[ Index ]

PHP Cross Reference of WordPress Trunk (Updated Daily)

Search

title

Body

[close]

/wp-includes/ -> formatting.php (source)

   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   *     &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221; &#8230;
  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( '&#8220;', 'opening curly double quote' );
  85          /* translators: Closing curly double quote. */
  86          $closing_quote = _x( '&#8221;', 'closing curly double quote' );
  87  
  88          /* translators: Apostrophe, for example in 'cause or can't. */
  89          $apos = _x( '&#8217;', 'apostrophe' );
  90  
  91          /* translators: Prime, for example in 9' (nine feet). */
  92          $prime = _x( '&#8242;', 'prime' );
  93          /* translators: Double prime, for example in 9" (nine inches). */
  94          $double_prime = _x( '&#8243;', 'double prime' );
  95  
  96          /* translators: Opening curly single quote. */
  97          $opening_single_quote = _x( '&#8216;', 'opening curly single quote' );
  98          /* translators: Closing curly single quote. */
  99          $closing_single_quote = _x( '&#8217;', 'closing curly single quote' );
 100  
 101          /* translators: En dash. */
 102          $en_dash = _x( '&#8211;', 'en dash' );
 103          /* translators: Em dash. */
 104          $em_dash = _x( '&#8212;', '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                      '&#8217;tain&#8217;t,&#8217;twere,&#8217;twas,&#8217;tis,&#8217;twill,&#8217;til,&#8217;bout,&#8217;nuff,&#8217;round,&#8217;cause,&#8217;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( '&#8230;', $opening_quote, $closing_quote, ' &#8482;' ), $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|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
 159          }
 160          if ( "'" !== $apos || '"' !== $closing_quote ) {
 161              $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $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|[([{"\-]|&lt;|' . $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|[([{\-]|&lt;|' . $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 &#038; unless it already looks like an entity.
 254                  $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $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&#215;$2', $curl );
 296              }
 297  
 298              // Replace each & with &#038; unless it already looks like an entity.
 299              $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $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|[.,:;!?)}\\-\\]]|&gt;|" . $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          foreach ( $replace_pairs as $needle => $replace ) {
 766          }
 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   *
 880   * @param string $str The string to be checked
 881   * @return bool True if $str fits a UTF-8 model, false otherwise.
 882   */
 883  function seems_utf8( $str ) {
 884      mbstring_binary_safe_encoding();
 885      $length = strlen( $str );
 886      reset_mbstring_encoding();
 887  
 888      for ( $i = 0; $i < $length; $i++ ) {
 889          $c = ord( $str[ $i ] );
 890  
 891          if ( $c < 0x80 ) {
 892              $n = 0; // 0bbbbbbb
 893          } elseif ( ( $c & 0xE0 ) === 0xC0 ) {
 894              $n = 1; // 110bbbbb
 895          } elseif ( ( $c & 0xF0 ) === 0xE0 ) {
 896              $n = 2; // 1110bbbb
 897          } elseif ( ( $c & 0xF8 ) === 0xF0 ) {
 898              $n = 3; // 11110bbb
 899          } elseif ( ( $c & 0xFC ) === 0xF8 ) {
 900              $n = 4; // 111110bb
 901          } elseif ( ( $c & 0xFE ) === 0xFC ) {
 902              $n = 5; // 1111110b
 903          } else {
 904              return false; // Does not match any model.
 905          }
 906  
 907          for ( $j = 0; $j < $n; $j++ ) { // n bytes matching 10bbbbbb follow ?
 908              if ( ( ++$i === $length ) || ( ( ord( $str[ $i ] ) & 0xC0 ) !== 0x80 ) ) {
 909                  return false;
 910              }
 911          }
 912      }
 913  
 914      return true;
 915  }
 916  
 917  /**
 918   * Converts a number of special characters into their HTML entities.
 919   *
 920   * Specifically deals with: `&`, `<`, `>`, `"`, and `'`.
 921   *
 922   * `$quote_style` can be set to ENT_COMPAT to encode `"` to
 923   * `&quot;`, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
 924   *
 925   * @since 1.2.2
 926   * @since 5.5.0 `$quote_style` also accepts `ENT_XML1`.
 927   * @access private
 928   *
 929   * @param string       $text          The text which is to be encoded.
 930   * @param int|string   $quote_style   Optional. Converts double quotes if set to ENT_COMPAT,
 931   *                                    both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
 932   *                                    Converts single and double quotes, as well as converting HTML
 933   *                                    named entities (that are not also XML named entities) to their
 934   *                                    code points if set to ENT_XML1. Also compatible with old values;
 935   *                                    converting single quotes if set to 'single',
 936   *                                    double if set to 'double' or both if otherwise set.
 937   *                                    Default is ENT_NOQUOTES.
 938   * @param false|string $charset       Optional. The character encoding of the string. Default false.
 939   * @param bool         $double_encode Optional. Whether to encode existing HTML entities. Default false.
 940   * @return string The encoded text with HTML entities.
 941   */
 942  function _wp_specialchars( $text, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
 943      $text = (string) $text;
 944  
 945      if ( 0 === strlen( $text ) ) {
 946          return '';
 947      }
 948  
 949      // Don't bother if there are no specialchars - saves some processing.
 950      if ( ! preg_match( '/[&<>"\']/', $text ) ) {
 951          return $text;
 952      }
 953  
 954      // Account for the previous behavior of the function when the $quote_style is not an accepted value.
 955      if ( empty( $quote_style ) ) {
 956          $quote_style = ENT_NOQUOTES;
 957      } elseif ( ENT_XML1 === $quote_style ) {
 958          $quote_style = ENT_QUOTES | ENT_XML1;
 959      } elseif ( ! in_array( $quote_style, array( ENT_NOQUOTES, ENT_COMPAT, ENT_QUOTES, 'single', 'double' ), true ) ) {
 960          $quote_style = ENT_QUOTES;
 961      }
 962  
 963      $charset = _canonical_charset( $charset ? $charset : get_option( 'blog_charset' ) );
 964  
 965      $_quote_style = $quote_style;
 966  
 967      if ( 'double' === $quote_style ) {
 968          $quote_style  = ENT_COMPAT;
 969          $_quote_style = ENT_COMPAT;
 970      } elseif ( 'single' === $quote_style ) {
 971          $quote_style = ENT_NOQUOTES;
 972      }
 973  
 974      if ( ! $double_encode ) {
 975          /*
 976           * Guarantee every &entity; is valid, convert &garbage; into &amp;garbage;
 977           * This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
 978           */
 979          $text = wp_kses_normalize_entities( $text, ( $quote_style & ENT_XML1 ) ? 'xml' : 'html' );
 980      }
 981  
 982      $text = htmlspecialchars( $text, $quote_style, $charset, $double_encode );
 983  
 984      // Back-compat.
 985      if ( 'single' === $_quote_style ) {
 986          $text = str_replace( "'", '&#039;', $text );
 987      }
 988  
 989      return $text;
 990  }
 991  
 992  /**
 993   * Converts a number of HTML entities into their special characters.
 994   *
 995   * Specifically deals with: `&`, `<`, `>`, `"`, and `'`.
 996   *
 997   * `$quote_style` can be set to ENT_COMPAT to decode `"` entities,
 998   * or ENT_QUOTES to do both `"` and `'`. Default is ENT_NOQUOTES where no quotes are decoded.
 999   *
1000   * @since 2.8.0
1001   *
1002   * @param string     $text        The text which is to be decoded.
1003   * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
1004   *                                both single and double if set to ENT_QUOTES or
1005   *                                none if set to ENT_NOQUOTES.
1006   *                                Also compatible with old _wp_specialchars() values;
1007   *                                converting single quotes if set to 'single',
1008   *                                double if set to 'double' or both if otherwise set.
1009   *                                Default is ENT_NOQUOTES.
1010   * @return string The decoded text without HTML entities.
1011   */
1012  function wp_specialchars_decode( $text, $quote_style = ENT_NOQUOTES ) {
1013      $text = (string) $text;
1014  
1015      if ( 0 === strlen( $text ) ) {
1016          return '';
1017      }
1018  
1019      // Don't bother if there are no entities - saves a lot of processing.
1020      if ( ! str_contains( $text, '&' ) ) {
1021          return $text;
1022      }
1023  
1024      // Match the previous behavior of _wp_specialchars() when the $quote_style is not an accepted value.
1025      if ( empty( $quote_style ) ) {
1026          $quote_style = ENT_NOQUOTES;
1027      } elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
1028          $quote_style = ENT_QUOTES;
1029      }
1030  
1031      // More complete than get_html_translation_table( HTML_SPECIALCHARS ).
1032      $single      = array(
1033          '&#039;' => '\'',
1034          '&#x27;' => '\'',
1035      );
1036      $single_preg = array(
1037          '/&#0*39;/'   => '&#039;',
1038          '/&#x0*27;/i' => '&#x27;',
1039      );
1040      $double      = array(
1041          '&quot;' => '"',
1042          '&#034;' => '"',
1043          '&#x22;' => '"',
1044      );
1045      $double_preg = array(
1046          '/&#0*34;/'   => '&#034;',
1047          '/&#x0*22;/i' => '&#x22;',
1048      );
1049      $others      = array(
1050          '&lt;'   => '<',
1051          '&#060;' => '<',
1052          '&gt;'   => '>',
1053          '&#062;' => '>',
1054          '&amp;'  => '&',
1055          '&#038;' => '&',
1056          '&#x26;' => '&',
1057      );
1058      $others_preg = array(
1059          '/&#0*60;/'   => '&#060;',
1060          '/&#0*62;/'   => '&#062;',
1061          '/&#0*38;/'   => '&#038;',
1062          '/&#x0*26;/i' => '&#x26;',
1063      );
1064  
1065      if ( ENT_QUOTES === $quote_style ) {
1066          $translation      = array_merge( $single, $double, $others );
1067          $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
1068      } elseif ( ENT_COMPAT === $quote_style || 'double' === $quote_style ) {
1069          $translation      = array_merge( $double, $others );
1070          $translation_preg = array_merge( $double_preg, $others_preg );
1071      } elseif ( 'single' === $quote_style ) {
1072          $translation      = array_merge( $single, $others );
1073          $translation_preg = array_merge( $single_preg, $others_preg );
1074      } elseif ( ENT_NOQUOTES === $quote_style ) {
1075          $translation      = $others;
1076          $translation_preg = $others_preg;
1077      }
1078  
1079      // Remove zero padding on numeric entities.
1080      $text = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $text );
1081  
1082      // Replace characters according to translation table.
1083      return strtr( $text, $translation );
1084  }
1085  
1086  /**
1087   * Checks for invalid UTF8 in a string.
1088   *
1089   * @since 2.8.0
1090   *
1091   * @param string $text   The text which is to be checked.
1092   * @param bool   $strip  Optional. Whether to attempt to strip out invalid UTF8. Default false.
1093   * @return string The checked text.
1094   */
1095  function wp_check_invalid_utf8( $text, $strip = false ) {
1096      $text = (string) $text;
1097  
1098      if ( 0 === strlen( $text ) ) {
1099          return '';
1100      }
1101  
1102      // Store the site charset as a static to avoid multiple calls to get_option().
1103      static $is_utf8 = null;
1104      if ( ! isset( $is_utf8 ) ) {
1105          $is_utf8 = is_utf8_charset();
1106      }
1107      if ( ! $is_utf8 ) {
1108          return $text;
1109      }
1110  
1111      // Check for support for utf8 in the installed PCRE library once and store the result in a static.
1112      static $utf8_pcre = null;
1113      if ( ! isset( $utf8_pcre ) ) {
1114          // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged
1115          $utf8_pcre = @preg_match( '/^./u', 'a' );
1116      }
1117      // We can't demand utf8 in the PCRE installation, so just return the string in those cases.
1118      if ( ! $utf8_pcre ) {
1119          return $text;
1120      }
1121  
1122      // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged -- preg_match fails when it encounters invalid UTF8 in $text.
1123      if ( 1 === @preg_match( '/^./us', $text ) ) {
1124          return $text;
1125      }
1126  
1127      // Attempt to strip the bad chars if requested (not recommended).
1128      if ( $strip && function_exists( 'iconv' ) ) {
1129          return iconv( 'utf-8', 'utf-8', $text );
1130      }
1131  
1132      return '';
1133  }
1134  
1135  /**
1136   * Encodes the Unicode values to be used in the URI.
1137   *
1138   * @since 1.5.0
1139   * @since 5.8.3 Added the `encode_ascii_characters` parameter.
1140   *
1141   * @param string $utf8_string             String to encode.
1142   * @param int    $length                  Max length of the string
1143   * @param bool   $encode_ascii_characters Whether to encode ascii characters such as < " '
1144   * @return string String with Unicode encoded for URI.
1145   */
1146  function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters = false ) {
1147      $unicode        = '';
1148      $values         = array();
1149      $num_octets     = 1;
1150      $unicode_length = 0;
1151  
1152      mbstring_binary_safe_encoding();
1153      $string_length = strlen( $utf8_string );
1154      reset_mbstring_encoding();
1155  
1156      for ( $i = 0; $i < $string_length; $i++ ) {
1157  
1158          $value = ord( $utf8_string[ $i ] );
1159  
1160          if ( $value < 128 ) {
1161              $char                = chr( $value );
1162              $encoded_char        = $encode_ascii_characters ? rawurlencode( $char ) : $char;
1163              $encoded_char_length = strlen( $encoded_char );
1164              if ( $length && ( $unicode_length + $encoded_char_length ) > $length ) {
1165                  break;
1166              }
1167              $unicode        .= $encoded_char;
1168              $unicode_length += $encoded_char_length;
1169          } else {
1170              if ( count( $values ) === 0 ) {
1171                  if ( $value < 224 ) {
1172                      $num_octets = 2;
1173                  } elseif ( $value < 240 ) {
1174                      $num_octets = 3;
1175                  } else {
1176                      $num_octets = 4;
1177                  }
1178              }
1179  
1180              $values[] = $value;
1181  
1182              if ( $length && ( $unicode_length + ( $num_octets * 3 ) ) > $length ) {
1183                  break;
1184              }
1185              if ( count( $values ) === $num_octets ) {
1186                  for ( $j = 0; $j < $num_octets; $j++ ) {
1187                      $unicode .= '%' . dechex( $values[ $j ] );
1188                  }
1189  
1190                  $unicode_length += $num_octets * 3;
1191  
1192                  $values     = array();
1193                  $num_octets = 1;
1194              }
1195          }
1196      }
1197  
1198      return $unicode;
1199  }
1200  
1201  /**
1202   * Converts all accent characters to ASCII characters.
1203   *
1204   * If there are no accent characters, then the string given is just returned.
1205   *
1206   * **Accent characters converted:**
1207   *
1208   * Currency signs:
1209   *
1210   * |   Code   | Glyph | Replacement |     Description     |
1211   * | -------- | ----- | ----------- | ------------------- |
1212   * | U+00A3   | £     | (empty)     | British Pound sign  |
1213   * | U+20AC   | €     | E           | Euro sign           |
1214   *
1215   * Decompositions for Latin-1 Supplement:
1216   *
1217   * |  Code   | Glyph | Replacement |               Description              |
1218   * | ------- | ----- | ----------- | -------------------------------------- |
1219   * | U+00AA  | ª     | a           | Feminine ordinal indicator             |
1220   * | U+00BA  | º     | o           | Masculine ordinal indicator            |
1221   * | U+00C0  | À     | A           | Latin capital letter A with grave      |
1222   * | U+00C1  | Á     | A           | Latin capital letter A with acute      |
1223   * | U+00C2  | Â     | A           | Latin capital letter A with circumflex |
1224   * | U+00C3  | Ã     | A           | Latin capital letter A with tilde      |
1225   * | U+00C4  | Ä     | A           | Latin capital letter A with diaeresis  |
1226   * | U+00C5  | Å     | A           | Latin capital letter A with ring above |
1227   * | U+00C6  | Æ     | AE          | Latin capital letter AE                |
1228   * | U+00C7  | Ç     | C           | Latin capital letter C with cedilla    |
1229   * | U+00C8  | È     | E           | Latin capital letter E with grave      |
1230   * | U+00C9  | É     | E           | Latin capital letter E with acute      |
1231   * | U+00CA  | Ê     | E           | Latin capital letter E with circumflex |
1232   * | U+00CB  | Ë     | E           | Latin capital letter E with diaeresis  |
1233   * | U+00CC  | Ì     | I           | Latin capital letter I with grave      |
1234   * | U+00CD  | Í     | I           | Latin capital letter I with acute      |
1235   * | U+00CE  | Î     | I           | Latin capital letter I with circumflex |
1236   * | U+00CF  | Ï     | I           | Latin capital letter I with diaeresis  |
1237   * | U+00D0  | Ð     | D           | Latin capital letter Eth               |
1238   * | U+00D1  | Ñ     | N           | Latin capital letter N with tilde      |
1239   * | U+00D2  | Ò     | O           | Latin capital letter O with grave      |
1240   * | U+00D3  | Ó     | O           | Latin capital letter O with acute      |
1241   * | U+00D4  | Ô     | O           | Latin capital letter O with circumflex |
1242   * | U+00D5  | Õ     | O           | Latin capital letter O with tilde      |
1243   * | U+00D6  | Ö     | O           | Latin capital letter O with diaeresis  |
1244   * | U+00D8  | Ø     | O           | Latin capital letter O with stroke     |
1245   * | U+00D9  | Ù     | U           | Latin capital letter U with grave      |
1246   * | U+00DA  | Ú     | U           | Latin capital letter U with acute      |
1247   * | U+00DB  | Û     | U           | Latin capital letter U with circumflex |
1248   * | U+00DC  | Ü     | U           | Latin capital letter U with diaeresis  |
1249   * | U+00DD  | Ý     | Y           | Latin capital letter Y with acute      |
1250   * | U+00DE  | Þ     | TH          | Latin capital letter Thorn             |
1251   * | U+00DF  | ß     | s           | Latin small letter sharp s             |
1252   * | U+00E0  | à     | a           | Latin small letter a with grave        |
1253   * | U+00E1  | á     | a           | Latin small letter a with acute        |
1254   * | U+00E2  | â     | a           | Latin small letter a with circumflex   |
1255   * | U+00E3  | ã     | a           | Latin small letter a with tilde        |
1256   * | U+00E4  | ä     | a           | Latin small letter a with diaeresis    |
1257   * | U+00E5  | å     | a           | Latin small letter a with ring above   |
1258   * | U+00E6  | æ     | ae          | Latin small letter ae                  |
1259   * | U+00E7  | ç     | c           | Latin small letter c with cedilla      |
1260   * | U+00E8  | è     | e           | Latin small letter e with grave        |
1261   * | U+00E9  | é     | e           | Latin small letter e with acute        |
1262   * | U+00EA  | ê     | e           | Latin small letter e with circumflex   |
1263   * | U+00EB  | ë     | e           | Latin small letter e with diaeresis    |
1264   * | U+00EC  | ì     | i           | Latin small letter i with grave        |
1265   * | U+00ED  | í     | i           | Latin small letter i with acute        |
1266   * | U+00EE  | î     | i           | Latin small letter i with circumflex   |
1267   * | U+00EF  | ï     | i           | Latin small letter i with diaeresis    |
1268   * | U+00F0  | ð     | d           | Latin small letter Eth                 |
1269   * | U+00F1  | ñ     | n           | Latin small letter n with tilde        |
1270   * | U+00F2  | ò     | o           | Latin small letter o with grave        |
1271   * | U+00F3  | ó     | o           | Latin small letter o with acute        |
1272   * | U+00F4  | ô     | o           | Latin small letter o with circumflex   |
1273   * | U+00F5  | õ     | o           | Latin small letter o with tilde        |
1274   * | U+00F6  | ö     | o           | Latin small letter o with diaeresis    |
1275   * | U+00F8  | ø     | o           | Latin small letter o with stroke       |
1276   * | U+00F9  | ù     | u           | Latin small letter u with grave        |
1277   * | U+00FA  | ú     | u           | Latin small letter u with acute        |
1278   * | U+00FB  | û     | u           | Latin small letter u with circumflex   |
1279   * | U+00FC  | ü     | u           | Latin small letter u with diaeresis    |
1280   * | U+00FD  | ý     | y           | Latin small letter y with acute        |
1281   * | U+00FE  | þ     | th          | Latin small letter Thorn               |
1282   * | U+00FF  | ÿ     | y           | Latin small letter y with diaeresis    |
1283   *
1284   * Decompositions for Latin Extended-A:
1285   *
1286   * |  Code   | Glyph | Replacement |                    Description                    |
1287   * | ------- | ----- | ----------- | ------------------------------------------------- |
1288   * | U+0100  | Ā     | A           | Latin capital letter A with macron                |
1289   * | U+0101  | ā     | a           | Latin small letter a with macron                  |
1290   * | U+0102  | Ă     | A           | Latin capital letter A with breve                 |
1291   * | U+0103  | ă     | a           | Latin small letter a with breve                   |
1292   * | U+0104  | Ą     | A           | Latin capital letter A with ogonek                |
1293   * | U+0105  | ą     | a           | Latin small letter a with ogonek                  |
1294   * | U+01006 | Ć     | C           | Latin capital letter C with acute                 |
1295   * | U+0107  | ć     | c           | Latin small letter c with acute                   |
1296   * | U+0108  | Ĉ     | C           | Latin capital letter C with circumflex            |
1297   * | U+0109  | ĉ     | c           | Latin small letter c with circumflex              |
1298   * | U+010A  | Ċ     | C           | Latin capital letter C with dot above             |
1299   * | U+010B  | ċ     | c           | Latin small letter c with dot above               |
1300   * | U+010C  | Č     | C           | Latin capital letter C with caron                 |
1301   * | U+010D  | č     | c           | Latin small letter c with caron                   |
1302   * | U+010E  | Ď     | D           | Latin capital letter D with caron                 |
1303   * | U+010F  | ď     | d           | Latin small letter d with caron                   |
1304   * | U+0110  | Đ     | D           | Latin capital letter D with stroke                |
1305   * | U+0111  | đ     | d           | Latin small letter d with stroke                  |
1306   * | U+0112  | Ē     | E           | Latin capital letter E with macron                |
1307   * | U+0113  | ē     | e           | Latin small letter e with macron                  |
1308   * | U+0114  | Ĕ     | E           | Latin capital letter E with breve                 |
1309   * | U+0115  | ĕ     | e           | Latin small letter e with breve                   |
1310   * | U+0116  | Ė     | E           | Latin capital letter E with dot above             |
1311   * | U+0117  | ė     | e           | Latin small letter e with dot above               |
1312   * | U+0118  | Ę     | E           | Latin capital letter E with ogonek                |
1313   * | U+0119  | ę     | e           | Latin small letter e with ogonek                  |
1314   * | U+011A  | Ě     | E           | Latin capital letter E with caron                 |
1315   * | U+011B  | ě     | e           | Latin small letter e with caron                   |
1316   * | U+011C  | Ĝ     | G           | Latin capital letter G with circumflex            |
1317   * | U+011D  | ĝ     | g           | Latin small letter g with circumflex              |
1318   * | U+011E  | Ğ     | G           | Latin capital letter G with breve                 |
1319   * | U+011F  | ğ     | g           | Latin small letter g with breve                   |
1320   * | U+0120  | Ġ     | G           | Latin capital letter G with dot above             |
1321   * | U+0121  | ġ     | g           | Latin small letter g with dot above               |
1322   * | U+0122  | Ģ     | G           | Latin capital letter G with cedilla               |
1323   * | U+0123  | ģ     | g           | Latin small letter g with cedilla                 |
1324   * | U+0124  | Ĥ     | H           | Latin capital letter H with circumflex            |
1325   * | U+0125  | ĥ     | h           | Latin small letter h with circumflex              |
1326   * | U+0126  | Ħ     | H           | Latin capital letter H with stroke                |
1327   * | U+0127  | ħ     | h           | Latin small letter h with stroke                  |
1328   * | U+0128  | Ĩ     | I           | Latin capital letter I with tilde                 |
1329   * | U+0129  | ĩ     | i           | Latin small letter i with tilde                   |
1330   * | U+012A  | Ī     | I           | Latin capital letter I with macron                |
1331   * | U+012B  | ī     | i           | Latin small letter i with macron                  |
1332   * | U+012C  | Ĭ     | I           | Latin capital letter I with breve                 |
1333   * | U+012D  | ĭ     | i           | Latin small letter i with breve                   |
1334   * | U+012E  | Į     | I           | Latin capital letter I with ogonek                |
1335   * | U+012F  | į     | i           | Latin small letter i with ogonek                  |
1336   * | U+0130  | İ     | I           | Latin capital letter I with dot above             |
1337   * | U+0131  | ı     | i           | Latin small letter dotless i                      |
1338   * | U+0132  | IJ     | IJ          | Latin capital ligature IJ                         |
1339   * | U+0133  | ij     | ij          | Latin small ligature ij                           |
1340   * | U+0134  | Ĵ     | J           | Latin capital letter J with circumflex            |
1341   * | U+0135  | ĵ     | j           | Latin small letter j with circumflex              |
1342   * | U+0136  | Ķ     | K           | Latin capital letter K with cedilla               |
1343   * | U+0137  | ķ     | k           | Latin small letter k with cedilla                 |
1344   * | U+0138  | ĸ     | k           | Latin small letter Kra                            |
1345   * | U+0139  | Ĺ     | L           | Latin capital letter L with acute                 |
1346   * | U+013A  | ĺ     | l           | Latin small letter l with acute                   |
1347   * | U+013B  | Ļ     | L           | Latin capital letter L with cedilla               |
1348   * | U+013C  | ļ     | l           | Latin small letter l with cedilla                 |
1349   * | U+013D  | Ľ     | L           | Latin capital letter L with caron                 |
1350   * | U+013E  | ľ     | l           | Latin small letter l with caron                   |
1351   * | U+013F  | Ŀ     | L           | Latin capital letter L with middle dot            |
1352   * | U+0140  | ŀ     | l           | Latin small letter l with middle dot              |
1353   * | U+0141  | Ł     | L           | Latin capital letter L with stroke                |
1354   * | U+0142  | ł     | l           | Latin small letter l with stroke                  |
1355   * | U+0143  | Ń     | N           | Latin capital letter N with acute                 |
1356   * | U+0144  | ń     | n           | Latin small letter N with acute                   |
1357   * | U+0145  | Ņ     | N           | Latin capital letter N with cedilla               |
1358   * | U+0146  | ņ     | n           | Latin small letter n with cedilla                 |
1359   * | U+0147  | Ň     | N           | Latin capital letter N with caron                 |
1360   * | U+0148  | ň     | n           | Latin small letter n with caron                   |
1361   * | U+0149  | ʼn     | n           | Latin small letter n preceded by apostrophe       |
1362   * | U+014A  | Ŋ     | N           | Latin capital letter Eng                          |
1363   * | U+014B  | ŋ     | n           | Latin small letter Eng                            |
1364   * | U+014C  | Ō     | O           | Latin capital letter O with macron                |
1365   * | U+014D  | ō     | o           | Latin small letter o with macron                  |
1366   * | U+014E  | Ŏ     | O           | Latin capital letter O with breve                 |
1367   * | U+014F  | ŏ     | o           | Latin small letter o with breve                   |
1368   * | U+0150  | Ő     | O           | Latin capital letter O with double acute          |
1369   * | U+0151  | ő     | o           | Latin small letter o with double acute            |
1370   * | U+0152  | Π    | OE          | Latin capital ligature OE                         |
1371   * | U+0153  | œ     | oe          | Latin small ligature oe                           |
1372   * | U+0154  | Ŕ     | R           | Latin capital letter R with acute                 |
1373   * | U+0155  | ŕ     | r           | Latin small letter r with acute                   |
1374   * | U+0156  | Ŗ     | R           | Latin capital letter R with cedilla               |
1375   * | U+0157  | ŗ     | r           | Latin small letter r with cedilla                 |
1376   * | U+0158  | Ř     | R           | Latin capital letter R with caron                 |
1377   * | U+0159  | ř     | r           | Latin small letter r with caron                   |
1378   * | U+015A  | Ś     | S           | Latin capital letter S with acute                 |
1379   * | U+015B  | ś     | s           | Latin small letter s with acute                   |
1380   * | U+015C  | Ŝ     | S           | Latin capital letter S with circumflex            |
1381   * | U+015D  | ŝ     | s           | Latin small letter s with circumflex              |
1382   * | U+015E  | Ş     | S           | Latin capital letter S with cedilla               |
1383   * | U+015F  | ş     | s           | Latin small letter s with cedilla                 |
1384   * | U+0160  | Š     | S           | Latin capital letter S with caron                 |
1385   * | U+0161  | š     | s           | Latin small letter s with caron                   |
1386   * | U+0162  | Ţ     | T           | Latin capital letter T with cedilla               |
1387   * | U+0163  | ţ     | t           | Latin small letter t with cedilla                 |
1388   * | U+0164  | Ť     | T           | Latin capital letter T with caron                 |
1389   * | U+0165  | ť     | t           | Latin small letter t with caron                   |
1390   * | U+0166  | Ŧ     | T           | Latin capital letter T with stroke                |
1391   * | U+0167  | ŧ     | t           | Latin small letter t with stroke                  |
1392   * | U+0168  | Ũ     | U           | Latin capital letter U with tilde                 |
1393   * | U+0169  | ũ     | u           | Latin small letter u with tilde                   |
1394   * | U+016A  | Ū     | U           | Latin capital letter U with macron                |
1395   * | U+016B  | ū     | u           | Latin small letter u with macron                  |
1396   * | U+016C  | Ŭ     | U           | Latin capital letter U with breve                 |
1397   * | U+016D  | ŭ     | u           | Latin small letter u with breve                   |
1398   * | U+016E  | Ů     | U           | Latin capital letter U with ring above            |
1399   * | U+016F  | ů     | u           | Latin small letter u with ring above              |
1400   * | U+0170  | Ű     | U           | Latin capital letter U with double acute          |
1401   * | U+0171  | ű     | u           | Latin small letter u with double acute            |
1402   * | U+0172  | Ų     | U           | Latin capital letter U with ogonek                |
1403   * | U+0173  | ų     | u           | Latin small letter u with ogonek                  |
1404   * | U+0174  | Ŵ     | W           | Latin capital letter W with circumflex            |
1405   * | U+0175  | ŵ     | w           | Latin small letter w with circumflex              |
1406   * | U+0176  | Ŷ     | Y           | Latin capital letter Y with circumflex            |
1407   * | U+0177  | ŷ     | y           | Latin small letter y with circumflex              |
1408   * | U+0178  | Ÿ     | Y           | Latin capital letter Y with diaeresis             |
1409   * | U+0179  | Ź     | Z           | Latin capital letter Z with acute                 |
1410   * | U+017A  | ź     | z           | Latin small letter z with acute                   |
1411   * | U+017B  | Ż     | Z           | Latin capital letter Z with dot above             |
1412   * | U+017C  | ż     | z           | Latin small letter z with dot above               |
1413   * | U+017D  | Ž     | Z           | Latin capital letter Z with caron                 |
1414   * | U+017E  | ž     | z           | Latin small letter z with caron                   |
1415   * | U+017F  | ſ     | s           | Latin small letter long s                         |
1416   * | U+01A0  | Ơ     | O           | Latin capital letter O with horn                  |
1417   * | U+01A1  | ơ     | o           | Latin small letter o with horn                    |
1418   * | U+01AF  | Ư     | U           | Latin capital letter U with horn                  |
1419   * | U+01B0  | ư     | u           | Latin small letter u with horn                    |
1420   * | U+01CD  | Ǎ     | A           | Latin capital letter A with caron                 |
1421   * | U+01CE  | ǎ     | a           | Latin small letter a with caron                   |
1422   * | U+01CF  | Ǐ     | I           | Latin capital letter I with caron                 |
1423   * | U+01D0  | ǐ     | i           | Latin small letter i with caron                   |
1424   * | U+01D1  | Ǒ     | O           | Latin capital letter O with caron                 |
1425   * | U+01D2  | ǒ     | o           | Latin small letter o with caron                   |
1426   * | U+01D3  | Ǔ     | U           | Latin capital letter U with caron                 |
1427   * | U+01D4  | ǔ     | u           | Latin small letter u with caron                   |
1428   * | U+01D5  | Ǖ     | U           | Latin capital letter U with diaeresis and macron  |
1429   * | U+01D6  | ǖ     | u           | Latin small letter u with diaeresis and macron    |
1430   * | U+01D7  | Ǘ     | U           | Latin capital letter U with diaeresis and acute   |
1431   * | U+01D8  | ǘ     | u           | Latin small letter u with diaeresis and acute     |
1432   * | U+01D9  | Ǚ     | U           | Latin capital letter U with diaeresis and caron   |
1433   * | U+01DA  | ǚ     | u           | Latin small letter u with diaeresis and caron     |
1434   * | U+01DB  | Ǜ     | U           | Latin capital letter U with diaeresis and grave   |
1435   * | U+01DC  | ǜ     | u           | Latin small letter u with diaeresis and grave     |
1436   *
1437   * Decompositions for Latin Extended-B:
1438   *
1439   * |   Code   | Glyph | Replacement |                Description                |
1440   * | -------- | ----- | ----------- | ----------------------------------------- |
1441   * | U+018F   | Ə     | E           | Latin capital letter Ə                    |
1442   * | U+0259   | ǝ     | e           | Latin small letter ǝ                      |
1443   * | U+0218   | Ș     | S           | Latin capital letter S with comma below   |
1444   * | U+0219   | ș     | s           | Latin small letter s with comma below     |
1445   * | U+021A   | Ț     | T           | Latin capital letter T with comma below   |
1446   * | U+021B   | ț     | t           | Latin small letter t with comma below     |
1447   *
1448   * Vowels with diacritic (Chinese, Hanyu Pinyin):
1449   *
1450   * |   Code   | Glyph | Replacement |                      Description                      |
1451   * | -------- | ----- | ----------- | ----------------------------------------------------- |
1452   * | U+0251   | ɑ     | a           | Latin small letter alpha                              |
1453   * | U+1EA0   | Ạ     | A           | Latin capital letter A with dot below                 |
1454   * | U+1EA1   | ạ     | a           | Latin small letter a with dot below                   |
1455   * | U+1EA2   | Ả     | A           | Latin capital letter A with hook above                |
1456   * | U+1EA3   | ả     | a           | Latin small letter a with hook above                  |
1457   * | U+1EA4   | Ấ     | A           | Latin capital letter A with circumflex and acute      |
1458   * | U+1EA5   | ấ     | a           | Latin small letter a with circumflex and acute        |
1459   * | U+1EA6   | Ầ     | A           | Latin capital letter A with circumflex and grave      |
1460   * | U+1EA7   | ầ     | a           | Latin small letter a with circumflex and grave        |
1461   * | U+1EA8   | Ẩ     | A           | Latin capital letter A with circumflex and hook above |
1462   * | U+1EA9   | ẩ     | a           | Latin small letter a with circumflex and hook above   |
1463   * | U+1EAA   | Ẫ     | A           | Latin capital letter A with circumflex and tilde      |
1464   * | U+1EAB   | ẫ     | a           | Latin small letter a with circumflex and tilde        |
1465   * | U+1EA6   | Ậ     | A           | Latin capital letter A with circumflex and dot below  |
1466   * | U+1EAD   | ậ     | a           | Latin small letter a with circumflex and dot below    |
1467   * | U+1EAE   | Ắ     | A           | Latin capital letter A with breve and acute           |
1468   * | U+1EAF   | ắ     | a           | Latin small letter a with breve and acute             |
1469   * | U+1EB0   | Ằ     | A           | Latin capital letter A with breve and grave           |
1470   * | U+1EB1   | ằ     | a           | Latin small letter a with breve and grave             |
1471   * | U+1EB2   | Ẳ     | A           | Latin capital letter A with breve and hook above      |
1472   * | U+1EB3   | ẳ     | a           | Latin small letter a with breve and hook above        |
1473   * | U+1EB4   | Ẵ     | A           | Latin capital letter A with breve and tilde           |
1474   * | U+1EB5   | ẵ     | a           | Latin small letter a with breve and tilde             |
1475   * | U+1EB6   | Ặ     | A           | Latin capital letter A with breve and dot below       |
1476   * | U+1EB7   | ặ     | a           | Latin small letter a with breve and dot below         |
1477   * | U+1EB8   | Ẹ     | E           | Latin capital letter E with dot below                 |
1478   * | U+1EB9   | ẹ     | e           | Latin small letter e with dot below                   |
1479   * | U+1EBA   | Ẻ     | E           | Latin capital letter E with hook above                |
1480   * | U+1EBB   | ẻ     | e           | Latin small letter e with hook above                  |
1481   * | U+1EBC   | Ẽ     | E           | Latin capital letter E with tilde                     |
1482   * | U+1EBD   | ẽ     | e           | Latin small letter e with tilde                       |
1483   * | U+1EBE   | Ế     | E           | Latin capital letter E with circumflex and acute      |
1484   * | U+1EBF   | ế     | e           | Latin small letter e with circumflex and acute        |
1485   * | U+1EC0   | Ề     | E           | Latin capital letter E with circumflex and grave      |
1486   * | U+1EC1   | ề     | e           | Latin small letter e with circumflex and grave        |
1487   * | U+1EC2   | Ể     | E           | Latin capital letter E with circumflex and hook above |
1488   * | U+1EC3   | ể     | e           | Latin small letter e with circumflex and hook above   |
1489   * | U+1EC4   | Ễ     | E           | Latin capital letter E with circumflex and tilde      |
1490   * | U+1EC5   | ễ     | e           | Latin small letter e with circumflex and tilde        |
1491   * | U+1EC6   | Ệ     | E           | Latin capital letter E with circumflex and dot below  |
1492   * | U+1EC7   | ệ     | e           | Latin small letter e with circumflex and dot below    |
1493   * | U+1EC8   | Ỉ     | I           | Latin capital letter I with hook above                |
1494   * | U+1EC9   | ỉ     | i           | Latin small letter i with hook above                  |
1495   * | U+1ECA   | Ị     | I           | Latin capital letter I with dot below                 |
1496   * | U+1ECB   | ị     | i           | Latin small letter i with dot below                   |
1497   * | U+1ECC   | Ọ     | O           | Latin capital letter O with dot below                 |
1498   * | U+1ECD   | ọ     | o           | Latin small letter o with dot below                   |
1499   * | U+1ECE   | Ỏ     | O           | Latin capital letter O with hook above                |
1500   * | U+1ECF   | ỏ     | o           | Latin small letter o with hook above                  |
1501   * | U+1ED0   | Ố     | O           | Latin capital letter O with circumflex and acute      |
1502   * | U+1ED1   | ố     | o           | Latin small letter o with circumflex and acute        |
1503   * | U+1ED2   | Ồ     | O           | Latin capital letter O with circumflex and grave      |
1504   * | U+1ED3   | ồ     | o           | Latin small letter o with circumflex and grave        |
1505   * | U+1ED4   | Ổ     | O           | Latin capital letter O with circumflex and hook above |
1506   * | U+1ED5   | ổ     | o           | Latin small letter o with circumflex and hook above   |
1507   * | U+1ED6   | Ỗ     | O           | Latin capital letter O with circumflex and tilde      |
1508   * | U+1ED7   | ỗ     | o           | Latin small letter o with circumflex and tilde        |
1509   * | U+1ED8   | Ộ     | O           | Latin capital letter O with circumflex and dot below  |
1510   * | U+1ED9   | ộ     | o           | Latin small letter o with circumflex and dot below    |
1511   * | U+1EDA   | Ớ     | O           | Latin capital letter O with horn and acute            |
1512   * | U+1EDB   | ớ     | o           | Latin small letter o with horn and acute              |
1513   * | U+1EDC   | Ờ     | O           | Latin capital letter O with horn and grave            |
1514   * | U+1EDD   | ờ     | o           | Latin small letter o with horn and grave              |
1515   * | U+1EDE   | Ở     | O           | Latin capital letter O with horn and hook above       |
1516   * | U+1EDF   | ở     | o           | Latin small letter o with horn and hook above         |
1517   * | U+1EE0   | Ỡ     | O           | Latin capital letter O with horn and tilde            |
1518   * | U+1EE1   | ỡ     | o           | Latin small letter o with horn and tilde              |
1519   * | U+1EE2   | Ợ     | O           | Latin capital letter O with horn and dot below        |
1520   * | U+1EE3   | ợ     | o           | Latin small letter o with horn and dot below          |
1521   * | U+1EE4   | Ụ     | U           | Latin capital letter U with dot below                 |
1522   * | U+1EE5   | ụ     | u           | Latin small letter u with dot below                   |
1523   * | U+1EE6   | Ủ     | U           | Latin capital letter U with hook above                |
1524   * | U+1EE7   | ủ     | u           | Latin small letter u with hook above                  |
1525   * | U+1EE8   | Ứ     | U           | Latin capital letter U with horn and acute            |
1526   * | U+1EE9   | ứ     | u           | Latin small letter u with horn and acute              |
1527   * | U+1EEA   | Ừ     | U           | Latin capital letter U with horn and grave            |
1528   * | U+1EEB   | ừ     | u           | Latin small letter u with horn and grave              |
1529   * | U+1EEC   | Ử     | U           | Latin capital letter U with horn and hook above       |
1530   * | U+1EED   | ử     | u           | Latin small letter u with horn and hook above         |
1531   * | U+1EEE   | Ữ     | U           | Latin capital letter U with horn and tilde            |
1532   * | U+1EEF   | ữ     | u           | Latin small letter u with horn and tilde              |
1533   * | U+1EF0   | Ự     | U           | Latin capital letter U with horn and dot below        |
1534   * | U+1EF1   | ự     | u           | Latin small letter u with horn and dot below          |
1535   * | U+1EF2   | Ỳ     | Y           | Latin capital letter Y with grave                     |
1536   * | U+1EF3   | ỳ     | y           | Latin small letter y with grave                       |
1537   * | U+1EF4   | Ỵ     | Y           | Latin capital letter Y with dot below                 |
1538   * | U+1EF5   | ỵ     | y           | Latin small letter y with dot below                   |
1539   * | U+1EF6   | Ỷ     | Y           | Latin capital letter Y with hook above                |
1540   * | U+1EF7   | ỷ     | y           | Latin small letter y with hook above                  |
1541   * | U+1EF8   | Ỹ     | Y           | Latin capital letter Y with tilde                     |
1542   * | U+1EF9   | ỹ     | y           | Latin small letter y with tilde                       |
1543   *
1544   * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`),
1545   * German (Switzerland) informal (`de_CH_informal`), and German (Austria) (`de_AT`) locales:
1546   *
1547   * |   Code   | Glyph | Replacement |               Description               |
1548   * | -------- | ----- | ----------- | --------------------------------------- |
1549   * | U+00C4   | Ä     | Ae          | Latin capital letter A with diaeresis   |
1550   * | U+00E4   | ä     | ae          | Latin small letter a with diaeresis     |
1551   * | U+00D6   | Ö     | Oe          | Latin capital letter O with diaeresis   |
1552   * | U+00F6   | ö     | oe          | Latin small letter o with diaeresis     |
1553   * | U+00DC   | Ü     | Ue          | Latin capital letter U with diaeresis   |
1554   * | U+00FC   | ü     | ue          | Latin small letter u with diaeresis     |
1555   * | U+00DF   | ß     | ss          | Latin small letter sharp s              |
1556   *
1557   * Danish (`da_DK`) locale:
1558   *
1559   * |   Code   | Glyph | Replacement |               Description               |
1560   * | -------- | ----- | ----------- | --------------------------------------- |
1561   * | U+00C6   | Æ     | Ae          | Latin capital letter AE                 |
1562   * | U+00E6   | æ     | ae          | Latin small letter ae                   |
1563   * | U+00D8   | Ø     | Oe          | Latin capital letter O with stroke      |
1564   * | U+00F8   | ø     | oe          | Latin small letter o with stroke        |
1565   * | U+00C5   | Å     | Aa          | Latin capital letter A with ring above  |
1566   * | U+00E5   | å     | aa          | Latin small letter a with ring above    |
1567   *
1568   * Catalan (`ca`) locale:
1569   *
1570   * |   Code   | Glyph | Replacement |               Description               |
1571   * | -------- | ----- | ----------- | --------------------------------------- |
1572   * | U+00B7   | l·l   | ll          | Flown dot (between two Ls)              |
1573   *
1574   * Serbian (`sr_RS`) and Bosnian (`bs_BA`) locales:
1575   *
1576   * |   Code   | Glyph | Replacement |               Description               |
1577   * | -------- | ----- | ----------- | --------------------------------------- |
1578   * | U+0110   | Đ     | DJ          | Latin capital letter D with stroke      |
1579   * | U+0111   | đ     | dj          | Latin small letter d with stroke        |
1580   *
1581   * @since 1.2.1
1582   * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`.
1583   * @since 4.7.0 Added locale support for `sr_RS`.
1584   * @since 4.8.0 Added locale support for `bs_BA`.
1585   * @since 5.7.0 Added locale support for `de_AT`.
1586   * @since 6.0.0 Added the `$locale` parameter.
1587   * @since 6.1.0 Added Unicode NFC encoding normalization support.
1588   *
1589   * @param string $text   Text that might have accent characters.
1590   * @param string $locale Optional. The locale to use for accent removal. Some character
1591   *                       replacements depend on the locale being used (e.g. 'de_DE').
1592   *                       Defaults to the current locale.
1593   * @return string Filtered string with replaced "nice" characters.
1594   */
1595  function remove_accents( $text, $locale = '' ) {
1596      if ( ! preg_match( '/[\x80-\xff]/', $text ) ) {
1597          return $text;
1598      }
1599  
1600      if ( seems_utf8( $text ) ) {
1601  
1602          /*
1603           * Unicode sequence normalization from NFD (Normalization Form Decomposed)
1604           * to NFC (Normalization Form [Pre]Composed), the encoding used in this function.
1605           */
1606          if ( function_exists( 'normalizer_is_normalized' )
1607              && function_exists( 'normalizer_normalize' )
1608          ) {
1609              if ( ! normalizer_is_normalized( $text ) ) {
1610                  $text = normalizer_normalize( $text );
1611              }
1612          }
1613  
1614          $chars = array(
1615              // Decompositions for Latin-1 Supplement.
1616              'ª' => 'a',
1617              'º' => 'o',
1618              'À' => 'A',
1619              'Á' => 'A',
1620              'Â' => 'A',
1621              'Ã' => 'A',
1622              'Ä' => 'A',
1623              'Å' => 'A',
1624              'Æ' => 'AE',
1625              'Ç' => 'C',
1626              'È' => 'E',
1627              'É' => 'E',
1628              'Ê' => 'E',
1629              'Ë' => 'E',
1630              'Ì' => 'I',
1631              'Í' => 'I',
1632              'Î' => 'I',
1633              'Ï' => 'I',
1634              'Ð' => 'D',
1635              'Ñ' => 'N',
1636              'Ò' => 'O',
1637              'Ó' => 'O',
1638              'Ô' => 'O',
1639              'Õ' => 'O',
1640              'Ö' => 'O',
1641              'Ù' => 'U',
1642              'Ú' => 'U',
1643              'Û' => 'U',
1644              'Ü' => 'U',
1645              'Ý' => 'Y',
1646              'Þ' => 'TH',
1647              'ß' => 's',
1648              'à' => 'a',
1649              'á' => 'a',
1650              'â' => 'a',
1651              'ã' => 'a',
1652              'ä' => 'a',
1653              'å' => 'a',
1654              'æ' => 'ae',
1655              'ç' => 'c',
1656              'è' => 'e',
1657              'é' => 'e',
1658              'ê' => 'e',
1659              'ë' => 'e',
1660              'ì' => 'i',
1661              'í' => 'i',
1662              'î' => 'i',
1663              'ï' => 'i',
1664              'ð' => 'd',
1665              'ñ' => 'n',
1666              'ò' => 'o',
1667              'ó' => 'o',
1668              'ô' => 'o',
1669              'õ' => 'o',
1670              'ö' => 'o',
1671              'ø' => 'o',
1672              'ù' => 'u',
1673              'ú' => 'u',
1674              'û' => 'u',
1675              'ü' => 'u',
1676              'ý' => 'y',
1677              'þ' => 'th',
1678              'ÿ' => 'y',
1679              'Ø' => 'O',
1680              // Decompositions for Latin Extended-A.
1681              'Ā' => 'A',
1682              'ā' => 'a',
1683              'Ă' => 'A',
1684              'ă' => 'a',
1685              'Ą' => 'A',
1686              'ą' => 'a',
1687              'Ć' => 'C',
1688              'ć' => 'c',
1689              'Ĉ' => 'C',
1690              'ĉ' => 'c',
1691              'Ċ' => 'C',
1692              'ċ' => 'c',
1693              'Č' => 'C',
1694              'č' => 'c',
1695              'Ď' => 'D',
1696              'ď' => 'd',
1697              'Đ' => 'D',
1698              'đ' => 'd',
1699              'Ē' => 'E',
1700              'ē' => 'e',
1701              'Ĕ' => 'E',
1702              'ĕ' => 'e',
1703              'Ė' => 'E',
1704              'ė' => 'e',
1705              'Ę' => 'E',
1706              'ę' => 'e',
1707              'Ě' => 'E',
1708              'ě' => 'e',
1709              'Ĝ' => 'G',
1710              'ĝ' => 'g',
1711              'Ğ' => 'G',
1712              'ğ' => 'g',
1713              'Ġ' => 'G',
1714              'ġ' => 'g',
1715              'Ģ' => 'G',
1716              'ģ' => 'g',
1717              'Ĥ' => 'H',
1718              'ĥ' => 'h',
1719              'Ħ' => 'H',
1720              'ħ' => 'h',
1721              'Ĩ' => 'I',
1722              'ĩ' => 'i',
1723              'Ī' => 'I',
1724              'ī' => 'i',
1725              'Ĭ' => 'I',
1726              'ĭ' => 'i',
1727              'Į' => 'I',
1728              'į' => 'i',
1729              'İ' => 'I',
1730              'ı' => 'i',
1731              'IJ' => 'IJ',
1732              'ij' => 'ij',
1733              'Ĵ' => 'J',
1734              'ĵ' => 'j',
1735              'Ķ' => 'K',
1736              'ķ' => 'k',
1737              'ĸ' => 'k',
1738              'Ĺ' => 'L',
1739              'ĺ' => 'l',
1740              'Ļ' => 'L',
1741              'ļ' => 'l',
1742              'Ľ' => 'L',
1743              'ľ' => 'l',
1744              'Ŀ' => 'L',
1745              'ŀ' => 'l',
1746              'Ł' => 'L',
1747              'ł' => 'l',
1748              'Ń' => 'N',
1749              'ń' => 'n',
1750              'Ņ' => 'N',
1751              'ņ' => 'n',
1752              'Ň' => 'N',
1753              'ň' => 'n',
1754              'ʼn' => 'n',
1755              'Ŋ' => 'N',
1756              'ŋ' => 'n',
1757              'Ō' => 'O',
1758              'ō' => 'o',
1759              'Ŏ' => 'O',
1760              'ŏ' => 'o',
1761              'Ő' => 'O',
1762              'ő' => 'o',
1763              'Œ' => 'OE',
1764              'œ' => 'oe',
1765              'Ŕ' => 'R',
1766              'ŕ' => 'r',
1767              'Ŗ' => 'R',
1768              'ŗ' => 'r',
1769              'Ř' => 'R',
1770              'ř' => 'r',
1771              'Ś' => 'S',
1772              'ś' => 's',
1773              'Ŝ' => 'S',
1774              'ŝ' => 's',
1775              'Ş' => 'S',
1776              'ş' => 's',
1777              'Š' => 'S',
1778              'š' => 's',
1779              'Ţ' => 'T',
1780              'ţ' => 't',
1781              'Ť' => 'T',
1782              'ť' => 't',
1783              'Ŧ' => 'T',
1784              'ŧ' => 't',
1785              'Ũ' => 'U',
1786              'ũ' => 'u',
1787              'Ū' => 'U',
1788              'ū' => 'u',
1789              'Ŭ' => 'U',
1790              'ŭ' => 'u',
1791              'Ů' => 'U',
1792              'ů' => 'u',
1793              'Ű' => 'U',
1794              'ű' => 'u',
1795              'Ų' => 'U',
1796              'ų' => 'u',
1797              'Ŵ' => 'W',
1798              'ŵ' => 'w',
1799              'Ŷ' => 'Y',
1800              'ŷ' => 'y',
1801              'Ÿ' => 'Y',
1802              'Ź' => 'Z',
1803              'ź' => 'z',
1804              'Ż' => 'Z',
1805              'ż' => 'z',
1806              'Ž' => 'Z',
1807              'ž' => 'z',
1808              'ſ' => 's',
1809              // Decompositions for Latin Extended-B.
1810              'Ə' => 'E',
1811              'ǝ' => 'e',
1812              'Ș' => 'S',
1813              'ș' => 's',
1814              'Ț' => 'T',
1815              'ț' => 't',
1816              // Euro sign.
1817              '€' => 'E',
1818              // GBP (Pound) sign.
1819              '£' => '',
1820              // Vowels with diacritic (Vietnamese). Unmarked.
1821              'Ơ' => 'O',
1822              'ơ' => 'o',
1823              'Ư' => 'U',
1824              'ư' => 'u',
1825              // Grave accent.
1826              'Ầ' => 'A',
1827              'ầ' => 'a',
1828              'Ằ' => 'A',
1829              'ằ' => 'a',
1830              'Ề' => 'E',
1831              'ề' => 'e',
1832              'Ồ' => 'O',
1833              'ồ' => 'o',
1834              'Ờ' => 'O',
1835              'ờ' => 'o',
1836              'Ừ' => 'U',
1837              'ừ' => 'u',
1838              'Ỳ' => 'Y',
1839              'ỳ' => 'y',
1840              // Hook.
1841              'Ả' => 'A',
1842              'ả' => 'a',
1843              'Ẩ' => 'A',
1844              'ẩ' => 'a',
1845              'Ẳ' => 'A',
1846              'ẳ' => 'a',
1847              'Ẻ' => 'E',
1848              'ẻ' => 'e',
1849              'Ể' => 'E',
1850              'ể' => 'e',
1851              'Ỉ' => 'I',
1852              'ỉ' => 'i',
1853              'Ỏ' => 'O',
1854              'ỏ' => 'o',
1855              'Ổ' => 'O',
1856              'ổ' => 'o',
1857              'Ở' => 'O',
1858              'ở' => 'o',
1859              'Ủ' => 'U',
1860              'ủ' => 'u',
1861              'Ử' => 'U',
1862              'ử' => 'u',
1863              'Ỷ' => 'Y',
1864              'ỷ' => 'y',
1865              // Tilde.
1866              'Ẫ' => 'A',
1867              'ẫ' => 'a',
1868              'Ẵ' => 'A',
1869              'ẵ' => 'a',
1870              'Ẽ' => 'E',
1871              'ẽ' => 'e',
1872              'Ễ' => 'E',
1873              'ễ' => 'e',
1874              'Ỗ' => 'O',
1875              'ỗ' => 'o',
1876              'Ỡ' => 'O',
1877              'ỡ' => 'o',
1878              'Ữ' => 'U',
1879              'ữ' => 'u',
1880              'Ỹ' => 'Y',
1881              'ỹ' => 'y',
1882              // Acute accent.
1883              'Ấ' => 'A',
1884              'ấ' => 'a',
1885              'Ắ' => 'A',
1886              'ắ' => 'a',
1887              'Ế' => 'E',
1888              'ế' => 'e',
1889              'Ố' => 'O',
1890              'ố' => 'o',
1891              'Ớ' => 'O',
1892              'ớ' => 'o',
1893              'Ứ' => 'U',
1894              'ứ' => 'u',
1895              // Dot below.
1896              'Ạ' => 'A',
1897              'ạ' => 'a',
1898              'Ậ' => 'A',
1899              'ậ' => 'a',
1900              'Ặ' => 'A',
1901              'ặ' => 'a',
1902              'Ẹ' => 'E',
1903              'ẹ' => 'e',
1904              'Ệ' => 'E',
1905              'ệ' => 'e',
1906              'Ị' => 'I',
1907              'ị' => 'i',
1908              'Ọ' => 'O',
1909              'ọ' => 'o',
1910              'Ộ' => 'O',
1911              'ộ' => 'o',
1912              'Ợ' => 'O',
1913              'ợ' => 'o',
1914              'Ụ' => 'U',
1915              'ụ' => 'u',
1916              'Ự' => 'U',
1917              'ự' => 'u',
1918              'Ỵ' => 'Y',
1919              'ỵ' => 'y',
1920              // Vowels with diacritic (Chinese, Hanyu Pinyin).
1921              'ɑ' => 'a',
1922              // Macron.
1923              'Ǖ' => 'U',
1924              'ǖ' => 'u',
1925              // Acute accent.
1926              'Ǘ' => 'U',
1927              'ǘ' => 'u',
1928              // Caron.
1929              'Ǎ' => 'A',
1930              'ǎ' => 'a',
1931              'Ǐ' => 'I',
1932              'ǐ' => 'i',
1933              'Ǒ' => 'O',
1934              'ǒ' => 'o',
1935              'Ǔ' => 'U',
1936              'ǔ' => 'u',
1937              'Ǚ' => 'U',
1938              'ǚ' => 'u',
1939              // Grave accent.
1940              'Ǜ' => 'U',
1941              'ǜ' => 'u',
1942          );
1943  
1944          // Used for locale-specific rules.
1945          if ( empty( $locale ) ) {
1946              $locale = get_locale();
1947          }
1948  
1949          /*
1950           * German has various locales (de_DE, de_CH, de_AT, ...) with formal and informal variants.
1951           * There is no 3-letter locale like 'def', so checking for 'de' instead of 'de_' is safe,
1952           * since 'de' itself would be a valid locale too.
1953           */
1954          if ( str_starts_with( $locale, 'de' ) ) {
1955              $chars['Ä'] = 'Ae';
1956              $chars['ä'] = 'ae';
1957              $chars['Ö'] = 'Oe';
1958              $chars['ö'] = 'oe';
1959              $chars['Ü'] = 'Ue';
1960              $chars['ü'] = 'ue';
1961              $chars['ß'] = 'ss';
1962          } elseif ( 'da_DK' === $locale ) {
1963              $chars['Æ'] = 'Ae';
1964              $chars['æ'] = 'ae';
1965              $chars['Ø'] = 'Oe';
1966              $chars['ø'] = 'oe';
1967              $chars['Å'] = 'Aa';
1968              $chars['å'] = 'aa';
1969          } elseif ( 'ca' === $locale ) {
1970              $chars['l·l'] = 'll';
1971          } elseif ( 'sr_RS' === $locale || 'bs_BA' === $locale ) {
1972              $chars['Đ'] = 'DJ';
1973              $chars['đ'] = 'dj';
1974          }
1975  
1976          $text = strtr( $text, $chars );
1977      } else {
1978          $chars = array();
1979          // Assume ISO-8859-1 if not UTF-8.
1980          $chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e"
1981              . "\x9f\xa2\xa5\xb5\xc0\xc1\xc2"
1982              . "\xc3\xc4\xc5\xc7\xc8\xc9\xca"
1983              . "\xcb\xcc\xcd\xce\xcf\xd1\xd2"
1984              . "\xd3\xd4\xd5\xd6\xd8\xd9\xda"
1985              . "\xdb\xdc\xdd\xe0\xe1\xe2\xe3"
1986              . "\xe4\xe5\xe7\xe8\xe9\xea\xeb"
1987              . "\xec\xed\xee\xef\xf1\xf2\xf3"
1988              . "\xf4\xf5\xf6\xf8\xf9\xfa\xfb"
1989              . "\xfc\xfd\xff";
1990  
1991          $chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy';
1992  
1993          $text                = strtr( $text, $chars['in'], $chars['out'] );
1994          $double_chars        = array();
1995          $double_chars['in']  = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" );
1996          $double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' );
1997          $text                = str_replace( $double_chars['in'], $double_chars['out'], $text );
1998      }
1999  
2000      return $text;
2001  }
2002  
2003  /**
2004   * Sanitizes a filename, replacing whitespace with dashes.
2005   *
2006   * Removes special characters that are illegal in filenames on certain
2007   * operating systems and special characters requiring special escaping
2008   * to manipulate at the command line. Replaces spaces and consecutive
2009   * dashes with a single dash. Trims period, dash and underscore from beginning
2010   * and end of filename. It is not guaranteed that this function will return a
2011   * filename that is allowed to be uploaded.
2012   *
2013   * @since 2.1.0
2014   *
2015   * @param string $filename The filename to be sanitized.
2016   * @return string The sanitized filename.
2017   */
2018  function sanitize_file_name( $filename ) {
2019      $filename_raw = $filename;
2020      $filename     = remove_accents( $filename );
2021  
2022      $special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '|', '~', '`', '!', '{', '}', '%', '+', '’', '«', '»', '”', '“', chr( 0 ) );
2023  
2024      // Check for support for utf8 in the installed PCRE library once and store the result in a static.
2025      static $utf8_pcre = null;
2026      if ( ! isset( $utf8_pcre ) ) {
2027          // phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged
2028          $utf8_pcre = @preg_match( '/^./u', 'a' );
2029      }
2030  
2031      if ( ! seems_utf8( $filename ) ) {
2032          $_ext     = pathinfo( $filename, PATHINFO_EXTENSION );
2033          $_name    = pathinfo( $filename, PATHINFO_FILENAME );
2034          $filename = sanitize_title_with_dashes( $_name ) . '.' . $_ext;
2035      }
2036  
2037      if ( $utf8_pcre ) {
2038          $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
2039      }
2040  
2041      /**
2042       * Filters the list of characters to remove from a filename.
2043       *
2044       * @since 2.8.0
2045       *
2046       * @param string[] $special_chars Array of characters to remove.
2047       * @param string   $filename_raw  The original filename to be sanitized.
2048       */
2049      $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
2050  
2051      $filename = str_replace( $special_chars, '', $filename );
2052      $filename = str_replace( array( '%20', '+' ), '-', $filename );
2053      $filename = preg_replace( '/\.{2,}/', '.', $filename );
2054      $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
2055      $filename = trim( $filename, '.-_' );
2056  
2057      if ( ! str_contains( $filename, '.' ) ) {
2058          $mime_types = wp_get_mime_types();
2059          $filetype   = wp_check_filetype( 'test.' . $filename, $mime_types );
2060          if ( $filetype['ext'] === $filename ) {
2061              $filename = 'unnamed-file.' . $filetype['ext'];
2062          }
2063      }
2064  
2065      // Split the filename into a base and extension[s].
2066      $parts = explode( '.', $filename );
2067  
2068      // Return if only one extension.
2069      if ( count( $parts ) <= 2 ) {
2070          /** This filter is documented in wp-includes/formatting.php */
2071          return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
2072      }
2073  
2074      // Process multiple extensions.
2075      $filename  = array_shift( $parts );
2076      $extension = array_pop( $parts );
2077      $mimes     = get_allowed_mime_types();
2078  
2079      /*
2080       * Loop over any intermediate extensions. Postfix them with a trailing underscore
2081       * if they are a 2 - 5 character long alpha string not in the allowed extension list.
2082       */
2083      foreach ( (array) $parts as $part ) {
2084          $filename .= '.' . $part;
2085  
2086          if ( preg_match( '/^[a-zA-Z]{2,5}\d?$/', $part ) ) {
2087              $allowed = false;
2088              foreach ( $mimes as $ext_preg => $mime_match ) {
2089                  $ext_preg = '!^(' . $ext_preg . ')$!i';
2090                  if ( preg_match( $ext_preg, $part ) ) {
2091                      $allowed = true;
2092                      break;
2093                  }
2094              }
2095              if ( ! $allowed ) {
2096                  $filename .= '_';
2097              }
2098          }
2099      }
2100  
2101      $filename .= '.' . $extension;
2102  
2103      /**
2104       * Filters a sanitized filename string.
2105       *
2106       * @since 2.8.0
2107       *
2108       * @param string $filename     Sanitized filename.
2109       * @param string $filename_raw The filename prior to sanitization.
2110       */
2111      return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
2112  }
2113  
2114  /**
2115   * Sanitizes a username, stripping out unsafe characters.
2116   *
2117   * Removes tags, percent-encoded characters, HTML entities, and if strict is enabled,
2118   * will only keep alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
2119   * raw username (the username in the parameter), and the value of $strict as parameters
2120   * for the {@see 'sanitize_user'} filter.
2121   *
2122   * @since 2.0.0
2123   *
2124   * @param string $username The username to be sanitized.
2125   * @param bool   $strict   Optional. If set to true, limits $username to specific characters.
2126   *                         Default false.
2127   * @return string The sanitized username, after passing through filters.
2128   */
2129  function sanitize_user( $username, $strict = false ) {
2130      $raw_username = $username;
2131      $username     = wp_strip_all_tags( $username );
2132      $username     = remove_accents( $username );
2133      // Remove percent-encoded characters.
2134      $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
2135      // Remove HTML entities.
2136      $username = preg_replace( '/&.+?;/', '', $username );
2137  
2138      // If strict, reduce to ASCII for max portability.
2139      if ( $strict ) {
2140          $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
2141      }
2142  
2143      $username = trim( $username );
2144      // Consolidate contiguous whitespace.
2145      $username = preg_replace( '|\s+|', ' ', $username );
2146  
2147      /**
2148       * Filters a sanitized username string.
2149       *
2150       * @since 2.0.1
2151       *
2152       * @param string $username     Sanitized username.
2153       * @param string $raw_username The username prior to sanitization.
2154       * @param bool   $strict       Whether to limit the sanitization to specific characters.
2155       */
2156      return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
2157  }
2158  
2159  /**
2160   * Sanitizes a string key.
2161   *
2162   * Keys are used as internal identifiers. Lowercase alphanumeric characters,
2163   * dashes, and underscores are allowed.
2164   *
2165   * @since 3.0.0
2166   *
2167   * @param string $key String key.
2168   * @return string Sanitized key.
2169   */
2170  function sanitize_key( $key ) {
2171      $sanitized_key = '';
2172  
2173      if ( is_scalar( $key ) ) {
2174          $sanitized_key = strtolower( $key );
2175          $sanitized_key = preg_replace( '/[^a-z0-9_\-]/', '', $sanitized_key );
2176      }
2177  
2178      /**
2179       * Filters a sanitized key string.
2180       *
2181       * @since 3.0.0
2182       *
2183       * @param string $sanitized_key Sanitized key.
2184       * @param string $key           The key prior to sanitization.
2185       */
2186      return apply_filters( 'sanitize_key', $sanitized_key, $key );
2187  }
2188  
2189  /**
2190   * Sanitizes a string into a slug, which can be used in URLs or HTML attributes.
2191   *
2192   * By default, converts accent characters to ASCII characters and further
2193   * limits the output to alphanumeric characters, underscore (_) and dash (-)
2194   * through the {@see 'sanitize_title'} filter.
2195   *
2196   * If `$title` is empty and `$fallback_title` is set, the latter will be used.
2197   *
2198   * @since 1.0.0
2199   *
2200   * @param string $title          The string to be sanitized.
2201   * @param string $fallback_title Optional. A title to use if $title is empty. Default empty.
2202   * @param string $context        Optional. The operation for which the string is sanitized.
2203   *                               When set to 'save', the string runs through remove_accents().
2204   *                               Default 'save'.
2205   * @return string The sanitized string.
2206   */
2207  function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
2208      $raw_title = $title;
2209  
2210      if ( 'save' === $context ) {
2211          $title = remove_accents( $title );
2212      }
2213  
2214      /**
2215       * Filters a sanitized title string.
2216       *
2217       * @since 1.2.0
2218       *
2219       * @param string $title     Sanitized title.
2220       * @param string $raw_title The title prior to sanitization.
2221       * @param string $context   The context for which the title is being sanitized.
2222       */
2223      $title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
2224  
2225      if ( '' === $title || false === $title ) {
2226          $title = $fallback_title;
2227      }
2228  
2229      return $title;
2230  }
2231  
2232  /**
2233   * Sanitizes a title with the 'query' context.
2234   *
2235   * Used for querying the database for a value from URL.
2236   *
2237   * @since 3.1.0
2238   *
2239   * @param string $title The string to be sanitized.
2240   * @return string The sanitized string.
2241   */
2242  function sanitize_title_for_query( $title ) {
2243      return sanitize_title( $title, '', 'query' );
2244  }
2245  
2246  /**
2247   * Sanitizes a title, replacing whitespace and a few other characters with dashes.
2248   *
2249   * Limits the output to alphanumeric characters, underscore (_) and dash (-).
2250   * Whitespace becomes a dash.
2251   *
2252   * @since 1.2.0
2253   *
2254   * @param string $title     The title to be sanitized.
2255   * @param string $raw_title Optional. Not used. Default empty.
2256   * @param string $context   Optional. The operation for which the string is sanitized.
2257   *                          When set to 'save', additional entities are converted to hyphens
2258   *                          or stripped entirely. Default 'display'.
2259   * @return string The sanitized title.
2260   */
2261  function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
2262      $title = strip_tags( $title );
2263      // Preserve escaped octets.
2264      $title = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title );
2265      // Remove percent signs that are not part of an octet.
2266      $title = str_replace( '%', '', $title );
2267      // Restore octets.
2268      $title = preg_replace( '|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title );
2269  
2270      if ( seems_utf8( $title ) ) {
2271          if ( function_exists( 'mb_strtolower' ) ) {
2272              $title = mb_strtolower( $title, 'UTF-8' );
2273          }
2274          $title = utf8_uri_encode( $title, 200 );
2275      }
2276  
2277      $title = strtolower( $title );
2278  
2279      if ( 'save' === $context ) {
2280          // Convert &nbsp, &ndash, and &mdash to hyphens.
2281          $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
2282          // Convert &nbsp, &ndash, and &mdash HTML entities to hyphens.
2283          $title = str_replace( array( '&nbsp;', '&#160;', '&ndash;', '&#8211;', '&mdash;', '&#8212;' ), '-', $title );
2284          // Convert forward slash to hyphen.
2285          $title = str_replace( '/', '-', $title );
2286  
2287          // Strip these characters entirely.
2288          $title = str_replace(
2289              array(
2290                  // Soft hyphens.
2291                  '%c2%ad',
2292                  // &iexcl and &iquest.
2293                  '%c2%a1',
2294                  '%c2%bf',
2295                  // Angle quotes.
2296                  '%c2%ab',
2297                  '%c2%bb',
2298                  '%e2%80%b9',
2299                  '%e2%80%ba',
2300                  // Curly quotes.
2301                  '%e2%80%98',
2302                  '%e2%80%99',
2303                  '%e2%80%9c',
2304                  '%e2%80%9d',
2305                  '%e2%80%9a',
2306                  '%e2%80%9b',
2307                  '%e2%80%9e',
2308                  '%e2%80%9f',
2309                  // Bullet.
2310                  '%e2%80%a2',
2311                  // &copy, &reg, &deg, &hellip, and &trade.
2312                  '%c2%a9',
2313                  '%c2%ae',
2314                  '%c2%b0',
2315                  '%e2%80%a6',
2316                  '%e2%84%a2',
2317                  // Acute accents.
2318                  '%c2%b4',
2319                  '%cb%8a',
2320                  '%cc%81',
2321                  '%cd%81',
2322                  // Grave accent, macron, caron.
2323                  '%cc%80',
2324                  '%cc%84',
2325                  '%cc%8c',
2326                  // Non-visible characters that display without a width.
2327                  '%e2%80%8b', // Zero width space.
2328                  '%e2%80%8c', // Zero width non-joiner.
2329                  '%e2%80%8d', // Zero width joiner.
2330                  '%e2%80%8e', // Left-to-right mark.
2331                  '%e2%80%8f', // Right-to-left mark.
2332                  '%e2%80%aa', // Left-to-right embedding.
2333                  '%e2%80%ab', // Right-to-left embedding.
2334                  '%e2%80%ac', // Pop directional formatting.
2335                  '%e2%80%ad', // Left-to-right override.
2336                  '%e2%80%ae', // Right-to-left override.
2337                  '%ef%bb%bf', // Byte order mark.
2338                  '%ef%bf%bc', // Object replacement character.
2339              ),
2340              '',
2341              $title
2342          );
2343  
2344          // Convert non-visible characters that display with a width to hyphen.
2345          $title = str_replace(
2346              array(
2347                  '%e2%80%80', // En quad.
2348                  '%e2%80%81', // Em quad.
2349                  '%e2%80%82', // En space.
2350                  '%e2%80%83', // Em space.
2351                  '%e2%80%84', // Three-per-em space.
2352                  '%e2%80%85', // Four-per-em space.
2353                  '%e2%80%86', // Six-per-em space.
2354                  '%e2%80%87', // Figure space.
2355                  '%e2%80%88', // Punctuation space.
2356                  '%e2%80%89', // Thin space.
2357                  '%e2%80%8a', // Hair space.
2358                  '%e2%80%a8', // Line separator.
2359                  '%e2%80%a9', // Paragraph separator.
2360                  '%e2%80%af', // Narrow no-break space.
2361              ),
2362              '-',
2363              $title
2364          );
2365  
2366          // Convert &times to 'x'.
2367          $title = str_replace( '%c3%97', 'x', $title );
2368      }
2369  
2370      // Remove HTML entities.
2371      $title = preg_replace( '/&.+?;/', '', $title );
2372      $title = str_replace( '.', '-', $title );
2373  
2374      $title = preg_replace( '/[^%a-z0-9 _-]/', '', $title );
2375      $title = preg_replace( '/\s+/', '-', $title );
2376      $title = preg_replace( '|-+|', '-', $title );
2377      $title = trim( $title, '-' );
2378  
2379      return $title;
2380  }
2381  
2382  /**
2383   * Ensures a string is a valid SQL 'order by' clause.
2384   *
2385   * Accepts one or more columns, with or without a sort order (ASC / DESC).
2386   * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
2387   *
2388   * Also accepts 'RAND()'.
2389   *
2390   * @since 2.5.1
2391   *
2392   * @param string $orderby Order by clause to be validated.
2393   * @return string|false Returns $orderby if valid, false otherwise.
2394   */
2395  function sanitize_sql_orderby( $orderby ) {
2396      if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) {
2397          return $orderby;
2398      }
2399      return false;
2400  }
2401  
2402  /**
2403   * Sanitizes an HTML classname to ensure it only contains valid characters.
2404   *
2405   * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
2406   * string then it will return the alternative value supplied.
2407   *
2408   * @todo Expand to support the full range of CDATA that a class attribute can contain.
2409   *
2410   * @since 2.8.0
2411   *
2412   * @param string $classname The classname to be sanitized.
2413   * @param string $fallback  Optional. The value to return if the sanitization ends up as an empty string.
2414   *                          Default empty string.
2415   * @return string The sanitized value.
2416   */
2417  function sanitize_html_class( $classname, $fallback = '' ) {
2418      // Strip out any percent-encoded characters.
2419      $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $classname );
2420  
2421      // Limit to A-Z, a-z, 0-9, '_', '-'.
2422      $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
2423  
2424      if ( '' === $sanitized && $fallback ) {
2425          return sanitize_html_class( $fallback );
2426      }
2427      /**
2428       * Filters a sanitized HTML class string.
2429       *
2430       * @since 2.8.0
2431       *
2432       * @param string $sanitized The sanitized HTML class.
2433       * @param string $classname HTML class before sanitization.
2434       * @param string $fallback  The fallback string.
2435       */
2436      return apply_filters( 'sanitize_html_class', $sanitized, $classname, $fallback );
2437  }
2438  
2439  /**
2440   * Strips out all characters not allowed in a locale name.
2441   *
2442   * @since 6.2.1
2443   *
2444   * @param string $locale_name The locale name to be sanitized.
2445   * @return string The sanitized value.
2446   */
2447  function sanitize_locale_name( $locale_name ) {
2448      // Limit to A-Z, a-z, 0-9, '_', '-'.
2449      $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $locale_name );
2450  
2451      /**
2452       * Filters a sanitized locale name string.
2453       *
2454       * @since 6.2.1
2455       *
2456       * @param string $sanitized   The sanitized locale name.
2457       * @param string $locale_name The locale name before sanitization.
2458       */
2459      return apply_filters( 'sanitize_locale_name', $sanitized, $locale_name );
2460  }
2461  
2462  /**
2463   * Converts lone & characters into `&#038;` (a.k.a. `&amp;`)
2464   *
2465   * @since 0.71
2466   *
2467   * @param string $content    String of characters to be converted.
2468   * @param string $deprecated Not used.
2469   * @return string Converted string.
2470   */
2471  function convert_chars( $content, $deprecated = '' ) {
2472      if ( ! empty( $deprecated ) ) {
2473          _deprecated_argument( __FUNCTION__, '0.71' );
2474      }
2475  
2476      if ( str_contains( $content, '&' ) ) {
2477          $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content );
2478      }
2479  
2480      return $content;
2481  }
2482  
2483  /**
2484   * Converts invalid Unicode references range to valid range.
2485   *
2486   * @since 4.3.0
2487   *
2488   * @param string $content String with entities that need converting.
2489   * @return string Converted string.
2490   */
2491  function convert_invalid_entities( $content ) {
2492      $wp_htmltranswinuni = array(
2493          '&#128;' => '&#8364;', // The Euro sign.
2494          '&#129;' => '',
2495          '&#130;' => '&#8218;', // These are Windows CP1252 specific characters.
2496          '&#131;' => '&#402;',  // They would look weird on non-Windows browsers.
2497          '&#132;' => '&#8222;',
2498          '&#133;' => '&#8230;',
2499          '&#134;' => '&#8224;',
2500          '&#135;' => '&#8225;',
2501          '&#136;' => '&#710;',
2502          '&#137;' => '&#8240;',
2503          '&#138;' => '&#352;',
2504          '&#139;' => '&#8249;',
2505          '&#140;' => '&#338;',
2506          '&#141;' => '',
2507          '&#142;' => '&#381;',
2508          '&#143;' => '',
2509          '&#144;' => '',
2510          '&#145;' => '&#8216;',
2511          '&#146;' => '&#8217;',
2512          '&#147;' => '&#8220;',
2513          '&#148;' => '&#8221;',
2514          '&#149;' => '&#8226;',
2515          '&#150;' => '&#8211;',
2516          '&#151;' => '&#8212;',
2517          '&#152;' => '&#732;',
2518          '&#153;' => '&#8482;',
2519          '&#154;' => '&#353;',
2520          '&#155;' => '&#8250;',
2521          '&#156;' => '&#339;',
2522          '&#157;' => '',
2523          '&#158;' => '&#382;',
2524          '&#159;' => '&#376;',
2525      );
2526  
2527      if ( str_contains( $content, '&#1' ) ) {
2528          $content = strtr( $content, $wp_htmltranswinuni );
2529      }
2530  
2531      return $content;
2532  }
2533  
2534  /**
2535   * Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
2536   *
2537   * @since 0.71
2538   *
2539   * @param string $text  Text to be balanced
2540   * @param bool   $force If true, forces balancing, ignoring the value of the option. Default false.
2541   * @return string Balanced text
2542   */
2543  function balanceTags( $text, $force = false ) {  // phpcs:ignore WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid
2544      if ( $force || (int) get_option( 'use_balanceTags' ) === 1 ) {
2545          return force_balance_tags( $text );
2546      } else {
2547          return $text;
2548      }
2549  }
2550  
2551  /**
2552   * Balances tags of string using a modified stack.
2553   *
2554   * @since 2.0.4
2555   * @since 5.3.0 Improve accuracy and add support for custom element tags.
2556   *
2557   * @author Leonard Lin <leonard@acm.org>
2558   * @license GPL
2559   * @copyright November 4, 2001
2560   * @version 1.1
2561   * @todo Make better - change loop condition to $text in 1.2
2562   * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
2563   *      1.1  Fixed handling of append/stack pop order of end text
2564   *           Added Cleaning Hooks
2565   *      1.0  First Version
2566   *
2567   * @param string $text Text to be balanced.
2568   * @return string Balanced text.
2569   */
2570  function force_balance_tags( $text ) {
2571      $tagstack  = array();
2572      $stacksize = 0;
2573      $tagqueue  = '';
2574      $newtext   = '';
2575      // Known single-entity/self-closing tags.
2576      $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source', 'track', 'wbr' );
2577      // Tags that can be immediately nested within themselves.
2578      $nestable_tags = array( 'article', 'aside', 'blockquote', 'details', 'div', 'figure', 'object', 'q', 'section', 'span' );
2579  
2580      // WP bug fix for comments - in case you REALLY meant to type '< !--'.
2581      $text = str_replace( '< !--', '<    !--', $text );
2582      // WP bug fix for LOVE <3 (and other situations with '<' before a number).
2583      $text = preg_replace( '#<([0-9]{1})#', '&lt;$1', $text );
2584  
2585      /**
2586       * Matches supported tags.
2587       *
2588       * To get the pattern as a string without the comments paste into a PHP
2589       * REPL like `php -a`.
2590       *
2591       * @see https://html.spec.whatwg.org/#elements-2
2592       * @see https://html.spec.whatwg.org/multipage/custom-elements.html#valid-custom-element-name
2593       *
2594       * @example
2595       * ~# php -a
2596       * php > $s = [paste copied contents of expression below including parentheses];
2597       * php > echo $s;
2598       */
2599      $tag_pattern = (
2600          '#<' . // Start with an opening bracket.
2601          '(/?)' . // Group 1 - If it's a closing tag it'll have a leading slash.
2602          '(' . // Group 2 - Tag name.
2603              // Custom element tags have more lenient rules than HTML tag names.
2604              '(?:[a-z](?:[a-z0-9._]*)-(?:[a-z0-9._-]+)+)' .
2605                  '|' .
2606              // Traditional tag rules approximate HTML tag names.
2607              '(?:[\w:]+)' .
2608          ')' .
2609          '(?:' .
2610              // We either immediately close the tag with its '>' and have nothing here.
2611              '\s*' .
2612              '(/?)' . // Group 3 - "attributes" for empty tag.
2613                  '|' .
2614              // Or we must start with space characters to separate the tag name from the attributes (or whitespace).
2615              '(\s+)' . // Group 4 - Pre-attribute whitespace.
2616              '([^>]*)' . // Group 5 - Attributes.
2617          ')' .
2618          '>#' // End with a closing bracket.
2619      );
2620  
2621      while ( preg_match( $tag_pattern, $text, $regex ) ) {
2622          $full_match        = $regex[0];
2623          $has_leading_slash = ! empty( $regex[1] );
2624          $tag_name          = $regex[2];
2625          $tag               = strtolower( $tag_name );
2626          $is_single_tag     = in_array( $tag, $single_tags, true );
2627          $pre_attribute_ws  = isset( $regex[4] ) ? $regex[4] : '';
2628          $attributes        = trim( isset( $regex[5] ) ? $regex[5] : $regex[3] );
2629          $has_self_closer   = str_ends_with( $attributes, '/' );
2630  
2631          $newtext .= $tagqueue;
2632  
2633          $i = strpos( $text, $full_match );
2634          $l = strlen( $full_match );
2635  
2636          // Clear the shifter.
2637          $tagqueue = '';
2638          if ( $has_leading_slash ) { // End tag.
2639              // If too many closing tags.
2640              if ( $stacksize <= 0 ) {
2641                  $tag = '';
2642                  // Or close to be safe $tag = '/' . $tag.
2643  
2644                  // If stacktop value = tag close value, then pop.
2645              } elseif ( $tagstack[ $stacksize - 1 ] === $tag ) { // Found closing tag.
2646                  $tag = '</' . $tag . '>'; // Close tag.
2647                  array_pop( $tagstack );
2648                  --$stacksize;
2649              } else { // Closing tag not at top, search for it.
2650                  for ( $j = $stacksize - 1; $j >= 0; $j-- ) {
2651                      if ( $tagstack[ $j ] === $tag ) {
2652                          // Add tag to tagqueue.
2653                          for ( $k = $stacksize - 1; $k >= $j; $k-- ) {
2654                              $tagqueue .= '</' . array_pop( $tagstack ) . '>';
2655                              --$stacksize;
2656                          }
2657                          break;
2658                      }
2659                  }
2660                  $tag = '';
2661              }
2662          } else { // Begin tag.
2663              if ( $has_self_closer ) {
2664                  /*
2665                   * If it presents itself as a self-closing tag, but it isn't a known single-entity self-closing tag,
2666                   * then don't let it be treated as such and immediately close it with a closing tag.
2667                   * The tag will encapsulate no text as a result.
2668                   */
2669                  if ( ! $is_single_tag ) {
2670                      $attributes = trim( substr( $attributes, 0, -1 ) ) . "></$tag";
2671                  }
2672              } elseif ( $is_single_tag ) {
2673                  // Else if it's a known single-entity tag but it doesn't close itself, do so.
2674                  $pre_attribute_ws = ' ';
2675                  $attributes      .= '/';
2676              } else {
2677                  /*
2678                   * It's not a single-entity tag.
2679                   * If the top of the stack is the same as the tag we want to push, close previous tag.
2680                   */
2681                  if ( $stacksize > 0 && ! in_array( $tag, $nestable_tags, true ) && $tagstack[ $stacksize - 1 ] === $tag ) {
2682                      $tagqueue = '</' . array_pop( $tagstack ) . '>';
2683                      --$stacksize;
2684                  }
2685                  $stacksize = array_push( $tagstack, $tag );
2686              }
2687  
2688              // Attributes.
2689              if ( $has_self_closer && $is_single_tag ) {
2690                  // We need some space - avoid <br/> and prefer <br />.
2691                  $pre_attribute_ws = ' ';
2692              }
2693  
2694              $tag = '<' . $tag . $pre_attribute_ws . $attributes . '>';
2695              // If already queuing a close tag, then put this tag on too.
2696              if ( ! empty( $tagqueue ) ) {
2697                  $tagqueue .= $tag;
2698                  $tag       = '';
2699              }
2700          }
2701          $newtext .= substr( $text, 0, $i ) . $tag;
2702          $text     = substr( $text, $i + $l );
2703      }
2704  
2705      // Clear tag queue.
2706      $newtext .= $tagqueue;
2707  
2708      // Add remaining text.
2709      $newtext .= $text;
2710  
2711      while ( $x = array_pop( $tagstack ) ) {
2712          $newtext .= '</' . $x . '>'; // Add remaining tags to close.
2713      }
2714  
2715      // WP fix for the bug with HTML comments.
2716      $newtext = str_replace( '< !--', '<!--', $newtext );
2717      $newtext = str_replace( '<    !--', '< !--', $newtext );
2718  
2719      return $newtext;
2720  }
2721  
2722  /**
2723   * Acts on text which is about to be edited.
2724   *
2725   * The $content is run through esc_textarea(), which uses htmlspecialchars()
2726   * to convert special characters to HTML entities. If `$richedit` is set to true,
2727   * it is simply a holder for the {@see 'format_to_edit'} filter.
2728   *
2729   * @since 0.71
2730   * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
2731   *
2732   * @param string $content   The text about to be edited.
2733   * @param bool   $rich_text Optional. Whether `$content` should be considered rich text,
2734   *                          in which case it would not be passed through esc_textarea().
2735   *                          Default false.
2736   * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
2737   */
2738  function format_to_edit( $content, $rich_text = false ) {
2739      /**
2740       * Filters the text to be formatted for editing.
2741       *
2742       * @since 1.2.0
2743       *
2744       * @param string $content The text, prior to formatting for editing.
2745       */
2746      $content = apply_filters( 'format_to_edit', $content );
2747      if ( ! $rich_text ) {
2748          $content = esc_textarea( $content );
2749      }
2750      return $content;
2751  }
2752  
2753  /**
2754   * Add leading zeros when necessary.
2755   *
2756   * If you set the threshold to '4' and the number is '10', then you will get
2757   * back '0010'. If you set the threshold to '4' and the number is '5000', then you
2758   * will get back '5000'.
2759   *
2760   * Uses sprintf to append the amount of zeros based on the $threshold parameter
2761   * and the size of the number. If the number is large enough, then no zeros will
2762   * be appended.
2763   *
2764   * @since 0.71
2765   *
2766   * @param int $number     Number to append zeros to if not greater than threshold.
2767   * @param int $threshold  Digit places number needs to be to not have zeros added.
2768   * @return string Adds leading zeros to number if needed.
2769   */
2770  function zeroise( $number, $threshold ) {
2771      return sprintf( '%0' . $threshold . 's', $number );
2772  }
2773  
2774  /**
2775   * Adds backslashes before letters and before a number at the start of a string.
2776   *
2777   * @since 0.71
2778   *
2779   * @param string $value Value to which backslashes will be added.
2780   * @return string String with backslashes inserted.
2781   */
2782  function backslashit( $value ) {
2783      if ( isset( $value[0] ) && $value[0] >= '0' && $value[0] <= '9' ) {
2784          $value = '\\\\' . $value;
2785      }
2786      return addcslashes( $value, 'A..Za..z' );
2787  }
2788  
2789  /**
2790   * Appends a trailing slash.
2791   *
2792   * Will remove trailing forward and backslashes if it exists already before adding
2793   * a trailing forward slash. This prevents double slashing a string or path.
2794   *
2795   * The primary use of this is for paths and thus should be used for paths. It is
2796   * not restricted to paths and offers no specific path support.
2797   *
2798   * @since 1.2.0
2799   *
2800   * @param string $value Value to which trailing slash will be added.
2801   * @return string String with trailing slash added.
2802   */
2803  function trailingslashit( $value ) {
2804      return untrailingslashit( $value ) . '/';
2805  }
2806  
2807  /**
2808   * Removes trailing forward slashes and backslashes if they exist.
2809   *
2810   * The primary use of this is for paths and thus should be used for paths. It is
2811   * not restricted to paths and offers no specific path support.
2812   *
2813   * @since 2.2.0
2814   *
2815   * @param string $text Value from which trailing slashes will be removed.
2816   * @return string String without the trailing slashes.
2817   */
2818  function untrailingslashit( $value ) {
2819      return rtrim( $value, '/\\' );
2820  }
2821  
2822  /**
2823   * Adds slashes to a string or recursively adds slashes to strings within an array.
2824   *
2825   * @since 0.71
2826   *
2827   * @param string|array $gpc String or array of data to slash.
2828   * @return string|array Slashed `$gpc`.
2829   */
2830  function addslashes_gpc( $gpc ) {
2831      return wp_slash( $gpc );
2832  }
2833  
2834  /**
2835   * Navigates through an array, object, or scalar, and removes slashes from the values.
2836   *
2837   * @since 2.0.0
2838   *
2839   * @param mixed $value The value to be stripped.
2840   * @return mixed Stripped value.
2841   */
2842  function stripslashes_deep( $value ) {
2843      return map_deep( $value, 'stripslashes_from_strings_only' );
2844  }
2845  
2846  /**
2847   * Callback function for `stripslashes_deep()` which strips slashes from strings.
2848   *
2849   * @since 4.4.0
2850   *
2851   * @param mixed $value The array or string to be stripped.
2852   * @return mixed The stripped value.
2853   */
2854  function stripslashes_from_strings_only( $value ) {
2855      return is_string( $value ) ? stripslashes( $value ) : $value;
2856  }
2857  
2858  /**
2859   * Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
2860   *
2861   * @since 2.2.0
2862   *
2863   * @param mixed $value The array or string to be encoded.
2864   * @return mixed The encoded value.
2865   */
2866  function urlencode_deep( $value ) {
2867      return map_deep( $value, 'urlencode' );
2868  }
2869  
2870  /**
2871   * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
2872   *
2873   * @since 3.4.0
2874   *
2875   * @param mixed $value The array or string to be encoded.
2876   * @return mixed The encoded value.
2877   */
2878  function rawurlencode_deep( $value ) {
2879      return map_deep( $value, 'rawurlencode' );
2880  }
2881  
2882  /**
2883   * Navigates through an array, object, or scalar, and decodes URL-encoded values
2884   *
2885   * @since 4.4.0
2886   *
2887   * @param mixed $value The array or string to be decoded.
2888   * @return mixed The decoded value.
2889   */
2890  function urldecode_deep( $value ) {
2891      return map_deep( $value, 'urldecode' );
2892  }
2893  
2894  /**
2895   * Converts email addresses characters to HTML entities to block spam bots.
2896   *
2897   * @since 0.71
2898   *
2899   * @param string $email_address Email address.
2900   * @param int    $hex_encoding  Optional. Set to 1 to enable hex encoding.
2901   * @return string Converted email address.
2902   */
2903  function antispambot( $email_address, $hex_encoding = 0 ) {
2904      $email_no_spam_address = '';
2905  
2906      for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
2907          $j = rand( 0, 1 + $hex_encoding );
2908  
2909          if ( 0 === $j ) {
2910              $email_no_spam_address .= '&#' . ord( $email_address[ $i ] ) . ';';
2911          } elseif ( 1 === $j ) {
2912              $email_no_spam_address .= $email_address[ $i ];
2913          } elseif ( 2 === $j ) {
2914              $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[ $i ] ) ), 2 );
2915          }
2916      }
2917  
2918      return str_replace( '@', '&#64;', $email_no_spam_address );
2919  }
2920  
2921  /**
2922   * Callback to convert URI match to HTML A element.
2923   *
2924   * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2925   *
2926   * @since 2.3.2
2927   * @access private
2928   *
2929   * @param array $matches Single Regex Match.
2930   * @return string HTML A element with URI address.
2931   */
2932  function _make_url_clickable_cb( $matches ) {
2933      $url = $matches[2];
2934  
2935      if ( ')' === $matches[3] && strpos( $url, '(' ) ) {
2936          /*
2937           * If the trailing character is a closing parenthesis, and the URL has an opening parenthesis in it,
2938           * add the closing parenthesis to the URL. Then we can let the parenthesis balancer do its thing below.
2939           */
2940          $url   .= $matches[3];
2941          $suffix = '';
2942      } else {
2943          $suffix = $matches[3];
2944      }
2945  
2946      // Include parentheses in the URL only if paired.
2947      while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
2948          $suffix = strrchr( $url, ')' ) . $suffix;
2949          $url    = substr( $url, 0, strrpos( $url, ')' ) );
2950      }
2951  
2952      $url = esc_url( $url );
2953      if ( empty( $url ) ) {
2954          return $matches[0];
2955      }
2956  
2957      $rel_attr = _make_clickable_rel_attr( $url );
2958  
2959      return $matches[1] . "<a href=\"{$url}\"{$rel_attr}>{$url}</a>" . $suffix;
2960  }
2961  
2962  /**
2963   * Callback to convert URL match to HTML A element.
2964   *
2965   * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2966   *
2967   * @since 2.3.2
2968   * @access private
2969   *
2970   * @param array $matches Single Regex Match.
2971   * @return string HTML A element with URL address.
2972   */
2973  function _make_web_ftp_clickable_cb( $matches ) {
2974      $ret  = '';
2975      $dest = $matches[2];
2976      $dest = 'http://' . $dest;
2977  
2978      // Removed trailing [.,;:)] from URL.
2979      $last_char = substr( $dest, -1 );
2980      if ( in_array( $last_char, array( '.', ',', ';', ':', ')' ), true ) === true ) {
2981          $ret  = $last_char;
2982          $dest = substr( $dest, 0, strlen( $dest ) - 1 );
2983      }
2984  
2985      $dest = esc_url( $dest );
2986      if ( empty( $dest ) ) {
2987          return $matches[0];
2988      }
2989  
2990      $rel_attr = _make_clickable_rel_attr( $dest );
2991  
2992      return $matches[1] . "<a href=\"{$dest}\"{$rel_attr}>{$dest}</a>{$ret}";
2993  }
2994  
2995  /**
2996   * Callback to convert email address match to HTML A element.
2997   *
2998   * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2999   *
3000   * @since 2.3.2
3001   * @access private
3002   *
3003   * @param array $matches Single Regex Match.
3004   * @return string HTML A element with email address.
3005   */
3006  function _make_email_clickable_cb( $matches ) {
3007      $email = $matches[2] . '@' . $matches[3];
3008  
3009      return $matches[1] . "<a href=\"mailto:{$email}\">{$email}</a>";
3010  }
3011  
3012  /**
3013   * Helper function used to build the "rel" attribute for a URL when creating an anchor using make_clickable().
3014   *
3015   * @since 6.2.0
3016   *
3017   * @param string $url The URL.
3018   * @return string The rel attribute for the anchor or an empty string if no rel attribute should be added.
3019   */
3020  function _make_clickable_rel_attr( $url ) {
3021      $rel_parts        = array();
3022      $scheme           = strtolower( wp_parse_url( $url, PHP_URL_SCHEME ) );
3023      $nofollow_schemes = array_intersect( wp_allowed_protocols(), array( 'https', 'http' ) );
3024  
3025      // Apply "nofollow" to external links with qualifying URL schemes (mailto:, tel:, etc... shouldn't be followed).
3026      if ( ! wp_is_internal_link( $url ) && in_array( $scheme, $nofollow_schemes, true ) ) {
3027          $rel_parts[] = 'nofollow';
3028      }
3029  
3030      // Apply "ugc" when in comment context.
3031      if ( 'comment_text' === current_filter() ) {
3032          $rel_parts[] = 'ugc';
3033      }
3034  
3035      $rel = implode( ' ', $rel_parts );
3036  
3037      /**
3038       * Filters the rel value that is added to URL matches converted to links.
3039       *
3040       * @since 5.3.0
3041       *
3042       * @param string $rel The rel value.
3043       * @param string $url The matched URL being converted to a link tag.
3044       */
3045      $rel = apply_filters( 'make_clickable_rel', $rel, $url );
3046  
3047      $rel_attr = $rel ? ' rel="' . esc_attr( $rel ) . '"' : '';
3048  
3049      return $rel_attr;
3050  }
3051  
3052  /**
3053   * Converts plaintext URI to HTML links.
3054   *
3055   * Converts URI, www and ftp, and email addresses. Finishes by fixing links
3056   * within links.
3057   *
3058   * @since 0.71
3059   *
3060   * @param string $text Content to convert URIs.
3061   * @return string Content with converted URIs.
3062   */
3063  function make_clickable( $text ) {
3064      $r               = '';
3065      $textarr         = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Split out HTML tags.
3066      $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>.
3067      foreach ( $textarr as $piece ) {
3068  
3069          if ( preg_match( '|^<code[\s>]|i', $piece )
3070              || preg_match( '|^<pre[\s>]|i', $piece )
3071              || preg_match( '|^<script[\s>]|i', $piece )
3072              || preg_match( '|^<style[\s>]|i', $piece )
3073          ) {
3074              ++$nested_code_pre;
3075          } elseif ( $nested_code_pre
3076              && ( '</code>' === strtolower( $piece )
3077                  || '</pre>' === strtolower( $piece )
3078                  || '</script>' === strtolower( $piece )
3079                  || '</style>' === strtolower( $piece )
3080              )
3081          ) {
3082              --$nested_code_pre;
3083          }
3084  
3085          if ( $nested_code_pre
3086              || empty( $piece )
3087              || ( '<' === $piece[0] && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) )
3088          ) {
3089              $r .= $piece;
3090              continue;
3091          }
3092  
3093          // Long strings might contain expensive edge cases...
3094          if ( 10000 < strlen( $piece ) ) {
3095              // ...break it up.
3096              foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing parentheses.
3097                  if ( 2101 < strlen( $chunk ) ) {
3098                      $r .= $chunk; // Too big, no whitespace: bail.
3099                  } else {
3100                      $r .= make_clickable( $chunk );
3101                  }
3102              }
3103          } else {
3104              $ret = " $piece "; // Pad with whitespace to simplify the regexes.
3105  
3106              $url_clickable = '~
3107                  ([\\s(<.,;:!?])                                # 1: Leading whitespace, or punctuation.
3108                  (                                              # 2: URL.
3109                      [\\w]{1,20}+://                                # Scheme and hier-part prefix.
3110                      (?=\S{1,2000}\s)                               # Limit to URLs less than about 2000 characters long.
3111                      [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+         # Non-punctuation URL character.
3112                      (?:                                            # Unroll the Loop: Only allow punctuation URL character if followed by a non-punctuation URL character.
3113                          [\'.,;:!?)]                                    # Punctuation URL character.
3114                          [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++         # Non-punctuation URL character.
3115                      )*
3116                  )
3117                  (\)?)                                          # 3: Trailing closing parenthesis (for parenthesis balancing post processing).
3118              ~xS';
3119              /*
3120               * The regex is a non-anchored pattern and does not have a single fixed starting character.
3121               * Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
3122               */
3123  
3124              $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
3125  
3126              $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
3127              $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
3128  
3129              $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
3130              $r  .= $ret;
3131          }
3132      }
3133  
3134      // Cleanup of accidental links within links.
3135      return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', '$1$3</a>', $r );
3136  }
3137  
3138  /**
3139   * Breaks a string into chunks by splitting at whitespace characters.
3140   *
3141   * The length of each returned chunk is as close to the specified length goal as possible,
3142   * with the caveat that each chunk includes its trailing delimiter.
3143   * Chunks longer than the goal are guaranteed to not have any inner whitespace.
3144   *
3145   * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
3146   *
3147   * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
3148   *
3149   *     _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234   890 123456789 1234567890a    45678   1 3 5 7 90 ", 10 ) ==
3150   *     array (
3151   *         0 => '1234 67890 ',  // 11 characters: Perfect split.
3152   *         1 => '1234 ',        //  5 characters: '1234 67890a' was too long.
3153   *         2 => '67890a cd ',   // 10 characters: '67890a cd 1234' was too long.
3154   *         3 => '1234   890 ',  // 11 characters: Perfect split.
3155   *         4 => '123456789 ',   // 10 characters: '123456789 1234567890a' was too long.
3156   *         5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split.
3157   *         6 => '   45678   ',  // 11 characters: Perfect split.
3158   *         7 => '1 3 5 7 90 ',  // 11 characters: End of $text.
3159   *     );
3160   *
3161   * @since 3.4.0
3162   * @access private
3163   *
3164   * @param string $text   The string to split.
3165   * @param int    $goal   The desired chunk length.
3166   * @return array Numeric array of chunks.
3167   */
3168  function _split_str_by_whitespace( $text, $goal ) {
3169      $chunks = array();
3170  
3171      $string_nullspace = strtr( $text, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
3172  
3173      while ( $goal < strlen( $string_nullspace ) ) {
3174          $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
3175  
3176          if ( false === $pos ) {
3177              $pos = strpos( $string_nullspace, "\000", $goal + 1 );
3178              if ( false === $pos ) {
3179                  break;
3180              }
3181          }
3182  
3183          $chunks[]         = substr( $text, 0, $pos + 1 );
3184          $text             = substr( $text, $pos + 1 );
3185          $string_nullspace = substr( $string_nullspace, $pos + 1 );
3186      }
3187  
3188      if ( $text ) {
3189          $chunks[] = $text;
3190      }
3191  
3192      return $chunks;
3193  }
3194  
3195  /**
3196   * Callback to add a rel attribute to HTML A element.
3197   *
3198   * Will remove already existing string before adding to prevent invalidating (X)HTML.
3199   *
3200   * @since 5.3.0
3201   *
3202   * @param array  $matches Single match.
3203   * @param string $rel     The rel attribute to add.
3204   * @return string HTML A element with the added rel attribute.
3205   */
3206  function wp_rel_callback( $matches, $rel ) {
3207      $text = $matches[1];
3208      $atts = wp_kses_hair( $matches[1], wp_allowed_protocols() );
3209  
3210      if ( ! empty( $atts['href'] ) && wp_is_internal_link( $atts['href']['value'] ) ) {
3211          $rel = trim( str_replace( 'nofollow', '', $rel ) );
3212      }
3213  
3214      if ( ! empty( $atts['rel'] ) ) {
3215          $parts     = array_map( 'trim', explode( ' ', $atts['rel']['value'] ) );
3216          $rel_array = array_map( 'trim', explode( ' ', $rel ) );
3217          $parts     = array_unique( array_merge( $parts, $rel_array ) );
3218          $rel       = implode( ' ', $parts );
3219          unset( $atts['rel'] );
3220  
3221          $html = '';
3222          foreach ( $atts as $name => $value ) {
3223              if ( isset( $value['vless'] ) && 'y' === $value['vless'] ) {
3224                  $html .= $name . ' ';
3225              } else {
3226                  $html .= "{$name}=\"" . esc_attr( $value['value'] ) . '" ';
3227              }
3228          }
3229          $text = trim( $html );
3230      }
3231  
3232      $rel_attr = $rel ? ' rel="' . esc_attr( $rel ) . '"' : '';
3233  
3234      return "<a {$text}{$rel_attr}>";
3235  }
3236  
3237  /**
3238   * Adds `rel="nofollow"` string to all HTML A elements in content.
3239   *
3240   * @since 1.5.0
3241   *
3242   * @param string $text Content that may contain HTML A elements.
3243   * @return string Converted content.
3244   */
3245  function wp_rel_nofollow( $text ) {
3246      // This is a pre-save filter, so text is already escaped.
3247      $text = stripslashes( $text );
3248      $text = preg_replace_callback(
3249          '|<a (.+?)>|i',
3250          static function ( $matches ) {
3251              return wp_rel_callback( $matches, 'nofollow' );
3252          },
3253          $text
3254      );
3255      return wp_slash( $text );
3256  }
3257  
3258  /**
3259   * Callback to add `rel="nofollow"` string to HTML A element.
3260   *
3261   * @since 2.3.0
3262   * @deprecated 5.3.0 Use wp_rel_callback()
3263   *
3264   * @param array $matches Single match.
3265   * @return string HTML A Element with `rel="nofollow"`.
3266   */
3267  function wp_rel_nofollow_callback( $matches ) {
3268      return wp_rel_callback( $matches, 'nofollow' );
3269  }
3270  
3271  /**
3272   * Adds `rel="nofollow ugc"` string to all HTML A elements in content.
3273   *
3274   * @since 5.3.0
3275   *
3276   * @param string $text Content that may contain HTML A elements.
3277   * @return string Converted content.
3278   */
3279  function wp_rel_ugc( $text ) {
3280      // This is a pre-save filter, so text is already escaped.
3281      $text = stripslashes( $text );
3282      $text = preg_replace_callback(
3283          '|<a (.+?)>|i',
3284          static function ( $matches ) {
3285              return wp_rel_callback( $matches, 'nofollow ugc' );
3286          },
3287          $text
3288      );
3289      return wp_slash( $text );
3290  }
3291  
3292  /**
3293   * Adds `rel="noopener"` to all HTML A elements that have a target.
3294   *
3295   * @since 5.1.0
3296   * @since 5.6.0 Removed 'noreferrer' relationship.
3297   *
3298   * @param string $text Content that may contain HTML A elements.
3299   * @return string Converted content.
3300   */
3301  function wp_targeted_link_rel( $text ) {
3302      // Don't run (more expensive) regex if no links with targets.
3303      if ( stripos( $text, 'target' ) === false || stripos( $text, '<a ' ) === false || is_serialized( $text ) ) {
3304          return $text;
3305      }
3306  
3307      $script_and_style_regex = '/<(script|style).*?<\/\\1>/si';
3308  
3309      preg_match_all( $script_and_style_regex, $text, $matches );
3310      $extra_parts = $matches[0];
3311      $html_parts  = preg_split( $script_and_style_regex, $text );
3312  
3313      foreach ( $html_parts as &$part ) {
3314          $part = preg_replace_callback( '|<a\s([^>]*target\s*=[^>]*)>|i', 'wp_targeted_link_rel_callback', $part );
3315      }
3316  
3317      $text = '';
3318      for ( $i = 0; $i < count( $html_parts ); $i++ ) {
3319          $text .= $html_parts[ $i ];
3320          if ( isset( $extra_parts[ $i ] ) ) {
3321              $text .= $extra_parts[ $i ];
3322          }
3323      }
3324  
3325      return $text;
3326  }
3327  
3328  /**
3329   * Callback to add `rel="noopener"` string to HTML A element.
3330   *
3331   * Will not duplicate an existing 'noopener' value to avoid invalidating the HTML.
3332   *
3333   * @since 5.1.0
3334   * @since 5.6.0 Removed 'noreferrer' relationship.
3335   *
3336   * @param array $matches Single match.
3337   * @return string HTML A Element with `rel="noopener"` in addition to any existing values.
3338   */
3339  function wp_targeted_link_rel_callback( $matches ) {
3340      $link_html          = $matches[1];
3341      $original_link_html = $link_html;
3342  
3343      // Consider the HTML escaped if there are no unescaped quotes.
3344      $is_escaped = ! preg_match( '/(^|[^\\\\])[\'"]/', $link_html );
3345      if ( $is_escaped ) {
3346          // Replace only the quotes so that they are parsable by wp_kses_hair(), leave the rest as is.
3347          $link_html = preg_replace( '/\\\\([\'"])/', '$1', $link_html );
3348      }
3349  
3350      $atts = wp_kses_hair( $link_html, wp_allowed_protocols() );
3351  
3352      /**
3353       * Filters the rel values that are added to links with `target` attribute.
3354       *
3355       * @since 5.1.0
3356       *
3357       * @param string $rel       The rel values.
3358       * @param string $link_html The matched content of the link tag including all HTML attributes.
3359       */
3360      $rel = apply_filters( 'wp_targeted_link_rel', 'noopener', $link_html );
3361  
3362      // Return early if no rel values to be added or if no actual target attribute.
3363      if ( ! $rel || ! isset( $atts['target'] ) ) {
3364          return "<a $original_link_html>";
3365      }
3366  
3367      if ( isset( $atts['rel'] ) ) {
3368          $all_parts = preg_split( '/\s/', "{$atts['rel']['value']} $rel", -1, PREG_SPLIT_NO_EMPTY );
3369          $rel       = implode( ' ', array_unique( $all_parts ) );
3370      }
3371  
3372      $atts['rel']['whole'] = 'rel="' . esc_attr( $rel ) . '"';
3373      $link_html            = implode( ' ', array_column( $atts, 'whole' ) );
3374  
3375      if ( $is_escaped ) {
3376          $link_html = preg_replace( '/[\'"]/', '\\\\$0', $link_html );
3377      }
3378  
3379      return "<a $link_html>";
3380  }
3381  
3382  /**
3383   * Adds all filters modifying the rel attribute of targeted links.
3384   *
3385   * @since 5.1.0
3386   */
3387  function wp_init_targeted_link_rel_filters() {
3388      $filters = array(
3389          'title_save_pre',
3390          'content_save_pre',
3391          'excerpt_save_pre',
3392          'content_filtered_save_pre',
3393          'pre_comment_content',
3394          'pre_term_description',
3395          'pre_link_description',
3396          'pre_link_notes',
3397          'pre_user_description',
3398      );
3399  
3400      foreach ( $filters as $filter ) {
3401          add_filter( $filter, 'wp_targeted_link_rel' );
3402      }
3403  }
3404  
3405  /**
3406   * Removes all filters modifying the rel attribute of targeted links.
3407   *
3408   * @since 5.1.0
3409   */
3410  function wp_remove_targeted_link_rel_filters() {
3411      $filters = array(
3412          'title_save_pre',
3413          'content_save_pre',
3414          'excerpt_save_pre',
3415          'content_filtered_save_pre',
3416          'pre_comment_content',
3417          'pre_term_description',
3418          'pre_link_description',
3419          'pre_link_notes',
3420          'pre_user_description',
3421      );
3422  
3423      foreach ( $filters as $filter ) {
3424          remove_filter( $filter, 'wp_targeted_link_rel' );
3425      }
3426  }
3427  
3428  /**
3429   * Converts one smiley code to the icon graphic file equivalent.
3430   *
3431   * Callback handler for convert_smilies().
3432   *
3433   * Looks up one smiley code in the $wpsmiliestrans global array and returns an
3434   * `<img>` string for that smiley.
3435   *
3436   * @since 2.8.0
3437   *
3438   * @global array $wpsmiliestrans
3439   *
3440   * @param array $matches Single match. Smiley code to convert to image.
3441   * @return string Image string for smiley.
3442   */
3443  function translate_smiley( $matches ) {
3444      global $wpsmiliestrans;
3445  
3446      if ( count( $matches ) === 0 ) {
3447          return '';
3448      }
3449  
3450      $smiley = trim( reset( $matches ) );
3451      $img    = $wpsmiliestrans[ $smiley ];
3452  
3453      $matches    = array();
3454      $ext        = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
3455      $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png', 'webp', 'avif' );
3456  
3457      // Don't convert smilies that aren't images - they're probably emoji.
3458      if ( ! in_array( $ext, $image_exts, true ) ) {
3459          return $img;
3460      }
3461  
3462      /**
3463       * Filters the Smiley image URL before it's used in the image element.
3464       *
3465       * @since 2.9.0
3466       *
3467       * @param string $smiley_url URL for the smiley image.
3468       * @param string $img        Filename for the smiley image.
3469       * @param string $site_url   Site URL, as returned by site_url().
3470       */
3471      $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
3472  
3473      return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
3474  }
3475  
3476  /**
3477   * Converts text equivalent of smilies to images.
3478   *
3479   * Will only convert smilies if the option 'use_smilies' is true and the global
3480   * used in the function isn't empty.
3481   *
3482   * @since 0.71
3483   *
3484   * @global string|array $wp_smiliessearch
3485   *
3486   * @param string $text Content to convert smilies from text.
3487   * @return string Converted content with text smilies replaced with images.
3488   */
3489  function convert_smilies( $text ) {
3490      global $wp_smiliessearch;
3491      $output = '';
3492      if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
3493          // HTML loop taken from texturize function, could possible be consolidated.
3494          $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Capture the tags as well as in between.
3495          $stop    = count( $textarr ); // Loop stuff.
3496  
3497          // Ignore processing of specific tags.
3498          $tags_to_ignore       = 'code|pre|style|script|textarea';
3499          $ignore_block_element = '';
3500  
3501          for ( $i = 0; $i < $stop; $i++ ) {
3502              $content = $textarr[ $i ];
3503  
3504              // If we're in an ignore block, wait until we find its closing tag.
3505              if ( '' === $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')[^>]*>/', $content, $matches ) ) {
3506                  $ignore_block_element = $matches[1];
3507              }
3508  
3509              // If it's not a tag and not in ignore block.
3510              if ( '' === $ignore_block_element && strlen( $content ) > 0 && '<' !== $content[0] ) {
3511                  $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
3512              }
3513  
3514              // Did we exit ignore block?
3515              if ( '' !== $ignore_block_element && '</' . $ignore_block_element . '>' === $content ) {
3516                  $ignore_block_element = '';
3517              }
3518  
3519              $output .= $content;
3520          }
3521      } else {
3522          // Return default text.
3523          $output = $text;
3524      }
3525      return $output;
3526  }
3527  
3528  /**
3529   * Verifies that an email is valid.
3530   *
3531   * Does not grok i18n domains. Not RFC compliant.
3532   *
3533   * @since 0.71
3534   *
3535   * @param string $email      Email address to verify.
3536   * @param bool   $deprecated Deprecated.
3537   * @return string|false Valid email address on success, false on failure.
3538   */
3539  function is_email( $email, $deprecated = false ) {
3540      if ( ! empty( $deprecated ) ) {
3541          _deprecated_argument( __FUNCTION__, '3.0.0' );
3542      }
3543  
3544      // Test for the minimum length the email can be.
3545      if ( strlen( $email ) < 6 ) {
3546          /**
3547           * Filters whether an email address is valid.
3548           *
3549           * This filter is evaluated under several different contexts, such as 'email_too_short',
3550           * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3551           * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
3552           *
3553           * @since 2.8.0
3554           *
3555           * @param string|false $is_email The email address if successfully passed the is_email() checks, false otherwise.
3556           * @param string       $email    The email address being checked.
3557           * @param string       $context  Context under which the email was tested.
3558           */
3559          return apply_filters( 'is_email', false, $email, 'email_too_short' );
3560      }
3561  
3562      // Test for an @ character after the first position.
3563      if ( strpos( $email, '@', 1 ) === false ) {
3564          /** This filter is documented in wp-includes/formatting.php */
3565          return apply_filters( 'is_email', false, $email, 'email_no_at' );
3566      }
3567  
3568      // Split out the local and domain parts.
3569      list( $local, $domain ) = explode( '@', $email, 2 );
3570  
3571      /*
3572       * LOCAL PART
3573       * Test for invalid characters.
3574       */
3575      if ( ! preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
3576          /** This filter is documented in wp-includes/formatting.php */
3577          return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
3578      }
3579  
3580      /*
3581       * DOMAIN PART
3582       * Test for sequences of periods.
3583       */
3584      if ( preg_match( '/\.{2,}/', $domain ) ) {
3585          /** This filter is documented in wp-includes/formatting.php */
3586          return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
3587      }
3588  
3589      // Test for leading and trailing periods and whitespace.
3590      if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
3591          /** This filter is documented in wp-includes/formatting.php */
3592          return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
3593      }
3594  
3595      // Split the domain into subs.
3596      $subs = explode( '.', $domain );
3597  
3598      // Assume the domain will have at least two subs.
3599      if ( 2 > count( $subs ) ) {
3600          /** This filter is documented in wp-includes/formatting.php */
3601          return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
3602      }
3603  
3604      // Loop through each sub.
3605      foreach ( $subs as $sub ) {
3606          // Test for leading and trailing hyphens and whitespace.
3607          if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
3608              /** This filter is documented in wp-includes/formatting.php */
3609              return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
3610          }
3611  
3612          // Test for invalid characters.
3613          if ( ! preg_match( '/^[a-z0-9-]+$/i', $sub ) ) {
3614              /** This filter is documented in wp-includes/formatting.php */
3615              return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
3616          }
3617      }
3618  
3619      // Congratulations, your email made it!
3620      /** This filter is documented in wp-includes/formatting.php */
3621      return apply_filters( 'is_email', $email, $email, null );
3622  }
3623  
3624  /**
3625   * Converts to ASCII from email subjects.
3626   *
3627   * @since 1.2.0
3628   *
3629   * @param string $subject Subject line.
3630   * @return string Converted string to ASCII.
3631   */
3632  function wp_iso_descrambler( $subject ) {
3633      /* this may only work with iso-8859-1, I'm afraid */
3634      if ( ! preg_match( '#\=\?(.+)\?Q\?(.+)\?\=#i', $subject, $matches ) ) {
3635          return $subject;
3636      }
3637  
3638      $subject = str_replace( '_', ' ', $matches[2] );
3639      return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
3640  }
3641  
3642  /**
3643   * Helper function to convert hex encoded chars to ASCII.
3644   *
3645   * @since 3.1.0
3646   * @access private
3647   *
3648   * @param array $matches The preg_replace_callback matches array.
3649   * @return string Converted chars.
3650   */
3651  function _wp_iso_convert( $matches ) {
3652      return chr( hexdec( strtolower( $matches[1] ) ) );
3653  }
3654  
3655  /**
3656   * Given a date in the timezone of the site, returns that date in UTC.
3657   *
3658   * Requires and returns a date in the Y-m-d H:i:s format.
3659   * Return format can be overridden using the $format parameter.
3660   *
3661   * @since 1.2.0
3662   *
3663   * @param string $date_string The date to be converted, in the timezone of the site.
3664   * @param string $format      The format string for the returned date. Default 'Y-m-d H:i:s'.
3665   * @return string Formatted version of the date, in UTC.
3666   */
3667  function get_gmt_from_date( $date_string, $format = 'Y-m-d H:i:s' ) {
3668      $datetime = date_create( $date_string, wp_timezone() );
3669  
3670      if ( false === $datetime ) {
3671          return gmdate( $format, 0 );
3672      }
3673  
3674      return $datetime->setTimezone( new DateTimeZone( 'UTC' ) )->format( $format );
3675  }
3676  
3677  /**
3678   * Given a date in UTC or GMT timezone, returns that date in the timezone of the site.
3679   *
3680   * Requires a date in the Y-m-d H:i:s format.
3681   * Default return format of 'Y-m-d H:i:s' can be overridden using the `$format` parameter.
3682   *
3683   * @since 1.2.0
3684   *
3685   * @param string $date_string The date to be converted, in UTC or GMT timezone.
3686   * @param string $format      The format string for the returned date. Default 'Y-m-d H:i:s'.
3687   * @return string Formatted version of the date, in the site's timezone.
3688   */
3689  function get_date_from_gmt( $date_string, $format = 'Y-m-d H:i:s' ) {
3690      $datetime = date_create( $date_string, new DateTimeZone( 'UTC' ) );
3691  
3692      if ( false === $datetime ) {
3693          return gmdate( $format, 0 );
3694      }
3695  
3696      return $datetime->setTimezone( wp_timezone() )->format( $format );
3697  }
3698  
3699  /**
3700   * Given an ISO 8601 timezone, returns its UTC offset in seconds.
3701   *
3702   * @since 1.5.0
3703   *
3704   * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
3705   * @return int|float The offset in seconds.
3706   */
3707  function iso8601_timezone_to_offset( $timezone ) {
3708      // $timezone is either 'Z' or '[+|-]hhmm'.
3709      if ( 'Z' === $timezone ) {
3710          $offset = 0;
3711      } else {
3712          $sign    = ( str_starts_with( $timezone, '+' ) ) ? 1 : -1;
3713          $hours   = (int) substr( $timezone, 1, 2 );
3714          $minutes = (int) substr( $timezone, 3, 4 ) / 60;
3715          $offset  = $sign * HOUR_IN_SECONDS * ( $hours + $minutes );
3716      }
3717      return $offset;
3718  }
3719  
3720  /**
3721   * 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].
3722   *
3723   * @since 1.5.0
3724   *
3725   * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}.
3726   * @param string $timezone    Optional. If set to 'gmt' returns the result in UTC. Default 'user'.
3727   * @return string|false The date and time in MySQL DateTime format - Y-m-d H:i:s, or false on failure.
3728   */
3729  function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
3730      $timezone    = strtolower( $timezone );
3731      $wp_timezone = wp_timezone();
3732      $datetime    = date_create( $date_string, $wp_timezone ); // Timezone is ignored if input has one.
3733  
3734      if ( false === $datetime ) {
3735          return false;
3736      }
3737  
3738      if ( 'gmt' === $timezone ) {
3739          return $datetime->setTimezone( new DateTimeZone( 'UTC' ) )->format( 'Y-m-d H:i:s' );
3740      }
3741  
3742      if ( 'user' === $timezone ) {
3743          return $datetime->setTimezone( $wp_timezone )->format( 'Y-m-d H:i:s' );
3744      }
3745  
3746      return false;
3747  }
3748  
3749  /**
3750   * Strips out all characters that are not allowable in an email.
3751   *
3752   * @since 1.5.0
3753   *
3754   * @param string $email Email address to filter.
3755   * @return string Filtered email address.
3756   */
3757  function sanitize_email( $email ) {
3758      // Test for the minimum length the email can be.
3759      if ( strlen( $email ) < 6 ) {
3760          /**
3761           * Filters a sanitized email address.
3762           *
3763           * This filter is evaluated under several contexts, including 'email_too_short',
3764           * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3765           * 'domain_no_periods', 'domain_no_valid_subs', or no context.
3766           *
3767           * @since 2.8.0
3768           *
3769           * @param string $sanitized_email The sanitized email address.
3770           * @param string $email           The email address, as provided to sanitize_email().
3771           * @param string|null $message    A message to pass to the user. null if email is sanitized.
3772           */
3773          return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
3774      }
3775  
3776      // Test for an @ character after the first position.
3777      if ( strpos( $email, '@', 1 ) === false ) {
3778          /** This filter is documented in wp-includes/formatting.php */
3779          return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
3780      }
3781  
3782      // Split out the local and domain parts.
3783      list( $local, $domain ) = explode( '@', $email, 2 );
3784  
3785      /*
3786       * LOCAL PART
3787       * Test for invalid characters.
3788       */
3789      $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
3790      if ( '' === $local ) {
3791          /** This filter is documented in wp-includes/formatting.php */
3792          return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
3793      }
3794  
3795      /*
3796       * DOMAIN PART
3797       * Test for sequences of periods.
3798       */
3799      $domain = preg_replace( '/\.{2,}/', '', $domain );
3800      if ( '' === $domain ) {
3801          /** This filter is documented in wp-includes/formatting.php */
3802          return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
3803      }
3804  
3805      // Test for leading and trailing periods and whitespace.
3806      $domain = trim( $domain, " \t\n\r\0\x0B." );
3807      if ( '' === $domain ) {
3808          /** This filter is documented in wp-includes/formatting.php */
3809          return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
3810      }
3811  
3812      // Split the domain into subs.
3813      $subs = explode( '.', $domain );
3814  
3815      // Assume the domain will have at least two subs.
3816      if ( 2 > count( $subs ) ) {
3817          /** This filter is documented in wp-includes/formatting.php */
3818          return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
3819      }
3820  
3821      // Create an array that will contain valid subs.
3822      $new_subs = array();
3823  
3824      // Loop through each sub.
3825      foreach ( $subs as $sub ) {
3826          // Test for leading and trailing hyphens.
3827          $sub = trim( $sub, " \t\n\r\0\x0B-" );
3828  
3829          // Test for invalid characters.
3830          $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
3831  
3832          // If there's anything left, add it to the valid subs.
3833          if ( '' !== $sub ) {
3834              $new_subs[] = $sub;
3835          }
3836      }
3837  
3838      // If there aren't 2 or more valid subs.
3839      if ( 2 > count( $new_subs ) ) {
3840          /** This filter is documented in wp-includes/formatting.php */
3841          return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
3842      }
3843  
3844      // Join valid subs into the new domain.
3845      $domain = implode( '.', $new_subs );
3846  
3847      // Put the email back together.
3848      $sanitized_email = $local . '@' . $domain;
3849  
3850      // Congratulations, your email made it!
3851      /** This filter is documented in wp-includes/formatting.php */
3852      return apply_filters( 'sanitize_email', $sanitized_email, $email, null );
3853  }
3854  
3855  /**
3856   * Determines the difference between two timestamps.
3857   *
3858   * The difference is returned in a human-readable format such as "1 hour",
3859   * "5 mins", "2 days".
3860   *
3861   * @since 1.5.0
3862   * @since 5.3.0 Added support for showing a difference in seconds.
3863   *
3864   * @param int $from Unix timestamp from which the difference begins.
3865   * @param int $to   Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
3866   * @return string Human-readable time difference.
3867   */
3868  function human_time_diff( $from, $to = 0 ) {
3869      if ( empty( $to ) ) {
3870          $to = time();
3871      }
3872  
3873      $diff = (int) abs( $to - $from );
3874  
3875      if ( $diff < MINUTE_IN_SECONDS ) {
3876          $secs = $diff;
3877          if ( $secs <= 1 ) {
3878              $secs = 1;
3879          }
3880          /* translators: Time difference between two dates, in seconds. %s: Number of seconds. */
3881          $since = sprintf( _n( '%s second', '%s seconds', $secs ), $secs );
3882      } elseif ( $diff < HOUR_IN_SECONDS && $diff >= MINUTE_IN_SECONDS ) {
3883          $mins = round( $diff / MINUTE_IN_SECONDS );
3884          if ( $mins <= 1 ) {
3885              $mins = 1;
3886          }
3887          /* translators: Time difference between two dates, in minutes (min=minute). %s: Number of minutes. */
3888          $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
3889      } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
3890          $hours = round( $diff / HOUR_IN_SECONDS );
3891          if ( $hours <= 1 ) {
3892              $hours = 1;
3893          }
3894          /* translators: Time difference between two dates, in hours. %s: Number of hours. */
3895          $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
3896      } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
3897          $days = round( $diff / DAY_IN_SECONDS );
3898          if ( $days <= 1 ) {
3899              $days = 1;
3900          }
3901          /* translators: Time difference between two dates, in days. %s: Number of days. */
3902          $since = sprintf( _n( '%s day', '%s days', $days ), $days );
3903      } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
3904          $weeks = round( $diff / WEEK_IN_SECONDS );
3905          if ( $weeks <= 1 ) {
3906              $weeks = 1;
3907          }
3908          /* translators: Time difference between two dates, in weeks. %s: Number of weeks. */
3909          $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
3910      } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
3911          $months = round( $diff / MONTH_IN_SECONDS );
3912          if ( $months <= 1 ) {
3913              $months = 1;
3914          }
3915          /* translators: Time difference between two dates, in months. %s: Number of months. */
3916          $since = sprintf( _n( '%s month', '%s months', $months ), $months );
3917      } elseif ( $diff >= YEAR_IN_SECONDS ) {
3918          $years = round( $diff / YEAR_IN_SECONDS );
3919          if ( $years <= 1 ) {
3920              $years = 1;
3921          }
3922          /* translators: Time difference between two dates, in years. %s: Number of years. */
3923          $since = sprintf( _n( '%s year', '%s years', $years ), $years );
3924      }
3925  
3926      /**
3927       * Filters the human-readable difference between two timestamps.
3928       *
3929       * @since 4.0.0
3930       *
3931       * @param string $since The difference in human-readable text.
3932       * @param int    $diff  The difference in seconds.
3933       * @param int    $from  Unix timestamp from which the difference begins.
3934       * @param int    $to    Unix timestamp to end the time difference.
3935       */
3936      return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
3937  }
3938  
3939  /**
3940   * Generates an excerpt from the content, if needed.
3941   *
3942   * Returns a maximum of 55 words with an ellipsis appended if necessary.
3943   *
3944   * The 55-word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter
3945   * The ' [&hellip;]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter
3946   *
3947   * @since 1.5.0
3948   * @since 5.2.0 Added the `$post` parameter.
3949   * @since 6.3.0 Removes footnotes markup from the excerpt content.
3950   *
3951   * @param string             $text Optional. The excerpt. If set to empty, an excerpt is generated.
3952   * @param WP_Post|object|int $post Optional. WP_Post instance or Post ID/object. Default null.
3953   * @return string The excerpt.
3954   */
3955  function wp_trim_excerpt( $text = '', $post = null ) {
3956      $raw_excerpt = $text;
3957  
3958      if ( '' === trim( $text ) ) {
3959          $post = get_post( $post );
3960          $text = get_the_content( '', false, $post );
3961  
3962          $text = strip_shortcodes( $text );
3963          $text = excerpt_remove_blocks( $text );
3964          $text = excerpt_remove_footnotes( $text );
3965  
3966          /*
3967           * Temporarily unhook wp_filter_content_tags() since any tags
3968           * within the excerpt are stripped out. Modifying the tags here
3969           * is wasteful and can lead to bugs in the image counting logic.
3970           */
3971          $filter_image_removed = remove_filter( 'the_content', 'wp_filter_content_tags', 12 );
3972  
3973          /*
3974           * Temporarily unhook do_blocks() since excerpt_remove_blocks( $text )
3975           * handles block rendering needed for excerpt.
3976           */
3977          $filter_block_removed = remove_filter( 'the_content', 'do_blocks', 9 );
3978  
3979          /** This filter is documented in wp-includes/post-template.php */
3980          $text = apply_filters( 'the_content', $text );
3981          $text = str_replace( ']]>', ']]&gt;', $text );
3982  
3983          // Restore the original filter if removed.
3984          if ( $filter_block_removed ) {
3985              add_filter( 'the_content', 'do_blocks', 9 );
3986          }
3987  
3988          /*
3989           * Only restore the filter callback if it was removed above. The logic
3990           * to unhook and restore only applies on the default priority of 10,
3991           * which is generally used for the filter callback in WordPress core.
3992           */
3993          if ( $filter_image_removed ) {
3994              add_filter( 'the_content', 'wp_filter_content_tags', 12 );
3995          }
3996  
3997          /* translators: Maximum number of words used in a post excerpt. */
3998          $excerpt_length = (int) _x( '55', 'excerpt_length' );
3999  
4000          /**
4001           * Filters the maximum number of words in a post excerpt.
4002           *
4003           * @since 2.7.0
4004           *
4005           * @param int $number The maximum number of words. Default 55.
4006           */
4007          $excerpt_length = (int) apply_filters( 'excerpt_length', $excerpt_length );
4008  
4009          /**
4010           * Filters the string in the "more" link displayed after a trimmed excerpt.
4011           *
4012           * @since 2.9.0
4013           *
4014           * @param string $more_string The string shown within the more link.
4015           */
4016          $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[&hellip;]' );
4017          $text         = wp_trim_words( $text, $excerpt_length, $excerpt_more );
4018  
4019      }
4020  
4021      /**
4022       * Filters the trimmed excerpt string.
4023       *
4024       * @since 2.8.0
4025       *
4026       * @param string $text        The trimmed text.
4027       * @param string $raw_excerpt The text prior to trimming.
4028       */
4029      return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
4030  }
4031  
4032  /**
4033   * Trims text to a certain number of words.
4034   *
4035   * This function is localized. For languages that count 'words' by the individual
4036   * character (such as East Asian languages), the $num_words argument will apply
4037   * to the number of individual characters.
4038   *
4039   * @since 3.3.0
4040   *
4041   * @param string $text      Text to trim.
4042   * @param int    $num_words Number of words. Default 55.
4043   * @param string $more      Optional. What to append if $text needs to be trimmed. Default '&hellip;'.
4044   * @return string Trimmed text.
4045   */
4046  function wp_trim_words( $text, $num_words = 55, $more = null ) {
4047      if ( null === $more ) {
4048          $more = __( '&hellip;' );
4049      }
4050  
4051      $original_text = $text;
4052      $text          = wp_strip_all_tags( $text );
4053      $num_words     = (int) $num_words;
4054  
4055      if ( str_starts_with( wp_get_word_count_type(), 'characters' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
4056          $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
4057          preg_match_all( '/./u', $text, $words_array );
4058          $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
4059          $sep         = '';
4060      } else {
4061          $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
4062          $sep         = ' ';
4063      }
4064  
4065      if ( count( $words_array ) > $num_words ) {
4066          array_pop( $words_array );
4067          $text = implode( $sep, $words_array );
4068          $text = $text . $more;
4069      } else {
4070          $text = implode( $sep, $words_array );
4071      }
4072  
4073      /**
4074       * Filters the text content after words have been trimmed.
4075       *
4076       * @since 3.3.0
4077       *
4078       * @param string $text          The trimmed text.
4079       * @param int    $num_words     The number of words to trim the text to. Default 55.
4080       * @param string $more          An optional string to append to the end of the trimmed text, e.g. &hellip;.
4081       * @param string $original_text The text before it was trimmed.
4082       */
4083      return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
4084  }
4085  
4086  /**
4087   * Converts named entities into numbered entities.
4088   *
4089   * @since 1.5.1
4090   *
4091   * @param string $text The text within which entities will be converted.
4092   * @return string Text with converted entities.
4093   */
4094  function ent2ncr( $text ) {
4095  
4096      /**
4097       * Filters text before named entities are converted into numbered entities.
4098       *
4099       * A non-null string must be returned for the filter to be evaluated.
4100       *
4101       * @since 3.3.0
4102       *
4103       * @param string|null $converted_text The text to be converted. Default null.
4104       * @param string      $text           The text prior to entity conversion.
4105       */
4106      $filtered = apply_filters( 'pre_ent2ncr', null, $text );
4107      if ( null !== $filtered ) {
4108          return $filtered;
4109      }
4110  
4111      $to_ncr = array(
4112          '&quot;'     => '&#34;',
4113          '&amp;'      => '&#38;',
4114          '&lt;'       => '&#60;',
4115          '&gt;'       => '&#62;',
4116          '|'          => '&#124;',
4117          '&nbsp;'     => '&#160;',
4118          '&iexcl;'    => '&#161;',
4119          '&cent;'     => '&#162;',
4120          '&pound;'    => '&#163;',
4121          '&curren;'   => '&#164;',
4122          '&yen;'      => '&#165;',
4123          '&brvbar;'   => '&#166;',
4124          '&brkbar;'   => '&#166;',
4125          '&sect;'     => '&#167;',
4126          '&uml;'      => '&#168;',
4127          '&die;'      => '&#168;',
4128          '&copy;'     => '&#169;',
4129          '&ordf;'     => '&#170;',
4130          '&laquo;'    => '&#171;',
4131          '&not;'      => '&#172;',
4132          '&shy;'      => '&#173;',
4133          '&reg;'      => '&#174;',
4134          '&macr;'     => '&#175;',
4135          '&hibar;'    => '&#175;',
4136          '&deg;'      => '&#176;',
4137          '&plusmn;'   => '&#177;',
4138          '&sup2;'     => '&#178;',
4139          '&sup3;'     => '&#179;',
4140          '&acute;'    => '&#180;',
4141          '&micro;'    => '&#181;',
4142          '&para;'     => '&#182;',
4143          '&middot;'   => '&#183;',
4144          '&cedil;'    => '&#184;',
4145          '&sup1;'     => '&#185;',
4146          '&ordm;'     => '&#186;',
4147          '&raquo;'    => '&#187;',
4148          '&frac14;'   => '&#188;',
4149          '&frac12;'   => '&#189;',
4150          '&frac34;'   => '&#190;',
4151          '&iquest;'   => '&#191;',
4152          '&Agrave;'   => '&#192;',
4153          '&Aacute;'   => '&#193;',
4154          '&Acirc;'    => '&#194;',
4155          '&Atilde;'   => '&#195;',
4156          '&Auml;'     => '&#196;',
4157          '&Aring;'    => '&#197;',
4158          '&AElig;'    => '&#198;',
4159          '&Ccedil;'   => '&#199;',
4160          '&Egrave;'   => '&#200;',
4161          '&Eacute;'   => '&#201;',
4162          '&Ecirc;'    => '&#202;',
4163          '&Euml;'     => '&#203;',
4164          '&Igrave;'   => '&#204;',
4165          '&Iacute;'   => '&#205;',
4166          '&Icirc;'    => '&#206;',
4167          '&Iuml;'     => '&#207;',
4168          '&ETH;'      => '&#208;',
4169          '&Ntilde;'   => '&#209;',
4170          '&Ograve;'   => '&#210;',
4171          '&Oacute;'   => '&#211;',
4172          '&Ocirc;'    => '&#212;',
4173          '&Otilde;'   => '&#213;',
4174          '&Ouml;'     => '&#214;',
4175          '&times;'    => '&#215;',
4176          '&Oslash;'   => '&#216;',
4177          '&Ugrave;'   => '&#217;',
4178          '&Uacute;'   => '&#218;',
4179          '&Ucirc;'    => '&#219;',
4180          '&Uuml;'     => '&#220;',
4181          '&Yacute;'   => '&#221;',
4182          '&THORN;'    => '&#222;',
4183          '&szlig;'    => '&#223;',
4184          '&agrave;'   => '&#224;',
4185          '&aacute;'   => '&#225;',
4186          '&acirc;'    => '&#226;',
4187          '&atilde;'   => '&#227;',
4188          '&auml;'     => '&#228;',
4189          '&aring;'    => '&#229;',
4190          '&aelig;'    => '&#230;',
4191          '&ccedil;'   => '&#231;',
4192          '&egrave;'   => '&#232;',
4193          '&eacute;'   => '&#233;',
4194          '&ecirc;'    => '&#234;',
4195          '&euml;'     => '&#235;',
4196          '&igrave;'   => '&#236;',
4197          '&iacute;'   => '&#237;',
4198          '&icirc;'    => '&#238;',
4199          '&iuml;'     => '&#239;',
4200          '&eth;'      => '&#240;',
4201          '&ntilde;'   => '&#241;',
4202          '&ograve;'   => '&#242;',
4203          '&oacute;'   => '&#243;',
4204          '&ocirc;'    => '&#244;',
4205          '&otilde;'   => '&#245;',
4206          '&ouml;'     => '&#246;',
4207          '&divide;'   => '&#247;',
4208          '&oslash;'   => '&#248;',
4209          '&ugrave;'   => '&#249;',
4210          '&uacute;'   => '&#250;',
4211          '&ucirc;'    => '&#251;',
4212          '&uuml;'     => '&#252;',
4213          '&yacute;'   => '&#253;',
4214          '&thorn;'    => '&#254;',
4215          '&yuml;'     => '&#255;',
4216          '&OElig;'    => '&#338;',
4217          '&oelig;'    => '&#339;',
4218          '&Scaron;'   => '&#352;',
4219          '&scaron;'   => '&#353;',
4220          '&Yuml;'     => '&#376;',
4221          '&fnof;'     => '&#402;',
4222          '&circ;'     => '&#710;',
4223          '&tilde;'    => '&#732;',
4224          '&Alpha;'    => '&#913;',
4225          '&Beta;'     => '&#914;',
4226          '&Gamma;'    => '&#915;',
4227          '&Delta;'    => '&#916;',
4228          '&Epsilon;'  => '&#917;',
4229          '&Zeta;'     => '&#918;',
4230          '&Eta;'      => '&#919;',
4231          '&Theta;'    => '&#920;',
4232          '&Iota;'     => '&#921;',
4233          '&Kappa;'    => '&#922;',
4234          '&Lambda;'   => '&#923;',
4235          '&Mu;'       => '&#924;',
4236          '&Nu;'       => '&#925;',
4237          '&Xi;'       => '&#926;',
4238          '&Omicron;'  => '&#927;',
4239          '&Pi;'       => '&#928;',
4240          '&Rho;'      => '&#929;',
4241          '&Sigma;'    => '&#931;',
4242          '&Tau;'      => '&#932;',
4243          '&Upsilon;'  => '&#933;',
4244          '&Phi;'      => '&#934;',
4245          '&Chi;'      => '&#935;',
4246          '&Psi;'      => '&#936;',
4247          '&Omega;'    => '&#937;',
4248          '&alpha;'    => '&#945;',
4249          '&beta;'     => '&#946;',
4250          '&gamma;'    => '&#947;',
4251          '&delta;'    => '&#948;',
4252          '&epsilon;'  => '&#949;',
4253          '&zeta;'     => '&#950;',
4254          '&eta;'      => '&#951;',
4255          '&theta;'    => '&#952;',
4256          '&iota;'     => '&#953;',
4257          '&kappa;'    => '&#954;',
4258          '&lambda;'   => '&#955;',
4259          '&mu;'       => '&#956;',
4260          '&nu;'       => '&#957;',
4261          '&xi;'       => '&#958;',
4262          '&omicron;'  => '&#959;',
4263          '&pi;'       => '&#960;',
4264          '&rho;'      => '&#961;',
4265          '&sigmaf;'   => '&#962;',
4266          '&sigma;'    => '&#963;',
4267          '&tau;'      => '&#964;',
4268          '&upsilon;'  => '&#965;',
4269          '&phi;'      => '&#966;',
4270          '&chi;'      => '&#967;',
4271          '&psi;'      => '&#968;',
4272          '&omega;'    => '&#969;',
4273          '&thetasym;' => '&#977;',
4274          '&upsih;'    => '&#978;',
4275          '&piv;'      => '&#982;',
4276          '&ensp;'     => '&#8194;',
4277          '&emsp;'     => '&#8195;',
4278          '&thinsp;'   => '&#8201;',
4279          '&zwnj;'     => '&#8204;',
4280          '&zwj;'      => '&#8205;',
4281          '&lrm;'      => '&#8206;',
4282          '&rlm;'      => '&#8207;',
4283          '&ndash;'    => '&#8211;',
4284          '&mdash;'    => '&#8212;',
4285          '&lsquo;'    => '&#8216;',
4286          '&rsquo;'    => '&#8217;',
4287          '&sbquo;'    => '&#8218;',
4288          '&ldquo;'    => '&#8220;',
4289          '&rdquo;'    => '&#8221;',
4290          '&bdquo;'    => '&#8222;',
4291          '&dagger;'   => '&#8224;',
4292          '&Dagger;'   => '&#8225;',
4293          '&bull;'     => '&#8226;',
4294          '&hellip;'   => '&#8230;',
4295          '&permil;'   => '&#8240;',
4296          '&prime;'    => '&#8242;',
4297          '&Prime;'    => '&#8243;',
4298          '&lsaquo;'   => '&#8249;',
4299          '&rsaquo;'   => '&#8250;',
4300          '&oline;'    => '&#8254;',
4301          '&frasl;'    => '&#8260;',
4302          '&euro;'     => '&#8364;',
4303          '&image;'    => '&#8465;',
4304          '&weierp;'   => '&#8472;',
4305          '&real;'     => '&#8476;',
4306          '&trade;'    => '&#8482;',
4307          '&alefsym;'  => '&#8501;',
4308          '&crarr;'    => '&#8629;',
4309          '&lArr;'     => '&#8656;',
4310          '&uArr;'     => '&#8657;',
4311          '&rArr;'     => '&#8658;',
4312          '&dArr;'     => '&#8659;',
4313          '&hArr;'     => '&#8660;',
4314          '&forall;'   => '&#8704;',
4315          '&part;'     => '&#8706;',
4316          '&exist;'    => '&#8707;',
4317          '&empty;'    => '&#8709;',
4318          '&nabla;'    => '&#8711;',
4319          '&isin;'     => '&#8712;',
4320          '&notin;'    => '&#8713;',
4321          '&ni;'       => '&#8715;',
4322          '&prod;'     => '&#8719;',
4323          '&sum;'      => '&#8721;',
4324          '&minus;'    => '&#8722;',
4325          '&lowast;'   => '&#8727;',
4326          '&radic;'    => '&#8730;',
4327          '&prop;'     => '&#8733;',
4328          '&infin;'    => '&#8734;',
4329          '&ang;'      => '&#8736;',
4330          '&and;'      => '&#8743;',
4331          '&or;'       => '&#8744;',
4332          '&cap;'      => '&#8745;',
4333          '&cup;'      => '&#8746;',
4334          '&int;'      => '&#8747;',
4335          '&there4;'   => '&#8756;',
4336          '&sim;'      => '&#8764;',
4337          '&cong;'     => '&#8773;',
4338          '&asymp;'    => '&#8776;',
4339          '&ne;'       => '&#8800;',
4340          '&equiv;'    => '&#8801;',
4341          '&le;'       => '&#8804;',
4342          '&ge;'       => '&#8805;',
4343          '&sub;'      => '&#8834;',
4344          '&sup;'      => '&#8835;',
4345          '&nsub;'     => '&#8836;',
4346          '&sube;'     => '&#8838;',
4347          '&supe;'     => '&#8839;',
4348          '&oplus;'    => '&#8853;',
4349          '&otimes;'   => '&#8855;',
4350          '&perp;'     => '&#8869;',
4351          '&sdot;'     => '&#8901;',
4352          '&lceil;'    => '&#8968;',
4353          '&rceil;'    => '&#8969;',
4354          '&lfloor;'   => '&#8970;',
4355          '&rfloor;'   => '&#8971;',
4356          '&lang;'     => '&#9001;',
4357          '&rang;'     => '&#9002;',
4358          '&larr;'     => '&#8592;',
4359          '&uarr;'     => '&#8593;',
4360          '&rarr;'     => '&#8594;',
4361          '&darr;'     => '&#8595;',
4362          '&harr;'     => '&#8596;',
4363          '&loz;'      => '&#9674;',
4364          '&spades;'   => '&#9824;',
4365          '&clubs;'    => '&#9827;',
4366          '&hearts;'   => '&#9829;',
4367          '&diams;'    => '&#9830;',
4368      );
4369  
4370      return str_replace( array_keys( $to_ncr ), array_values( $to_ncr ), $text );
4371  }
4372  
4373  /**
4374   * Formats text for the editor.
4375   *
4376   * Generally the browsers treat everything inside a textarea as text, but
4377   * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
4378   *
4379   * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
4380   * filter will be applied to an empty string.
4381   *
4382   * @since 4.3.0
4383   *
4384   * @see _WP_Editors::editor()
4385   *
4386   * @param string $text           The text to be formatted.
4387   * @param string $default_editor The default editor for the current user.
4388   *                               It is usually either 'html' or 'tinymce'.
4389   * @return string The formatted text after filter is applied.
4390   */
4391  function format_for_editor( $text, $default_editor = null ) {
4392      if ( $text ) {
4393          $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
4394      }
4395  
4396      /**
4397       * Filters the text after it is formatted for the editor.
4398       *
4399       * @since 4.3.0
4400       *
4401       * @param string $text           The formatted text.
4402       * @param string $default_editor The default editor for the current user.
4403       *                               It is usually either 'html' or 'tinymce'.
4404       */
4405      return apply_filters( 'format_for_editor', $text, $default_editor );
4406  }
4407  
4408  /**
4409   * Performs a deep string replace operation to ensure the values in $search are no longer present.
4410   *
4411   * Repeats the replacement operation until it no longer replaces anything to remove "nested" values
4412   * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
4413   * str_replace would return
4414   *
4415   * @since 2.8.1
4416   * @access private
4417   *
4418   * @param string|array $search  The value being searched for, otherwise known as the needle.
4419   *                              An array may be used to designate multiple needles.
4420   * @param string       $subject The string being searched and replaced on, otherwise known as the haystack.
4421   * @return string The string with the replaced values.
4422   */
4423  function _deep_replace( $search, $subject ) {
4424      $subject = (string) $subject;
4425  
4426      $count = 1;
4427      while ( $count ) {
4428          $subject = str_replace( $search, '', $subject, $count );
4429      }
4430  
4431      return $subject;
4432  }
4433  
4434  /**
4435   * Escapes data for use in a MySQL query.
4436   *
4437   * Usually you should prepare queries using wpdb::prepare().
4438   * Sometimes, spot-escaping is required or useful. One example
4439   * is preparing an array for use in an IN clause.
4440   *
4441   * NOTE: Since 4.8.3, '%' characters will be replaced with a placeholder string,
4442   * this prevents certain SQLi attacks from taking place. This change in behavior
4443   * may cause issues for code that expects the return value of esc_sql() to be usable
4444   * for other purposes.
4445   *
4446   * @since 2.8.0
4447   *
4448   * @global wpdb $wpdb WordPress database abstraction object.
4449   *
4450   * @param string|array $data Unescaped data.
4451   * @return string|array Escaped data, in the same type as supplied.
4452   */
4453  function esc_sql( $data ) {
4454      global $wpdb;
4455      return $wpdb->_escape( $data );
4456  }
4457  
4458  /**
4459   * Checks and cleans a URL.
4460   *
4461   * A number of characters are removed from the URL. If the URL is for displaying
4462   * (the default behavior) ampersands are also replaced. The {@see 'clean_url'} filter
4463   * is applied to the returned cleaned URL.
4464   *
4465   * @since 2.8.0
4466   *
4467   * @param string   $url       The URL to be cleaned.
4468   * @param string[] $protocols Optional. An array of acceptable protocols.
4469   *                            Defaults to return value of wp_allowed_protocols().
4470   * @param string   $_context  Private. Use sanitize_url() for database usage.
4471   * @return string The cleaned URL after the {@see 'clean_url'} filter is applied.
4472   *                An empty string is returned if `$url` specifies a protocol other than
4473   *                those in `$protocols`, or if `$url` contains an empty string.
4474   */
4475  function esc_url( $url, $protocols = null, $_context = 'display' ) {
4476      $original_url = $url;
4477  
4478      if ( '' === $url ) {
4479          return $url;
4480      }
4481  
4482      $url = str_replace( ' ', '%20', ltrim( $url ) );
4483      $url = preg_replace( '|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url );
4484  
4485      if ( '' === $url ) {
4486          return $url;
4487      }
4488  
4489      if ( 0 !== stripos( $url, 'mailto:' ) ) {
4490          $strip = array( '%0d', '%0a', '%0D', '%0A' );
4491          $url   = _deep_replace( $strip, $url );
4492      }
4493  
4494      $url = str_replace( ';//', '://', $url );
4495      /*
4496       * If the URL doesn't appear to contain a scheme, we presume
4497       * it needs http:// prepended (unless it's a relative link
4498       * starting with /, # or ?, or a PHP file).
4499       */
4500      if ( ! str_contains( $url, ':' ) && ! in_array( $url[0], array( '/', '#', '?' ), true ) &&
4501          ! preg_match( '/^[a-z0-9-]+?\.php/i', $url )
4502      ) {
4503          $url = 'http://' . $url;
4504      }
4505  
4506      // Replace ampersands and single quotes only when displaying.
4507      if ( 'display' === $_context ) {
4508          $url = wp_kses_normalize_entities( $url );
4509          $url = str_replace( '&amp;', '&#038;', $url );
4510          $url = str_replace( "'", '&#039;', $url );
4511      }
4512  
4513      if ( str_contains( $url, '[' ) || str_contains( $url, ']' ) ) {
4514  
4515          $parsed = wp_parse_url( $url );
4516          $front  = '';
4517  
4518          if ( isset( $parsed['scheme'] ) ) {
4519              $front .= $parsed['scheme'] . '://';
4520          } elseif ( '/' === $url[0] ) {
4521              $front .= '//';
4522          }
4523  
4524          if ( isset( $parsed['user'] ) ) {
4525              $front .= $parsed['user'];
4526          }
4527  
4528          if ( isset( $parsed['pass'] ) ) {
4529              $front .= ':' . $parsed['pass'];
4530          }
4531  
4532          if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) {
4533              $front .= '@';
4534          }
4535  
4536          if ( isset( $parsed['host'] ) ) {
4537              $front .= $parsed['host'];
4538          }
4539  
4540          if ( isset( $parsed['port'] ) ) {
4541              $front .= ':' . $parsed['port'];
4542          }
4543  
4544          $end_dirty = str_replace( $front, '', $url );
4545          $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty );
4546          $url       = str_replace( $end_dirty, $end_clean, $url );
4547  
4548      }
4549  
4550      if ( '/' === $url[0] ) {
4551          $good_protocol_url = $url;
4552      } else {
4553          if ( ! is_array( $protocols ) ) {
4554              $protocols = wp_allowed_protocols();
4555          }
4556          $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
4557          if ( strtolower( $good_protocol_url ) !== strtolower( $url ) ) {
4558              return '';
4559          }
4560      }
4561  
4562      /**
4563       * Filters a string cleaned and escaped for output as a URL.
4564       *
4565       * @since 2.3.0
4566       *
4567       * @param string $good_protocol_url The cleaned URL to be returned.
4568       * @param string $original_url      The URL prior to cleaning.
4569       * @param string $_context          If 'display', replace ampersands and single quotes only.
4570       */
4571      return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
4572  }
4573  
4574  /**
4575   * Sanitizes a URL for database or redirect usage.
4576   *
4577   * This function is an alias for sanitize_url().
4578   *
4579   * @since 2.8.0
4580   * @since 6.1.0 Turned into an alias for sanitize_url().
4581   *
4582   * @see sanitize_url()
4583   *
4584   * @param string   $url       The URL to be cleaned.
4585   * @param string[] $protocols Optional. An array of acceptable protocols.
4586   *                            Defaults to return value of wp_allowed_protocols().
4587   * @return string The cleaned URL after sanitize_url() is run.
4588   */
4589  function esc_url_raw( $url, $protocols = null ) {
4590      return sanitize_url( $url, $protocols );
4591  }
4592  
4593  /**
4594   * Sanitizes a URL for database or redirect usage.
4595   *
4596   * @since 2.3.1
4597   * @since 2.8.0 Deprecated in favor of esc_url_raw().
4598   * @since 5.9.0 Restored (un-deprecated).
4599   *
4600   * @see esc_url()
4601   *
4602   * @param string   $url       The URL to be cleaned.
4603   * @param string[] $protocols Optional. An array of acceptable protocols.
4604   *                            Defaults to return value of wp_allowed_protocols().
4605   * @return string The cleaned URL after esc_url() is run with the 'db' context.
4606   */
4607  function sanitize_url( $url, $protocols = null ) {
4608      return esc_url( $url, $protocols, 'db' );
4609  }
4610  
4611  /**
4612   * Converts entities, while preserving already-encoded entities.
4613   *
4614   * @link https://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
4615   *
4616   * @since 1.2.2
4617   *
4618   * @param string $text The text to be converted.
4619   * @return string Converted text.
4620   */
4621  function htmlentities2( $text ) {
4622      $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
4623  
4624      $translation_table[ chr( 38 ) ] = '&';
4625  
4626      return preg_replace( '/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/', '&amp;', strtr( $text, $translation_table ) );
4627  }
4628  
4629  /**
4630   * Escapes single quotes, `"`, `<`, `>`, `&`, and fixes line endings.
4631   *
4632   * Escapes text strings for echoing in JS. It is intended to be used for inline JS
4633   * (in a tag attribute, for example `onclick="..."`). Note that the strings have to
4634   * be in single quotes. The {@see 'js_escape'} filter is also applied here.
4635   *
4636   * @since 2.8.0
4637   *
4638   * @param string $text The text to be escaped.
4639   * @return string Escaped text.
4640   */
4641  function esc_js( $text ) {
4642      $safe_text = wp_check_invalid_utf8( $text );
4643      $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
4644      $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
4645      $safe_text = str_replace( "\r", '', $safe_text );
4646      $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
4647      /**
4648       * Filters a string cleaned and escaped for output in JavaScript.
4649       *
4650       * Text passed to esc_js() is stripped of invalid or special characters,
4651       * and properly slashed for output.
4652       *
4653       * @since 2.0.6
4654       *
4655       * @param string $safe_text The text after it has been escaped.
4656       * @param string $text      The text prior to being escaped.
4657       */
4658      return apply_filters( 'js_escape', $safe_text, $text );
4659  }
4660  
4661  /**
4662   * Escaping for HTML blocks.
4663   *
4664   * @since 2.8.0
4665   *
4666   * @param string $text
4667   * @return string
4668   */
4669  function esc_html( $text ) {
4670      $safe_text = wp_check_invalid_utf8( $text );
4671      $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
4672      /**
4673       * Filters a string cleaned and escaped for output in HTML.
4674       *
4675       * Text passed to esc_html() is stripped of invalid or special characters
4676       * before output.
4677       *
4678       * @since 2.8.0
4679       *
4680       * @param string $safe_text The text after it has been escaped.
4681       * @param string $text      The text prior to being escaped.
4682       */
4683      return apply_filters( 'esc_html', $safe_text, $text );
4684  }
4685  
4686  /**
4687   * Escaping for HTML attributes.
4688   *
4689   * @since 2.8.0
4690   *
4691   * @param string $text
4692   * @return string
4693   */
4694  function esc_attr( $text ) {
4695      $safe_text = wp_check_invalid_utf8( $text );
4696      $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
4697      /**
4698       * Filters a string cleaned and escaped for output in an HTML attribute.
4699       *
4700       * Text passed to esc_attr() is stripped of invalid or special characters
4701       * before output.
4702       *
4703       * @since 2.0.6
4704       *
4705       * @param string $safe_text The text after it has been escaped.
4706       * @param string $text      The text prior to being escaped.
4707       */
4708      return apply_filters( 'attribute_escape', $safe_text, $text );
4709  }
4710  
4711  /**
4712   * Escaping for textarea values.
4713   *
4714   * @since 3.1.0
4715   *
4716   * @param string $text
4717   * @return string
4718   */
4719  function esc_textarea( $text ) {
4720      $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
4721      /**
4722       * Filters a string cleaned and escaped for output in a textarea element.
4723       *
4724       * @since 3.1.0
4725       *
4726       * @param string $safe_text The text after it has been escaped.
4727       * @param string $text      The text prior to being escaped.
4728       */
4729      return apply_filters( 'esc_textarea', $safe_text, $text );
4730  }
4731  
4732  /**
4733   * Escaping for XML blocks.
4734   *
4735   * @since 5.5.0
4736   *
4737   * @param string $text Text to escape.
4738   * @return string Escaped text.
4739   */
4740  function esc_xml( $text ) {
4741      $safe_text = wp_check_invalid_utf8( $text );
4742  
4743      $cdata_regex = '\<\!\[CDATA\[.*?\]\]\>';
4744      $regex       = <<<EOF
4745  /
4746      (?=.*?{$cdata_regex})                 # lookahead that will match anything followed by a CDATA Section
4747      (?<non_cdata_followed_by_cdata>(.*?)) # the "anything" matched by the lookahead
4748      (?<cdata>({$cdata_regex}))            # the CDATA Section matched by the lookahead
4749  
4750  |                                          # alternative
4751  
4752      (?<non_cdata>(.*))                    # non-CDATA Section
4753  /sx
4754  EOF;
4755  
4756      $safe_text = (string) preg_replace_callback(
4757          $regex,
4758          static function ( $matches ) {
4759              if ( ! isset( $matches[0] ) ) {
4760                  return '';
4761              }
4762  
4763              if ( isset( $matches['non_cdata'] ) ) {
4764                  // escape HTML entities in the non-CDATA Section.
4765                  return _wp_specialchars( $matches['non_cdata'], ENT_XML1 );
4766              }
4767  
4768              // Return the CDATA Section unchanged, escape HTML entities in the rest.
4769              return _wp_specialchars( $matches['non_cdata_followed_by_cdata'], ENT_XML1 ) . $matches['cdata'];
4770          },
4771          $safe_text
4772      );
4773  
4774      /**
4775       * Filters a string cleaned and escaped for output in XML.
4776       *
4777       * Text passed to esc_xml() is stripped of invalid or special characters
4778       * before output. HTML named character references are converted to their
4779       * equivalent code points.
4780       *
4781       * @since 5.5.0
4782       *
4783       * @param string $safe_text The text after it has been escaped.
4784       * @param string $text      The text prior to being escaped.
4785       */
4786      return apply_filters( 'esc_xml', $safe_text, $text );
4787  }
4788  
4789  /**
4790   * Escapes an HTML tag name.
4791   *
4792   * @since 2.5.0
4793   *
4794   * @param string $tag_name
4795   * @return string
4796   */
4797  function tag_escape( $tag_name ) {
4798      $safe_tag = strtolower( preg_replace( '/[^a-zA-Z0-9_:]/', '', $tag_name ) );
4799      /**
4800       * Filters a string cleaned and escaped for output as an HTML tag.
4801       *
4802       * @since 2.8.0
4803       *
4804       * @param string $safe_tag The tag name after it has been escaped.
4805       * @param string $tag_name The text before it was escaped.
4806       */
4807      return apply_filters( 'tag_escape', $safe_tag, $tag_name );
4808  }
4809  
4810  /**
4811   * Converts full URL paths to absolute paths.
4812   *
4813   * Removes the http or https protocols and the domain. Keeps the path '/' at the
4814   * beginning, so it isn't a true relative link, but from the web root base.
4815   *
4816   * @since 2.1.0
4817   * @since 4.1.0 Support was added for relative URLs.
4818   *
4819   * @param string $link Full URL path.
4820   * @return string Absolute path.
4821   */
4822  function wp_make_link_relative( $link ) {
4823      return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link );
4824  }
4825  
4826  /**
4827   * Sanitizes various option values based on the nature of the option.
4828   *
4829   * This is basically a switch statement which will pass $value through a number
4830   * of functions depending on the $option.
4831   *
4832   * @since 2.0.5
4833   *
4834   * @global wpdb $wpdb WordPress database abstraction object.
4835   *
4836   * @param string $option The name of the option.
4837   * @param mixed  $value  The unsanitized value.
4838   * @return mixed Sanitized value.
4839   */
4840  function sanitize_option( $option, $value ) {
4841      global $wpdb;
4842  
4843      $original_value = $value;
4844      $error          = null;
4845  
4846      switch ( $option ) {
4847          case 'admin_email':
4848          case 'new_admin_email':
4849              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4850              if ( is_wp_error( $value ) ) {
4851                  $error = $value->get_error_message();
4852              } else {
4853                  $value = sanitize_email( $value );
4854                  if ( ! is_email( $value ) ) {
4855                      $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
4856                  }
4857              }
4858              break;
4859  
4860          case 'thumbnail_size_w':
4861          case 'thumbnail_size_h':
4862          case 'medium_size_w':
4863          case 'medium_size_h':
4864          case 'medium_large_size_w':
4865          case 'medium_large_size_h':
4866          case 'large_size_w':
4867          case 'large_size_h':
4868          case 'mailserver_port':
4869          case 'comment_max_links':
4870          case 'page_on_front':
4871          case 'page_for_posts':
4872          case 'rss_excerpt_length':
4873          case 'default_category':
4874          case 'default_email_category':
4875          case 'default_link_category':
4876          case 'close_comments_days_old':
4877          case 'comments_per_page':
4878          case 'thread_comments_depth':
4879          case 'users_can_register':
4880          case 'start_of_week':
4881          case 'site_icon':
4882          case 'fileupload_maxk':
4883              $value = absint( $value );
4884              break;
4885  
4886          case 'posts_per_page':
4887          case 'posts_per_rss':
4888              $value = (int) $value;
4889              if ( empty( $value ) ) {
4890                  $value = 1;
4891              }
4892              if ( $value < -1 ) {
4893                  $value = abs( $value );
4894              }
4895              break;
4896  
4897          case 'default_ping_status':
4898          case 'default_comment_status':
4899              // Options that if not there have 0 value but need to be something like "closed".
4900              if ( '0' === (string) $value || '' === $value ) {
4901                  $value = 'closed';
4902              }
4903              break;
4904  
4905          case 'blogdescription':
4906          case 'blogname':
4907              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4908              if ( $value !== $original_value ) {
4909                  $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) );
4910              }
4911  
4912              if ( is_wp_error( $value ) ) {
4913                  $error = $value->get_error_message();
4914              } else {
4915                  $value = esc_html( $value );
4916              }
4917              break;
4918  
4919          case 'blog_charset':
4920              if ( is_string( $value ) ) {
4921                  $value = preg_replace( '/[^a-zA-Z0-9_-]/', '', $value ); // Strips slashes.
4922              } else {
4923                  $value = '';
4924              }
4925              break;
4926  
4927          case 'blog_public':
4928              // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
4929              if ( null === $value ) {
4930                  $value = 1;
4931              } else {
4932                  $value = (int) $value;
4933              }
4934              break;
4935  
4936          case 'date_format':
4937          case 'time_format':
4938          case 'mailserver_url':
4939          case 'mailserver_login':
4940          case 'mailserver_pass':
4941          case 'upload_path':
4942              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4943              if ( is_wp_error( $value ) ) {
4944                  $error = $value->get_error_message();
4945              } else {
4946                  $value = strip_tags( $value );
4947                  $value = wp_kses_data( $value );
4948              }
4949              break;
4950  
4951          case 'ping_sites':
4952              $value = explode( "\n", $value );
4953              $value = array_filter( array_map( 'trim', $value ) );
4954              $value = array_filter( array_map( 'sanitize_url', $value ) );
4955              $value = implode( "\n", $value );
4956              break;
4957  
4958          case 'gmt_offset':
4959              if ( is_numeric( $value ) ) {
4960                  $value = preg_replace( '/[^0-9:.-]/', '', $value ); // Strips slashes.
4961              } else {
4962                  $value = '';
4963              }
4964              break;
4965  
4966          case 'siteurl':
4967              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4968              if ( is_wp_error( $value ) ) {
4969                  $error = $value->get_error_message();
4970              } else {
4971                  if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
4972                      $value = sanitize_url( $value );
4973                  } else {
4974                      $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
4975                  }
4976              }
4977              break;
4978  
4979          case 'home':
4980              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4981              if ( is_wp_error( $value ) ) {
4982                  $error = $value->get_error_message();
4983              } else {
4984                  if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
4985                      $value = sanitize_url( $value );
4986                  } else {
4987                      $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
4988                  }
4989              }
4990              break;
4991  
4992          case 'WPLANG':
4993              $allowed = get_available_languages();
4994              if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
4995                  $allowed[] = WPLANG;
4996              }
4997              if ( ! in_array( $value, $allowed, true ) && ! empty( $value ) ) {
4998                  $value = get_option( $option );
4999              }
5000              break;
5001  
5002          case 'illegal_names':
5003              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
5004              if ( is_wp_error( $value ) ) {
5005                  $error = $value->get_error_message();
5006              } else {
5007                  if ( ! is_array( $value ) ) {
5008                      $value = explode( ' ', $value );
5009                  }
5010  
5011                  $value = array_values( array_filter( array_map( 'trim', $value ) ) );
5012  
5013                  if ( ! $value ) {
5014                      $value = '';
5015                  }
5016              }
5017              break;
5018  
5019          case 'limited_email_domains':
5020          case 'banned_email_domains':
5021              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
5022              if ( is_wp_error( $value ) ) {
5023                  $error = $value->get_error_message();
5024              } else {
5025                  if ( ! is_array( $value ) ) {
5026                      $value = explode( "\n", $value );
5027                  }
5028  
5029                  $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
5030                  $value   = array();
5031  
5032                  foreach ( $domains as $domain ) {
5033                      if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
5034                          $value[] = $domain;
5035                      }
5036                  }
5037                  if ( ! $value ) {
5038                      $value = '';
5039                  }
5040              }
5041              break;
5042  
5043          case 'timezone_string':
5044              $allowed_zones = timezone_identifiers_list( DateTimeZone::ALL_WITH_BC );
5045              if ( ! in_array( $value, $allowed_zones, true ) && ! empty( $value ) ) {
5046                  $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
5047              }
5048              break;
5049  
5050          case 'permalink_structure':
5051          case 'category_base':
5052          case 'tag_base':
5053              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
5054              if ( is_wp_error( $value ) ) {
5055                  $error = $value->get_error_message();
5056              } else {
5057                  $value = sanitize_url( $value );
5058                  $value = str_replace( 'http://', '', $value );
5059              }
5060  
5061              if ( 'permalink_structure' === $option && null === $error
5062                  && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value )
5063              ) {
5064                  $error = sprintf(
5065                      /* translators: %s: Documentation URL. */
5066                      __( 'A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>' ),
5067                      __( 'https://wordpress.org/documentation/article/customize-permalinks/#choosing-your-permalink-structure' )
5068                  );
5069              }
5070              break;
5071  
5072          case 'default_role':
5073              if ( ! get_role( $value ) && get_role( 'subscriber' ) ) {
5074                  $value = 'subscriber';
5075              }
5076              break;
5077  
5078          case 'moderation_keys':
5079          case 'disallowed_keys':
5080              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
5081              if ( is_wp_error( $value ) ) {
5082                  $error = $value->get_error_message();
5083              } else {
5084                  $value = explode( "\n", $value );
5085                  $value = array_filter( array_map( 'trim', $value ) );
5086                  $value = array_unique( $value );
5087                  $value = implode( "\n", $value );
5088              }
5089              break;
5090      }
5091  
5092      if ( null !== $error ) {
5093          if ( '' === $error && is_wp_error( $value ) ) {
5094              /* translators: 1: Option name, 2: Error code. */
5095              $error = sprintf( __( 'Could not sanitize the %1$s option. Error code: %2$s' ), $option, $value->get_error_code() );
5096          }
5097  
5098          $value = get_option( $option );
5099          if ( function_exists( 'add_settings_error' ) ) {
5100              add_settings_error( $option, "invalid_{$option}", $error );
5101          }
5102      }
5103  
5104      /**
5105       * Filters an option value following sanitization.
5106       *
5107       * @since 2.3.0
5108       * @since 4.3.0 Added the `$original_value` parameter.
5109       *
5110       * @param mixed  $value          The sanitized option value.
5111       * @param string $option         The option name.
5112       * @param mixed  $original_value The original value passed to the function.
5113       */
5114      return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value );
5115  }
5116  
5117  /**
5118   * Maps a function to all non-iterable elements of an array or an object.
5119   *
5120   * This is similar to `array_walk_recursive()` but acts upon objects too.
5121   *
5122   * @since 4.4.0
5123   *
5124   * @param mixed    $value    The array, object, or scalar.
5125   * @param callable $callback The function to map onto $value.
5126   * @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
5127   */
5128  function map_deep( $value, $callback ) {
5129      if ( is_array( $value ) ) {
5130          foreach ( $value as $index => $item ) {
5131              $value[ $index ] = map_deep( $item, $callback );
5132          }
5133      } elseif ( is_object( $value ) ) {
5134          $object_vars = get_object_vars( $value );
5135          foreach ( $object_vars as $property_name => $property_value ) {
5136              $value->$property_name = map_deep( $property_value, $callback );
5137          }
5138      } else {
5139          $value = call_user_func( $callback, $value );
5140      }
5141  
5142      return $value;
5143  }
5144  
5145  /**
5146   * Parses a string into variables to be stored in an array.
5147   *
5148   * @since 2.2.1
5149   *
5150   * @param string $input_string The string to be parsed.
5151   * @param array  $result       Variables will be stored in this array.
5152   */
5153  function wp_parse_str( $input_string, &$result ) {
5154      parse_str( (string) $input_string, $result );
5155  
5156      /**
5157       * Filters the array of variables derived from a parsed string.
5158       *
5159       * @since 2.2.1
5160       *
5161       * @param array $result The array populated with variables.
5162       */
5163      $result = apply_filters( 'wp_parse_str', $result );
5164  }
5165  
5166  /**
5167   * Converts lone less than signs.
5168   *
5169   * KSES already converts lone greater than signs.
5170   *
5171   * @since 2.3.0
5172   *
5173   * @param string $content Text to be converted.
5174   * @return string Converted text.
5175   */
5176  function wp_pre_kses_less_than( $content ) {
5177      return preg_replace_callback( '%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $content );
5178  }
5179  
5180  /**
5181   * Callback function used by preg_replace.
5182   *
5183   * @since 2.3.0
5184   *
5185   * @param string[] $matches Populated by matches to preg_replace.
5186   * @return string The text returned after esc_html if needed.
5187   */
5188  function wp_pre_kses_less_than_callback( $matches ) {
5189      if ( ! str_contains( $matches[0], '>' ) ) {
5190          return esc_html( $matches[0] );
5191      }
5192      return $matches[0];
5193  }
5194  
5195  /**
5196   * Removes non-allowable HTML from parsed block attribute values when filtering
5197   * in the post context.
5198   *
5199   * @since 5.3.1
5200   *
5201   * @param string         $content           Content to be run through KSES.
5202   * @param array[]|string $allowed_html      An array of allowed HTML elements
5203   *                                          and attributes, or a context name
5204   *                                          such as 'post'.
5205   * @param string[]       $allowed_protocols Array of allowed URL protocols.
5206   * @return string Filtered text to run through KSES.
5207   */
5208  function wp_pre_kses_block_attributes( $content, $allowed_html, $allowed_protocols ) {
5209      /*
5210       * `filter_block_content` is expected to call `wp_kses`. Temporarily remove
5211       * the filter to avoid recursion.
5212       */
5213      remove_filter( 'pre_kses', 'wp_pre_kses_block_attributes', 10 );
5214      $content = filter_block_content( $content, $allowed_html, $allowed_protocols );
5215      add_filter( 'pre_kses', 'wp_pre_kses_block_attributes', 10, 3 );
5216  
5217      return $content;
5218  }
5219  
5220  /**
5221   * WordPress' implementation of PHP sprintf() with filters.
5222   *
5223   * @since 2.5.0
5224   * @since 5.3.0 Formalized the existing and already documented `...$args` parameter
5225   *              by adding it to the function signature.
5226   *
5227   * @link https://www.php.net/sprintf
5228   *
5229   * @param string $pattern The string which formatted args are inserted.
5230   * @param mixed  ...$args Arguments to be formatted into the $pattern string.
5231   * @return string The formatted string.
5232   */
5233  function wp_sprintf( $pattern, ...$args ) {
5234      $len       = strlen( $pattern );
5235      $start     = 0;
5236      $result    = '';
5237      $arg_index = 0;
5238  
5239      while ( $len > $start ) {
5240          // Last character: append and break.
5241          if ( strlen( $pattern ) - 1 === $start ) {
5242              $result .= substr( $pattern, -1 );
5243              break;
5244          }
5245  
5246          // Literal %: append and continue.
5247          if ( '%%' === substr( $pattern, $start, 2 ) ) {
5248              $start  += 2;
5249              $result .= '%';
5250              continue;
5251          }
5252  
5253          // Get fragment before next %.
5254          $end = strpos( $pattern, '%', $start + 1 );
5255          if ( false === $end ) {
5256              $end = $len;
5257          }
5258          $fragment = substr( $pattern, $start, $end - $start );
5259  
5260          // Fragment has a specifier.
5261          if ( '%' === $pattern[ $start ] ) {
5262              // Find numbered arguments or take the next one in order.
5263              if ( preg_match( '/^%(\d+)\$/', $fragment, $matches ) ) {
5264                  $index    = $matches[1] - 1; // 0-based array vs 1-based sprintf() arguments.
5265                  $arg      = isset( $args[ $index ] ) ? $args[ $index ] : '';
5266                  $fragment = str_replace( "%{$matches[1]}$", '%', $fragment );
5267              } else {
5268                  $arg = isset( $args[ $arg_index ] ) ? $args[ $arg_index ] : '';
5269                  ++$arg_index;
5270              }
5271  
5272              /**
5273               * Filters a fragment from the pattern passed to wp_sprintf().
5274               *
5275               * If the fragment is unchanged, then sprintf() will be run on the fragment.
5276               *
5277               * @since 2.5.0
5278               *
5279               * @param string $fragment A fragment from the pattern.
5280               * @param string $arg      The argument.
5281               */
5282              $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
5283  
5284              if ( $_fragment !== $fragment ) {
5285                  $fragment = $_fragment;
5286              } else {
5287                  $fragment = sprintf( $fragment, (string) $arg );
5288              }
5289          }
5290  
5291          // Append to result and move to next fragment.
5292          $result .= $fragment;
5293          $start   = $end;
5294      }
5295  
5296      return $result;
5297  }
5298  
5299  /**
5300   * Localizes list items before the rest of the content.
5301   *
5302   * The '%l' must be at the first characters can then contain the rest of the
5303   * content. The list items will have ', ', ', and', and ' and ' added depending
5304   * on the amount of list items in the $args parameter.
5305   *
5306   * @since 2.5.0
5307   *
5308   * @param string $pattern Content containing '%l' at the beginning.
5309   * @param array  $args    List items to prepend to the content and replace '%l'.
5310   * @return string Localized list items and rest of the content.
5311   */
5312  function wp_sprintf_l( $pattern, $args ) {
5313      // Not a match.
5314      if ( ! str_starts_with( $pattern, '%l' ) ) {
5315          return $pattern;
5316      }
5317  
5318      // Nothing to work with.
5319      if ( empty( $args ) ) {
5320          return '';
5321      }
5322  
5323      /**
5324       * Filters the translated delimiters used by wp_sprintf_l().
5325       * Placeholders (%s) are included to assist translators and then
5326       * removed before the array of strings reaches the filter.
5327       *
5328       * Please note: Ampersands and entities should be avoided here.
5329       *
5330       * @since 2.5.0
5331       *
5332       * @param array $delimiters An array of translated delimiters.
5333       */
5334      $l = apply_filters(
5335          'wp_sprintf_l',
5336          array(
5337              /* translators: Used to join items in a list with more than 2 items. */
5338              'between'          => sprintf( __( '%1$s, %2$s' ), '', '' ),
5339              /* translators: Used to join last two items in a list with more than 2 times. */
5340              'between_last_two' => sprintf( __( '%1$s, and %2$s' ), '', '' ),
5341              /* translators: Used to join items in a list with only 2 items. */
5342              'between_only_two' => sprintf( __( '%1$s and %2$s' ), '', '' ),
5343          )
5344      );
5345  
5346      $args   = (array) $args;
5347      $result = array_shift( $args );
5348      if ( count( $args ) === 1 ) {
5349          $result .= $l['between_only_two'] . array_shift( $args );
5350      }
5351  
5352      // Loop when more than two args.
5353      $i = count( $args );
5354      while ( $i ) {
5355          $arg = array_shift( $args );
5356          --$i;
5357          if ( 0 === $i ) {
5358              $result .= $l['between_last_two'] . $arg;
5359          } else {
5360              $result .= $l['between'] . $arg;
5361          }
5362      }
5363  
5364      return $result . substr( $pattern, 2 );
5365  }
5366  
5367  /**
5368   * Safely extracts not more than the first $count characters from HTML string.
5369   *
5370   * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
5371   * be counted as one character. For example &amp; will be counted as 4, &lt; as
5372   * 3, etc.
5373   *
5374   * @since 2.5.0
5375   *
5376   * @param string $str   String to get the excerpt from.
5377   * @param int    $count Maximum number of characters to take.
5378   * @param string $more  Optional. What to append if $str needs to be trimmed. Defaults to empty string.
5379   * @return string The excerpt.
5380   */
5381  function wp_html_excerpt( $str, $count, $more = null ) {
5382      if ( null === $more ) {
5383          $more = '';
5384      }
5385  
5386      $str     = wp_strip_all_tags( $str, true );
5387      $excerpt = mb_substr( $str, 0, $count );
5388  
5389      // Remove part of an entity at the end.
5390      $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
5391  
5392      if ( $str !== $excerpt ) {
5393          $excerpt = trim( $excerpt ) . $more;
5394      }
5395  
5396      return $excerpt;
5397  }
5398  
5399  /**
5400   * Adds a base URL to relative links in passed content.
5401   *
5402   * By default, this function supports the 'src' and 'href' attributes.
5403   * However, this can be modified via the `$attrs` parameter.
5404   *
5405   * @since 2.7.0
5406   *
5407   * @global string $_links_add_base
5408   *
5409   * @param string $content String to search for links in.
5410   * @param string $base    The base URL to prefix to links.
5411   * @param array  $attrs   The attributes which should be processed.
5412   * @return string The processed content.
5413   */
5414  function links_add_base_url( $content, $base, $attrs = array( 'src', 'href' ) ) {
5415      global $_links_add_base;
5416      $_links_add_base = $base;
5417      $attrs           = implode( '|', (array) $attrs );
5418      return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
5419  }
5420  
5421  /**
5422   * Callback to add a base URL to relative links in passed content.
5423   *
5424   * @since 2.7.0
5425   * @access private
5426   *
5427   * @global string $_links_add_base
5428   *
5429   * @param string $m The matched link.
5430   * @return string The processed link.
5431   */
5432  function _links_add_base( $m ) {
5433      global $_links_add_base;
5434      // 1 = attribute name  2 = quotation mark  3 = URL.
5435      return $m[1] . '=' . $m[2] .
5436          ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols(), true ) ?
5437              $m[3] :
5438              WP_Http::make_absolute_url( $m[3], $_links_add_base )
5439          )
5440          . $m[2];
5441  }
5442  
5443  /**
5444   * Adds a target attribute to all links in passed content.
5445   *
5446   * By default, this function only applies to `<a>` tags.
5447   * However, this can be modified via the `$tags` parameter.
5448   *
5449   * *NOTE:* Any current target attribute will be stripped and replaced.
5450   *
5451   * @since 2.7.0
5452   *
5453   * @global string $_links_add_target
5454   *
5455   * @param string   $content String to search for links in.
5456   * @param string   $target  The target to add to the links.
5457   * @param string[] $tags    An array of tags to apply to.
5458   * @return string The processed content.
5459   */
5460  function links_add_target( $content, $target = '_blank', $tags = array( 'a' ) ) {
5461      global $_links_add_target;
5462      $_links_add_target = $target;
5463      $tags              = implode( '|', (array) $tags );
5464      return preg_replace_callback( "!<($tags)((\s[^>]*)?)>!i", '_links_add_target', $content );
5465  }
5466  
5467  /**
5468   * Callback to add a target attribute to all links in passed content.
5469   *
5470   * @since 2.7.0
5471   * @access private
5472   *
5473   * @global string $_links_add_target
5474   *
5475   * @param string $m The matched link.
5476   * @return string The processed link.
5477   */
5478  function _links_add_target( $m ) {
5479      global $_links_add_target;
5480      $tag  = $m[1];
5481      $link = preg_replace( '|( target=([\'"])(.*?)\2)|i', '', $m[2] );
5482      return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
5483  }
5484  
5485  /**
5486   * Normalizes EOL characters and strips duplicate whitespace.
5487   *
5488   * @since 2.7.0
5489   *
5490   * @param string $str The string to normalize.
5491   * @return string The normalized string.
5492   */
5493  function normalize_whitespace( $str ) {
5494      $str = trim( $str );
5495      $str = str_replace( "\r", "\n", $str );
5496      $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
5497      return $str;
5498  }
5499  
5500  /**
5501   * Properly strips all HTML tags including script and style
5502   *
5503   * This differs from strip_tags() because it removes the contents of
5504   * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
5505   * will return 'something'. wp_strip_all_tags will return ''
5506   *
5507   * @since 2.9.0
5508   *
5509   * @param string $text          String containing HTML tags
5510   * @param bool   $remove_breaks Optional. Whether to remove left over line breaks and white space chars
5511   * @return string The processed string.
5512   */
5513  function wp_strip_all_tags( $text, $remove_breaks = false ) {
5514      if ( is_null( $text ) ) {
5515          return '';
5516      }
5517  
5518      if ( ! is_scalar( $text ) ) {
5519          /*
5520           * To maintain consistency with pre-PHP 8 error levels,
5521           * trigger_error() is used to trigger an E_USER_WARNING,
5522           * rather than _doing_it_wrong(), which triggers an E_USER_NOTICE.
5523           */
5524          trigger_error(
5525              sprintf(
5526                  /* translators: 1: The function name, 2: The argument number, 3: The argument name, 4: The expected type, 5: The provided type. */
5527                  __( 'Warning: %1$s expects parameter %2$s (%3$s) to be a %4$s, %5$s given.' ),
5528                  __FUNCTION__,
5529                  '#1',
5530                  '$text',
5531                  'string',
5532                  gettype( $text )
5533              ),
5534              E_USER_WARNING
5535          );
5536  
5537          return '';
5538      }
5539  
5540      $text = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $text );
5541      $text = strip_tags( $text );
5542  
5543      if ( $remove_breaks ) {
5544          $text = preg_replace( '/[\r\n\t ]+/', ' ', $text );
5545      }
5546  
5547      return trim( $text );
5548  }
5549  
5550  /**
5551   * Sanitizes a string from user input or from the database.
5552   *
5553   * - Checks for invalid UTF-8,
5554   * - Converts single `<` characters to entities
5555   * - Strips all tags
5556   * - Removes line breaks, tabs, and extra whitespace
5557   * - Strips percent-encoded characters
5558   *
5559   * @since 2.9.0
5560   *
5561   * @see sanitize_textarea_field()
5562   * @see wp_check_invalid_utf8()
5563   * @see wp_strip_all_tags()
5564   *
5565   * @param string $str String to sanitize.
5566   * @return string Sanitized string.
5567   */
5568  function sanitize_text_field( $str ) {
5569      $filtered = _sanitize_text_fields( $str, false );
5570  
5571      /**
5572       * Filters a sanitized text field string.
5573       *
5574       * @since 2.9.0
5575       *
5576       * @param string $filtered The sanitized string.
5577       * @param string $str      The string prior to being sanitized.
5578       */
5579      return apply_filters( 'sanitize_text_field', $filtered, $str );
5580  }
5581  
5582  /**
5583   * Sanitizes a multiline string from user input or from the database.
5584   *
5585   * The function is like sanitize_text_field(), but preserves
5586   * new lines (\n) and other whitespace, which are legitimate
5587   * input in textarea elements.
5588   *
5589   * @see sanitize_text_field()
5590   *
5591   * @since 4.7.0
5592   *
5593   * @param string $str String to sanitize.
5594   * @return string Sanitized string.
5595   */
5596  function sanitize_textarea_field( $str ) {
5597      $filtered = _sanitize_text_fields( $str, true );
5598  
5599      /**
5600       * Filters a sanitized textarea field string.
5601       *
5602       * @since 4.7.0
5603       *
5604       * @param string $filtered The sanitized string.
5605       * @param string $str      The string prior to being sanitized.
5606       */
5607      return apply_filters( 'sanitize_textarea_field', $filtered, $str );
5608  }
5609  
5610  /**
5611   * Internal helper function to sanitize a string from user input or from the database.
5612   *
5613   * @since 4.7.0
5614   * @access private
5615   *
5616   * @param string $str           String to sanitize.
5617   * @param bool   $keep_newlines Optional. Whether to keep newlines. Default: false.
5618   * @return string Sanitized string.
5619   */
5620  function _sanitize_text_fields( $str, $keep_newlines = false ) {
5621      if ( is_object( $str ) || is_array( $str ) ) {
5622          return '';
5623      }
5624  
5625      $str = (string) $str;
5626  
5627      $filtered = wp_check_invalid_utf8( $str );
5628  
5629      if ( str_contains( $filtered, '<' ) ) {
5630          $filtered = wp_pre_kses_less_than( $filtered );
5631          // This will strip extra whitespace for us.
5632          $filtered = wp_strip_all_tags( $filtered, false );
5633  
5634          /*
5635           * Use HTML entities in a special case to make sure that
5636           * later newline stripping stages cannot lead to a functional tag.
5637           */
5638          $filtered = str_replace( "<\n", "&lt;\n", $filtered );
5639      }
5640  
5641      if ( ! $keep_newlines ) {
5642          $filtered = preg_replace( '/[\r\n\t ]+/', ' ', $filtered );
5643      }
5644      $filtered = trim( $filtered );
5645  
5646      // Remove percent-encoded characters.
5647      $found = false;
5648      while ( preg_match( '/%[a-f0-9]{2}/i', $filtered, $match ) ) {
5649          $filtered = str_replace( $match[0], '', $filtered );
5650          $found    = true;
5651      }
5652  
5653      if ( $found ) {
5654          // Strip out the whitespace that may now exist after removing percent-encoded characters.
5655          $filtered = trim( preg_replace( '/ +/', ' ', $filtered ) );
5656      }
5657  
5658      return $filtered;
5659  }
5660  
5661  /**
5662   * i18n-friendly version of basename().
5663   *
5664   * @since 3.1.0
5665   *
5666   * @param string $path   A path.
5667   * @param string $suffix If the filename ends in suffix this will also be cut off.
5668   * @return string
5669   */
5670  function wp_basename( $path, $suffix = '' ) {
5671      return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
5672  }
5673  
5674  // phpcs:disable WordPress.WP.CapitalPDangit.MisspelledInComment,WordPress.WP.CapitalPDangit.MisspelledInText,WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid -- 8-)
5675  /**
5676   * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
5677   *
5678   * Violating our coding standards for a good function name.
5679   *
5680   * @since 3.0.0
5681   *
5682   * @param string $text The text to be modified.
5683   * @return string The modified text.
5684   */
5685  function capital_P_dangit( $text ) {
5686      // Simple replacement for titles.
5687      $current_filter = current_filter();
5688      if ( 'the_title' === $current_filter || 'wp_title' === $current_filter ) {
5689          return str_replace( 'Wordpress', 'WordPress', $text );
5690      }
5691      // Still here? Use the more judicious replacement.
5692      static $dblq = false;
5693      if ( false === $dblq ) {
5694          $dblq = _x( '&#8220;', 'opening curly double quote' );
5695      }
5696      return str_replace(
5697          array( ' Wordpress', '&#8216;Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
5698          array( ' WordPress', '&#8216;WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
5699          $text
5700      );
5701  }
5702  // phpcs:enable
5703  
5704  /**
5705   * Sanitizes a mime type
5706   *
5707   * @since 3.1.3
5708   *
5709   * @param string $mime_type Mime type.
5710   * @return string Sanitized mime type.
5711   */
5712  function sanitize_mime_type( $mime_type ) {
5713      $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '',