♂️', '🧝🏼‍♀️', '🧝🏼‍♂️', '🧝🏽‍♀️', '🧝🏽‍♂️', '🧝🏾‍♀️', '🧝🏾‍♂️', '🧝🏿‍♀️', '🧝🏿‍♂️', '🏋️‍♀️', '🏋️‍♂️', '🏌️‍♀️', '🏌️‍♂️', '🏳️‍⚧️', '🕴️‍♀️', '🕴️‍♂️', '🕵️‍♀️', '🕵️‍♂️', '⛹🏻‍♀️', '⛹🏻‍♂️', '⛹🏼‍♀️', '⛹🏼‍♂️', '⛹🏽‍♀️', '⛹🏽‍♂️', '⛹🏾‍♀️', '⛹🏾‍♂️', '⛹🏿‍♀️', '⛹🏿‍♂️', '⛹️‍♀️', '⛹️‍♂️', '👨🏻‍🌾', '👨🏻‍🍳', '👨🏻‍🍼', '👨🏻‍🎄', '👨🏻‍🎓', '👨🏻‍🎤', '👨🏻‍🎨', '👨🏻‍🏫', '👨🏻‍🏭', '👨🏻‍💻', '👨🏻‍💼', '👨🏻‍🔧', '👨🏻‍🔬', '👨🏻‍🚀', '👨🏻‍🚒', '👨🏻‍🦯', '👨🏻‍🦰', '👨🏻‍🦱', '👨🏻‍🦲', '👨🏻‍🦳', '👨🏻‍🦼', '👨🏻‍🦽', '👨🏼‍🌾', '👨🏼‍🍳', '👨🏼‍🍼', '👨🏼‍🎄', '👨🏼‍🎓', '👨🏼‍🎤', '👨🏼‍🎨', '👨🏼‍🏫', '👨🏼‍🏭', '👨🏼‍💻', '👨🏼‍💼', '👨🏼‍🔧', '👨🏼‍🔬', '👨🏼‍🚀', '👨🏼‍🚒', '👨🏼‍🦯', '👨🏼‍🦰', '👨🏼‍🦱', '👨🏼‍🦲', '👨🏼‍🦳', '👨🏼‍🦼', '👨🏼‍🦽', '👨🏽‍🌾', '👨🏽‍🍳', '👨🏽‍🍼', '👨🏽‍🎄', '👨🏽‍🎓', '👨🏽‍🎤', '👨🏽‍🎨', '👨🏽‍🏫', '👨🏽‍🏭', '👨🏽‍💻', '👨🏽‍💼', '👨🏽‍🔧', '👨🏽‍🔬', '👨🏽‍🚀', '👨🏽‍🚒', '👨🏽‍🦯', '👨🏽‍🦰', '👨🏽‍🦱', '👨🏽‍🦲', '👨🏽‍🦳', '👨🏽‍🦼', '👨🏽‍🦽', '👨🏾‍🌾', '👨🏾‍🍳', '👨🏾‍🍼', '👨🏾‍🎄', '👨🏾‍🎓', '👨🏾‍🎤', '👨🏾‍🎨', '👨🏾‍🏫', '👨🏾‍🏭', '👨🏾‍💻', '👨🏾‍💼', '👨🏾‍🔧', '👨🏾‍🔬', '👨🏾‍🚀', '👨🏾‍🚒', '👨🏾‍🦯', '👨🏾‍🦰', '👨🏾‍🦱', '👨🏾‍🦲', '👨🏾‍🦳', '👨🏾‍🦼', '👨🏾‍🦽', '👨🏿‍🌾', '👨🏿‍🍳', '👨🏿‍🍼', '👨🏿‍🎄', '👨🏿‍🎓', '👨🏿‍🎤', '👨🏿‍🎨', '👨🏿‍🏫', '👨🏿‍🏭', '👨🏿‍💻', '👨🏿‍💼', '👨🏿‍🔧', '👨🏿‍🔬', '👨🏿‍🚀', '👨🏿‍🚒', '👨🏿‍🦯', '👨🏿‍🦰', '👨🏿‍🦱', '👨🏿‍🦲', '👨🏿‍🦳', '👨🏿‍🦼', '👨🏿‍🦽', '👩🏻‍🌾', '👩🏻‍🍳', '👩🏻‍🍼', '👩🏻‍🎄', '👩🏻‍🎓', '👩🏻‍🎤', '👩🏻‍🎨', '👩🏻‍🏫', '👩🏻‍🏭', '👩🏻‍💻', '👩🏻‍💼', '👩🏻‍🔧', '👩🏻‍🔬', '👩🏻‍🚀', '👩🏻‍🚒', '👩🏻‍🦯', '👩🏻‍🦰', '👩🏻‍🦱', '👩🏻‍🦲', '👩🏻‍🦳', '👩🏻‍🦼', '👩🏻‍🦽', '👩🏼‍🌾', '👩🏼‍🍳', '👩🏼‍🍼', '👩🏼‍🎄', '👩🏼‍🎓', '👩🏼‍🎤', '👩🏼‍🎨', '👩🏼‍🏫', '👩🏼‍🏭', '👩🏼‍💻', '👩🏼‍💼', '👩🏼‍🔧', '👩🏼‍🔬', '👩🏼‍🚀', '👩🏼‍🚒', '👩🏼‍🦯', '👩🏼‍🦰', '👩🏼‍🦱', '👩🏼‍🦲', '👩🏼‍🦳', '👩🏼‍🦼', '👩🏼‍🦽', '👩🏽‍🌾', '👩🏽‍🍳', '👩🏽‍🍼', '👩🏽‍🎄', '👩🏽‍🎓', '👩🏽‍🎤', '👩🏽‍🎨', '👩🏽‍🏫', '👩🏽‍🏭', '👩🏽‍💻', '👩🏽‍💼', '👩🏽‍🔧', '👩🏽‍🔬', '👩🏽‍🚀', '👩🏽‍🚒', '👩🏽‍🦯', '👩🏽‍🦰', '👩🏽‍🦱', '👩🏽‍🦲', '👩🏽‍🦳', '👩🏽‍🦼', '👩🏽‍🦽', '👩🏾‍🌾', '👩🏾‍🍳', '👩🏾‍🍼', '👩🏾‍🎄', '👩🏾‍🎓', '👩🏾‍🎤', '👩🏾‍🎨', '👩🏾‍🏫', '👩🏾‍🏭', '👩🏾‍💻', '👩🏾‍💼', '👩🏾‍🔧', '👩🏾‍🔬', '👩🏾‍🚀', '👩🏾‍🚒', '👩🏾‍🦯', '👩🏾‍🦰', '👩🏾‍🦱', '👩🏾‍🦲', '👩🏾‍🦳', '👩🏾‍🦼', '👩🏾‍🦽', '👩🏿‍🌾', '👩🏿‍🍳', '👩🏿‍🍼', '👩🏿‍🎄', '👩🏿‍🎓', '👩🏿‍🎤', '👩🏿‍🎨', '👩🏿‍🏫', '👩🏿‍🏭', '👩🏿‍💻', '👩🏿‍💼', '👩🏿‍🔧', '👩🏿‍🔬', '👩🏿‍🚀', '👩🏿‍🚒', '👩🏿‍🦯', '👩🏿‍🦰', '👩🏿‍🦱', '👩🏿‍🦲', '👩🏿‍🦳', '👩🏿‍🦼', '👩🏿‍🦽', '🧑🏻‍🌾', '🧑🏻‍🍳', '🧑🏻‍🍼', '🧑🏻‍🎄', '🧑🏻‍🎓', '🧑🏻‍🎤', '🧑🏻‍🎨', '🧑🏻‍🏫', '🧑🏻‍🏭', '🧑🏻‍💻', '🧑🏻‍💼', '🧑🏻‍🔧', '🧑🏻‍🔬', '🧑🏻‍🚀', '🧑🏻‍🚒', '🧑🏻‍🦯', '🧑🏻‍🦰', '🧑🏻‍🦱', '🧑🏻‍🦲', '🧑🏻‍🦳', '🧑🏻‍🦼', '🧑🏻‍🦽', '🧑🏼‍🌾', '🧑🏼‍🍳', '🧑🏼‍🍼', '🧑🏼‍🎄', '🧑🏼‍🎓', '🧑🏼‍🎤', '🧑🏼‍🎨', '🧑🏼‍🏫', '🧑🏼‍🏭', '🧑🏼‍💻', '🧑🏼‍💼', '🧑🏼‍🔧', '🧑🏼‍🔬', '🧑🏼‍🚀', '🧑🏼‍🚒', '🧑🏼‍🦯', '🧑🏼‍🦰', '🧑🏼‍🦱', '🧑🏼‍🦲', '🧑🏼‍🦳', '🧑🏼‍🦼', '🧑🏼‍🦽', '🧑🏽‍🌾', '🧑🏽‍🍳', '🧑🏽‍🍼', '🧑🏽‍🎄', '🧑🏽‍🎓', '🧑🏽‍🎤', '🧑🏽‍🎨', '🧑🏽‍🏫', '🧑🏽‍🏭', '🧑🏽‍💻', '🧑🏽‍💼', '🧑🏽‍🔧', '🧑🏽‍🔬', '🧑🏽‍🚀', '🧑🏽‍🚒', '🧑🏽‍🦯', '🧑🏽‍🦰', '🧑🏽‍🦱', '🧑🏽‍🦲', '🧑🏽‍🦳', '🧑🏽‍🦼', '🧑🏽‍🦽', '🧑🏾‍🌾', '🧑🏾‍🍳', '🧑🏾‍🍼', '🧑🏾‍🎄', '🧑🏾‍🎓', '🧑🏾‍🎤', '🧑🏾‍🎨', '🧑🏾‍🏫', '🧑🏾‍🏭', '🧑🏾‍💻', '🧑🏾‍💼', '🧑🏾‍🔧', '🧑🏾‍🔬', '🧑🏾‍🚀', '🧑🏾‍🚒', '🧑🏾‍🦯', '🧑🏾‍🦰', '🧑🏾‍🦱', '🧑🏾‍🦲', '🧑🏾‍🦳', '🧑🏾‍🦼', '🧑🏾‍🦽', '🧑🏿‍🌾', '🧑🏿‍🍳', '🧑🏿‍🍼', '🧑🏿‍🎄', '🧑🏿‍🎓', '🧑🏿‍🎤', '🧑🏿‍🎨', '🧑🏿‍🏫', '🧑🏿‍🏭', '🧑🏿‍💻', '🧑🏿‍💼', '🧑🏿‍🔧', '🧑🏿‍🔬', '🧑🏿‍🚀', '🧑🏿‍🚒', '🧑🏿‍🦯', '🧑🏿‍🦰', '🧑🏿‍🦱', '🧑🏿‍🦲', '🧑🏿‍🦳', '🧑🏿‍🦼', '🧑🏿‍🦽', '🏳️‍🌈', '😶‍🌫️', '🏃‍♀️', '🏃‍♂️', '🏃‍➡️', '🏄‍♀️', '🏄‍♂️', '🏊‍♀️', '🏊‍♂️', '🏴‍☠️', '🐻‍❄️', '👨‍⚕️', '👨‍⚖️', '👨‍✈️', '👩‍⚕️', '👩‍⚖️', '👩‍✈️', '👮‍♀️', '👮‍♂️', '👯‍♀️', '👯‍♂️', '👰‍♀️', '👰‍♂️', '👱‍♀️', '👱‍♂️', '👳‍♀️', '👳‍♂️', '👷‍♀️', '👷‍♂️', '💁‍♀️', '💁‍♂️', '💂‍♀️', '💂‍♂️', '💆‍♀️', '💆‍♂️', '💇‍♀️', '💇‍♂️', '🙂‍↔️', '🙂‍↕️', '🙅‍♀️', '🙅‍♂️', '🙆‍♀️', '🙆‍♂️', '🙇‍♀️', '🙇‍♂️', '🙋‍♀️', '🙋‍♂️', '🙍‍♀️', '🙍‍♂️', '🙎‍♀️', '🙎‍♂️', '🚣‍♀️', '🚣‍♂️', '🚴‍♀️', '🚴‍♂️', '🚵‍♀️', '🚵‍♂️', '🚶‍♀️', '🚶‍♂️', '🚶‍➡️', '🤦‍♀️', '🤦‍♂️', '🤵‍♀️', '🤵‍♂️', '🤷‍♀️', '🤷‍♂️', '🤸‍♀️', '🤸‍♂️', '🤹‍♀️', '🤹‍♂️', '🤼‍♀️', '🤼‍♂️', '🤽‍♀️', '🤽‍♂️', '🤾‍♀️', '🤾‍♂️', '🦸‍♀️', '🦸‍♂️', '🦹‍♀️', '🦹‍♂️', '🧍‍♀️', '🧍‍♂️', '🧎‍♀️', '🧎‍♂️', '🧎‍➡️', '🧏‍♀️', '🧏‍♂️', '🧑‍⚕️', '🧑‍⚖️', '🧑‍✈️', '🧔‍♀️', '🧔‍♂️', '🧖‍♀️', '🧖‍♂️', '🧗‍♀️', '🧗‍♂️', '🧘‍♀️', '🧘‍♂️', '🧙‍♀️', '🧙‍♂️', '🧚‍♀️', '🧚‍♂️', '🧛‍♀️', '🧛‍♂️', '🧜‍♀️', '🧜‍♂️', '🧝‍♀️', '🧝‍♂️', '🧞‍♀️', '🧞‍♂️', '🧟‍♀️', '🧟‍♂️', '⛓️‍💥', '❤️‍🔥', '❤️‍🩹', '🍄‍🟫', '🍋‍🟩', '🐕‍🦺', '🐦‍🔥', '👁‍🗨', '👨‍🌾', '👨‍🍳', '👨‍🍼', '👨‍🎄', '👨‍🎓', '👨‍🎤', '👨‍🎨', '👨‍🏫', '👨‍🏭', '👨‍👦', '👨‍👧', '👨‍💻', '👨‍💼', '👨‍🔧', '👨‍🔬', '👨‍🚀', '👨‍🚒', '👨‍🦯', '👨‍🦰', '👨‍🦱', '👨‍🦲', '👨‍🦳', '👨‍🦼', '👨‍🦽', '👩‍🌾', '👩‍🍳', '👩‍🍼', '👩‍🎄', '👩‍🎓', '👩‍🎤', '👩‍🎨', '👩‍🏫', '👩‍🏭', '👩‍👦', '👩‍👧', '👩‍💻', '👩‍💼', '👩‍🔧', '👩‍🔬', '👩‍🚀', '👩‍🚒', '👩‍🦯', '👩‍🦰', '👩‍🦱', '👩‍🦲', '👩‍🦳', '👩‍🦼', '👩‍🦽', '😮‍💨', '😵‍💫', '🧑‍🌾', '🧑‍🍳', '🧑‍🍼', '🧑‍🎄', '🧑‍🎓', '🧑‍🎤', '🧑‍🎨', '🧑‍🏫', '🧑‍🏭', '🧑‍💻', '🧑‍💼', '🧑‍🔧', '🧑‍🔬', '🧑‍🚀', '🧑‍🚒', '🧑‍🦯', '🧑‍🦰', '🧑‍🦱', '🧑‍🦲', '🧑‍🦳', '🧑‍🦼', '🧑‍🦽', '🧑‍🧒', '🐈‍⬛', '🐦‍⬛', '🇦🇨', '🇦🇩', '🇦🇪', '🇦🇫', '🇦🇬', '🇦🇮', '🇦🇱', '🇦🇲', '🇦🇴', '🇦🇶', '🇦🇷', '🇦🇸', '🇦🇹', '🇦🇺', '🇦🇼', '🇦🇽', '🇦🇿', '🇧🇦', '🇧🇧', '🇧🇩', '🇧🇪', '🇧🇫', '🇧🇬', '🇧🇭', '🇧🇮', '🇧🇯', '🇧🇱', '🇧🇲', '🇧🇳', '🇧🇴', '🇧🇶', '🇧🇷', '🇧🇸', '🇧🇹', '🇧🇻', '🇧🇼', '🇧🇾', '🇧🇿', '🇨🇦', '🇨🇨', '🇨🇩', '🇨🇫', '🇨🇬', '🇨🇭', '🇨🇮', '🇨🇰', '🇨🇱', '🇨🇲', '🇨🇳', '🇨🇴', '🇨🇵', '🇨🇶', '🇨🇷', '🇨🇺', '🇨🇻', '🇨🇼', '🇨🇽', '🇨🇾', '🇨🇿', '🇩🇪', '🇩🇬', '🇩🇯', '🇩🇰', '🇩🇲', '🇩🇴', '🇩🇿', '🇪🇦', '🇪🇨', '🇪🇪', '🇪🇬', '🇪🇭', '🇪🇷', '🇪🇸', '🇪🇹', '🇪🇺', '🇫🇮', '🇫🇯', '🇫🇰', '🇫🇲', '🇫🇴', '🇫🇷', '🇬🇦', '🇬🇧', '🇬🇩', '🇬🇪', '🇬🇫', '🇬🇬', '🇬🇭', '🇬🇮', '🇬🇱', '🇬🇲', '🇬🇳', '🇬🇵', '🇬🇶', '🇬🇷', '🇬🇸', '🇬🇹', '🇬🇺', '🇬🇼', '🇬🇾', '🇭🇰', '🇭🇲', '🇭🇳', '🇭🇷', '🇭🇹', '🇭🇺', '🇮🇨', '🇮🇩', '🇮🇪', '🇮🇱', '🇮🇲', '🇮🇳', '🇮🇴', '🇮🇶', '🇮🇷', '🇮🇸', '🇮🇹', '🇯🇪', '🇯🇲', '🇯🇴', '🇯🇵', '🇰🇪', '🇰🇬', '🇰🇭', '🇰🇮', '🇰🇲', '🇰🇳', '🇰🇵', '🇰🇷', '🇰🇼', '🇰🇾', '🇰🇿', '🇱🇦', '🇱🇧', '🇱🇨', '🇱🇮', '🇱🇰', '🇱🇷', '🇱🇸', '🇱🇹', '🇱🇺', '🇱🇻', '🇱🇾', '🇲🇦', '🇲🇨', '🇲🇩', '🇲🇪', '🇲🇫', '🇲🇬', '🇲🇭', '🇲🇰', '🇲🇱', '🇲🇲', '🇲🇳', '🇲🇴', '🇲🇵', '🇲🇶', '🇲🇷', '🇲🇸', '🇲🇹', '🇲🇺', '🇲🇻', '🇲🇼', '🇲🇽', '🇲🇾', '🇲🇿', '🇳🇦', '🇳🇨', '🇳🇪', '🇳🇫', '🇳🇬', '🇳🇮', '🇳🇱', '🇳🇴', '🇳🇵', '🇳🇷', '🇳🇺', '🇳🇿', '🇴🇲', '🇵🇦', '🇵🇪', '🇵🇫', '🇵🇬', '🇵🇭', '🇵🇰', '🇵🇱', '🇵🇲', '🇵🇳', '🇵🇷', '🇵🇸', '🇵🇹', '🇵🇼', '🇵🇾', '🇶🇦', '🇷🇪', '🇷🇴', '🇷🇸', '🇷🇺', '🇷🇼', '🇸🇦', '🇸🇧', '🇸🇨', '🇸🇩', '🇸🇪', '🇸🇬', '🇸🇭', '🇸🇮', '🇸🇯', '🇸🇰', '🇸🇱', '🇸🇲', '🇸🇳', '🇸🇴', '🇸🇷', '🇸🇸', '🇸🇹', '🇸🇻', '🇸🇽', '🇸🇾', '🇸🇿', '🇹🇦', '🇹🇨', '🇹🇩', '🇹🇫', '🇹🇬', '🇹🇭', '🇹🇯', '🇹🇰', '🇹🇱', '🇹🇲', '🇹🇳', '🇹🇴', '🇹🇷', '🇹🇹', '🇹🇻', '🇹🇼', '🇹🇿', '🇺🇦', '🇺🇬', '🇺🇲', '🇺🇳', '🇺🇸', '🇺🇾', '🇺🇿', '🇻🇦', '🇻🇨', '🇻🇪', '🇻🇬', '🇻🇮', '🇻🇳', '🇻🇺', '🇼🇫', '🇼🇸', '🇽🇰', '🇾🇪', '🇾🇹', '🇿🇦', '🇿🇲', '🇿🇼', '🎅🏻', '🎅🏼', '🎅🏽', '🎅🏾', '🎅🏿', '🏂🏻', '🏂🏼', '🏂🏽', '🏂🏾', '🏂🏿', '🏃🏻', '🏃🏼', '🏃🏽', '🏃🏾', '🏃🏿', '🏄🏻', '🏄🏼', '🏄🏽', '🏄🏾', '🏄🏿', '🏇🏻', '🏇🏼', '🏇🏽', '🏇🏾', '🏇🏿', '🏊🏻', '🏊🏼', '🏊🏽', '🏊🏾', '🏊🏿', '🏋🏻', '🏋🏼', '🏋🏽', '🏋🏾', '🏋🏿', '🏌🏻', '🏌🏼', '🏌🏽', '🏌🏾', '🏌🏿', '👂🏻', '👂🏼', '👂🏽', '👂🏾', '👂🏿', '👃🏻', '👃🏼', '👃🏽', '👃🏾', '👃🏿', '👆🏻', '👆🏼', '👆🏽', '👆🏾', '👆🏿', '👇🏻', '👇🏼', '👇🏽', '👇🏾', '👇🏿', '👈🏻', '👈🏼', '👈🏽', '👈🏾', '👈🏿', '👉🏻', '👉🏼', '👉🏽', '👉🏾', '👉🏿', '👊🏻', '👊🏼', '👊🏽', '👊🏾', '👊🏿', '👋🏻', '👋🏼', '👋🏽', '👋🏾', '👋🏿', '👌🏻', '👌🏼', '👌🏽', '👌🏾', '👌🏿', '👍🏻', '👍🏼', '👍🏽', '👍🏾', '👍🏿', '👎🏻', '👎🏼', '👎🏽', '👎🏾', '👎🏿', '👏🏻', '👏🏼', '👏🏽', '👏🏾', '👏🏿', '👐🏻', '👐🏼', '👐🏽', '👐🏾', '👐🏿', '👦🏻', '👦🏼', '👦🏽', '👦🏾', '👦🏿', '👧🏻', '👧🏼', '👧🏽', '👧🏾', '👧🏿', '👨🏻', '👨🏼', '👨🏽', '👨🏾', '👨🏿', '👩🏻', '👩🏼', '👩🏽', '👩🏾', '👩🏿', '👫🏻', '👫🏼', '👫🏽', '👫🏾', '👫🏿', '👬🏻', '👬🏼', '👬🏽', '👬🏾', '👬🏿', '👭🏻', '👭🏼', '👭🏽', '👭🏾', '👭🏿', '👮🏻', '👮🏼', '👮🏽', '👮🏾', '👮🏿', '👰🏻', '👰🏼', '👰🏽', '👰🏾', '👰🏿', '👱🏻', '👱🏼', '👱🏽', '👱🏾', '👱🏿', '👲🏻', '👲🏼', '👲🏽', '👲🏾', '👲🏿', '👳🏻', '👳🏼', '👳🏽', '👳🏾', '👳🏿', '👴🏻', '👴🏼', '👴🏽', '👴🏾', '👴🏿', '👵🏻', '👵🏼', '👵🏽', '👵🏾', '👵🏿', '👶🏻', '👶🏼', '👶🏽', '👶🏾', '👶🏿', '👷🏻', '👷🏼', '👷🏽', '👷🏾', '👷🏿', '👸🏻', '👸🏼', '👸🏽', '👸🏾', '👸🏿', '👼🏻', '👼🏼', '👼🏽', '👼🏾', '👼🏿', '💁🏻', '💁🏼', '💁🏽', '💁🏾', '💁🏿', '💂🏻', '💂🏼', '💂🏽', '💂🏾', '💂🏿', '💃🏻', '💃🏼', '💃🏽', '💃🏾', '💃🏿', '💅🏻', '💅🏼', '💅🏽', '💅🏾', '💅🏿', '💆🏻', '💆🏼', '💆🏽', '💆🏾', '💆🏿', '💇🏻', '💇🏼', '💇🏽', '💇🏾', '💇🏿', '💏🏻', '💏🏼', '💏🏽', '💏🏾', '💏🏿', '💑🏻', '💑🏼', '💑🏽', '💑🏾', '💑🏿', '💪🏻', '💪🏼', '💪🏽', '💪🏾', '💪🏿', '🕴🏻', '🕴🏼', '🕴🏽', '🕴🏾', '🕴🏿', '🕵🏻', '🕵🏼', '🕵🏽', '🕵🏾', '🕵🏿', '🕺🏻', '🕺🏼', '🕺🏽', '🕺🏾', '🕺🏿', '🖐🏻', '🖐🏼', '🖐🏽', '🖐🏾', '🖐🏿', '🖕🏻', '🖕🏼', '🖕🏽', '🖕🏾', '🖕🏿', '🖖🏻', '🖖🏼', '🖖🏽', '🖖🏾', '🖖🏿', '🙅🏻', '🙅🏼', '🙅🏽', '🙅🏾', '🙅🏿', '🙆🏻', '🙆🏼', '🙆🏽', '🙆🏾', '🙆🏿', '🙇🏻', '🙇🏼', '🙇🏽', '🙇🏾', '🙇🏿', '🙋🏻', '🙋🏼', '🙋🏽', '🙋🏾', '🙋🏿', '🙌🏻', '🙌🏼', '🙌🏽', '🙌🏾', '🙌🏿', '🙍🏻', '🙍🏼', '🙍🏽', '🙍🏾', '🙍🏿', '🙎🏻', '🙎🏼', '🙎🏽', '🙎🏾', '🙎🏿', '🙏🏻', '🙏🏼', '🙏🏽', '🙏🏾', '🙏🏿', '🚣🏻', '🚣🏼', '🚣🏽', '🚣🏾', '🚣🏿', '🚴🏻', '🚴🏼', '🚴🏽', '🚴🏾', '🚴🏿', '🚵🏻', '🚵🏼', '🚵🏽', '🚵🏾', '🚵🏿', '🚶🏻', '🚶🏼', '🚶🏽', '🚶🏾', '🚶🏿', '🛀🏻', '🛀🏼', '🛀🏽', '🛀🏾', '🛀🏿', '🛌🏻', '🛌🏼', '🛌🏽', '🛌🏾', '🛌🏿', '🤌🏻', '🤌🏼', '🤌🏽', '🤌🏾', '🤌🏿', '🤏🏻', '🤏🏼', '🤏🏽', '🤏🏾', '🤏🏿', '🤘🏻', '🤘🏼', '🤘🏽', '🤘🏾', '🤘🏿', '🤙🏻', '🤙🏼', '🤙🏽', '🤙🏾', '🤙🏿', '🤚🏻', '🤚🏼', '🤚🏽', '🤚🏾', '🤚🏿', '🤛🏻', '🤛🏼', '🤛🏽', '🤛🏾', '🤛🏿', '🤜🏻', '🤜🏼', '🤜🏽', '🤜🏾', '🤜🏿', '🤝🏻', '🤝🏼', '🤝🏽', '🤝🏾', '🤝🏿', '🤞🏻', '🤞🏼', '🤞🏽', '🤞🏾', '🤞🏿', '🤟🏻', '🤟🏼', '🤟🏽', '🤟🏾', '🤟🏿', '🤦🏻', '🤦🏼', '🤦🏽', '🤦🏾', '🤦🏿', '🤰🏻', '🤰🏼', '🤰🏽', '🤰🏾', '🤰🏿', '🤱🏻', '🤱🏼', '🤱🏽', '🤱🏾', '🤱🏿', '🤲🏻', '🤲🏼', '🤲🏽', '🤲🏾', '🤲🏿', '🤳🏻', '🤳🏼', '🤳🏽', '🤳🏾', '🤳🏿', '🤴🏻', '🤴🏼', '🤴🏽', '🤴🏾', '🤴🏿', '🤵🏻', '🤵🏼', '🤵🏽', '🤵🏾', '🤵🏿', '🤶🏻', '🤶🏼', '🤶🏽', '🤶🏾', '🤶🏿', '🤷🏻', '🤷🏼', '🤷🏽', '🤷🏾', '🤷🏿', '🤸🏻', '🤸🏼', '🤸🏽', '🤸🏾', '🤸🏿', '🤹🏻', '🤹🏼', '🤹🏽', '🤹🏾', '🤹🏿', '🤽🏻', '🤽🏼', '🤽🏽', '🤽🏾', '🤽🏿', '🤾🏻', '🤾🏼', '🤾🏽', '🤾🏾', '🤾🏿', '🥷🏻', '🥷🏼', '🥷🏽', '🥷🏾', '🥷🏿', '🦵🏻', '🦵🏼', '🦵🏽', '🦵🏾', '🦵🏿', '🦶🏻', '🦶🏼', '🦶🏽', '🦶🏾', '🦶🏿', '🦸🏻', '🦸🏼', '🦸🏽', '🦸🏾', '🦸🏿', '🦹🏻', '🦹🏼', '🦹🏽', '🦹🏾', '🦹🏿', '🦻🏻', '🦻🏼', '🦻🏽', '🦻🏾', '🦻🏿', '🧍🏻', '🧍🏼', '🧍🏽', '🧍🏾', '🧍🏿', '🧎🏻', '🧎🏼', '🧎🏽', '🧎🏾', '🧎🏿', '🧏🏻', '🧏🏼', '🧏🏽', '🧏🏾', '🧏🏿', '🧑🏻', '🧑🏼', '🧑🏽', '🧑🏾', '🧑🏿', '🧒🏻', '🧒🏼', '🧒🏽', '🧒🏾', '🧒🏿', '🧓🏻', '🧓🏼', '🧓🏽', '🧓🏾', '🧓🏿', '🧔🏻', '🧔🏼', '🧔🏽', '🧔🏾', '🧔🏿', '🧕🏻', '🧕🏼', '🧕🏽', '🧕🏾', '🧕🏿', '🧖🏻', '🧖🏼', '🧖🏽', '🧖🏾', '🧖🏿', '🧗🏻', '🧗🏼', '🧗🏽', '🧗🏾', '🧗🏿', '🧘🏻', '🧘🏼', '🧘🏽', '🧘🏾', '🧘🏿', '🧙🏻', '🧙🏼', '🧙🏽', '🧙🏾', '🧙🏿', '🧚🏻', '🧚🏼', '🧚🏽', '🧚🏾', '🧚🏿', '🧛🏻', '🧛🏼', '🧛🏽', '🧛🏾', '🧛🏿', '🧜🏻', '🧜🏼', '🧜🏽', '🧜🏾', '🧜🏿', '🧝🏻', '🧝🏼', '🧝🏽', '🧝🏾', '🧝🏿', '🫃🏻', '🫃🏼', '🫃🏽', '🫃🏾', '🫃🏿', '🫄🏻', '🫄🏼', '🫄🏽', '🫄🏾', '🫄🏿', '🫅🏻', '🫅🏼', '🫅🏽', '🫅🏾', '🫅🏿', '🫰🏻', '🫰🏼', '🫰🏽', '🫰🏾', '🫰🏿', '🫱🏻', '🫱🏼', '🫱🏽', '🫱🏾', '🫱🏿', '🫲🏻', '🫲🏼', '🫲🏽', '🫲🏾', '🫲🏿', '🫳🏻', '🫳🏼', '🫳🏽', '🫳🏾', '🫳🏿', '🫴🏻', '🫴🏼', '🫴🏽', '🫴🏾', '🫴🏿', '🫵🏻', '🫵🏼', '🫵🏽', '🫵🏾', '🫵🏿', '🫶🏻', '🫶🏼', '🫶🏽', '🫶🏾', '🫶🏿', '🫷🏻', '🫷🏼', '🫷🏽', '🫷🏾', '🫷🏿', '🫸🏻', '🫸🏼', '🫸🏽', '🫸🏾', '🫸🏿', '☝🏻', '☝🏼', '☝🏽', '☝🏾', '☝🏿', '⛷🏻', '⛷🏼', '⛷🏽', '⛷🏾', '⛷🏿', '⛹🏻', '⛹🏼', '⛹🏽', '⛹🏾', '⛹🏿', '✊🏻', '✊🏼', '✊🏽', '✊🏾', '✊🏿', '✋🏻', '✋🏼', '✋🏽', '✋🏾', '✋🏿', '✌🏻', '✌🏼', '✌🏽', '✌🏾', '✌🏿', '✍🏻', '✍🏼', '✍🏽', '✍🏾', '✍🏿', '#⃣', '*⃣', '0⃣', '1⃣', '2⃣', '3⃣', '4⃣', '5⃣', '6⃣', '7⃣', '8⃣', '9⃣', '🀄', '🃏', '🅰', '🅱', '🅾', '🅿', '🆎', '🆑', '🆒', '🆓', '🆔', '🆕', '🆖', '🆗', '🆘', '🆙', '🆚', '🇦', '🇧', '🇨', '🇩', '🇪', '🇫', '🇬', '🇭', '🇮', '🇯', '🇰', '🇱', '🇲', '🇳', '🇴', '🇵', '🇶', '🇷', '🇸', '🇹', '🇺', '🇻', '🇼', '🇽', '🇾', '🇿', '🈁', '🈂', '🈚', '🈯', '🈲', '🈳', '🈴', '🈵', '🈶', '🈷', '🈸', '🈹', '🈺', '🉐', '🉑', '🌀', '🌁', '🌂', '🌃', '🌄', '🌅', '🌆', '🌇', '🌈', '🌉', '🌊', '🌋', '🌌', '🌍', '🌎', '🌏', '🌐', '🌑', '🌒', '🌓', '🌔', '🌕', '🌖', '🌗', '🌘', '🌙', '🌚', '🌛', '🌜', '🌝', '🌞', '🌟', '🌠', '🌡', '🌤', '🌥', '🌦', '🌧', '🌨', '🌩', '🌪', '🌫', '🌬', '🌭', '🌮', '🌯', '🌰', '🌱', '🌲', '🌳', '🌴', '🌵', '🌶', '🌷', '🌸', '🌹', '🌺', '🌻', '🌼', '🌽', '🌾', '🌿', '🍀', '🍁', '🍂', '🍃', '🍄', '🍅', '🍆', '🍇', '🍈', '🍉', '🍊', '🍋', '🍌', '🍍', '🍎', '🍏', '🍐', '🍑', '🍒', '🍓', '🍔', '🍕', '🍖', '🍗', '🍘', '🍙', '🍚', '🍛', '🍜', '🍝', '🍞', '🍟', '🍠', '🍡', '🍢', '🍣', '🍤', '🍥', '🍦', '🍧', '🍨', '🍩', '🍪', '🍫', '🍬', '🍭', '🍮', '🍯', '🍰', '🍱', '🍲', '🍳', '🍴', '🍵', '🍶', '🍷', '🍸', '🍹', '🍺', '🍻', '🍼', '🍽', '🍾', '🍿', '🎀', '🎁', '🎂', '🎃', '🎄', '🎅', '🎆', '🎇', '🎈', '🎉', '🎊', '🎋', '🎌', '🎍', '🎎', '🎏', '🎐', '🎑', '🎒', '🎓', '🎖', '🎗', '🎙', '🎚', '🎛', '🎞', '🎟', '🎠', '🎡', '🎢', '🎣', '🎤', '🎥', '🎦', '🎧', '🎨', '🎩', '🎪', '🎫', '🎬', '🎭', '🎮', '🎯', '🎰', '🎱', '🎲', '🎳', '🎴', '🎵', '🎶', '🎷', '🎸', '🎹', '🎺', '🎻', '🎼', '🎽', '🎾', '🎿', '🏀', '🏁', '🏂', '🏃', '🏄', '🏅', '🏆', '🏇', '🏈', '🏉', '🏊', '🏋', '🏌', '🏍', '🏎', '🏏', '🏐', '🏑', '🏒', '🏓', '🏔', '🏕', '🏖', '🏗', '🏘', '🏙', '🏚', '🏛', '🏜', '🏝', '🏞', '🏟', '🏠', '🏡', '🏢', '🏣', '🏤', '🏥', '🏦', '🏧', '🏨', '🏩', '🏪', '🏫', '🏬', '🏭', '🏮', '🏯', '🏰', '🏳', '🏴', '🏵', '🏷', '🏸', '🏹', '🏺', '🏻', '🏼', '🏽', '🏾', '🏿', '🐀', '🐁', '🐂', '🐃', '🐄', '🐅', '🐆', '🐇', '🐈', '🐉', '🐊', '🐋', '🐌', '🐍', '🐎', '🐏', '🐐', '🐑', '🐒', '🐓', '🐔', '🐕', '🐖', '🐗', '🐘', '🐙', '🐚', '🐛', '🐜', '🐝', '🐞', '🐟', '🐠', '🐡', '🐢', '🐣', '🐤', '🐥', '🐦', '🐧', '🐨', '🐩', '🐪', '🐫', '🐬', '🐭', '🐮', '🐯', '🐰', '🐱', '🐲', '🐳', '🐴', '🐵', '🐶', '🐷', '🐸', '🐹', '🐺', '🐻', '🐼', '🐽', '🐾', '🐿', '👀', '👁', '👂', '👃', '👄', '👅', '👆', '👇', '👈', '👉', '👊', '👋', '👌', '👍', '👎', '👏', '👐', '👑', '👒', '👓', '👔', '👕', '👖', '👗', '👘', '👙', '👚', '👛', '👜', '👝', '👞', '👟', '👠', '👡', '👢', '👣', '👤', '👥', '👦', '👧', '👨', '👩', '👪', '👫', '👬', '👭', '👮', '👯', '👰', '👱', '👲', '👳', '👴', '👵', '👶', '👷', '👸', '👹', '👺', '👻', '👼', '👽', '👾', '👿', '💀', '💁', '💂', '💃', '💄', '💅', '💆', '💇', '💈', '💉', '💊', '💋', '💌', '💍', '💎', '💏', '💐', '💑', '💒', '💓', '💔', '💕', '💖', '💗', '💘', '💙', '💚', '💛', '💜', '💝', '💞', '💟', '💠', '💡', '💢', '💣', '💤', '💥', '💦', '💧', '💨', '💩', '💪', '💫', '💬', '💭', '💮', '💯', '💰', '💱', '💲', '💳', '💴', '💵', '💶', '💷', '💸', '💹', '💺', '💻', '💼', '💽', '💾', '💿', '📀', '📁', '📂', '📃', '📄', '📅', '📆', '📇', '📈', '📉', '📊', '📋', '📌', '📍', '📎', '📏', '📐', '📑', '📒', '📓', '📔', '📕', '📖', '📗', '📘', '📙', '📚', '📛', '📜', '📝', '📞', '📟', '📠', '📡', '📢', '📣', '📤', '📥', '📦', '📧', '📨', '📩', '📪', '📫', '📬', '📭', '📮', '📯', '📰', '📱', '📲', '📳', '📴', '📵', '📶', '📷', '📸', '📹', '📺', '📻', '📼', '📽', '📿', '🔀', '🔁', '🔂', '🔃', '🔄', '🔅', '🔆', '🔇', '🔈', '🔉', '🔊', '🔋', '🔌', '🔍', '🔎', '🔏', '🔐', '🔑', '🔒', '🔓', '🔔', '🔕', '🔖', '🔗', '🔘', '🔙', '🔚', '🔛', '🔜', '🔝', '🔞', '🔟', '🔠', '🔡', '🔢', '🔣', '🔤', '🔥', '🔦', '🔧', '🔨', '🔩', '🔪', '🔫', '🔬', '🔭', '🔮', '🔯', '🔰', '🔱', '🔲', '🔳', '🔴', '🔵', '🔶', '🔷', '🔸', '🔹', '🔺', '🔻', '🔼', '🔽', '🕉', '🕊', '🕋', '🕌', '🕍', '🕎', '🕐', '🕑', '🕒', '🕓', '🕔', '🕕', '🕖', '🕗', '🕘', '🕙', '🕚', '🕛', '🕜', '🕝', '🕞', '🕟', '🕠', '🕡', '🕢', '🕣', '🕤', '🕥', '🕦', '🕧', '🕯', '🕰', '🕳', '🕴', '🕵', '🕶', '🕷', '🕸', '🕹', '🕺', '🖇', '🖊', '🖋', '🖌', '🖍', '🖐', '🖕', '🖖', '🖤', '🖥', '🖨', '🖱', '🖲', '🖼', '🗂', '🗃', '🗄', '🗑', '🗒', '🗓', '🗜', '🗝', '🗞', '🗡', '🗣', '🗨', '🗯', '🗳', '🗺', '🗻', '🗼', '🗽', '🗾', '🗿', '😀', '😁', '😂', '😃', '😄', '😅', '😆', '😇', '😈', '😉', '😊', '😋', '😌', '😍', '😎', '😏', '😐', '😑', '😒', '😓', '😔', '😕', '😖', '😗', '😘', '😙', '😚', '😛', '😜', '😝', '😞', '😟', '😠', '😡', '😢', '😣', '😤', '😥', '😦', '😧', '😨', '😩', '😪', '😫', '😬', '😭', '😮', '😯', '😰', '😱', '😲', '😳', '😴', '😵', '😶', '😷', '😸', '😹', '😺', '😻', '😼', '😽', '😾', '😿', '🙀', '🙁', '🙂', '🙃', '🙄', '🙅', '🙆', '🙇', '🙈', '🙉', '🙊', '🙋', '🙌', '🙍', '🙎', '🙏', '🚀', '🚁', '🚂', '🚃', '🚄', '🚅', '🚆', '🚇', '🚈', '🚉', '🚊', '🚋', '🚌', '🚍', '🚎', '🚏', '🚐', '🚑', '🚒', '🚓', '🚔', '🚕', '🚖', '🚗', '🚘', '🚙', '🚚', '🚛', '🚜', '🚝', '🚞', '🚟', '🚠', '🚡', '🚢', '🚣', '🚤', '🚥', '🚦', '🚧', '🚨', '🚩', '🚪', '🚫', '🚬', '🚭', '🚮', '🚯', '🚰', '🚱', '🚲', '🚳', '🚴', '🚵', '🚶', '🚷', '🚸', '🚹', '🚺', '🚻', '🚼', '🚽', '🚾', '🚿', '🛀', '🛁', '🛂', '🛃', '🛄', '🛅', '🛋', '🛌', '🛍', '🛎', '🛏', '🛐', '🛑', '🛒', '🛕', '🛖', '🛗', '🛜', '🛝', '🛞', '🛟', '🛠', '🛡', '🛢', '🛣', '🛤', '🛥', '🛩', '🛫', '🛬', '🛰', '🛳', '🛴', '🛵', '🛶', '🛷', '🛸', '🛹', '🛺', '🛻', '🛼', '🟠', '🟡', '🟢', '🟣', '🟤', '🟥', '🟦', '🟧', '🟨', '🟩', '🟪', '🟫', '🟰', '🤌', '🤍', '🤎', '🤏', '🤐', '🤑', '🤒', '🤓', '🤔', '🤕', '🤖', '🤗', '🤘', '🤙', '🤚', '🤛', '🤜', '🤝', '🤞', '🤟', '🤠', '🤡', '🤢', '🤣', '🤤', '🤥', '🤦', '🤧', '🤨', '🤩', '🤪', '🤫', '🤬', '🤭', '🤮', '🤯', '🤰', '🤱', '🤲', '🤳', '🤴', '🤵', '🤶', '🤷', '🤸', '🤹', '🤺', '🤼', '🤽', '🤾', '🤿', '🥀', '🥁', '🥂', '🥃', '🥄', '🥅', '🥇', '🥈', '🥉', '🥊', '🥋', '🥌', '🥍', '🥎', '🥏', '🥐', '🥑', '🥒', '🥓', '🥔', '🥕', '🥖', '🥗', '🥘', '🥙', '🥚', '🥛', '🥜', '🥝', '🥞', '🥟', '🥠', '🥡', '🥢', '🥣', '🥤', '🥥', '🥦', '🥧', '🥨', '🥩', '🥪', '🥫', '🥬', '🥭', '🥮', '🥯', '🥰', '🥱', '🥲', '🥳', '🥴', '🥵', '🥶', '🥷', '🥸', '🥹', '🥺', '🥻', '🥼', '🥽', '🥾', '🥿', '🦀', '🦁', '🦂', '🦃', '🦄', '🦅', '🦆', '🦇', '🦈', '🦉', '🦊', '🦋', '🦌', '🦍', '🦎', '🦏', '🦐', '🦑', '🦒', '🦓', '🦔', '🦕', '🦖', '🦗', '🦘', '🦙', '🦚', '🦛', '🦜', '🦝', '🦞', '🦟', '🦠', '🦡', '🦢', '🦣', '🦤', '🦥', '🦦', '🦧', '🦨', '🦩', '🦪', '🦫', '🦬', '🦭', '🦮', '🦯', '🦰', '🦱', '🦲', '🦳', '🦴', '🦵', '🦶', '🦷', '🦸', '🦹', '🦺', '🦻', '🦼', '🦽', '🦾', '🦿', '🧀', '🧁', '🧂', '🧃', '🧄', '🧅', '🧆', '🧇', '🧈', '🧉', '🧊', '🧋', '🧌', '🧍', '🧎', '🧏', '🧐', '🧑', '🧒', '🧓', '🧔', '🧕', '🧖', '🧗', '🧘', '🧙', '🧚', '🧛', '🧜', '🧝', '🧞', '🧟', '🧠', '🧡', '🧢', '🧣', '🧤', '🧥', '🧦', '🧧', '🧨', '🧩', '🧪', '🧫', '🧬', '🧭', '🧮', '🧯', '🧰', '🧱', '🧲', '🧳', '🧴', '🧵', '🧶', '🧷', '🧸', '🧹', '🧺', '🧻', '🧼', '🧽', '🧾', '🧿', '🩰', '🩱', '🩲', '🩳', '🩴', '🩵', '🩶', '🩷', '🩸', '🩹', '🩺', '🩻', '🩼', '🪀', '🪁', '🪂', '🪃', '🪄', '🪅', '🪆', '🪇', '🪈', '🪉', '🪏', '🪐', '🪑', '🪒', '🪓', '🪔', '🪕', '🪖', '🪗', '🪘', '🪙', '🪚', '🪛', '🪜', '🪝', '🪞', '🪟', '🪠', '🪡', '🪢', '🪣', '🪤', '🪥', '🪦', '🪧', '🪨', '🪩', '🪪', '🪫', '🪬', '🪭', '🪮', '🪯', '🪰', '🪱', '🪲', '🪳', '🪴', '🪵', '🪶', '🪷', '🪸', '🪹', '🪺', '🪻', '🪼', '🪽', '🪾', '🪿', '🫀', '🫁', '🫂', '🫃', '🫄', '🫅', '🫆', '🫎', '🫏', '🫐', '🫑', '🫒', '🫓', '🫔', '🫕', '🫖', '🫗', '🫘', '🫙', '🫚', '🫛', '🫜', '🫟', '🫠', '🫡', '🫢', '🫣', '🫤', '🫥', '🫦', '🫧', '🫨', '🫩', '🫰', '🫱', '🫲', '🫳', '🫴', '🫵', '🫶', '🫷', '🫸', '‼', '⁉', '™', 'ℹ', '↔', '↕', '↖', '↗', '↘', '↙', '↩', '↪', '⌚', '⌛', '⌨', '⏏', '⏩', '⏪', '⏫', '⏬', '⏭', '⏮', '⏯', '⏰', '⏱', '⏲', '⏳', '⏸', '⏹', '⏺', 'Ⓜ', '▪', '▫', '▶', '◀', '◻', '◼', '◽', '◾', '☀', '☁', '☂', '☃', '☄', '☎', '☑', '☔', '☕', '☘', '☝', '☠', '☢', '☣', '☦', '☪', '☮', '☯', '☸', '☹', '☺', '♀', '♂', '♈', '♉', '♊', '♋', '♌', '♍', '♎', '♏', '♐', '♑', '♒', '♓', '♟', '♠', '♣', '♥', '♦', '♨', '♻', '♾', '♿', '⚒', '⚓', '⚔', '⚕', '⚖', '⚗', '⚙', '⚛', '⚜', '⚠', '⚡', '⚧', '⚪', '⚫', '⚰', '⚱', '⚽', '⚾', '⛄', '⛅', '⛈', '⛎', '⛏', '⛑', '⛓', '⛔', '⛩', '⛪', '⛰', '⛱', '⛲', '⛳', '⛴', '⛵', '⛷', '⛸', '⛹', '⛺', '⛽', '✂', '✅', '✈', '✉', '✊', '✋', '✌', '✍', '✏', '✒', '✔', '✖', '✝', '✡', '✨', '✳', '✴', '❄', '❇', '❌', '❎', '❓', '❔', '❕', '❗', '❣', '❤', '➕', '➖', '➗', '➡', '➰', '➿', '⤴', '⤵', '⬅', '⬆', '⬇', '⬛', '⬜', '⭐', '⭕', '〰', '〽', '㊗', '㊙', '' ); 6351 $partials = array( '🀄', '🃏', '🅰', '🅱', '🅾', '🅿', '🆎', '🆑', '🆒', '🆓', '🆔', '🆕', '🆖', '🆗', '🆘', '🆙', '🆚', '🇦', '🇨', '🇩', '🇪', '🇫', '🇬', '🇮', '🇱', '🇲', '🇴', '🇶', '🇷', '🇸', '🇹', '🇺', '🇼', '🇽', '🇿', '🇧', '🇭', '🇯', '🇳', '🇻', '🇾', '🇰', '🇵', '🈁', '🈂', '🈚', '🈯', '🈲', '🈳', '🈴', '🈵', '🈶', '🈷', '🈸', '🈹', '🈺', '🉐', '🉑', '🌀', '🌁', '🌂', '🌃', '🌄', '🌅', '🌆', '🌇', '🌈', '🌉', '🌊', '🌋', '🌌', '🌍', '🌎', '🌏', '🌐', '🌑', '🌒', '🌓', '🌔', '🌕', '🌖', '🌗', '🌘', '🌙', '🌚', '🌛', '🌜', '🌝', '🌞', '🌟', '🌠', '🌡', '🌤', '🌥', '🌦', '🌧', '🌨', '🌩', '🌪', '🌫', '🌬', '🌭', '🌮', '🌯', '🌰', '🌱', '🌲', '🌳', '🌴', '🌵', '🌶', '🌷', '🌸', '🌹', '🌺', '🌻', '🌼', '🌽', '🌾', '🌿', '🍀', '🍁', '🍂', '🍃', '🍄', '‍', '🟫', '🍅', '🍆', '🍇', '🍈', '🍉', '🍊', '🍋', '🟩', '🍌', '🍍', '🍎', '🍏', '🍐', '🍑', '🍒', '🍓', '🍔', '🍕', '🍖', '🍗', '🍘', '🍙', '🍚', '🍛', '🍜', '🍝', '🍞', '🍟', '🍠', '🍡', '🍢', '🍣', '🍤', '🍥', '🍦', '🍧', '🍨', '🍩', '🍪', '🍫', '🍬', '🍭', '🍮', '🍯', '🍰', '🍱', '🍲', '🍳', '🍴', '🍵', '🍶', '🍷', '🍸', '🍹', '🍺', '🍻', '🍼', '🍽', '🍾', '🍿', '🎀', '🎁', '🎂', '🎃', '🎄', '🎅', '🏻', '🏼', '🏽', '🏾', '🏿', '🎆', '🎇', '🎈', '🎉', '🎊', '🎋', '🎌', '🎍', '🎎', '🎏', '🎐', '🎑', '🎒', '🎓', '🎖', '🎗', '🎙', '🎚', '🎛', '🎞', '🎟', '🎠', '🎡', '🎢', '🎣', '🎤', '🎥', '🎦', '🎧', '🎨', '🎩', '🎪', '🎫', '🎬', '🎭', '🎮', '🎯', '🎰', '🎱', '🎲', '🎳', '🎴', '🎵', '🎶', '🎷', '🎸', '🎹', '🎺', '🎻', '🎼', '🎽', '🎾', '🎿', '🏀', '🏁', '🏂', '🏃', '♀', '️', '➡', '♂', '🏄', '🏅', '🏆', '🏇', '🏈', '🏉', '🏊', '🏋', '🏌', '🏍', '🏎', '🏏', '🏐', '🏑', '🏒', '🏓', '🏔', '🏕', '🏖', '🏗', '🏘', '🏙', '🏚', '🏛', '🏜', '🏝', '🏞', '🏟', '🏠', '🏡', '🏢', '🏣', '🏤', '🏥', '🏦', '🏧', '🏨', '🏩', '🏪', '🏫', '🏬', '🏭', '🏮', '🏯', '🏰', '🏳', '⚧', '🏴', '☠', '󠁧', '󠁢', '󠁥', '󠁮', '󠁿', '󠁳', '󠁣', '󠁴', '󠁷', '󠁬', '🏵', '🏷', '🏸', '🏹', '🏺', '🐀', '🐁', '🐂', '🐃', '🐄', '🐅', '🐆', '🐇', '🐈', '⬛', '🐉', '🐊', '🐋', '🐌', '🐍', '🐎', '🐏', '🐐', '🐑', '🐒', '🐓', '🐔', '🐕', '🦺', '🐖', '🐗', '🐘', '🐙', '🐚', '🐛', '🐜', '🐝', '🐞', '🐟', '🐠', '🐡', '🐢', '🐣', '🐤', '🐥', '🐦', '🔥', '🐧', '🐨', '🐩', '🐪', '🐫', '🐬', '🐭', '🐮', '🐯', '🐰', '🐱', '🐲', '🐳', '🐴', '🐵', '🐶', '🐷', '🐸', '🐹', '🐺', '🐻', '❄', '🐼', '🐽', '🐾', '🐿', '👀', '👁', '🗨', '👂', '👃', '👄', '👅', '👆', '👇', '👈', '👉', '👊', '👋', '👌', '👍', '👎', '👏', '👐', '👑', '👒', '👓', '👔', '👕', '👖', '👗', '👘', '👙', '👚', '👛', '👜', '👝', '👞', '👟', '👠', '👡', '👢', '👣', '👤', '👥', '👦', '👧', '👨', '💻', '💼', '🔧', '🔬', '🚀', '🚒', '🤝', '🦯', '🦰', '🦱', '🦲', '🦳', '🦼', '🦽', '⚕', '⚖', '✈', '❤', '💋', '👩', '👪', '👫', '👬', '👭', '👮', '👯', '👰', '👱', '👲', '👳', '👴', '👵', '👶', '👷', '👸', '👹', '👺', '👻', '👼', '👽', '👾', '👿', '💀', '💁', '💂', '💃', '💄', '💅', '💆', '💇', '💈', '💉', '💊', '💌', '💍', '💎', '💏', '💐', '💑', '💒', '💓', '💔', '💕', '💖', '💗', '💘', '💙', '💚', '💛', '💜', '💝', '💞', '💟', '💠', '💡', '💢', '💣', '💤', '💥', '💦', '💧', '💨', '💩', '💪', '💫', '💬', '💭', '💮', '💯', '💰', '💱', '💲', '💳', '💴', '💵', '💶', '💷', '💸', '💹', '💺', '💽', '💾', '💿', '📀', '📁', '📂', '📃', '📄', '📅', '📆', '📇', '📈', '📉', '📊', '📋', '📌', '📍', '📎', '📏', '📐', '📑', '📒', '📓', '📔', '📕', '📖', '📗', '📘', '📙', '📚', '📛', '📜', '📝', '📞', '📟', '📠', '📡', '📢', '📣', '📤', '📥', '📦', '📧', '📨', '📩', '📪', '📫', '📬', '📭', '📮', '📯', '📰', '📱', '📲', '📳', '📴', '📵', '📶', '📷', '📸', '📹', '📺', '📻', '📼', '📽', '📿', '🔀', '🔁', '🔂', '🔃', '🔄', '🔅', '🔆', '🔇', '🔈', '🔉', '🔊', '🔋', '🔌', '🔍', '🔎', '🔏', '🔐', '🔑', '🔒', '🔓', '🔔', '🔕', '🔖', '🔗', '🔘', '🔙', '🔚', '🔛', '🔜', '🔝', '🔞', '🔟', '🔠', '🔡', '🔢', '🔣', '🔤', '🔦', '🔨', '🔩', '🔪', '🔫', '🔭', '🔮', '🔯', '🔰', '🔱', '🔲', '🔳', '🔴', '🔵', '🔶', '🔷', '🔸', '🔹', '🔺', '🔻', '🔼', '🔽', '🕉', '🕊', '🕋', '🕌', '🕍', '🕎', '🕐', '🕑', '🕒', '🕓', '🕔', '🕕', '🕖', '🕗', '🕘', '🕙', '🕚', '🕛', '🕜', '🕝', '🕞', '🕟', '🕠', '🕡', '🕢', '🕣', '🕤', '🕥', '🕦', '🕧', '🕯', '🕰', '🕳', '🕴', '🕵', '🕶', '🕷', '🕸', '🕹', '🕺', '🖇', '🖊', '🖋', '🖌', '🖍', '🖐', '🖕', '🖖', '🖤', '🖥', '🖨', '🖱', '🖲', '🖼', '🗂', '🗃', '🗄', '🗑', '🗒', '🗓', '🗜', '🗝', '🗞', '🗡', '🗣', '🗯', '🗳', '🗺', '🗻', '🗼', '🗽', '🗾', '🗿', '😀', '😁', '😂', '😃', '😄', '😅', '😆', '😇', '😈', '😉', '😊', '😋', '😌', '😍', '😎', '😏', '😐', '😑', '😒', '😓', '😔', '😕', '😖', '😗', '😘', '😙', '😚', '😛', '😜', '😝', '😞', '😟', '😠', '😡', '😢', '😣', '😤', '😥', '😦', '😧', '😨', '😩', '😪', '😫', '😬', '😭', '😮', '😯', '😰', '😱', '😲', '😳', '😴', '😵', '😶', '😷', '😸', '😹', '😺', '😻', '😼', '😽', '😾', '😿', '🙀', '🙁', '🙂', '↔', '↕', '🙃', '🙄', '🙅', '🙆', '🙇', '🙈', '🙉', '🙊', '🙋', '🙌', '🙍', '🙎', '🙏', '🚁', '🚂', '🚃', '🚄', '🚅', '🚆', '🚇', '🚈', '🚉', '🚊', '🚋', '🚌', '🚍', '🚎', '🚏', '🚐', '🚑', '🚓', '🚔', '🚕', '🚖', '🚗', '🚘', '🚙', '🚚', '🚛', '🚜', '🚝', '🚞', '🚟', '🚠', '🚡', '🚢', '🚣', '🚤', '🚥', '🚦', '🚧', '🚨', '🚩', '🚪', '🚫', '🚬', '🚭', '🚮', '🚯', '🚰', '🚱', '🚲', '🚳', '🚴', '🚵', '🚶', '🚷', '🚸', '🚹', '🚺', '🚻', '🚼', '🚽', '🚾', '🚿', '🛀', '🛁', '🛂', '🛃', '🛄', '🛅', '🛋', '🛌', '🛍', '🛎', '🛏', '🛐', '🛑', '🛒', '🛕', '🛖', '🛗', '🛜', '🛝', '🛞', '🛟', '🛠', '🛡', '🛢', '🛣', '🛤', '🛥', '🛩', '🛫', '🛬', '🛰', '🛳', '🛴', '🛵', '🛶', '🛷', '🛸', '🛹', '🛺', '🛻', '🛼', '🟠', '🟡', '🟢', '🟣', '🟤', '🟥', '🟦', '🟧', '🟨', '🟪', '🟰', '🤌', '🤍', '🤎', '🤏', '🤐', '🤑', '🤒', '🤓', '🤔', '🤕', '🤖', '🤗', '🤘', '🤙', '🤚', '🤛', '🤜', '🤞', '🤟', '🤠', '🤡', '🤢', '🤣', '🤤', '🤥', '🤦', '🤧', '🤨', '🤩', '🤪', '🤫', '🤬', '🤭', '🤮', '🤯', '🤰', '🤱', '🤲', '🤳', '🤴', '🤵', '🤶', '🤷', '🤸', '🤹', '🤺', '🤼', '🤽', '🤾', '🤿', '🥀', '🥁', '🥂', '🥃', '🥄', '🥅', '🥇', '🥈', '🥉', '🥊', '🥋', '🥌', '🥍', '🥎', '🥏', '🥐', '🥑', '🥒', '🥓', '🥔', '🥕', '🥖', '🥗', '🥘', '🥙', '🥚', '🥛', '🥜', '🥝', '🥞', '🥟', '🥠', '🥡', '🥢', '🥣', '🥤', '🥥', '🥦', '🥧', '🥨', '🥩', '🥪', '🥫', '🥬', '🥭', '🥮', '🥯', '🥰', '🥱', '🥲', '🥳', '🥴', '🥵', '🥶', '🥷', '🥸', '🥹', '🥺', '🥻', '🥼', '🥽', '🥾', '🥿', '🦀', '🦁', '🦂', '🦃', '🦄', '🦅', '🦆', '🦇', '🦈', '🦉', '🦊', '🦋', '🦌', '🦍', '🦎', '🦏', '🦐', '🦑', '🦒', '🦓', '🦔', '🦕', '🦖', '🦗', '🦘', '🦙', '🦚', '🦛', '🦜', '🦝', '🦞', '🦟', '🦠', '🦡', '🦢', '🦣', '🦤', '🦥', '🦦', '🦧', '🦨', '🦩', '🦪', '🦫', '🦬', '🦭', '🦮', '🦴', '🦵', '🦶', '🦷', '🦸', '🦹', '🦻', '🦾', '🦿', '🧀', '🧁', '🧂', '🧃', '🧄', '🧅', '🧆', '🧇', '🧈', '🧉', '🧊', '🧋', '🧌', '🧍', '🧎', '🧏', '🧐', '🧑', '🧒', '🧓', '🧔', '🧕', '🧖', '🧗', '🧘', '🧙', '🧚', '🧛', '🧜', '🧝', '🧞', '🧟', '🧠', '🧡', '🧢', '🧣', '🧤', '🧥', '🧦', '🧧', '🧨', '🧩', '🧪', '🧫', '🧬', '🧭', '🧮', '🧯', '🧰', '🧱', '🧲', '🧳', '🧴', '🧵', '🧶', '🧷', '🧸', '🧹', '🧺', '🧻', '🧼', '🧽', '🧾', '🧿', '🩰', '🩱', '🩲', '🩳', '🩴', '🩵', '🩶', '🩷', '🩸', '🩹', '🩺', '🩻', '🩼', '🪀', '🪁', '🪂', '🪃', '🪄', '🪅', '🪆', '🪇', '🪈', '🪉', '🪏', '🪐', '🪑', '🪒', '🪓', '🪔', '🪕', '🪖', '🪗', '🪘', '🪙', '🪚', '🪛', '🪜', '🪝', '🪞', '🪟', '🪠', '🪡', '🪢', '🪣', '🪤', '🪥', '🪦', '🪧', '🪨', '🪩', '🪪', '🪫', '🪬', '🪭', '🪮', '🪯', '🪰', '🪱', '🪲', '🪳', '🪴', '🪵', '🪶', '🪷', '🪸', '🪹', '🪺', '🪻', '🪼', '🪽', '🪾', '🪿', '🫀', '🫁', '🫂', '🫃', '🫄', '🫅', '🫆', '🫎', '🫏', '🫐', '🫑', '🫒', '🫓', '🫔', '🫕', '🫖', '🫗', '🫘', '🫙', '🫚', '🫛', '🫜', '🫟', '🫠', '🫡', '🫢', '🫣', '🫤', '🫥', '🫦', '🫧', '🫨', '🫩', '🫰', '🫱', '🫲', '🫳', '🫴', '🫵', '🫶', '🫷', '🫸', '‼', '⁉', '™', 'ℹ', '↖', '↗', '↘', '↙', '↩', '↪', '⃣', '⌚', '⌛', '⌨', '⏏', '⏩', '⏪', '⏫', '⏬', '⏭', '⏮', '⏯', '⏰', '⏱', '⏲', '⏳', '⏸', '⏹', '⏺', 'Ⓜ', '▪', '▫', '▶', '◀', '◻', '◼', '◽', '◾', '☀', '☁', '☂', '☃', '☄', '☎', '☑', '☔', '☕', '☘', '☝', '☢', '☣', '☦', '☪', '☮', '☯', '☸', '☹', '☺', '♈', '♉', '♊', '♋', '♌', '♍', '♎', '♏', '♐', '♑', '♒', '♓', '♟', '♠', '♣', '♥', '♦', '♨', '♻', '♾', '♿', '⚒', '⚓', '⚔', '⚗', '⚙', '⚛', '⚜', '⚠', '⚡', '⚪', '⚫', '⚰', '⚱', '⚽', '⚾', '⛄', '⛅', '⛈', '⛎', '⛏', '⛑', '⛓', '⛔', '⛩', '⛪', '⛰', '⛱', '⛲', '⛳', '⛴', '⛵', '⛷', '⛸', '⛹', '⛺', '⛽', '✂', '✅', '✉', '✊', '✋', '✌', '✍', '✏', '✒', '✔', '✖', '✝', '✡', '✨', '✳', '✴', '❇', '❌', '❎', '❓', '❔', '❕', '❗', '❣', '➕', '➖', '➗', '➰', '➿', '⤴', '⤵', '⬅', '⬆', '⬇', '⬜', '⭐', '⭕', '〰', '〽', '㊗', '㊙', '' ); 6352 // END: emoji arrays 6353 6354 if ( 'entities' === $type ) { 6355 return $entities; 6356 } 6357 6358 return $partials; 6359 } 6360 6361 /** 6362 * Shortens a URL, to be used as link text. 6363 * 6364 * @since 1.2.0 6365 * @since 4.4.0 Moved to wp-includes/formatting.php from wp-admin/includes/misc.php and added $length param. 6366 * 6367 * @param string $url URL to shorten. 6368 * @param int $length Optional. Maximum length of the shortened URL. Default 35 characters. 6369 * @return string Shortened URL. 6370 */ 6371 function url_shorten( $url, $length = 35 ) { 6372 $stripped = str_replace( array( 'https://', 'http://', 'www.' ), '', $url ); 6373 $short_url = untrailingslashit( $stripped ); 6374 6375 if ( strlen( $short_url ) > $length ) { 6376 $short_url = substr( $short_url, 0, $length - 3 ) . '…'; 6377 } 6378 return $short_url; 6379 } 6380 6381 /** 6382 * Sanitizes a hex color. 6383 * 6384 * Returns either '', a 3 or 6 digit hex color (with #), or nothing. 6385 * For sanitizing values without a #, see sanitize_hex_color_no_hash(). 6386 * 6387 * @since 3.4.0 6388 * 6389 * @param string $color 6390 * @return string|void 6391 */ 6392 function sanitize_hex_color( $color ) { 6393 if ( '' === $color ) { 6394 return ''; 6395 } 6396 6397 // 3 or 6 hex digits, or the empty string. 6398 if ( preg_match( '|^#([A-Fa-f0-9]{3}){1,2}$|', $color ) ) { 6399 return $color; 6400 } 6401 } 6402 6403 /** 6404 * Sanitizes a hex color without a hash. Use sanitize_hex_color() when possible. 6405 * 6406 * Saving hex colors without a hash puts the burden of adding the hash on the 6407 * UI, which makes it difficult to use or upgrade to other color types such as 6408 * rgba, hsl, rgb, and HTML color names. 6409 * 6410 * Returns either '', a 3 or 6 digit hex color (without a #), or null. 6411 * 6412 * @since 3.4.0 6413 * 6414 * @param string $color 6415 * @return string|null 6416 */ 6417 function sanitize_hex_color_no_hash( $color ) { 6418 $color = ltrim( $color, '#' ); 6419 6420 if ( '' === $color ) { 6421 return ''; 6422 } 6423 6424 return sanitize_hex_color( '#' . $color ) ? $color : null; 6425 } 6426 6427 /** 6428 * Ensures that any hex color is properly hashed. 6429 * Otherwise, returns value untouched. 6430 * 6431 * This method should only be necessary if using sanitize_hex_color_no_hash(). 6432 * 6433 * @since 3.4.0 6434 * 6435 * @param string $color 6436 * @return string 6437 */ 6438 function maybe_hash_hex_color( $color ) { 6439 $unhashed = sanitize_hex_color_no_hash( $color ); 6440 if ( $unhashed ) { 6441 return '#' . $unhashed; 6442 } 6443 6444 return $color; 6445 }
title
Description
Body
title
Description
Body
title
Description
Body
title
Body
| Generated : Thu Sep 4 08:20:02 2025 | Cross-referenced by PHPXref |