[ Index ]

PHP Cross Reference of WordPress

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 into formatted entities
  12   *
  13   * As an example,
  14   *
  15   *     'cause today's effort makes it worth tomorrow's "holiday" ...
  16   *
  17   * Becomes:
  18   *
  19   *     &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221; &#8230;
  20   *
  21   * Code within certain html blocks are skipped.
  22   *
  23   * Do not use this function before the {@see 'init'} action hook; everything will break.
  24   *
  25   * @since 0.71
  26   *
  27   * @global array $wp_cockneyreplace Array of formatted entities for certain common phrases
  28   * @global array $shortcode_tags
  29   * @staticvar array  $static_characters
  30   * @staticvar array  $static_replacements
  31   * @staticvar array  $dynamic_characters
  32   * @staticvar array  $dynamic_replacements
  33   * @staticvar array  $default_no_texturize_tags
  34   * @staticvar array  $default_no_texturize_shortcodes
  35   * @staticvar bool   $run_texturize
  36   * @staticvar string $apos
  37   * @staticvar string $prime
  38   * @staticvar string $double_prime
  39   * @staticvar string $opening_quote
  40   * @staticvar string $closing_quote
  41   * @staticvar string $opening_single_quote
  42   * @staticvar string $closing_single_quote
  43   * @staticvar string $open_q_flag
  44   * @staticvar string $open_sq_flag
  45   * @staticvar string $apos_flag
  46   *
  47   * @param string $text The text to be formatted
  48   * @param bool   $reset Set to true for unit testing. Translated patterns will reset.
  49   * @return string The string replaced with html entities
  50   */
  51  function wptexturize( $text, $reset = false ) {
  52      global $wp_cockneyreplace, $shortcode_tags;
  53      static $static_characters            = null,
  54          $static_replacements             = null,
  55          $dynamic_characters              = null,
  56          $dynamic_replacements            = null,
  57          $default_no_texturize_tags       = null,
  58          $default_no_texturize_shortcodes = null,
  59          $run_texturize                   = true,
  60          $apos                            = null,
  61          $prime                           = null,
  62          $double_prime                    = null,
  63          $opening_quote                   = null,
  64          $closing_quote                   = null,
  65          $opening_single_quote            = null,
  66          $closing_single_quote            = null,
  67          $open_q_flag                     = '<!--oq-->',
  68          $open_sq_flag                    = '<!--osq-->',
  69          $apos_flag                       = '<!--apos-->';
  70  
  71      // If there's nothing to do, just stop.
  72      if ( empty( $text ) || false === $run_texturize ) {
  73          return $text;
  74      }
  75  
  76      // Set up static variables. Run once only.
  77      if ( $reset || ! isset( $static_characters ) ) {
  78          /**
  79           * Filters whether to skip running wptexturize().
  80           *
  81           * Passing false to the filter will effectively short-circuit wptexturize().
  82           * returning the original text passed to the function instead.
  83           *
  84           * The filter runs only once, the first time wptexturize() is called.
  85           *
  86           * @since 4.0.0
  87           *
  88           * @see wptexturize()
  89           *
  90           * @param bool $run_texturize Whether to short-circuit wptexturize().
  91           */
  92          $run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
  93          if ( false === $run_texturize ) {
  94              return $text;
  95          }
  96  
  97          /* translators: opening curly double quote */
  98          $opening_quote = _x( '&#8220;', 'opening curly double quote' );
  99          /* translators: closing curly double quote */
 100          $closing_quote = _x( '&#8221;', 'closing curly double quote' );
 101  
 102          /* translators: apostrophe, for example in 'cause or can't */
 103          $apos = _x( '&#8217;', 'apostrophe' );
 104  
 105          /* translators: prime, for example in 9' (nine feet) */
 106          $prime = _x( '&#8242;', 'prime' );
 107          /* translators: double prime, for example in 9" (nine inches) */
 108          $double_prime = _x( '&#8243;', 'double prime' );
 109  
 110          /* translators: opening curly single quote */
 111          $opening_single_quote = _x( '&#8216;', 'opening curly single quote' );
 112          /* translators: closing curly single quote */
 113          $closing_single_quote = _x( '&#8217;', 'closing curly single quote' );
 114  
 115          /* translators: en dash */
 116          $en_dash = _x( '&#8211;', 'en dash' );
 117          /* translators: em dash */
 118          $em_dash = _x( '&#8212;', 'em dash' );
 119  
 120          $default_no_texturize_tags       = array( 'pre', 'code', 'kbd', 'style', 'script', 'tt' );
 121          $default_no_texturize_shortcodes = array( 'code' );
 122  
 123          // if a plugin has provided an autocorrect array, use it
 124          if ( isset( $wp_cockneyreplace ) ) {
 125              $cockney        = array_keys( $wp_cockneyreplace );
 126              $cockneyreplace = array_values( $wp_cockneyreplace );
 127          } else {
 128              /* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
 129               * for example...  'We do not have enough words yet' ... is a typical quoted phrase.  But when we write
 130               * lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
 131               */
 132              $cockney = explode(
 133                  ',',
 134                  _x(
 135                      "'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
 136                      'Comma-separated list of words to texturize in your language'
 137                  )
 138              );
 139  
 140              $cockneyreplace = explode(
 141                  ',',
 142                  _x(
 143                      '&#8217;tain&#8217;t,&#8217;twere,&#8217;twas,&#8217;tis,&#8217;twill,&#8217;til,&#8217;bout,&#8217;nuff,&#8217;round,&#8217;cause,&#8217;em',
 144                      'Comma-separated list of replacement words in your language'
 145                  )
 146              );
 147          }
 148  
 149          $static_characters   = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
 150          $static_replacements = array_merge( array( '&#8230;', $opening_quote, $closing_quote, ' &#8482;' ), $cockneyreplace );
 151  
 152          // Pattern-based replacements of characters.
 153          // Sort the remaining patterns into several arrays for performance tuning.
 154          $dynamic_characters   = array(
 155              'apos'  => array(),
 156              'quote' => array(),
 157              'dash'  => array(),
 158          );
 159          $dynamic_replacements = array(
 160              'apos'  => array(),
 161              'quote' => array(),
 162              'dash'  => array(),
 163          );
 164          $dynamic              = array();
 165          $spaces               = wp_spaces_regexp();
 166  
 167          // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
 168          if ( "'" !== $apos || "'" !== $closing_single_quote ) {
 169              $dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
 170          }
 171          if ( "'" !== $apos || '"' !== $closing_quote ) {
 172              $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
 173          }
 174  
 175          // '99 '99s '99's (apostrophe)  But never '9 or '99% or '999 or '99.0.
 176          if ( "'" !== $apos ) {
 177              $dynamic['/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/'] = $apos_flag;
 178          }
 179  
 180          // Quoted Numbers like '0.42'
 181          if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
 182              $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
 183          }
 184  
 185          // Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
 186          if ( "'" !== $opening_single_quote ) {
 187              $dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $open_sq_flag;
 188          }
 189  
 190          // Apostrophe in a word.  No spaces, double apostrophes, or other punctuation.
 191          if ( "'" !== $apos ) {
 192              $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
 193          }
 194  
 195          $dynamic_characters['apos']   = array_keys( $dynamic );
 196          $dynamic_replacements['apos'] = array_values( $dynamic );
 197          $dynamic                      = array();
 198  
 199          // Quoted Numbers like "42"
 200          if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
 201              $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
 202          }
 203  
 204          // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
 205          if ( '"' !== $opening_quote ) {
 206              $dynamic[ '/(?<=\A|[([{\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
 207          }
 208  
 209          $dynamic_characters['quote']   = array_keys( $dynamic );
 210          $dynamic_replacements['quote'] = array_values( $dynamic );
 211          $dynamic                       = array();
 212  
 213          // Dashes and spaces
 214          $dynamic['/---/'] = $em_dash;
 215          $dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash;
 216          $dynamic['/(?<!xn)--/']                                       = $en_dash;
 217          $dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ]  = $en_dash;
 218  
 219          $dynamic_characters['dash']   = array_keys( $dynamic );
 220          $dynamic_replacements['dash'] = array_values( $dynamic );
 221      }
 222  
 223      // Must do this every time in case plugins use these filters in a context sensitive manner
 224      /**
 225       * Filters the list of HTML elements not to texturize.
 226       *
 227       * @since 2.8.0
 228       *
 229       * @param array $default_no_texturize_tags An array of HTML element names.
 230       */
 231      $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
 232      /**
 233       * Filters the list of shortcodes not to texturize.
 234       *
 235       * @since 2.8.0
 236       *
 237       * @param array $default_no_texturize_shortcodes An array of shortcode names.
 238       */
 239      $no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
 240  
 241      $no_texturize_tags_stack       = array();
 242      $no_texturize_shortcodes_stack = array();
 243  
 244      // Look for shortcodes and HTML elements.
 245  
 246      preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
 247      $tagnames         = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
 248      $found_shortcodes = ! empty( $tagnames );
 249      $shortcode_regex  = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
 250      $regex            = _get_wptexturize_split_regex( $shortcode_regex );
 251  
 252      $textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
 253  
 254      foreach ( $textarr as &$curl ) {
 255          // Only call _wptexturize_pushpop_element if $curl is a delimiter.
 256          $first = $curl[0];
 257          if ( '<' === $first ) {
 258              if ( '<!--' === substr( $curl, 0, 4 ) ) {
 259                  // This is an HTML comment delimiter.
 260                  continue;
 261              } else {
 262                  // This is an HTML element delimiter.
 263  
 264                  // Replace each & with &#038; unless it already looks like an entity.
 265                  $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );
 266  
 267                  _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
 268              }
 269          } elseif ( '' === trim( $curl ) ) {
 270              // This is a newline between delimiters.  Performance improves when we check this.
 271              continue;
 272  
 273          } elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
 274              // This is a shortcode delimiter.
 275  
 276              if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
 277                  // Looks like a normal shortcode.
 278                  _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
 279              } else {
 280                  // Looks like an escaped shortcode.
 281                  continue;
 282              }
 283          } elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
 284              // This is neither a delimiter, nor is this content inside of no_texturize pairs.  Do texturize.
 285  
 286              $curl = str_replace( $static_characters, $static_replacements, $curl );
 287  
 288              if ( false !== strpos( $curl, "'" ) ) {
 289                  $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
 290                  $curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
 291                  $curl = str_replace( $apos_flag, $apos, $curl );
 292                  $curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
 293              }
 294              if ( false !== strpos( $curl, '"' ) ) {
 295                  $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
 296                  $curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
 297                  $curl = str_replace( $open_q_flag, $opening_quote, $curl );
 298              }
 299              if ( false !== strpos( $curl, '-' ) ) {
 300                  $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
 301              }
 302  
 303              // 9x9 (times), but never 0x9999
 304              if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
 305                  // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
 306                  $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1&#215;$2', $curl );
 307              }
 308  
 309              // Replace each & with &#038; unless it already looks like an entity.
 310              $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $curl );
 311          }
 312      }
 313  
 314      return implode( '', $textarr );
 315  }
 316  
 317  /**
 318   * Implements a logic tree to determine whether or not "7'." represents seven feet,
 319   * then converts the special char into either a prime char or a closing quote char.
 320   *
 321   * @since 4.3.0
 322   *
 323   * @param string $haystack    The plain text to be searched.
 324   * @param string $needle      The character to search for such as ' or ".
 325   * @param string $prime       The prime char to use for replacement.
 326   * @param string $open_quote  The opening quote char. Opening quote replacement must be
 327   *                            accomplished already.
 328   * @param string $close_quote The closing quote char to use for replacement.
 329   * @return string The $haystack value after primes and quotes replacements.
 330   */
 331  function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
 332      $spaces           = wp_spaces_regexp();
 333      $flag             = '<!--wp-prime-or-quote-->';
 334      $quote_pattern    = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|&gt;|" . $spaces . ')/';
 335      $prime_pattern    = "/(?<=\\d)$needle/";
 336      $flag_after_digit = "/(?<=\\d)$flag/";
 337      $flag_no_digit    = "/(?<!\\d)$flag/";
 338  
 339      $sentences = explode( $open_quote, $haystack );
 340  
 341      foreach ( $sentences as $key => &$sentence ) {
 342          if ( false === strpos( $sentence, $needle ) ) {
 343              continue;
 344          } elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
 345              $sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
 346              if ( $count > 1 ) {
 347                  // This sentence appears to have multiple closing quotes.  Attempt Vulcan logic.
 348                  $sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
 349                  if ( 0 === $count2 ) {
 350                      // Try looking for a quote followed by a period.
 351                      $count2 = substr_count( $sentence, "$flag." );
 352                      if ( $count2 > 0 ) {
 353                          // Assume the rightmost quote-period match is the end of quotation.
 354                          $pos = strrpos( $sentence, "$flag." );
 355                      } else {
 356                          // When all else fails, make the rightmost candidate a closing quote.
 357                          // This is most likely to be problematic in the context of bug #18549.
 358                          $pos = strrpos( $sentence, $flag );
 359                      }
 360                      $sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
 361                  }
 362                  // Use conventional replacement on any remaining primes and quotes.
 363                  $sentence = preg_replace( $prime_pattern, $prime, $sentence );
 364                  $sentence = preg_replace( $flag_after_digit, $prime, $sentence );
 365                  $sentence = str_replace( $flag, $close_quote, $sentence );
 366              } elseif ( 1 == $count ) {
 367                  // Found only one closing quote candidate, so give it priority over primes.
 368                  $sentence = str_replace( $flag, $close_quote, $sentence );
 369                  $sentence = preg_replace( $prime_pattern, $prime, $sentence );
 370              } else {
 371                  // No closing quotes found.  Just run primes pattern.
 372                  $sentence = preg_replace( $prime_pattern, $prime, $sentence );
 373              }
 374          } else {
 375              $sentence = preg_replace( $prime_pattern, $prime, $sentence );
 376              $sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
 377          }
 378          if ( '"' == $needle && false !== strpos( $sentence, '"' ) ) {
 379              $sentence = str_replace( '"', $close_quote, $sentence );
 380          }
 381      }
 382  
 383      return implode( $open_quote, $sentences );
 384  }
 385  
 386  /**
 387   * Search for disabled element tags. Push element to stack on tag open and pop
 388   * on tag close.
 389   *
 390   * Assumes first char of $text is tag opening and last char is tag closing.
 391   * Assumes second char of $text is optionally '/' to indicate closing as in </html>.
 392   *
 393   * @since 2.9.0
 394   * @access private
 395   *
 396   * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
 397   * @param array  $stack List of open tag elements.
 398   * @param array  $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
 399   */
 400  function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) {
 401      // Is it an opening tag or closing tag?
 402      if ( isset( $text[1] ) && '/' !== $text[1] ) {
 403          $opening_tag = true;
 404          $name_offset = 1;
 405      } elseif ( 0 == count( $stack ) ) {
 406          // Stack is empty. Just stop.
 407          return;
 408      } else {
 409          $opening_tag = false;
 410          $name_offset = 2;
 411      }
 412  
 413      // Parse out the tag name.
 414      $space = strpos( $text, ' ' );
 415      if ( false === $space ) {
 416          $space = -1;
 417      } else {
 418          $space -= $name_offset;
 419      }
 420      $tag = substr( $text, $name_offset, $space );
 421  
 422      // Handle disabled tags.
 423      if ( in_array( $tag, $disabled_elements ) ) {
 424          if ( $opening_tag ) {
 425              /*
 426               * This disables texturize until we find a closing tag of our type
 427               * (e.g. <pre>) even if there was invalid nesting before that
 428               *
 429               * Example: in the case <pre>sadsadasd</code>"baba"</pre>
 430               *          "baba" won't be texturize
 431               */
 432  
 433              array_push( $stack, $tag );
 434          } elseif ( end( $stack ) == $tag ) {
 435              array_pop( $stack );
 436          }
 437      }
 438  }
 439  
 440  /**
 441   * Replaces double line-breaks with paragraph elements.
 442   *
 443   * A group of regex replaces used to identify text formatted with newlines and
 444   * replace double line-breaks with HTML paragraph tags. The remaining line-breaks
 445   * after conversion become <<br />> tags, unless $br is set to '0' or 'false'.
 446   *
 447   * @since 0.71
 448   *
 449   * @param string $pee The text which has to be formatted.
 450   * @param bool   $br  Optional. If set, this will convert all remaining line-breaks
 451   *                    after paragraphing. Default true.
 452   * @return string Text which has been converted into correct paragraph tags.
 453   */
 454  function wpautop( $pee, $br = true ) {
 455      $pre_tags = array();
 456  
 457      if ( trim( $pee ) === '' ) {
 458          return '';
 459      }
 460  
 461      // Just to make things a little easier, pad the end.
 462      $pee = $pee . "\n";
 463  
 464      /*
 465       * Pre tags shouldn't be touched by autop.
 466       * Replace pre tags with placeholders and bring them back after autop.
 467       */
 468      if ( strpos( $pee, '<pre' ) !== false ) {
 469          $pee_parts = explode( '</pre>', $pee );
 470          $last_pee  = array_pop( $pee_parts );
 471          $pee       = '';
 472          $i         = 0;
 473  
 474          foreach ( $pee_parts as $pee_part ) {
 475              $start = strpos( $pee_part, '<pre' );
 476  
 477              // Malformed html?
 478              if ( $start === false ) {
 479                  $pee .= $pee_part;
 480                  continue;
 481              }
 482  
 483              $name              = "<pre wp-pre-tag-$i></pre>";
 484              $pre_tags[ $name ] = substr( $pee_part, $start ) . '</pre>';
 485  
 486              $pee .= substr( $pee_part, 0, $start ) . $name;
 487              $i++;
 488          }
 489  
 490          $pee .= $last_pee;
 491      }
 492      // Change multiple <br>s into two line breaks, which will turn into paragraphs.
 493      $pee = preg_replace( '|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee );
 494  
 495      $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
 496  
 497      // Add a double line break above block-level opening tags.
 498      $pee = preg_replace( '!(<' . $allblocks . '[\s/>])!', "\n\n$1", $pee );
 499  
 500      // Add a double line break below block-level closing tags.
 501      $pee = preg_replace( '!(</' . $allblocks . '>)!', "$1\n\n", $pee );
 502  
 503      // Standardize newline characters to "\n".
 504      $pee = str_replace( array( "\r\n", "\r" ), "\n", $pee );
 505  
 506      // Find newlines in all elements and add placeholders.
 507      $pee = wp_replace_in_html_tags( $pee, array( "\n" => ' <!-- wpnl --> ' ) );
 508  
 509      // Collapse line breaks before and after <option> elements so they don't get autop'd.
 510      if ( strpos( $pee, '<option' ) !== false ) {
 511          $pee = preg_replace( '|\s*<option|', '<option', $pee );
 512          $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
 513      }
 514  
 515      /*
 516       * Collapse line breaks inside <object> elements, before <param> and <embed> elements
 517       * so they don't get autop'd.
 518       */
 519      if ( strpos( $pee, '</object>' ) !== false ) {
 520          $pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
 521          $pee = preg_replace( '|\s*</object>|', '</object>', $pee );
 522          $pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
 523      }
 524  
 525      /*
 526       * Collapse line breaks inside <audio> and <video> elements,
 527       * before and after <source> and <track> elements.
 528       */
 529      if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
 530          $pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
 531          $pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
 532          $pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
 533      }
 534  
 535      // Collapse line breaks before and after <figcaption> elements.
 536      if ( strpos( $pee, '<figcaption' ) !== false ) {
 537          $pee = preg_replace( '|\s*(<figcaption[^>]*>)|', '$1', $pee );
 538          $pee = preg_replace( '|</figcaption>\s*|', '</figcaption>', $pee );
 539      }
 540  
 541      // Remove more than two contiguous line breaks.
 542      $pee = preg_replace( "/\n\n+/", "\n\n", $pee );
 543  
 544      // Split up the contents into an array of strings, separated by double line breaks.
 545      $pees = preg_split( '/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY );
 546  
 547      // Reset $pee prior to rebuilding.
 548      $pee = '';
 549  
 550      // Rebuild the content as a string, wrapping every bit with a <p>.
 551      foreach ( $pees as $tinkle ) {
 552          $pee .= '<p>' . trim( $tinkle, "\n" ) . "</p>\n";
 553      }
 554  
 555      // Under certain strange conditions it could create a P of entirely whitespace.
 556      $pee = preg_replace( '|<p>\s*</p>|', '', $pee );
 557  
 558      // Add a closing <p> inside <div>, <address>, or <form> tag if missing.
 559      $pee = preg_replace( '!<p>([^<]+)</(div|address|form)>!', '<p>$1</p></$2>', $pee );
 560  
 561      // If an opening or closing block element tag is wrapped in a <p>, unwrap it.
 562      $pee = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $pee );
 563  
 564      // In some cases <li> may get wrapped in <p>, fix them.
 565      $pee = preg_replace( '|<p>(<li.+?)</p>|', '$1', $pee );
 566  
 567      // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
 568      $pee = preg_replace( '|<p><blockquote([^>]*)>|i', '<blockquote$1><p>', $pee );
 569      $pee = str_replace( '</blockquote></p>', '</p></blockquote>', $pee );
 570  
 571      // If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
 572      $pee = preg_replace( '!<p>\s*(</?' . $allblocks . '[^>]*>)!', '$1', $pee );
 573  
 574      // If an opening or closing block element tag is followed by a closing <p> tag, remove it.
 575      $pee = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*</p>!', '$1', $pee );
 576  
 577      // Optionally insert line breaks.
 578      if ( $br ) {
 579          // Replace newlines that shouldn't be touched with a placeholder.
 580          $pee = preg_replace_callback( '/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee );
 581  
 582          // Normalize <br>
 583          $pee = str_replace( array( '<br>', '<br/>' ), '<br />', $pee );
 584  
 585          // Replace any new line characters that aren't preceded by a <br /> with a <br />.
 586          $pee = preg_replace( '|(?<!<br />)\s*\n|', "<br />\n", $pee );
 587  
 588          // Replace newline placeholders with newlines.
 589          $pee = str_replace( '<WPPreserveNewline />', "\n", $pee );
 590      }
 591  
 592      // If a <br /> tag is after an opening or closing block tag, remove it.
 593      $pee = preg_replace( '!(</?' . $allblocks . '[^>]*>)\s*<br />!', '$1', $pee );
 594  
 595      // If a <br /> tag is before a subset of opening or closing block tags, remove it.
 596      $pee = preg_replace( '!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee );
 597      $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
 598  
 599      // Replace placeholder <pre> tags with their original content.
 600      if ( ! empty( $pre_tags ) ) {
 601          $pee = str_replace( array_keys( $pre_tags ), array_values( $pre_tags ), $pee );
 602      }
 603  
 604      // Restore newlines in all elements.
 605      if ( false !== strpos( $pee, '<!-- wpnl -->' ) ) {
 606          $pee = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $pee );
 607      }
 608  
 609      return $pee;
 610  }
 611  
 612  /**
 613   * Separate HTML elements and comments from the text.
 614   *
 615   * @since 4.2.4
 616   *
 617   * @param string $input The text which has to be formatted.
 618   * @return array The formatted text.
 619   */
 620  function wp_html_split( $input ) {
 621      return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
 622  }
 623  
 624  /**
 625   * Retrieve the regular expression for an HTML element.
 626   *
 627   * @since 4.4.0
 628   *
 629   * @staticvar string $regex
 630   *
 631   * @return string The regular expression
 632   */
 633  function get_html_split_regex() {
 634      static $regex;
 635  
 636      if ( ! isset( $regex ) ) {
 637          // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
 638          $comments =
 639              '!'             // Start of comment, after the <.
 640              . '(?:'         // Unroll the loop: Consume everything until --> is found.
 641              .     '-(?!->)' // Dash not followed by end of comment.
 642              .     '[^\-]*+' // Consume non-dashes.
 643              . ')*+'         // Loop possessively.
 644              . '(?:-->)?';   // End of comment. If not found, match all input.
 645  
 646          $cdata =
 647              '!\[CDATA\['    // Start of comment, after the <.
 648              . '[^\]]*+'     // Consume non-].
 649              . '(?:'         // Unroll the loop: Consume everything until ]]> is found.
 650              .     '](?!]>)' // One ] not followed by end of comment.
 651              .     '[^\]]*+' // Consume non-].
 652              . ')*+'         // Loop possessively.
 653              . '(?:]]>)?';   // End of comment. If not found, match all input.
 654  
 655          $escaped =
 656              '(?='             // Is the element escaped?
 657              .    '!--'
 658              . '|'
 659              .    '!\[CDATA\['
 660              . ')'
 661              . '(?(?=!-)'      // If yes, which type?
 662              .     $comments
 663              . '|'
 664              .     $cdata
 665              . ')';
 666  
 667          $regex =
 668              '/('                // Capture the entire match.
 669              .     '<'           // Find start of element.
 670              .     '(?'          // Conditional expression follows.
 671              .         $escaped  // Find end of escaped element.
 672              .     '|'           // ... else ...
 673              .         '[^>]*>?' // Find end of normal element.
 674              .     ')'
 675              . ')/';
 676          // phpcs:enable
 677      }
 678  
 679      return $regex;
 680  }
 681  
 682  /**
 683   * Retrieve the combined regular expression for HTML and shortcodes.
 684   *
 685   * @access private
 686   * @ignore
 687   * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
 688   * @since 4.4.0
 689   *
 690   * @staticvar string $html_regex
 691   *
 692   * @param string $shortcode_regex The result from _get_wptexturize_shortcode_regex().  Optional.
 693   * @return string The regular expression
 694   */
 695  function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
 696      static $html_regex;
 697  
 698      if ( ! isset( $html_regex ) ) {
 699          // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
 700          $comment_regex =
 701              '!'             // Start of comment, after the <.
 702              . '(?:'         // Unroll the loop: Consume everything until --> is found.
 703              .     '-(?!->)' // Dash not followed by end of comment.
 704              .     '[^\-]*+' // Consume non-dashes.
 705              . ')*+'         // Loop possessively.
 706              . '(?:-->)?';   // End of comment. If not found, match all input.
 707  
 708          $html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
 709              '<'                  // Find start of element.
 710              . '(?(?=!--)'        // Is this a comment?
 711              .     $comment_regex // Find end of comment.
 712              . '|'
 713              .     '[^>]*>?'      // Find end of element. If not found, match all input.
 714              . ')';
 715          // phpcs:enable
 716      }
 717  
 718      if ( empty( $shortcode_regex ) ) {
 719          $regex = '/(' . $html_regex . ')/';
 720      } else {
 721          $regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
 722      }
 723  
 724      return $regex;
 725  }
 726  
 727  /**
 728   * Retrieve the regular expression for shortcodes.
 729   *
 730   * @access private
 731   * @ignore
 732   * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
 733   * @since 4.4.0
 734   *
 735   * @param array $tagnames List of shortcodes to find.
 736   * @return string The regular expression
 737   */
 738  function _get_wptexturize_shortcode_regex( $tagnames ) {
 739      $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
 740      $tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
 741      // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
 742      $regex =
 743          '\['              // Find start of shortcode.
 744          . '[\/\[]?'         // Shortcodes may begin with [/ or [[
 745          . $tagregexp        // Only match registered shortcodes, because performance.
 746          . '(?:'
 747          .     '[^\[\]<>]+'  // Shortcodes do not contain other shortcodes. Quantifier critical.
 748          . '|'
 749          .     '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
 750          . ')*+'             // Possessive critical.
 751          . '\]'              // Find end of shortcode.
 752          . '\]?';            // Shortcodes may end with ]]
 753      // phpcs:enable
 754  
 755      return $regex;
 756  }
 757  
 758  /**
 759   * Replace characters or phrases within HTML elements only.
 760   *
 761   * @since 4.2.3
 762   *
 763   * @param string $haystack The text which has to be formatted.
 764   * @param array $replace_pairs In the form array('from' => 'to', ...).
 765   * @return string The formatted text.
 766   */
 767  function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
 768      // Find all elements.
 769      $textarr = wp_html_split( $haystack );
 770      $changed = false;
 771  
 772      // Optimize when searching for one item.
 773      if ( 1 === count( $replace_pairs ) ) {
 774          // Extract $needle and $replace.
 775          foreach ( $replace_pairs as $needle => $replace ) {
 776          }
 777  
 778          // Loop through delimiters (elements) only.
 779          for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
 780              if ( false !== strpos( $textarr[ $i ], $needle ) ) {
 781                  $textarr[ $i ] = str_replace( $needle, $replace, $textarr[ $i ] );
 782                  $changed       = true;
 783              }
 784          }
 785      } else {
 786          // Extract all $needles.
 787          $needles = array_keys( $replace_pairs );
 788  
 789          // Loop through delimiters (elements) only.
 790          for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
 791              foreach ( $needles as $needle ) {
 792                  if ( false !== strpos( $textarr[ $i ], $needle ) ) {
 793                      $textarr[ $i ] = strtr( $textarr[ $i ], $replace_pairs );
 794                      $changed       = true;
 795                      // After one strtr() break out of the foreach loop and look at next element.
 796                      break;
 797                  }
 798              }
 799          }
 800      }
 801  
 802      if ( $changed ) {
 803          $haystack = implode( $textarr );
 804      }
 805  
 806      return $haystack;
 807  }
 808  
 809  /**
 810   * Newline preservation help function for wpautop
 811   *
 812   * @since 3.1.0
 813   * @access private
 814   *
 815   * @param array $matches preg_replace_callback matches array
 816   * @return string
 817   */
 818  function _autop_newline_preservation_helper( $matches ) {
 819      return str_replace( "\n", '<WPPreserveNewline />', $matches[0] );
 820  }
 821  
 822  /**
 823   * Don't auto-p wrap shortcodes that stand alone
 824   *
 825   * Ensures that shortcodes are not wrapped in `<p>...</p>`.
 826   *
 827   * @since 2.9.0
 828   *
 829   * @global array $shortcode_tags
 830   *
 831   * @param string $pee The content.
 832   * @return string The filtered content.
 833   */
 834  function shortcode_unautop( $pee ) {
 835      global $shortcode_tags;
 836  
 837      if ( empty( $shortcode_tags ) || ! is_array( $shortcode_tags ) ) {
 838          return $pee;
 839      }
 840  
 841      $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
 842      $spaces    = wp_spaces_regexp();
 843  
 844      // phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
 845      $pattern =
 846          '/'
 847          . '<p>'                              // Opening paragraph
 848          . '(?:' . $spaces . ')*+'            // Optional leading whitespace
 849          . '('                                // 1: The shortcode
 850          .     '\\['                          // Opening bracket
 851          .     "($tagregexp)"                 // 2: Shortcode name
 852          .     '(?![\\w-])'                   // Not followed by word character or hyphen
 853                                               // Unroll the loop: Inside the opening shortcode tag
 854          .     '[^\\]\\/]*'                   // Not a closing bracket or forward slash
 855          .     '(?:'
 856          .         '\\/(?!\\])'               // A forward slash not followed by a closing bracket
 857          .         '[^\\]\\/]*'               // Not a closing bracket or forward slash
 858          .     ')*?'
 859          .     '(?:'
 860          .         '\\/\\]'                   // Self closing tag and closing bracket
 861          .     '|'
 862          .         '\\]'                      // Closing bracket
 863          .         '(?:'                      // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
 864          .             '[^\\[]*+'             // Not an opening bracket
 865          .             '(?:'
 866          .                 '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
 867          .                 '[^\\[]*+'         // Not an opening bracket
 868          .             ')*+'
 869          .             '\\[\\/\\2\\]'         // Closing shortcode tag
 870          .         ')?'
 871          .     ')'
 872          . ')'
 873          . '(?:' . $spaces . ')*+'            // optional trailing whitespace
 874          . '<\\/p>'                           // closing paragraph
 875          . '/';
 876      // phpcs:enable
 877  
 878      return preg_replace( $pattern, '$1', $pee );
 879  }
 880  
 881  /**
 882   * Checks to see if a string is utf8 encoded.
 883   *
 884   * NOTE: This function checks for 5-Byte sequences, UTF8
 885   *       has Bytes Sequences with a maximum length of 4.
 886   *
 887   * @author bmorel at ssi dot fr (modified)
 888   * @since 1.2.1
 889   *
 890   * @param string $str The string to be checked
 891   * @return bool True if $str fits a UTF-8 model, false otherwise.
 892   */
 893  function seems_utf8( $str ) {
 894      mbstring_binary_safe_encoding();
 895      $length = strlen( $str );
 896      reset_mbstring_encoding();
 897      for ( $i = 0; $i < $length; $i++ ) {
 898          $c = ord( $str[ $i ] );
 899          if ( $c < 0x80 ) {
 900              $n = 0; // 0bbbbbbb
 901          } elseif ( ( $c & 0xE0 ) == 0xC0 ) {
 902              $n = 1; // 110bbbbb
 903          } elseif ( ( $c & 0xF0 ) == 0xE0 ) {
 904              $n = 2; // 1110bbbb
 905          } elseif ( ( $c & 0xF8 ) == 0xF0 ) {
 906              $n = 3; // 11110bbb
 907          } elseif ( ( $c & 0xFC ) == 0xF8 ) {
 908              $n = 4; // 111110bb
 909          } elseif ( ( $c & 0xFE ) == 0xFC ) {
 910              $n = 5; // 1111110b
 911          } else {
 912              return false; // Does not match any model
 913          }
 914          for ( $j = 0; $j < $n; $j++ ) { // n bytes matching 10bbbbbb follow ?
 915              if ( ( ++$i == $length ) || ( ( ord( $str[ $i ] ) & 0xC0 ) != 0x80 ) ) {
 916                  return false;
 917              }
 918          }
 919      }
 920      return true;
 921  }
 922  
 923  /**
 924   * Converts a number of special characters into their HTML entities.
 925   *
 926   * Specifically deals with: &, <, >, ", and '.
 927   *
 928   * $quote_style can be set to ENT_COMPAT to encode " to
 929   * &quot;, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
 930   *
 931   * @since 1.2.2
 932   * @access private
 933   *
 934   * @staticvar string $_charset
 935   *
 936   * @param string     $string         The text which is to be encoded.
 937   * @param int|string $quote_style    Optional. Converts double quotes if set to ENT_COMPAT,
 938   *                                   both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
 939   *                                   Also compatible with old values; converting single quotes if set to 'single',
 940   *                                   double if set to 'double' or both if otherwise set.
 941   *                                   Default is ENT_NOQUOTES.
 942   * @param string     $charset        Optional. The character encoding of the string. Default is false.
 943   * @param bool       $double_encode  Optional. Whether to encode existing html entities. Default is false.
 944   * @return string The encoded text with HTML entities.
 945   */
 946  function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
 947      $string = (string) $string;
 948  
 949      if ( 0 === strlen( $string ) ) {
 950          return '';
 951      }
 952  
 953      // Don't bother if there are no specialchars - saves some processing
 954      if ( ! preg_match( '/[&<>"\']/', $string ) ) {
 955          return $string;
 956      }
 957  
 958      // Account for the previous behaviour of the function when the $quote_style is not an accepted value
 959      if ( empty( $quote_style ) ) {
 960          $quote_style = ENT_NOQUOTES;
 961      } elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
 962          $quote_style = ENT_QUOTES;
 963      }
 964  
 965      // Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
 966      if ( ! $charset ) {
 967          static $_charset = null;
 968          if ( ! isset( $_charset ) ) {
 969              $alloptions = wp_load_alloptions();
 970              $_charset   = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
 971          }
 972          $charset = $_charset;
 973      }
 974  
 975      if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) {
 976          $charset = 'UTF-8';
 977      }
 978  
 979      $_quote_style = $quote_style;
 980  
 981      if ( $quote_style === 'double' ) {
 982          $quote_style  = ENT_COMPAT;
 983          $_quote_style = ENT_COMPAT;
 984      } elseif ( $quote_style === 'single' ) {
 985          $quote_style = ENT_NOQUOTES;
 986      }
 987  
 988      if ( ! $double_encode ) {
 989          // Guarantee every &entity; is valid, convert &garbage; into &amp;garbage;
 990          // This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
 991          $string = wp_kses_normalize_entities( $string );
 992      }
 993  
 994      $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode );
 995  
 996      // Back-compat.
 997      if ( 'single' === $_quote_style ) {
 998          $string = str_replace( "'", '&#039;', $string );
 999      }
1000  
1001      return $string;
1002  }
1003  
1004  /**
1005   * Converts a number of HTML entities into their special characters.
1006   *
1007   * Specifically deals with: &, <, >, ", and '.
1008   *
1009   * $quote_style can be set to ENT_COMPAT to decode " entities,
1010   * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
1011   *
1012   * @since 2.8.0
1013   *
1014   * @param string     $string The text which is to be decoded.
1015   * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
1016   *                                both single and double if set to ENT_QUOTES or
1017   *                                none if set to ENT_NOQUOTES.
1018   *                                Also compatible with old _wp_specialchars() values;
1019   *                                converting single quotes if set to 'single',
1020   *                                double if set to 'double' or both if otherwise set.
1021   *                                Default is ENT_NOQUOTES.
1022   * @return string The decoded text without HTML entities.
1023   */
1024  function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
1025      $string = (string) $string;
1026  
1027      if ( 0 === strlen( $string ) ) {
1028          return '';
1029      }
1030  
1031      // Don't bother if there are no entities - saves a lot of processing
1032      if ( strpos( $string, '&' ) === false ) {
1033          return $string;
1034      }
1035  
1036      // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
1037      if ( empty( $quote_style ) ) {
1038          $quote_style = ENT_NOQUOTES;
1039      } elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
1040          $quote_style = ENT_QUOTES;
1041      }
1042  
1043      // More complete than get_html_translation_table( HTML_SPECIALCHARS )
1044      $single      = array(
1045          '&#039;' => '\'',
1046          '&#x27;' => '\'',
1047      );
1048      $single_preg = array(
1049          '/&#0*39;/'   => '&#039;',
1050          '/&#x0*27;/i' => '&#x27;',
1051      );
1052      $double      = array(
1053          '&quot;' => '"',
1054          '&#034;' => '"',
1055          '&#x22;' => '"',
1056      );
1057      $double_preg = array(
1058          '/&#0*34;/'   => '&#034;',
1059          '/&#x0*22;/i' => '&#x22;',
1060      );
1061      $others      = array(
1062          '&lt;'   => '<',
1063          '&#060;' => '<',
1064          '&gt;'   => '>',
1065          '&#062;' => '>',
1066          '&amp;'  => '&',
1067          '&#038;' => '&',
1068          '&#x26;' => '&',
1069      );
1070      $others_preg = array(
1071          '/&#0*60;/'   => '&#060;',
1072          '/&#0*62;/'   => '&#062;',
1073          '/&#0*38;/'   => '&#038;',
1074          '/&#x0*26;/i' => '&#x26;',
1075      );
1076  
1077      if ( $quote_style === ENT_QUOTES ) {
1078          $translation      = array_merge( $single, $double, $others );
1079          $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
1080      } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
1081          $translation      = array_merge( $double, $others );
1082          $translation_preg = array_merge( $double_preg, $others_preg );
1083      } elseif ( $quote_style === 'single' ) {
1084          $translation      = array_merge( $single, $others );
1085          $translation_preg = array_merge( $single_preg, $others_preg );
1086      } elseif ( $quote_style === ENT_NOQUOTES ) {
1087          $translation      = $others;
1088          $translation_preg = $others_preg;
1089      }
1090  
1091      // Remove zero padding on numeric entities
1092      $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
1093  
1094      // Replace characters according to translation table
1095      return strtr( $string, $translation );
1096  }
1097  
1098  /**
1099   * Checks for invalid UTF8 in a string.
1100   *
1101   * @since 2.8.0
1102   *
1103   * @staticvar bool $is_utf8
1104   * @staticvar bool $utf8_pcre
1105   *
1106   * @param string  $string The text which is to be checked.
1107   * @param bool    $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
1108   * @return string The checked text.
1109   */
1110  function wp_check_invalid_utf8( $string, $strip = false ) {
1111      $string = (string) $string;
1112  
1113      if ( 0 === strlen( $string ) ) {
1114          return '';
1115      }
1116  
1117      // Store the site charset as a static to avoid multiple calls to get_option()
1118      static $is_utf8 = null;
1119      if ( ! isset( $is_utf8 ) ) {
1120          $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
1121      }
1122      if ( ! $is_utf8 ) {
1123          return $string;
1124      }
1125  
1126      // Check for support for utf8 in the installed PCRE library once and store the result in a static
1127      static $utf8_pcre = null;
1128      if ( ! isset( $utf8_pcre ) ) {
1129          $utf8_pcre = @preg_match( '/^./u', 'a' );
1130      }
1131      // We can't demand utf8 in the PCRE installation, so just return the string in those cases
1132      if ( ! $utf8_pcre ) {
1133          return $string;
1134      }
1135  
1136      // preg_match fails when it encounters invalid UTF8 in $string
1137      if ( 1 === @preg_match( '/^./us', $string ) ) {
1138          return $string;
1139      }
1140  
1141      // Attempt to strip the bad chars if requested (not recommended)
1142      if ( $strip && function_exists( 'iconv' ) ) {
1143          return iconv( 'utf-8', 'utf-8', $string );
1144      }
1145  
1146      return '';
1147  }
1148  
1149  /**
1150   * Encode the Unicode values to be used in the URI.
1151   *
1152   * @since 1.5.0
1153   *
1154   * @param string $utf8_string
1155   * @param int    $length Max  length of the string
1156   * @return string String with Unicode encoded for URI.
1157   */
1158  function utf8_uri_encode( $utf8_string, $length = 0 ) {
1159      $unicode        = '';
1160      $values         = array();
1161      $num_octets     = 1;
1162      $unicode_length = 0;
1163  
1164      mbstring_binary_safe_encoding();
1165      $string_length = strlen( $utf8_string );
1166      reset_mbstring_encoding();
1167  
1168      for ( $i = 0; $i < $string_length; $i++ ) {
1169  
1170          $value = ord( $utf8_string[ $i ] );
1171  
1172          if ( $value < 128 ) {
1173              if ( $length && ( $unicode_length >= $length ) ) {
1174                  break;
1175              }
1176              $unicode .= chr( $value );
1177              $unicode_length++;
1178          } else {
1179              if ( count( $values ) == 0 ) {
1180                  if ( $value < 224 ) {
1181                      $num_octets = 2;
1182                  } elseif ( $value < 240 ) {
1183                      $num_octets = 3;
1184                  } else {
1185                      $num_octets = 4;
1186                  }
1187              }
1188  
1189              $values[] = $value;
1190  
1191              if ( $length && ( $unicode_length + ( $num_octets * 3 ) ) > $length ) {
1192                  break;
1193              }
1194              if ( count( $values ) == $num_octets ) {
1195                  for ( $j = 0; $j < $num_octets; $j++ ) {
1196                      $unicode .= '%' . dechex( $values[ $j ] );
1197                  }
1198  
1199                  $unicode_length += $num_octets * 3;
1200  
1201                  $values     = array();
1202                  $num_octets = 1;
1203              }
1204          }
1205      }
1206  
1207      return $unicode;
1208  }
1209  
1210  /**
1211   * Converts all accent characters to ASCII characters.
1212   *
1213   * If there are no accent characters, then the string given is just returned.
1214   *
1215   * **Accent characters converted:**
1216   *
1217   * Currency signs:
1218   *
1219   * |   Code   | Glyph | Replacement |     Description     |
1220   * | -------- | ----- | ----------- | ------------------- |
1221   * | U+00A3   | £     | (empty)     | British Pound sign  |
1222   * | U+20AC   | €     | E           | Euro sign           |
1223   *
1224   * Decompositions for Latin-1 Supplement:
1225   *
1226   * |  Code   | Glyph | Replacement |               Description              |
1227   * | ------- | ----- | ----------- | -------------------------------------- |
1228   * | U+00AA  | ª     | a           | Feminine ordinal indicator             |
1229   * | U+00BA  | º     | o           | Masculine ordinal indicator            |
1230   * | U+00C0  | À     | A           | Latin capital letter A with grave      |
1231   * | U+00C1  | Á     | A           | Latin capital letter A with acute      |
1232   * | U+00C2  | Â     | A           | Latin capital letter A with circumflex |
1233   * | U+00C3  | Ã     | A           | Latin capital letter A with tilde      |
1234   * | U+00C4  | Ä     | A           | Latin capital letter A with diaeresis  |
1235   * | U+00C5  | Å     | A           | Latin capital letter A with ring above |
1236   * | U+00C6  | Æ     | AE          | Latin capital letter AE                |
1237   * | U+00C7  | Ç     | C           | Latin capital letter C with cedilla    |
1238   * | U+00C8  | È     | E           | Latin capital letter E with grave      |
1239   * | U+00C9  | É     | E           | Latin capital letter E with acute      |
1240   * | U+00CA  | Ê     | E           | Latin capital letter E with circumflex |
1241   * | U+00CB  | Ë     | E           | Latin capital letter E with diaeresis  |
1242   * | U+00CC  | Ì     | I           | Latin capital letter I with grave      |
1243   * | U+00CD  | Í     | I           | Latin capital letter I with acute      |
1244   * | U+00CE  | Î     | I           | Latin capital letter I with circumflex |
1245   * | U+00CF  | Ï     | I           | Latin capital letter I with diaeresis  |
1246   * | U+00D0  | Ð     | D           | Latin capital letter Eth               |
1247   * | U+00D1  | Ñ     | N           | Latin capital letter N with tilde      |
1248   * | U+00D2  | Ò     | O           | Latin capital letter O with grave      |
1249   * | U+00D3  | Ó     | O           | Latin capital letter O with acute      |
1250   * | U+00D4  | Ô     | O           | Latin capital letter O with circumflex |
1251   * | U+00D5  | Õ     | O           | Latin capital letter O with tilde      |
1252   * | U+00D6  | Ö     | O           | Latin capital letter O with diaeresis  |
1253   * | U+00D8  | Ø     | O           | Latin capital letter O with stroke     |
1254   * | U+00D9  | Ù     | U           | Latin capital letter U with grave      |
1255   * | U+00DA  | Ú     | U           | Latin capital letter U with acute      |
1256   * | U+00DB  | Û     | U           | Latin capital letter U with circumflex |
1257   * | U+00DC  | Ü     | U           | Latin capital letter U with diaeresis  |
1258   * | U+00DD  | Ý     | Y           | Latin capital letter Y with acute      |
1259   * | U+00DE  | Þ     | TH          | Latin capital letter Thorn             |
1260   * | U+00DF  | ß     | s           | Latin small letter sharp s             |
1261   * | U+00E0  | à     | a           | Latin small letter a with grave        |
1262   * | U+00E1  | á     | a           | Latin small letter a with acute        |
1263   * | U+00E2  | â     | a           | Latin small letter a with circumflex   |
1264   * | U+00E3  | ã     | a           | Latin small letter a with tilde        |
1265   * | U+00E4  | ä     | a           | Latin small letter a with diaeresis    |
1266   * | U+00E5  | å     | a           | Latin small letter a with ring above   |
1267   * | U+00E6  | æ     | ae          | Latin small letter ae                  |
1268   * | U+00E7  | ç     | c           | Latin small letter c with cedilla      |
1269   * | U+00E8  | è     | e           | Latin small letter e with grave        |
1270   * | U+00E9  | é     | e           | Latin small letter e with acute        |
1271   * | U+00EA  | ê     | e           | Latin small letter e with circumflex   |
1272   * | U+00EB  | ë     | e           | Latin small letter e with diaeresis    |
1273   * | U+00EC  | ì     | i           | Latin small letter i with grave        |
1274   * | U+00ED  | í     | i           | Latin small letter i with acute        |
1275   * | U+00EE  | î     | i           | Latin small letter i with circumflex   |
1276   * | U+00EF  | ï     | i           | Latin small letter i with diaeresis    |
1277   * | U+00F0  | ð     | d           | Latin small letter Eth                 |
1278   * | U+00F1  | ñ     | n           | Latin small letter n with tilde        |
1279   * | U+00F2  | ò     | o           | Latin small letter o with grave        |
1280   * | U+00F3  | ó     | o           | Latin small letter o with acute        |
1281   * | U+00F4  | ô     | o           | Latin small letter o with circumflex   |
1282   * | U+00F5  | õ     | o           | Latin small letter o with tilde        |
1283   * | U+00F6  | ö     | o           | Latin small letter o with diaeresis    |
1284   * | U+00F8  | ø     | o           | Latin small letter o with stroke       |
1285   * | U+00F9  | ù     | u           | Latin small letter u with grave        |
1286   * | U+00FA  | ú     | u           | Latin small letter u with acute        |
1287   * | U+00FB  | û     | u           | Latin small letter u with circumflex   |
1288   * | U+00FC  | ü     | u           | Latin small letter u with diaeresis    |
1289   * | U+00FD  | ý     | y           | Latin small letter y with acute        |
1290   * | U+00FE  | þ     | th          | Latin small letter Thorn               |
1291   * | U+00FF  | ÿ     | y           | Latin small letter y with diaeresis    |
1292   *
1293   * Decompositions for Latin Extended-A:
1294   *
1295   * |  Code   | Glyph | Replacement |                    Description                    |
1296   * | ------- | ----- | ----------- | ------------------------------------------------- |
1297   * | U+0100  | Ā     | A           | Latin capital letter A with macron                |
1298   * | U+0101  | ā     | a           | Latin small letter a with macron                  |
1299   * | U+0102  | Ă     | A           | Latin capital letter A with breve                 |
1300   * | U+0103  | ă     | a           | Latin small letter a with breve                   |
1301   * | U+0104  | Ą     | A           | Latin capital letter A with ogonek                |
1302   * | U+0105  | ą     | a           | Latin small letter a with ogonek                  |
1303   * | U+01006 | Ć     | C           | Latin capital letter C with acute                 |
1304   * | U+0107  | ć     | c           | Latin small letter c with acute                   |
1305   * | U+0108  | Ĉ     | C           | Latin capital letter C with circumflex            |
1306   * | U+0109  | ĉ     | c           | Latin small letter c with circumflex              |
1307   * | U+010A  | Ċ     | C           | Latin capital letter C with dot above             |
1308   * | U+010B  | ċ     | c           | Latin small letter c with dot above               |
1309   * | U+010C  | Č     | C           | Latin capital letter C with caron                 |
1310   * | U+010D  | č     | c           | Latin small letter c with caron                   |
1311   * | U+010E  | Ď     | D           | Latin capital letter D with caron                 |
1312   * | U+010F  | ď     | d           | Latin small letter d with caron                   |
1313   * | U+0110  | Đ     | D           | Latin capital letter D with stroke                |
1314   * | U+0111  | đ     | d           | Latin small letter d with stroke                  |
1315   * | U+0112  | Ē     | E           | Latin capital letter E with macron                |
1316   * | U+0113  | ē     | e           | Latin small letter e with macron                  |
1317   * | U+0114  | Ĕ     | E           | Latin capital letter E with breve                 |
1318   * | U+0115  | ĕ     | e           | Latin small letter e with breve                   |
1319   * | U+0116  | Ė     | E           | Latin capital letter E with dot above             |
1320   * | U+0117  | ė     | e           | Latin small letter e with dot above               |
1321   * | U+0118  | Ę     | E           | Latin capital letter E with ogonek                |
1322   * | U+0119  | ę     | e           | Latin small letter e with ogonek                  |
1323   * | U+011A  | Ě     | E           | Latin capital letter E with caron                 |
1324   * | U+011B  | ě     | e           | Latin small letter e with caron                   |
1325   * | U+011C  | Ĝ     | G           | Latin capital letter G with circumflex            |
1326   * | U+011D  | ĝ     | g           | Latin small letter g with circumflex              |
1327   * | U+011E  | Ğ     | G           | Latin capital letter G with breve                 |
1328   * | U+011F  | ğ     | g           | Latin small letter g with breve                   |
1329   * | U+0120  | Ġ     | G           | Latin capital letter G with dot above             |
1330   * | U+0121  | ġ     | g           | Latin small letter g with dot above               |
1331   * | U+0122  | Ģ     | G           | Latin capital letter G with cedilla               |
1332   * | U+0123  | ģ     | g           | Latin small letter g with cedilla                 |
1333   * | U+0124  | Ĥ     | H           | Latin capital letter H with circumflex            |
1334   * | U+0125  | ĥ     | h           | Latin small letter h with circumflex              |
1335   * | U+0126  | Ħ     | H           | Latin capital letter H with stroke                |
1336   * | U+0127  | ħ     | h           | Latin small letter h with stroke                  |
1337   * | U+0128  | Ĩ     | I           | Latin capital letter I with tilde                 |
1338   * | U+0129  | ĩ     | i           | Latin small letter i with tilde                   |
1339   * | U+012A  | Ī     | I           | Latin capital letter I with macron                |
1340   * | U+012B  | ī     | i           | Latin small letter i with macron                  |
1341   * | U+012C  | Ĭ     | I           | Latin capital letter I with breve                 |
1342   * | U+012D  | ĭ     | i           | Latin small letter i with breve                   |
1343   * | U+012E  | Į     | I           | Latin capital letter I with ogonek                |
1344   * | U+012F  | į     | i           | Latin small letter i with ogonek                  |
1345   * | U+0130  | İ     | I           | Latin capital letter I with dot above             |
1346   * | U+0131  | ı     | i           | Latin small letter dotless i                      |
1347   * | U+0132  | IJ     | IJ          | Latin capital ligature IJ                         |
1348   * | U+0133  | ij     | ij          | Latin small ligature ij                           |
1349   * | U+0134  | Ĵ     | J           | Latin capital letter J with circumflex            |
1350   * | U+0135  | ĵ     | j           | Latin small letter j with circumflex              |
1351   * | U+0136  | Ķ     | K           | Latin capital letter K with cedilla               |
1352   * | U+0137  | ķ     | k           | Latin small letter k with cedilla                 |
1353   * | U+0138  | ĸ     | k           | Latin small letter Kra                            |
1354   * | U+0139  | Ĺ     | L           | Latin capital letter L with acute                 |
1355   * | U+013A  | ĺ     | l           | Latin small letter l with acute                   |
1356   * | U+013B  | Ļ     | L           | Latin capital letter L with cedilla               |
1357   * | U+013C  | ļ     | l           | Latin small letter l with cedilla                 |
1358   * | U+013D  | Ľ     | L           | Latin capital letter L with caron                 |
1359   * | U+013E  | ľ     | l           | Latin small letter l with caron                   |
1360   * | U+013F  | Ŀ     | L           | Latin capital letter L with middle dot            |
1361   * | U+0140  | ŀ     | l           | Latin small letter l with middle dot              |
1362   * | U+0141  | Ł     | L           | Latin capital letter L with stroke                |
1363   * | U+0142  | ł     | l           | Latin small letter l with stroke                  |
1364   * | U+0143  | Ń     | N           | Latin capital letter N with acute                 |
1365   * | U+0144  | ń     | n           | Latin small letter N with acute                   |
1366   * | U+0145  | Ņ     | N           | Latin capital letter N with cedilla               |
1367   * | U+0146  | ņ     | n           | Latin small letter n with cedilla                 |
1368   * | U+0147  | Ň     | N           | Latin capital letter N with caron                 |
1369   * | U+0148  | ň     | n           | Latin small letter n with caron                   |
1370   * | U+0149  | ʼn     | n           | Latin small letter n preceded by apostrophe       |
1371   * | U+014A  | Ŋ     | N           | Latin capital letter Eng                          |
1372   * | U+014B  | ŋ     | n           | Latin small letter Eng                            |
1373   * | U+014C  | Ō     | O           | Latin capital letter O with macron                |
1374   * | U+014D  | ō     | o           | Latin small letter o with macron                  |
1375   * | U+014E  | Ŏ     | O           | Latin capital letter O with breve                 |
1376   * | U+014F  | ŏ     | o           | Latin small letter o with breve                   |
1377   * | U+0150  | Ő     | O           | Latin capital letter O with double acute          |
1378   * | U+0151  | ő     | o           | Latin small letter o with double acute            |
1379   * | U+0152  | Π    | OE          | Latin capital ligature OE                         |
1380   * | U+0153  | œ     | oe          | Latin small ligature oe                           |
1381   * | U+0154  | Ŕ     | R           | Latin capital letter R with acute                 |
1382   * | U+0155  | ŕ     | r           | Latin small letter r with acute                   |
1383   * | U+0156  | Ŗ     | R           | Latin capital letter R with cedilla               |
1384   * | U+0157  | ŗ     | r           | Latin small letter r with cedilla                 |
1385   * | U+0158  | Ř     | R           | Latin capital letter R with caron                 |
1386   * | U+0159  | ř     | r           | Latin small letter r with caron                   |
1387   * | U+015A  | Ś     | S           | Latin capital letter S with acute                 |
1388   * | U+015B  | ś     | s           | Latin small letter s with acute                   |
1389   * | U+015C  | Ŝ     | S           | Latin capital letter S with circumflex            |
1390   * | U+015D  | ŝ     | s           | Latin small letter s with circumflex              |
1391   * | U+015E  | Ş     | S           | Latin capital letter S with cedilla               |
1392   * | U+015F  | ş     | s           | Latin small letter s with cedilla                 |
1393   * | U+0160  | Š     | S           | Latin capital letter S with caron                 |
1394   * | U+0161  | š     | s           | Latin small letter s with caron                   |
1395   * | U+0162  | Ţ     | T           | Latin capital letter T with cedilla               |
1396   * | U+0163  | ţ     | t           | Latin small letter t with cedilla                 |
1397   * | U+0164  | Ť     | T           | Latin capital letter T with caron                 |
1398   * | U+0165  | ť     | t           | Latin small letter t with caron                   |
1399   * | U+0166  | Ŧ     | T           | Latin capital letter T with stroke                |
1400   * | U+0167  | ŧ     | t           | Latin small letter t with stroke                  |
1401   * | U+0168  | Ũ     | U           | Latin capital letter U with tilde                 |
1402   * | U+0169  | ũ     | u           | Latin small letter u with tilde                   |
1403   * | U+016A  | Ū     | U           | Latin capital letter U with macron                |
1404   * | U+016B  | ū     | u           | Latin small letter u with macron                  |
1405   * | U+016C  | Ŭ     | U           | Latin capital letter U with breve                 |
1406   * | U+016D  | ŭ     | u           | Latin small letter u with breve                   |
1407   * | U+016E  | Ů     | U           | Latin capital letter U with ring above            |
1408   * | U+016F  | ů     | u           | Latin small letter u with ring above              |
1409   * | U+0170  | Ű     | U           | Latin capital letter U with double acute          |
1410   * | U+0171  | ű     | u           | Latin small letter u with double acute            |
1411   * | U+0172  | Ų     | U           | Latin capital letter U with ogonek                |
1412   * | U+0173  | ų     | u           | Latin small letter u with ogonek                  |
1413   * | U+0174  | Ŵ     | W           | Latin capital letter W with circumflex            |
1414   * | U+0175  | ŵ     | w           | Latin small letter w with circumflex              |
1415   * | U+0176  | Ŷ     | Y           | Latin capital letter Y with circumflex            |
1416   * | U+0177  | ŷ     | y           | Latin small letter y with circumflex              |
1417   * | U+0178  | Ÿ     | Y           | Latin capital letter Y with diaeresis             |
1418   * | U+0179  | Ź     | Z           | Latin capital letter Z with acute                 |
1419   * | U+017A  | ź     | z           | Latin small letter z with acute                   |
1420   * | U+017B  | Ż     | Z           | Latin capital letter Z with dot above             |
1421   * | U+017C  | ż     | z           | Latin small letter z with dot above               |
1422   * | U+017D  | Ž     | Z           | Latin capital letter Z with caron                 |
1423   * | U+017E  | ž     | z           | Latin small letter z with caron                   |
1424   * | U+017F  | ſ     | s           | Latin small letter long s                         |
1425   * | U+01A0  | Ơ     | O           | Latin capital letter O with horn                  |
1426   * | U+01A1  | ơ     | o           | Latin small letter o with horn                    |
1427   * | U+01AF  | Ư     | U           | Latin capital letter U with horn                  |
1428   * | U+01B0  | ư     | u           | Latin small letter u with horn                    |
1429   * | U+01CD  | Ǎ     | A           | Latin capital letter A with caron                 |
1430   * | U+01CE  | ǎ     | a           | Latin small letter a with caron                   |
1431   * | U+01CF  | Ǐ     | I           | Latin capital letter I with caron                 |
1432   * | U+01D0  | ǐ     | i           | Latin small letter i with caron                   |
1433   * | U+01D1  | Ǒ     | O           | Latin capital letter O with caron                 |
1434   * | U+01D2  | ǒ     | o           | Latin small letter o with caron                   |
1435   * | U+01D3  | Ǔ     | U           | Latin capital letter U with caron                 |
1436   * | U+01D4  | ǔ     | u           | Latin small letter u with caron                   |
1437   * | U+01D5  | Ǖ     | U           | Latin capital letter U with diaeresis and macron  |
1438   * | U+01D6  | ǖ     | u           | Latin small letter u with diaeresis and macron    |
1439   * | U+01D7  | Ǘ     | U           | Latin capital letter U with diaeresis and acute   |
1440   * | U+01D8  | ǘ     | u           | Latin small letter u with diaeresis and acute     |
1441   * | U+01D9  | Ǚ     | U           | Latin capital letter U with diaeresis and caron   |
1442   * | U+01DA  | ǚ     | u           | Latin small letter u with diaeresis and caron     |
1443   * | U+01DB  | Ǜ     | U           | Latin capital letter U with diaeresis and grave   |
1444   * | U+01DC  | ǜ     | u           | Latin small letter u with diaeresis and grave     |
1445   *
1446   * Decompositions for Latin Extended-B:
1447   *
1448   * |   Code   | Glyph | Replacement |                Description                |
1449   * | -------- | ----- | ----------- | ----------------------------------------- |
1450   * | U+0218   | Ș     | S           | Latin capital letter S with comma below   |
1451   * | U+0219   | ș     | s           | Latin small letter s with comma below     |
1452   * | U+021A   | Ț     | T           | Latin capital letter T with comma below   |
1453   * | U+021B   | ț     | t           | Latin small letter t with comma below     |
1454   *
1455   * Vowels with diacritic (Chinese, Hanyu Pinyin):
1456   *
1457   * |   Code   | Glyph | Replacement |                      Description                      |
1458   * | -------- | ----- | ----------- | ----------------------------------------------------- |
1459   * | U+0251   | ɑ     | a           | Latin small letter alpha                              |
1460   * | U+1EA0   | Ạ     | A           | Latin capital letter A with dot below                 |
1461   * | U+1EA1   | ạ     | a           | Latin small letter a with dot below                   |
1462   * | U+1EA2   | Ả     | A           | Latin capital letter A with hook above                |
1463   * | U+1EA3   | ả     | a           | Latin small letter a with hook above                  |
1464   * | U+1EA4   | Ấ     | A           | Latin capital letter A with circumflex and acute      |
1465   * | U+1EA5   | ấ     | a           | Latin small letter a with circumflex and acute        |
1466   * | U+1EA6   | Ầ     | A           | Latin capital letter A with circumflex and grave      |
1467   * | U+1EA7   | ầ     | a           | Latin small letter a with circumflex and grave        |
1468   * | U+1EA8   | Ẩ     | A           | Latin capital letter A with circumflex and hook above |
1469   * | U+1EA9   | ẩ     | a           | Latin small letter a with circumflex and hook above   |
1470   * | U+1EAA   | Ẫ     | A           | Latin capital letter A with circumflex and tilde      |
1471   * | U+1EAB   | ẫ     | a           | Latin small letter a with circumflex and tilde        |
1472   * | U+1EA6   | Ậ     | A           | Latin capital letter A with circumflex and dot below  |
1473   * | U+1EAD   | ậ     | a           | Latin small letter a with circumflex and dot below    |
1474   * | U+1EAE   | Ắ     | A           | Latin capital letter A with breve and acute           |
1475   * | U+1EAF   | ắ     | a           | Latin small letter a with breve and acute             |
1476   * | U+1EB0   | Ằ     | A           | Latin capital letter A with breve and grave           |
1477   * | U+1EB1   | ằ     | a           | Latin small letter a with breve and grave             |
1478   * | U+1EB2   | Ẳ     | A           | Latin capital letter A with breve and hook above      |
1479   * | U+1EB3   | ẳ     | a           | Latin small letter a with breve and hook above        |
1480   * | U+1EB4   | Ẵ     | A           | Latin capital letter A with breve and tilde           |
1481   * | U+1EB5   | ẵ     | a           | Latin small letter a with breve and tilde             |
1482   * | U+1EB6   | Ặ     | A           | Latin capital letter A with breve and dot below       |
1483   * | U+1EB7   | ặ     | a           | Latin small letter a with breve and dot below         |
1484   * | U+1EB8   | Ẹ     | E           | Latin capital letter E with dot below                 |
1485   * | U+1EB9   | ẹ     | e           | Latin small letter e with dot below                   |
1486   * | U+1EBA   | Ẻ     | E           | Latin capital letter E with hook above                |
1487   * | U+1EBB   | ẻ     | e           | Latin small letter e with hook above                  |
1488   * | U+1EBC   | Ẽ     | E           | Latin capital letter E with tilde                     |
1489   * | U+1EBD   | ẽ     | e           | Latin small letter e with tilde                       |
1490   * | U+1EBE   | Ế     | E           | Latin capital letter E with circumflex and acute      |
1491   * | U+1EBF   | ế     | e           | Latin small letter e with circumflex and acute        |
1492   * | U+1EC0   | Ề     | E           | Latin capital letter E with circumflex and grave      |
1493   * | U+1EC1   | ề     | e           | Latin small letter e with circumflex and grave        |
1494   * | U+1EC2   | Ể     | E           | Latin capital letter E with circumflex and hook above |
1495   * | U+1EC3   | ể     | e           | Latin small letter e with circumflex and hook above   |
1496   * | U+1EC4   | Ễ     | E           | Latin capital letter E with circumflex and tilde      |
1497   * | U+1EC5   | ễ     | e           | Latin small letter e with circumflex and tilde        |
1498   * | U+1EC6   | Ệ     | E           | Latin capital letter E with circumflex and dot below  |
1499   * | U+1EC7   | ệ     | e           | Latin small letter e with circumflex and dot below    |
1500   * | U+1EC8   | Ỉ     | I           | Latin capital letter I with hook above                |
1501   * | U+1EC9   | ỉ     | i           | Latin small letter i with hook above                  |
1502   * | U+1ECA   | Ị     | I           | Latin capital letter I with dot below                 |
1503   * | U+1ECB   | ị     | i           | Latin small letter i with dot below                   |
1504   * | U+1ECC   | Ọ     | O           | Latin capital letter O with dot below                 |
1505   * | U+1ECD   | ọ     | o           | Latin small letter o with dot below                   |
1506   * | U+1ECE   | Ỏ     | O           | Latin capital letter O with hook above                |
1507   * | U+1ECF   | ỏ     | o           | Latin small letter o with hook above                  |
1508   * | U+1ED0   | Ố     | O           | Latin capital letter O with circumflex and acute      |
1509   * | U+1ED1   | ố     | o           | Latin small letter o with circumflex and acute        |
1510   * | U+1ED2   | Ồ     | O           | Latin capital letter O with circumflex and grave      |
1511   * | U+1ED3   | ồ     | o           | Latin small letter o with circumflex and grave        |
1512   * | U+1ED4   | Ổ     | O           | Latin capital letter O with circumflex and hook above |
1513   * | U+1ED5   | ổ     | o           | Latin small letter o with circumflex and hook above   |
1514   * | U+1ED6   | Ỗ     | O           | Latin capital letter O with circumflex and tilde      |
1515   * | U+1ED7   | ỗ     | o           | Latin small letter o with circumflex and tilde        |
1516   * | U+1ED8   | Ộ     | O           | Latin capital letter O with circumflex and dot below  |
1517   * | U+1ED9   | ộ     | o           | Latin small letter o with circumflex and dot below    |
1518   * | U+1EDA   | Ớ     | O           | Latin capital letter O with horn and acute            |
1519   * | U+1EDB   | ớ     | o           | Latin small letter o with horn and acute              |
1520   * | U+1EDC   | Ờ     | O           | Latin capital letter O with horn and grave            |
1521   * | U+1EDD   | ờ     | o           | Latin small letter o with horn and grave              |
1522   * | U+1EDE   | Ở     | O           | Latin capital letter O with horn and hook above       |
1523   * | U+1EDF   | ở     | o           | Latin small letter o with horn and hook above         |
1524   * | U+1EE0   | Ỡ     | O           | Latin capital letter O with horn and tilde            |
1525   * | U+1EE1   | ỡ     | o           | Latin small letter o with horn and tilde              |
1526   * | U+1EE2   | Ợ     | O           | Latin capital letter O with horn and dot below        |
1527   * | U+1EE3   | ợ     | o           | Latin small letter o with horn and dot below          |
1528   * | U+1EE4   | Ụ     | U           | Latin capital letter U with dot below                 |
1529   * | U+1EE5   | ụ     | u           | Latin small letter u with dot below                   |
1530   * | U+1EE6   | Ủ     | U           | Latin capital letter U with hook above                |
1531   * | U+1EE7   | ủ     | u           | Latin small letter u with hook above                  |
1532   * | U+1EE8   | Ứ     | U           | Latin capital letter U with horn and acute            |
1533   * | U+1EE9   | ứ     | u           | Latin small letter u with horn and acute              |
1534   * | U+1EEA   | Ừ     | U           | Latin capital letter U with horn and grave            |
1535   * | U+1EEB   | ừ     | u           | Latin small letter u with horn and grave              |
1536   * | U+1EEC   | Ử     | U           | Latin capital letter U with horn and hook above       |
1537   * | U+1EED   | ử     | u           | Latin small letter u with horn and hook above         |
1538   * | U+1EEE   | Ữ     | U           | Latin capital letter U with horn and tilde            |
1539   * | U+1EEF   | ữ     | u           | Latin small letter u with horn and tilde              |
1540   * | U+1EF0   | Ự     | U           | Latin capital letter U with horn and dot below        |
1541   * | U+1EF1   | ự     | u           | Latin small letter u with horn and dot below          |
1542   * | U+1EF2   | Ỳ     | Y           | Latin capital letter Y with grave                     |
1543   * | U+1EF3   | ỳ     | y           | Latin small letter y with grave                       |
1544   * | U+1EF4   | Ỵ     | Y           | Latin capital letter Y with dot below                 |
1545   * | U+1EF5   | ỵ     | y           | Latin small letter y with dot below                   |
1546   * | U+1EF6   | Ỷ     | Y           | Latin capital letter Y with hook above                |
1547   * | U+1EF7   | ỷ     | y           | Latin small letter y with hook above                  |
1548   * | U+1EF8   | Ỹ     | Y           | Latin capital letter Y with tilde                     |
1549   * | U+1EF9   | ỹ     | y           | Latin small letter y with tilde                       |
1550   *
1551   * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`),
1552   * and German (Switzerland) informal (`de_CH_informal`) locales:
1553   *
1554   * |   Code   | Glyph | Replacement |               Description               |
1555   * | -------- | ----- | ----------- | --------------------------------------- |
1556   * | U+00C4   | Ä     | Ae          | Latin capital letter A with diaeresis   |
1557   * | U+00E4   | ä     | ae          | Latin small letter a with diaeresis     |
1558   * | U+00D6   | Ö     | Oe          | Latin capital letter O with diaeresis   |
1559   * | U+00F6   | ö     | oe          | Latin small letter o with diaeresis     |
1560   * | U+00DC   | Ü     | Ue          | Latin capital letter U with diaeresis   |
1561   * | U+00FC   | ü     | ue          | Latin small letter u with diaeresis     |
1562   * | U+00DF   | ß     | ss          | Latin small letter sharp s              |
1563   *
1564   * Danish (`da_DK`) locale:
1565   *
1566   * |   Code   | Glyph | Replacement |               Description               |
1567   * | -------- | ----- | ----------- | --------------------------------------- |
1568   * | U+00C6   | Æ     | Ae          | Latin capital letter AE                 |
1569   * | U+00E6   | æ     | ae          | Latin small letter ae                   |
1570   * | U+00D8   | Ø     | Oe          | Latin capital letter O with stroke      |
1571   * | U+00F8   | ø     | oe          | Latin small letter o with stroke        |
1572   * | U+00C5   | Å     | Aa          | Latin capital letter A with ring above  |
1573   * | U+00E5   | å     | aa          | Latin small letter a with ring above    |
1574   *
1575   * Catalan (`ca`) locale:
1576   *
1577   * |   Code   | Glyph | Replacement |               Description               |
1578   * | -------- | ----- | ----------- | --------------------------------------- |
1579   * | U+00B7   | l·l   | ll          | Flown dot (between two Ls)              |
1580   *
1581   * Serbian (`sr_RS`) and Bosnian (`bs_BA`) locales:
1582   *
1583   * |   Code   | Glyph | Replacement |               Description               |
1584   * | -------- | ----- | ----------- | --------------------------------------- |
1585   * | U+0110   | Đ     | DJ          | Latin capital letter D with stroke      |
1586   * | U+0111   | đ     | dj          | Latin small letter d with stroke        |
1587   *
1588   * @since 1.2.1
1589   * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`.
1590   * @since 4.7.0 Added locale support for `sr_RS`.
1591   * @since 4.8.0 Added locale support for `bs_BA`.
1592   *
1593   * @param string $string Text that might have accent characters
1594   * @return string Filtered string with replaced "nice" characters.
1595   */
1596  function remove_accents( $string ) {
1597      if ( ! preg_match( '/[\x80-\xff]/', $string ) ) {
1598          return $string;
1599      }
1600  
1601      if ( seems_utf8( $string ) ) {
1602          $chars = array(
1603              // Decompositions for Latin-1 Supplement
1604              'ª' => 'a',
1605              'º' => 'o',
1606              'À' => 'A',
1607              'Á' => 'A',
1608              'Â' => 'A',
1609              'Ã' => 'A',
1610              'Ä' => 'A',
1611              'Å' => 'A',
1612              'Æ' => 'AE',
1613              'Ç' => 'C',
1614              'È' => 'E',
1615              'É' => 'E',
1616              'Ê' => 'E',
1617              'Ë' => 'E',
1618              'Ì' => 'I',
1619              'Í' => 'I',
1620              'Î' => 'I',
1621              'Ï' => 'I',
1622              'Ð' => 'D',
1623              'Ñ' => 'N',
1624              'Ò' => 'O',
1625              'Ó' => 'O',
1626              'Ô' => 'O',
1627              'Õ' => 'O',
1628              'Ö' => 'O',
1629              'Ù' => 'U',
1630              'Ú' => 'U',
1631              'Û' => 'U',
1632              'Ü' => 'U',
1633              'Ý' => 'Y',
1634              'Þ' => 'TH',
1635              'ß' => 's',
1636              'à' => 'a',
1637              'á' => 'a',
1638              'â' => 'a',
1639              'ã' => 'a',
1640              'ä' => 'a',
1641              'å' => 'a',
1642              'æ' => 'ae',
1643              'ç' => 'c',
1644              'è' => 'e',
1645              'é' => 'e',
1646              'ê' => 'e',
1647              'ë' => 'e',
1648              'ì' => 'i',
1649              'í' => 'i',
1650              'î' => 'i',
1651              'ï' => 'i',
1652              'ð' => 'd',
1653              'ñ' => 'n',
1654              'ò' => 'o',
1655              'ó' => 'o',
1656              'ô' => 'o',
1657              'õ' => 'o',
1658              'ö' => 'o',
1659              'ø' => 'o',
1660              'ù' => 'u',
1661              'ú' => 'u',
1662              'û' => 'u',
1663              'ü' => 'u',
1664              'ý' => 'y',
1665              'þ' => 'th',
1666              'ÿ' => 'y',
1667              'Ø' => 'O',
1668              // Decompositions for Latin Extended-A
1669              'Ā' => 'A',
1670              'ā' => 'a',
1671              'Ă' => 'A',
1672              'ă' => 'a',
1673              'Ą' => 'A',
1674              'ą' => 'a',
1675              'Ć' => 'C',
1676              'ć' => 'c',
1677              'Ĉ' => 'C',
1678              'ĉ' => 'c',
1679              'Ċ' => 'C',
1680              'ċ' => 'c',
1681              'Č' => 'C',
1682              'č' => 'c',
1683              'Ď' => 'D',
1684              'ď' => 'd',
1685              'Đ' => 'D',
1686              'đ' => 'd',
1687              'Ē' => 'E',
1688              'ē' => 'e',
1689              'Ĕ' => 'E',
1690              'ĕ' => 'e',
1691              'Ė' => 'E',
1692              'ė' => 'e',
1693              'Ę' => 'E',
1694              'ę' => 'e',
1695              'Ě' => 'E',
1696              'ě' => 'e',
1697              'Ĝ' => 'G',
1698              'ĝ' => 'g',
1699              'Ğ' => 'G',
1700              'ğ' => 'g',
1701              'Ġ' => 'G',
1702              'ġ' => 'g',
1703              'Ģ' => 'G',
1704              'ģ' => 'g',
1705              'Ĥ' => 'H',
1706              'ĥ' => 'h',
1707              'Ħ' => 'H',
1708              'ħ' => 'h',
1709              'Ĩ' => 'I',
1710              'ĩ' => 'i',
1711              'Ī' => 'I',
1712              'ī' => 'i',
1713              'Ĭ' => 'I',
1714              'ĭ' => 'i',
1715              'Į' => 'I',
1716              'į' => 'i',
1717              'İ' => 'I',
1718              'ı' => 'i',
1719              'IJ' => 'IJ',
1720              'ij' => 'ij',
1721              'Ĵ' => 'J',
1722              'ĵ' => 'j',
1723              'Ķ' => 'K',
1724              'ķ' => 'k',
1725              'ĸ' => 'k',
1726              'Ĺ' => 'L',
1727              'ĺ' => 'l',
1728              'Ļ' => 'L',
1729              'ļ' => 'l',
1730              'Ľ' => 'L',
1731              'ľ' => 'l',
1732              'Ŀ' => 'L',
1733              'ŀ' => 'l',
1734              'Ł' => 'L',
1735              'ł' => 'l',
1736              'Ń' => 'N',
1737              'ń' => 'n',
1738              'Ņ' => 'N',
1739              'ņ' => 'n',
1740              'Ň' => 'N',
1741              'ň' => 'n',
1742              'ʼn' => 'n',
1743              'Ŋ' => 'N',
1744              'ŋ' => 'n',
1745              'Ō' => 'O',
1746              'ō' => 'o',
1747              'Ŏ' => 'O',
1748              'ŏ' => 'o',
1749              'Ő' => 'O',
1750              'ő' => 'o',
1751              'Œ' => 'OE',
1752              'œ' => 'oe',
1753              'Ŕ' => 'R',
1754              'ŕ' => 'r',
1755              'Ŗ' => 'R',
1756              'ŗ' => 'r',
1757              'Ř' => 'R',
1758              'ř' => 'r',
1759              'Ś' => 'S',
1760              'ś' => 's',
1761              'Ŝ' => 'S',
1762              'ŝ' => 's',
1763              'Ş' => 'S',
1764              'ş' => 's',
1765              'Š' => 'S',
1766              'š' => 's',
1767              'Ţ' => 'T',
1768              'ţ' => 't',
1769              'Ť' => 'T',
1770              'ť' => 't',
1771              'Ŧ' => 'T',
1772              'ŧ' => 't',
1773              'Ũ' => 'U',
1774              'ũ' => 'u',
1775              'Ū' => 'U',
1776              'ū' => 'u',
1777              'Ŭ' => 'U',
1778              'ŭ' => 'u',
1779              'Ů' => 'U',
1780              'ů' => 'u',
1781              'Ű' => 'U',
1782              'ű' => 'u',
1783              'Ų' => 'U',
1784              'ų' => 'u',
1785              'Ŵ' => 'W',
1786              'ŵ' => 'w',
1787              'Ŷ' => 'Y',
1788              'ŷ' => 'y',
1789              'Ÿ' => 'Y',
1790              'Ź' => 'Z',
1791              'ź' => 'z',
1792              'Ż' => 'Z',
1793              'ż' => 'z',
1794              'Ž' => 'Z',
1795              'ž' => 'z',
1796              'ſ' => 's',
1797              // Decompositions for Latin Extended-B
1798              'Ș' => 'S',
1799              'ș' => 's',
1800              'Ț' => 'T',
1801              'ț' => 't',
1802              // Euro Sign
1803              '€' => 'E',
1804              // GBP (Pound) Sign
1805              '£' => '',
1806              // Vowels with diacritic (Vietnamese)
1807              // unmarked
1808              'Ơ' => 'O',
1809              'ơ' => 'o',
1810              'Ư' => 'U',
1811              'ư' => 'u',
1812              // grave accent
1813              'Ầ' => 'A',
1814              'ầ' => 'a',
1815              'Ằ' => 'A',
1816              'ằ' => 'a',
1817              'Ề' => 'E',
1818              'ề' => 'e',
1819              'Ồ' => 'O',
1820              'ồ' => 'o',
1821              'Ờ' => 'O',
1822              'ờ' => 'o',
1823              'Ừ' => 'U',
1824              'ừ' => 'u',
1825              'Ỳ' => 'Y',
1826              'ỳ' => 'y',
1827              // hook
1828              'Ả' => 'A',
1829              'ả' => 'a',
1830              'Ẩ' => 'A',
1831              'ẩ' => 'a',
1832              'Ẳ' => 'A',
1833              'ẳ' => 'a',
1834              'Ẻ' => 'E',
1835              'ẻ' => 'e',
1836              'Ể' => 'E',
1837              'ể' => 'e',
1838              'Ỉ' => 'I',
1839              'ỉ' => 'i',
1840              'Ỏ' => 'O',
1841              'ỏ' => 'o',
1842              'Ổ' => 'O',
1843              'ổ' => 'o',
1844              'Ở' => 'O',
1845              'ở' => 'o',
1846              'Ủ' => 'U',
1847              'ủ' => 'u',
1848              'Ử' => 'U',
1849              'ử' => 'u',
1850              'Ỷ' => 'Y',
1851              'ỷ' => 'y',
1852              // tilde
1853              'Ẫ' => 'A',
1854              'ẫ' => 'a',
1855              'Ẵ' => 'A',
1856              'ẵ' => 'a',
1857              'Ẽ' => 'E',
1858              'ẽ' => 'e',
1859              'Ễ' => 'E',
1860              'ễ' => 'e',
1861              'Ỗ' => 'O',
1862              'ỗ' => 'o',
1863              'Ỡ' => 'O',
1864              'ỡ' => 'o',
1865              'Ữ' => 'U',
1866              'ữ' => 'u',
1867              'Ỹ' => 'Y',
1868              'ỹ' => 'y',
1869              // acute accent
1870              'Ấ' => 'A',
1871              'ấ' => 'a',
1872              'Ắ' => 'A',
1873              'ắ' => 'a',
1874              'Ế' => 'E',
1875              'ế' => 'e',
1876              'Ố' => 'O',
1877              'ố' => 'o',
1878              'Ớ' => 'O',
1879              'ớ' => 'o',
1880              'Ứ' => 'U',
1881              'ứ' => 'u',
1882              // dot below
1883              'Ạ' => 'A',
1884              'ạ' => 'a',
1885              'Ậ' => 'A',
1886              'ậ' => 'a',
1887              'Ặ' => 'A',
1888              'ặ' => 'a',
1889              'Ẹ' => 'E',
1890              'ẹ' => 'e',
1891              'Ệ' => 'E',
1892              'ệ' => 'e',
1893              'Ị' => 'I',
1894              'ị' => 'i',
1895              'Ọ' => 'O',
1896              'ọ' => 'o',
1897              'Ộ' => 'O',
1898              'ộ' => 'o',
1899              'Ợ' => 'O',
1900              'ợ' => 'o',
1901              'Ụ' => 'U',
1902              'ụ' => 'u',
1903              'Ự' => 'U',
1904              'ự' => 'u',
1905              'Ỵ' => 'Y',
1906              'ỵ' => 'y',
1907              // Vowels with diacritic (Chinese, Hanyu Pinyin)
1908              'ɑ' => 'a',
1909              // macron
1910              'Ǖ' => 'U',
1911              'ǖ' => 'u',
1912              // acute accent
1913              'Ǘ' => 'U',
1914              'ǘ' => 'u',
1915              // caron
1916              'Ǎ' => 'A',
1917              'ǎ' => 'a',
1918              'Ǐ' => 'I',
1919              'ǐ' => 'i',
1920              'Ǒ' => 'O',
1921              'ǒ' => 'o',
1922              'Ǔ' => 'U',
1923              'ǔ' => 'u',
1924              'Ǚ' => 'U',
1925              'ǚ' => 'u',
1926              // grave accent
1927              'Ǜ' => 'U',
1928              'ǜ' => 'u',
1929          );
1930  
1931          // Used for locale-specific rules
1932          $locale = get_locale();
1933  
1934          if ( 'de_DE' == $locale || 'de_DE_formal' == $locale || 'de_CH' == $locale || 'de_CH_informal' == $locale ) {
1935              $chars['Ä'] = 'Ae';
1936              $chars['ä'] = 'ae';
1937              $chars['Ö'] = 'Oe';
1938              $chars['ö'] = 'oe';
1939              $chars['Ü'] = 'Ue';
1940              $chars['ü'] = 'ue';
1941              $chars['ß'] = 'ss';
1942          } elseif ( 'da_DK' === $locale ) {
1943              $chars['Æ'] = 'Ae';
1944              $chars['æ'] = 'ae';
1945              $chars['Ø'] = 'Oe';
1946              $chars['ø'] = 'oe';
1947              $chars['Å'] = 'Aa';
1948              $chars['å'] = 'aa';
1949          } elseif ( 'ca' === $locale ) {
1950              $chars['l·l'] = 'll';
1951          } elseif ( 'sr_RS' === $locale || 'bs_BA' === $locale ) {
1952              $chars['Đ'] = 'DJ';
1953              $chars['đ'] = 'dj';
1954          }
1955  
1956          $string = strtr( $string, $chars );
1957      } else {
1958          $chars = array();
1959          // Assume ISO-8859-1 if not UTF-8
1960          $chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e"
1961              . "\x9f\xa2\xa5\xb5\xc0\xc1\xc2"
1962              . "\xc3\xc4\xc5\xc7\xc8\xc9\xca"
1963              . "\xcb\xcc\xcd\xce\xcf\xd1\xd2"
1964              . "\xd3\xd4\xd5\xd6\xd8\xd9\xda"
1965              . "\xdb\xdc\xdd\xe0\xe1\xe2\xe3"
1966              . "\xe4\xe5\xe7\xe8\xe9\xea\xeb"
1967              . "\xec\xed\xee\xef\xf1\xf2\xf3"
1968              . "\xf4\xf5\xf6\xf8\xf9\xfa\xfb"
1969              . "\xfc\xfd\xff";
1970  
1971          $chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy';
1972  
1973          $string              = strtr( $string, $chars['in'], $chars['out'] );
1974          $double_chars        = array();
1975          $double_chars['in']  = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" );
1976          $double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' );
1977          $string              = str_replace( $double_chars['in'], $double_chars['out'], $string );
1978      }
1979  
1980      return $string;
1981  }
1982  
1983  /**
1984   * Sanitizes a filename, replacing whitespace with dashes.
1985   *
1986   * Removes special characters that are illegal in filenames on certain
1987   * operating systems and special characters requiring special escaping
1988   * to manipulate at the command line. Replaces spaces and consecutive
1989   * dashes with a single dash. Trims period, dash and underscore from beginning
1990   * and end of filename. It is not guaranteed that this function will return a
1991   * filename that is allowed to be uploaded.
1992   *
1993   * @since 2.1.0
1994   *
1995   * @param string $filename The filename to be sanitized
1996   * @return string The sanitized filename
1997   */
1998  function sanitize_file_name( $filename ) {
1999      $filename_raw  = $filename;
2000      $special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '|', '~', '`', '!', '{', '}', '%', '+', chr( 0 ) );
2001      /**
2002       * Filters the list of characters to remove from a filename.
2003       *
2004       * @since 2.8.0
2005       *
2006       * @param array  $special_chars Characters to remove.
2007       * @param string $filename_raw  Filename as it was passed into sanitize_file_name().
2008       */
2009      $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
2010      $filename      = preg_replace( "#\x{00a0}#siu", ' ', $filename );
2011      $filename      = str_replace( $special_chars, '', $filename );
2012      $filename      = str_replace( array( '%20', '+' ), '-', $filename );
2013      $filename      = preg_replace( '/[\r\n\t -]+/', '-', $filename );
2014      $filename      = trim( $filename, '.-_' );
2015  
2016      if ( false === strpos( $filename, '.' ) ) {
2017          $mime_types = wp_get_mime_types();
2018          $filetype   = wp_check_filetype( 'test.' . $filename, $mime_types );
2019          if ( $filetype['ext'] === $filename ) {
2020              $filename = 'unnamed-file.' . $filetype['ext'];
2021          }
2022      }
2023  
2024      // Split the filename into a base and extension[s]
2025      $parts = explode( '.', $filename );
2026  
2027      // Return if only one extension
2028      if ( count( $parts ) <= 2 ) {
2029          /**
2030           * Filters a sanitized filename string.
2031           *
2032           * @since 2.8.0
2033           *
2034           * @param string $filename     Sanitized filename.
2035           * @param string $filename_raw The filename prior to sanitization.
2036           */
2037          return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
2038      }
2039  
2040      // Process multiple extensions
2041      $filename  = array_shift( $parts );
2042      $extension = array_pop( $parts );
2043      $mimes     = get_allowed_mime_types();
2044  
2045      /*
2046       * Loop over any intermediate extensions. Postfix them with a trailing underscore
2047       * if they are a 2 - 5 character long alpha string not in the extension whitelist.
2048       */
2049      foreach ( (array) $parts as $part ) {
2050          $filename .= '.' . $part;
2051  
2052          if ( preg_match( '/^[a-zA-Z]{2,5}\d?$/', $part ) ) {
2053              $allowed = false;
2054              foreach ( $mimes as $ext_preg => $mime_match ) {
2055                  $ext_preg = '!^(' . $ext_preg . ')$!i';
2056                  if ( preg_match( $ext_preg, $part ) ) {
2057                      $allowed = true;
2058                      break;
2059                  }
2060              }
2061              if ( ! $allowed ) {
2062                  $filename .= '_';
2063              }
2064          }
2065      }
2066      $filename .= '.' . $extension;
2067      /** This filter is documented in wp-includes/formatting.php */
2068      return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
2069  }
2070  
2071  /**
2072   * Sanitizes a username, stripping out unsafe characters.
2073   *
2074   * Removes tags, octets, entities, and if strict is enabled, will only keep
2075   * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
2076   * raw username (the username in the parameter), and the value of $strict as
2077   * parameters for the {@see 'sanitize_user'} filter.
2078   *
2079   * @since 2.0.0
2080   *
2081   * @param string $username The username to be sanitized.
2082   * @param bool   $strict   If set limits $username to specific characters. Default false.
2083   * @return string The sanitized username, after passing through filters.
2084   */
2085  function sanitize_user( $username, $strict = false ) {
2086      $raw_username = $username;
2087      $username     = wp_strip_all_tags( $username );
2088      $username     = remove_accents( $username );
2089      // Kill octets
2090      $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
2091      $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
2092  
2093      // If strict, reduce to ASCII for max portability.
2094      if ( $strict ) {
2095          $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
2096      }
2097  
2098      $username = trim( $username );
2099      // Consolidate contiguous whitespace
2100      $username = preg_replace( '|\s+|', ' ', $username );
2101  
2102      /**
2103       * Filters a sanitized username string.
2104       *
2105       * @since 2.0.1
2106       *
2107       * @param string $username     Sanitized username.
2108       * @param string $raw_username The username prior to sanitization.
2109       * @param bool   $strict       Whether to limit the sanitization to specific characters. Default false.
2110       */
2111      return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
2112  }
2113  
2114  /**
2115   * Sanitizes a string key.
2116   *
2117   * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
2118   *
2119   * @since 3.0.0
2120   *
2121   * @param string $key String key
2122   * @return string Sanitized key
2123   */
2124  function sanitize_key( $key ) {
2125      $raw_key = $key;
2126      $key     = strtolower( $key );
2127      $key     = preg_replace( '/[^a-z0-9_\-]/', '', $key );
2128  
2129      /**
2130       * Filters a sanitized key string.
2131       *
2132       * @since 3.0.0
2133       *
2134       * @param string $key     Sanitized key.
2135       * @param string $raw_key The key prior to sanitization.
2136       */
2137      return apply_filters( 'sanitize_key', $key, $raw_key );
2138  }
2139  
2140  /**
2141   * Sanitizes a title, or returns a fallback title.
2142   *
2143   * Specifically, HTML and PHP tags are stripped. Further actions can be added
2144   * via the plugin API. If $title is empty and $fallback_title is set, the latter
2145   * will be used.
2146   *
2147   * @since 1.0.0
2148   *
2149   * @param string $title          The string to be sanitized.
2150   * @param string $fallback_title Optional. A title to use if $title is empty.
2151   * @param string $context        Optional. The operation for which the string is sanitized
2152   * @return string The sanitized string.
2153   */
2154  function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
2155      $raw_title = $title;
2156  
2157      if ( 'save' == $context ) {
2158          $title = remove_accents( $title );
2159      }
2160  
2161      /**
2162       * Filters a sanitized title string.
2163       *
2164       * @since 1.2.0
2165       *
2166       * @param string $title     Sanitized title.
2167       * @param string $raw_title The title prior to sanitization.
2168       * @param string $context   The context for which the title is being sanitized.
2169       */
2170      $title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
2171  
2172      if ( '' === $title || false === $title ) {
2173          $title = $fallback_title;
2174      }
2175  
2176      return $title;
2177  }
2178  
2179  /**
2180   * Sanitizes a title with the 'query' context.
2181   *
2182   * Used for querying the database for a value from URL.
2183   *
2184   * @since 3.1.0
2185   *
2186   * @param string $title The string to be sanitized.
2187   * @return string The sanitized string.
2188   */
2189  function sanitize_title_for_query( $title ) {
2190      return sanitize_title( $title, '', 'query' );
2191  }
2192  
2193  /**
2194   * Sanitizes a title, replacing whitespace and a few other characters with dashes.
2195   *
2196   * Limits the output to alphanumeric characters, underscore (_) and dash (-).
2197   * Whitespace becomes a dash.
2198   *
2199   * @since 1.2.0
2200   *
2201   * @param string $title     The title to be sanitized.
2202   * @param string $raw_title Optional. Not used.
2203   * @param string $context   Optional. The operation for which the string is sanitized.
2204   * @return string The sanitized title.
2205   */
2206  function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
2207      $title = strip_tags( $title );
2208      // Preserve escaped octets.
2209      $title = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title );
2210      // Remove percent signs that are not part of an octet.
2211      $title = str_replace( '%', '', $title );
2212      // Restore octets.
2213      $title = preg_replace( '|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title );
2214  
2215      if ( seems_utf8( $title ) ) {
2216          if ( function_exists( 'mb_strtolower' ) ) {
2217              $title = mb_strtolower( $title, 'UTF-8' );
2218          }
2219          $title = utf8_uri_encode( $title, 200 );
2220      }
2221  
2222      $title = strtolower( $title );
2223  
2224      if ( 'save' == $context ) {
2225          // Convert nbsp, ndash and mdash to hyphens
2226          $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
2227          // Convert nbsp, ndash and mdash HTML entities to hyphens
2228          $title = str_replace( array( '&nbsp;', '&#160;', '&ndash;', '&#8211;', '&mdash;', '&#8212;' ), '-', $title );
2229          // Convert forward slash to hyphen
2230          $title = str_replace( '/', '-', $title );
2231  
2232          // Strip these characters entirely
2233          $title = str_replace(
2234              array(
2235                  // soft hyphens
2236                  '%c2%ad',
2237                  // iexcl and iquest
2238                  '%c2%a1',
2239                  '%c2%bf',
2240                  // angle quotes
2241                  '%c2%ab',
2242                  '%c2%bb',
2243                  '%e2%80%b9',
2244                  '%e2%80%ba',
2245                  // curly quotes
2246                  '%e2%80%98',
2247                  '%e2%80%99',
2248                  '%e2%80%9c',
2249                  '%e2%80%9d',
2250                  '%e2%80%9a',
2251                  '%e2%80%9b',
2252                  '%e2%80%9e',
2253                  '%e2%80%9f',
2254                  // copy, reg, deg, hellip and trade
2255                  '%c2%a9',
2256                  '%c2%ae',
2257                  '%c2%b0',
2258                  '%e2%80%a6',
2259                  '%e2%84%a2',
2260                  // acute accents
2261                  '%c2%b4',
2262                  '%cb%8a',
2263                  '%cc%81',
2264                  '%cd%81',
2265                  // grave accent, macron, caron
2266                  '%cc%80',
2267                  '%cc%84',
2268                  '%cc%8c',
2269              ),
2270              '',
2271              $title
2272          );
2273  
2274          // Convert times to x
2275          $title = str_replace( '%c3%97', 'x', $title );
2276      }
2277  
2278      $title = preg_replace( '/&.+?;/', '', $title ); // kill entities
2279      $title = str_replace( '.', '-', $title );
2280  
2281      $title = preg_replace( '/[^%a-z0-9 _-]/', '', $title );
2282      $title = preg_replace( '/\s+/', '-', $title );
2283      $title = preg_replace( '|-+|', '-', $title );
2284      $title = trim( $title, '-' );
2285  
2286      return $title;
2287  }
2288  
2289  /**
2290   * Ensures a string is a valid SQL 'order by' clause.
2291   *
2292   * Accepts one or more columns, with or without a sort order (ASC / DESC).
2293   * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
2294   *
2295   * Also accepts 'RAND()'.
2296   *
2297   * @since 2.5.1
2298   *
2299   * @param string $orderby Order by clause to be validated.
2300   * @return string|false Returns $orderby if valid, false otherwise.
2301   */
2302  function sanitize_sql_orderby( $orderby ) {
2303      if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) {
2304          return $orderby;
2305      }
2306      return false;
2307  }
2308  
2309  /**
2310   * Sanitizes an HTML classname to ensure it only contains valid characters.
2311   *
2312   * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
2313   * string then it will return the alternative value supplied.
2314   *
2315   * @todo Expand to support the full range of CDATA that a class attribute can contain.
2316   *
2317   * @since 2.8.0
2318   *
2319   * @param string $class    The classname to be sanitized
2320   * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
2321   *  Defaults to an empty string.
2322   * @return string The sanitized value
2323   */
2324  function sanitize_html_class( $class, $fallback = '' ) {
2325      //Strip out any % encoded octets
2326      $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
2327  
2328      //Limit to A-Z,a-z,0-9,_,-
2329      $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
2330  
2331      if ( '' == $sanitized && $fallback ) {
2332          return sanitize_html_class( $fallback );
2333      }
2334      /**
2335       * Filters a sanitized HTML class string.
2336       *
2337       * @since 2.8.0
2338       *
2339       * @param string $sanitized The sanitized HTML class.
2340       * @param string $class     HTML class before sanitization.
2341       * @param string $fallback  The fallback string.
2342       */
2343      return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
2344  }
2345  
2346  /**
2347   * Converts lone & characters into `&#038;` (a.k.a. `&amp;`)
2348   *
2349   * @since 0.71
2350   *
2351   * @param string $content    String of characters to be converted.
2352   * @param string $deprecated Not used.
2353   * @return string Converted string.
2354   */
2355  function convert_chars( $content, $deprecated = '' ) {
2356      if ( ! empty( $deprecated ) ) {
2357          _deprecated_argument( __FUNCTION__, '0.71' );
2358      }
2359  
2360      if ( strpos( $content, '&' ) !== false ) {
2361          $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content );
2362      }
2363  
2364      return $content;
2365  }
2366  
2367  /**
2368   * Converts invalid Unicode references range to valid range.
2369   *
2370   * @since 4.3.0
2371   *
2372   * @param string $content String with entities that need converting.
2373   * @return string Converted string.
2374   */
2375  function convert_invalid_entities( $content ) {
2376      $wp_htmltranswinuni = array(
2377          '&#128;' => '&#8364;', // the Euro sign
2378          '&#129;' => '',
2379          '&#130;' => '&#8218;', // these are Windows CP1252 specific characters
2380          '&#131;' => '&#402;',  // they would look weird on non-Windows browsers
2381          '&#132;' => '&#8222;',
2382          '&#133;' => '&#8230;',
2383          '&#134;' => '&#8224;',
2384          '&#135;' => '&#8225;',
2385          '&#136;' => '&#710;',
2386          '&#137;' => '&#8240;',
2387          '&#138;' => '&#352;',
2388          '&#139;' => '&#8249;',
2389          '&#140;' => '&#338;',
2390          '&#141;' => '',
2391          '&#142;' => '&#381;',
2392          '&#143;' => '',
2393          '&#144;' => '',
2394          '&#145;' => '&#8216;',
2395          '&#146;' => '&#8217;',
2396          '&#147;' => '&#8220;',
2397          '&#148;' => '&#8221;',
2398          '&#149;' => '&#8226;',
2399          '&#150;' => '&#8211;',
2400          '&#151;' => '&#8212;',
2401          '&#152;' => '&#732;',
2402          '&#153;' => '&#8482;',
2403          '&#154;' => '&#353;',
2404          '&#155;' => '&#8250;',
2405          '&#156;' => '&#339;',
2406          '&#157;' => '',
2407          '&#158;' => '&#382;',
2408          '&#159;' => '&#376;',
2409      );
2410  
2411      if ( strpos( $content, '&#1' ) !== false ) {
2412          $content = strtr( $content, $wp_htmltranswinuni );
2413      }
2414  
2415      return $content;
2416  }
2417  
2418  /**
2419   * Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
2420   *
2421   * @since 0.71
2422   *
2423   * @param string $text  Text to be balanced
2424   * @param bool   $force If true, forces balancing, ignoring the value of the option. Default false.
2425   * @return string Balanced text
2426   */
2427  function balanceTags( $text, $force = false ) {
2428      if ( $force || get_option( 'use_balanceTags' ) == 1 ) {
2429          return force_balance_tags( $text );
2430      } else {
2431          return $text;
2432      }
2433  }
2434  
2435  /**
2436   * Balances tags of string using a modified stack.
2437   *
2438   * @since 2.0.4
2439   *
2440   * @author Leonard Lin <leonard@acm.org>
2441   * @license GPL
2442   * @copyright November 4, 2001
2443   * @version 1.1
2444   * @todo Make better - change loop condition to $text in 1.2
2445   * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
2446   *      1.1  Fixed handling of append/stack pop order of end text
2447   *           Added Cleaning Hooks
2448   *      1.0  First Version
2449   *
2450   * @param string $text Text to be balanced.
2451   * @return string Balanced text.
2452   */
2453  function force_balance_tags( $text ) {
2454      $tagstack  = array();
2455      $stacksize = 0;
2456      $tagqueue  = '';
2457      $newtext   = '';
2458      // Known single-entity/self-closing tags
2459      $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
2460      // Tags that can be immediately nested within themselves
2461      $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
2462  
2463      // WP bug fix for comments - in case you REALLY meant to type '< !--'
2464      $text = str_replace( '< !--', '<    !--', $text );
2465      // WP bug fix for LOVE <3 (and other situations with '<' before a number)
2466      $text = preg_replace( '#<([0-9]{1})#', '&lt;$1', $text );
2467  
2468      while ( preg_match( '/<(\/?[\w:]*)\s*([^>]*)>/', $text, $regex ) ) {
2469          $newtext .= $tagqueue;
2470  
2471          $i = strpos( $text, $regex[0] );
2472          $l = strlen( $regex[0] );
2473  
2474          // clear the shifter
2475          $tagqueue = '';
2476          // Pop or Push
2477          if ( isset( $regex[1][0] ) && '/' == $regex[1][0] ) { // End Tag
2478              $tag = strtolower( substr( $regex[1], 1 ) );
2479              // if too many closing tags
2480              if ( $stacksize <= 0 ) {
2481                  $tag = '';
2482                  // or close to be safe $tag = '/' . $tag;
2483  
2484                  // if stacktop value = tag close value then pop
2485              } elseif ( $tagstack[ $stacksize - 1 ] == $tag ) { // found closing tag
2486                  $tag = '</' . $tag . '>'; // Close Tag
2487                  // Pop
2488                  array_pop( $tagstack );
2489                  $stacksize--;
2490              } else { // closing tag not at top, search for it
2491                  for ( $j = $stacksize - 1; $j >= 0; $j-- ) {
2492                      if ( $tagstack[ $j ] == $tag ) {
2493                          // add tag to tagqueue
2494                          for ( $k = $stacksize - 1; $k >= $j; $k-- ) {
2495                              $tagqueue .= '</' . array_pop( $tagstack ) . '>';
2496                              $stacksize--;
2497                          }
2498                          break;
2499                      }
2500                  }
2501                  $tag = '';
2502              }
2503          } else { // Begin Tag
2504              $tag = strtolower( $regex[1] );
2505  
2506              // Tag Cleaning
2507  
2508              // If it's an empty tag "< >", do nothing
2509              if ( '' == $tag ) {
2510                  // do nothing
2511              } elseif ( substr( $regex[2], -1 ) == '/' ) { // ElseIf it presents itself as a self-closing tag...
2512                  // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
2513                  // immediately close it with a closing tag (the tag will encapsulate no text as a result)
2514                  if ( ! in_array( $tag, $single_tags ) ) {
2515                      $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
2516                  }
2517              } elseif ( in_array( $tag, $single_tags ) ) { // ElseIf it's a known single-entity tag but it doesn't close itself, do so
2518                  $regex[2] .= '/';
2519              } else { // Else it's not a single-entity tag
2520                  // If the top of the stack is the same as the tag we want to push, close previous tag
2521                  if ( $stacksize > 0 && ! in_array( $tag, $nestable_tags ) && $tagstack[ $stacksize - 1 ] == $tag ) {
2522                      $tagqueue = '</' . array_pop( $tagstack ) . '>';
2523                      $stacksize--;
2524                  }
2525                  $stacksize = array_push( $tagstack, $tag );
2526              }
2527  
2528              // Attributes
2529              $attributes = $regex[2];
2530              if ( ! empty( $attributes ) && $attributes[0] != '>' ) {
2531                  $attributes = ' ' . $attributes;
2532              }
2533  
2534              $tag = '<' . $tag . $attributes . '>';
2535              //If already queuing a close tag, then put this tag on, too
2536              if ( ! empty( $tagqueue ) ) {
2537                  $tagqueue .= $tag;
2538                  $tag       = '';
2539              }
2540          }
2541          $newtext .= substr( $text, 0, $i ) . $tag;
2542          $text     = substr( $text, $i + $l );
2543      }
2544  
2545      // Clear Tag Queue
2546      $newtext .= $tagqueue;
2547  
2548      // Add Remaining text
2549      $newtext .= $text;
2550  
2551      // Empty Stack
2552      while ( $x = array_pop( $tagstack ) ) {
2553          $newtext .= '</' . $x . '>'; // Add remaining tags to close
2554      }
2555  
2556      // WP fix for the bug with HTML comments
2557      $newtext = str_replace( '< !--', '<!--', $newtext );
2558      $newtext = str_replace( '<    !--', '< !--', $newtext );
2559  
2560      return $newtext;
2561  }
2562  
2563  /**
2564   * Acts on text which is about to be edited.
2565   *
2566   * The $content is run through esc_textarea(), which uses htmlspecialchars()
2567   * to convert special characters to HTML entities. If `$richedit` is set to true,
2568   * it is simply a holder for the {@see 'format_to_edit'} filter.
2569   *
2570   * @since 0.71
2571   * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
2572   *
2573   * @param string $content   The text about to be edited.
2574   * @param bool   $rich_text Optional. Whether `$content` should be considered rich text,
2575   *                          in which case it would not be passed through esc_textarea().
2576   *                          Default false.
2577   * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
2578   */
2579  function format_to_edit( $content, $rich_text = false ) {
2580      /**
2581       * Filters the text to be formatted for editing.
2582       *
2583       * @since 1.2.0
2584       *
2585       * @param string $content The text, prior to formatting for editing.
2586       */
2587      $content = apply_filters( 'format_to_edit', $content );
2588      if ( ! $rich_text ) {
2589          $content = esc_textarea( $content );
2590      }
2591      return $content;
2592  }
2593  
2594  /**
2595   * Add leading zeros when necessary.
2596   *
2597   * If you set the threshold to '4' and the number is '10', then you will get
2598   * back '0010'. If you set the threshold to '4' and the number is '5000', then you
2599   * will get back '5000'.
2600   *
2601   * Uses sprintf to append the amount of zeros based on the $threshold parameter
2602   * and the size of the number. If the number is large enough, then no zeros will
2603   * be appended.
2604   *
2605   * @since 0.71
2606   *
2607   * @param int $number     Number to append zeros to if not greater than threshold.
2608   * @param int $threshold  Digit places number needs to be to not have zeros added.
2609   * @return string Adds leading zeros to number if needed.
2610   */
2611  function zeroise( $number, $threshold ) {
2612      return sprintf( '%0' . $threshold . 's', $number );
2613  }
2614  
2615  /**
2616   * Adds backslashes before letters and before a number at the start of a string.
2617   *
2618   * @since 0.71
2619   *
2620   * @param string $string Value to which backslashes will be added.
2621   * @return string String with backslashes inserted.
2622   */
2623  function backslashit( $string ) {
2624      if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' ) {
2625          $string = '\\\\' . $string;
2626      }
2627      return addcslashes( $string, 'A..Za..z' );
2628  }
2629  
2630  /**
2631   * Appends a trailing slash.
2632   *
2633   * Will remove trailing forward and backslashes if it exists already before adding
2634   * a trailing forward slash. This prevents double slashing a string or path.
2635   *
2636   * The primary use of this is for paths and thus should be used for paths. It is
2637   * not restricted to paths and offers no specific path support.
2638   *
2639   * @since 1.2.0
2640   *
2641   * @param string $string What to add the trailing slash to.
2642   * @return string String with trailing slash added.
2643   */
2644  function trailingslashit( $string ) {
2645      return untrailingslashit( $string ) . '/';
2646  }
2647  
2648  /**
2649   * Removes trailing forward slashes and backslashes if they exist.
2650   *
2651   * The primary use of this is for paths and thus should be used for paths. It is
2652   * not restricted to paths and offers no specific path support.
2653   *
2654   * @since 2.2.0
2655   *
2656   * @param string $string What to remove the trailing slashes from.
2657   * @return string String without the trailing slashes.
2658   */
2659  function untrailingslashit( $string ) {
2660      return rtrim( $string, '/\\' );
2661  }
2662  
2663  /**
2664   * Adds slashes to escape strings.
2665   *
2666   * Slashes will first be removed if magic_quotes_gpc is set, see {@link
2667   * https://secure.php.net/magic_quotes} for more details.
2668   *
2669   * @since 0.71
2670   *
2671   * @param string $gpc The string returned from HTTP request data.
2672   * @return string Returns a string escaped with slashes.
2673   */
2674  function addslashes_gpc( $gpc ) {
2675      if ( get_magic_quotes_gpc() ) {
2676          $gpc = stripslashes( $gpc );
2677      }
2678  
2679      return wp_slash( $gpc );
2680  }
2681  
2682  /**
2683   * Navigates through an array, object, or scalar, and removes slashes from the values.
2684   *
2685   * @since 2.0.0
2686   *
2687   * @param mixed $value The value to be stripped.
2688   * @return mixed Stripped value.
2689   */
2690  function stripslashes_deep( $value ) {
2691      return map_deep( $value, 'stripslashes_from_strings_only' );
2692  }
2693  
2694  /**
2695   * Callback function for `stripslashes_deep()` which strips slashes from strings.
2696   *
2697   * @since 4.4.0
2698   *
2699   * @param mixed $value The array or string to be stripped.
2700   * @return mixed $value The stripped value.
2701   */
2702  function stripslashes_from_strings_only( $value ) {
2703      return is_string( $value ) ? stripslashes( $value ) : $value;
2704  }
2705  
2706  /**
2707   * Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
2708   *
2709   * @since 2.2.0
2710   *
2711   * @param mixed $value The array or string to be encoded.
2712   * @return mixed $value The encoded value.
2713   */
2714  function urlencode_deep( $value ) {
2715      return map_deep( $value, 'urlencode' );
2716  }
2717  
2718  /**
2719   * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
2720   *
2721   * @since 3.4.0
2722   *
2723   * @param mixed $value The array or string to be encoded.
2724   * @return mixed $value The encoded value.
2725   */
2726  function rawurlencode_deep( $value ) {
2727      return map_deep( $value, 'rawurlencode' );
2728  }
2729  
2730  /**
2731   * Navigates through an array, object, or scalar, and decodes URL-encoded values
2732   *
2733   * @since 4.4.0
2734   *
2735   * @param mixed $value The array or string to be decoded.
2736   * @return mixed $value The decoded value.
2737   */
2738  function urldecode_deep( $value ) {
2739      return map_deep( $value, 'urldecode' );
2740  }
2741  
2742  /**
2743   * Converts email addresses characters to HTML entities to block spam bots.
2744   *
2745   * @since 0.71
2746   *
2747   * @param string $email_address Email address.
2748   * @param int    $hex_encoding  Optional. Set to 1 to enable hex encoding.
2749   * @return string Converted email address.
2750   */
2751  function antispambot( $email_address, $hex_encoding = 0 ) {
2752      $email_no_spam_address = '';
2753      for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
2754          $j = rand( 0, 1 + $hex_encoding );
2755          if ( $j == 0 ) {
2756              $email_no_spam_address .= '&#' . ord( $email_address[ $i ] ) . ';';
2757          } elseif ( $j == 1 ) {
2758              $email_no_spam_address .= $email_address[ $i ];
2759          } elseif ( $j == 2 ) {
2760              $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[ $i ] ) ), 2 );
2761          }
2762      }
2763  
2764      return str_replace( '@', '&#64;', $email_no_spam_address );
2765  }
2766  
2767  /**
2768   * Callback to convert URI match to HTML A element.
2769   *
2770   * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2771   *
2772   * @since 2.3.2
2773   * @access private
2774   *
2775   * @param array $matches Single Regex Match.
2776   * @return string HTML A element with URI address.
2777   */
2778  function _make_url_clickable_cb( $matches ) {
2779      $url = $matches[2];
2780  
2781      if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
2782          // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
2783          // Then we can let the parenthesis balancer do its thing below.
2784          $url   .= $matches[3];
2785          $suffix = '';
2786      } else {
2787          $suffix = $matches[3];
2788      }
2789  
2790      // Include parentheses in the URL only if paired
2791      while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
2792          $suffix = strrchr( $url, ')' ) . $suffix;
2793          $url    = substr( $url, 0, strrpos( $url, ')' ) );
2794      }
2795  
2796      $url = esc_url( $url );
2797      if ( empty( $url ) ) {
2798          return $matches[0];
2799      }
2800  
2801      return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
2802  }
2803  
2804  /**
2805   * Callback to convert URL match to HTML A element.
2806   *
2807   * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2808   *
2809   * @since 2.3.2
2810   * @access private
2811   *
2812   * @param array $matches Single Regex Match.
2813   * @return string HTML A element with URL address.
2814   */
2815  function _make_web_ftp_clickable_cb( $matches ) {
2816      $ret  = '';
2817      $dest = $matches[2];
2818      $dest = 'http://' . $dest;
2819  
2820      // removed trailing [.,;:)] from URL
2821      if ( in_array( substr( $dest, -1 ), array( '.', ',', ';', ':', ')' ) ) === true ) {
2822          $ret  = substr( $dest, -1 );
2823          $dest = substr( $dest, 0, strlen( $dest ) - 1 );
2824      }
2825  
2826      $dest = esc_url( $dest );
2827      if ( empty( $dest ) ) {
2828          return $matches[0];
2829      }
2830  
2831      return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
2832  }
2833  
2834  /**
2835   * Callback to convert email address match to HTML A element.
2836   *
2837   * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2838   *
2839   * @since 2.3.2
2840   * @access private
2841   *
2842   * @param array $matches Single Regex Match.
2843   * @return string HTML A element with email address.
2844   */
2845  function _make_email_clickable_cb( $matches ) {
2846      $email = $matches[2] . '@' . $matches[3];
2847      return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
2848  }
2849  
2850  /**
2851   * Convert plaintext URI to HTML links.
2852   *
2853   * Converts URI, www and ftp, and email addresses. Finishes by fixing links
2854   * within links.
2855   *
2856   * @since 0.71
2857   *
2858   * @param string $text Content to convert URIs.
2859   * @return string Content with converted URIs.
2860   */
2861  function make_clickable( $text ) {
2862      $r               = '';
2863      $textarr         = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
2864      $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
2865      foreach ( $textarr as $piece ) {
2866  
2867          if ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) || preg_match( '|^<script[\s>]|i', $piece ) || preg_match( '|^<style[\s>]|i', $piece ) ) {
2868              $nested_code_pre++;
2869          } elseif ( $nested_code_pre && ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) || '</script>' === strtolower( $piece ) || '</style>' === strtolower( $piece ) ) ) {
2870              $nested_code_pre--;
2871          }
2872  
2873          if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
2874              $r .= $piece;
2875              continue;
2876          }
2877  
2878          // Long strings might contain expensive edge cases ...
2879          if ( 10000 < strlen( $piece ) ) {
2880              // ... break it up
2881              foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
2882                  if ( 2101 < strlen( $chunk ) ) {
2883                      $r .= $chunk; // Too big, no whitespace: bail.
2884                  } else {
2885                      $r .= make_clickable( $chunk );
2886                  }
2887              }
2888          } else {
2889              $ret = " $piece "; // Pad with whitespace to simplify the regexes
2890  
2891              $url_clickable = '~
2892                  ([\\s(<.,;:!?])                                        # 1: Leading whitespace, or punctuation
2893                  (                                                      # 2: URL
2894                      [\\w]{1,20}+://                                # Scheme and hier-part prefix
2895                      (?=\S{1,2000}\s)                               # Limit to URLs less than about 2000 characters long
2896                      [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+         # Non-punctuation URL character
2897                      (?:                                            # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
2898                          [\'.,;:!?)]                            # Punctuation URL character
2899                          [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
2900                      )*
2901                  )
2902                  (\)?)                                                  # 3: Trailing closing parenthesis (for parethesis balancing post processing)
2903              ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
2904                    // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
2905  
2906              $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
2907  
2908              $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
2909              $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
2910  
2911              $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
2912              $r  .= $ret;
2913          }
2914      }
2915  
2916      // Cleanup of accidental links within links
2917      return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', '$1$3</a>', $r );
2918  }
2919  
2920  /**
2921   * Breaks a string into chunks by splitting at whitespace characters.
2922   * The length of each returned chunk is as close to the specified length goal as possible,
2923   * with the caveat that each chunk includes its trailing delimiter.
2924   * Chunks longer than the goal are guaranteed to not have any inner whitespace.
2925   *
2926   * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
2927   *
2928   * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
2929   *
2930   *     _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234   890 123456789 1234567890a    45678   1 3 5 7 90 ", 10 ) ==
2931   *     array (
2932   *         0 => '1234 67890 ',  // 11 characters: Perfect split
2933   *         1 => '1234 ',        //  5 characters: '1234 67890a' was too long
2934   *         2 => '67890a cd ',   // 10 characters: '67890a cd 1234' was too long
2935   *         3 => '1234   890 ',  // 11 characters: Perfect split
2936   *         4 => '123456789 ',   // 10 characters: '123456789 1234567890a' was too long
2937   *         5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
2938   *         6 => '   45678   ',  // 11 characters: Perfect split
2939   *         7 => '1 3 5 7 90 ',  // 11 characters: End of $string
2940   *     );
2941   *
2942   * @since 3.4.0
2943   * @access private
2944   *
2945   * @param string $string The string to split.
2946   * @param int    $goal   The desired chunk length.
2947   * @return array Numeric array of chunks.
2948   */
2949  function _split_str_by_whitespace( $string, $goal ) {
2950      $chunks = array();
2951  
2952      $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
2953  
2954      while ( $goal < strlen( $string_nullspace ) ) {
2955          $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
2956  
2957          if ( false === $pos ) {
2958              $pos = strpos( $string_nullspace, "\000", $goal + 1 );
2959              if ( false === $pos ) {
2960                  break;
2961              }
2962          }
2963  
2964          $chunks[]         = substr( $string, 0, $pos + 1 );
2965          $string           = substr( $string, $pos + 1 );
2966          $string_nullspace = substr( $string_nullspace, $pos + 1 );
2967      }
2968  
2969      if ( $string ) {
2970          $chunks[] = $string;
2971      }
2972  
2973      return $chunks;
2974  }
2975  
2976  /**
2977   * Adds rel nofollow string to all HTML A elements in content.
2978   *
2979   * @since 1.5.0
2980   *
2981   * @param string $text Content that may contain HTML A elements.
2982   * @return string Converted content.
2983   */
2984  function wp_rel_nofollow( $text ) {
2985      // This is a pre save filter, so text is already escaped.
2986      $text = stripslashes( $text );
2987      $text = preg_replace_callback( '|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text );
2988      return wp_slash( $text );
2989  }
2990  
2991  /**
2992   * Callback to add rel=nofollow string to HTML A element.
2993   *
2994   * Will remove already existing rel="nofollow" and rel='nofollow' from the
2995   * string to prevent from invalidating (X)HTML.
2996   *
2997   * @since 2.3.0
2998   *
2999   * @param array $matches Single Match
3000   * @return string HTML A Element with rel nofollow.
3001   */
3002  function wp_rel_nofollow_callback( $matches ) {
3003      $text = $matches[1];
3004      $atts = shortcode_parse_atts( $matches[1] );
3005      $rel  = 'nofollow';
3006  
3007      if ( preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'http' ) ) . ')%i', $text ) ||
3008          preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'https' ) ) . ')%i', $text ) ) {
3009  
3010          return "<a $text>";
3011      }
3012  
3013      if ( ! empty( $atts['rel'] ) ) {
3014          $parts = array_map( 'trim', explode( ' ', $atts['rel'] ) );
3015          if ( false === array_search( 'nofollow', $parts ) ) {
3016              $parts[] = 'nofollow';
3017          }
3018          $rel = implode( ' ', $parts );
3019          unset( $atts['rel'] );
3020  
3021          $html = '';
3022          foreach ( $atts as $name => $value ) {
3023              $html .= "{$name}=\"$value\" ";
3024          }
3025          $text = trim( $html );
3026      }
3027      return "<a $text rel=\"$rel\">";
3028  }
3029  
3030  /**
3031   * Adds rel noreferrer and noopener to all HTML A elements that have a target.
3032   *
3033   * @param string $text Content that may contain HTML A elements.
3034   * @return string Converted content.
3035   */
3036  function wp_targeted_link_rel( $text ) {
3037      // Don't run (more expensive) regex if no links with targets.
3038      if ( stripos( $text, 'target' ) !== false && stripos( $text, '<a ' ) !== false ) {
3039          $text = preg_replace_callback( '|<a\s([^>]*target\s*=[^>]*)>|i', 'wp_targeted_link_rel_callback', $text );
3040      }
3041  
3042      return $text;
3043  }
3044  
3045  /**
3046   * Callback to add rel="noreferrer noopener" string to HTML A element.
3047   *
3048   * Will not duplicate existing noreferrer and noopener values
3049   * to prevent from invalidating the HTML.
3050   *
3051   * @param array $matches Single Match
3052   * @return string HTML A Element with rel noreferrer noopener in addition to any existing values
3053   */
3054  function wp_targeted_link_rel_callback( $matches ) {
3055      $link_html = $matches[1];
3056      $rel_match = array();
3057  
3058      /**
3059       * Filters the rel values that are added to links with `target` attribute.
3060       *
3061       * @since 5.1.0
3062       *
3063       * @param string The rel values.
3064       * @param string $link_html The matched content of the link tag including all HTML attributes.
3065       */
3066      $rel = apply_filters( 'wp_targeted_link_rel', 'noopener noreferrer', $link_html );
3067  
3068      // Avoid additional regex if the filter removes rel values.
3069      if ( ! $rel ) {
3070          return "<a $link_html>";
3071      }
3072  
3073      // Value with delimiters, spaces around are optional.
3074      $attr_regex = '|rel\s*=\s*?(\\\\{0,1}["\'])(.*?)\\1|i';
3075      preg_match( $attr_regex, $link_html, $rel_match );
3076  
3077      if ( empty( $rel_match[0] ) ) {
3078          // No delimiters, try with a single value and spaces, because `rel =  va"lue` is totally fine...
3079          $attr_regex = '|rel\s*=(\s*)([^\s]*)|i';
3080          preg_match( $attr_regex, $link_html, $rel_match );
3081      }
3082  
3083      if ( ! empty( $rel_match[0] ) ) {
3084          $parts     = preg_split( '|\s+|', strtolower( $rel_match[2] ) );
3085          $parts     = array_map( 'esc_attr', $parts );
3086          $needed    = explode( ' ', $rel );
3087          $parts     = array_unique( array_merge( $parts, $needed ) );
3088          $delimiter = trim( $rel_match[1] ) ? $rel_match[1] : '"';
3089          $rel       = 'rel=' . $delimiter . trim( implode( ' ', $parts ) ) . $delimiter;
3090          $link_html = str_replace( $rel_match[0], $rel, $link_html );
3091      } else {
3092          $link_html .= " rel=\"$rel\"";
3093      }
3094  
3095      return "<a $link_html>";
3096  }
3097  
3098  /**
3099   * Adds all filters modifying the rel attribute of targeted links.
3100   *
3101   * @since 5.1.0
3102   */
3103  function wp_init_targeted_link_rel_filters() {
3104      $filters = array(
3105          'title_save_pre',
3106          'content_save_pre',
3107          'excerpt_save_pre',
3108          'content_filtered_save_pre',
3109          'pre_comment_content',
3110          'pre_term_description',
3111          'pre_link_description',
3112          'pre_link_notes',
3113          'pre_user_description',
3114      );
3115  
3116      foreach ( $filters as $filter ) {
3117          add_filter( $filter, 'wp_targeted_link_rel' );
3118      };
3119  }
3120  
3121  /**
3122   * Removes all filters modifying the rel attribute of targeted links.
3123   *
3124   * @since 5.1.0
3125   */
3126  function wp_remove_targeted_link_rel_filters() {
3127      $filters = array(
3128          'title_save_pre',
3129          'content_save_pre',
3130          'excerpt_save_pre',
3131          'content_filtered_save_pre',
3132          'pre_comment_content',
3133          'pre_term_description',
3134          'pre_link_description',
3135          'pre_link_notes',
3136          'pre_user_description',
3137      );
3138  
3139      foreach ( $filters as $filter ) {
3140          remove_filter( $filter, 'wp_targeted_link_rel' );
3141      };
3142  }
3143  
3144  /**
3145   * Convert one smiley code to the icon graphic file equivalent.
3146   *
3147   * Callback handler for convert_smilies().
3148   *
3149   * Looks up one smiley code in the $wpsmiliestrans global array and returns an
3150   * `<img>` string for that smiley.
3151   *
3152   * @since 2.8.0
3153   *
3154   * @global array $wpsmiliestrans
3155   *
3156   * @param array $matches Single match. Smiley code to convert to image.
3157   * @return string Image string for smiley.
3158   */
3159  function translate_smiley( $matches ) {
3160      global $wpsmiliestrans;
3161  
3162      if ( count( $matches ) == 0 ) {
3163          return '';
3164      }
3165  
3166      $smiley = trim( reset( $matches ) );
3167      $img    = $wpsmiliestrans[ $smiley ];
3168  
3169      $matches    = array();
3170      $ext        = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
3171      $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
3172  
3173      // Don't convert smilies that aren't images - they're probably emoji.
3174      if ( ! in_array( $ext, $image_exts ) ) {
3175          return $img;
3176      }
3177  
3178      /**
3179       * Filters the Smiley image URL before it's used in the image element.
3180       *
3181       * @since 2.9.0
3182       *
3183       * @param string $smiley_url URL for the smiley image.
3184       * @param string $img        Filename for the smiley image.
3185       * @param string $site_url   Site URL, as returned by site_url().
3186       */
3187      $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
3188  
3189      return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
3190  }
3191  
3192  /**
3193   * Convert text equivalent of smilies to images.
3194   *
3195   * Will only convert smilies if the option 'use_smilies' is true and the global
3196   * used in the function isn't empty.
3197   *
3198   * @since 0.71
3199   *
3200   * @global string|array $wp_smiliessearch
3201   *
3202   * @param string $text Content to convert smilies from text.
3203   * @return string Converted content with text smilies replaced with images.
3204   */
3205  function convert_smilies( $text ) {
3206      global $wp_smiliessearch;
3207      $output = '';
3208      if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
3209          // HTML loop taken from texturize function, could possible be consolidated
3210          $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
3211          $stop    = count( $textarr );// loop stuff
3212  
3213          // Ignore proessing of specific tags
3214          $tags_to_ignore       = 'code|pre|style|script|textarea';
3215          $ignore_block_element = '';
3216  
3217          for ( $i = 0; $i < $stop; $i++ ) {
3218              $content = $textarr[ $i ];
3219  
3220              // If we're in an ignore block, wait until we find its closing tag
3221              if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
3222                  $ignore_block_element = $matches[1];
3223              }
3224  
3225              // If it's not a tag and not in ignore block
3226              if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
3227                  $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
3228              }
3229  
3230              // did we exit ignore block
3231              if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
3232                  $ignore_block_element = '';
3233              }
3234  
3235              $output .= $content;
3236          }
3237      } else {
3238          // return default text.
3239          $output = $text;
3240      }
3241      return $output;
3242  }
3243  
3244  /**
3245   * Verifies that an email is valid.
3246   *
3247   * Does not grok i18n domains. Not RFC compliant.
3248   *
3249   * @since 0.71
3250   *
3251   * @param string $email      Email address to verify.
3252   * @param bool   $deprecated Deprecated.
3253   * @return string|bool Either false or the valid email address.
3254   */
3255  function is_email( $email, $deprecated = false ) {
3256      if ( ! empty( $deprecated ) ) {
3257          _deprecated_argument( __FUNCTION__, '3.0.0' );
3258      }
3259  
3260      // Test for the minimum length the email can be
3261      if ( strlen( $email ) < 6 ) {
3262          /**
3263           * Filters whether an email address is valid.
3264           *
3265           * This filter is evaluated under several different contexts, such as 'email_too_short',
3266           * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3267           * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
3268           *
3269           * @since 2.8.0
3270           *
3271           * @param bool   $is_email Whether the email address has passed the is_email() checks. Default false.
3272           * @param string $email    The email address being checked.
3273           * @param string $context  Context under which the email was tested.
3274           */
3275          return apply_filters( 'is_email', false, $email, 'email_too_short' );
3276      }
3277  
3278      // Test for an @ character after the first position
3279      if ( strpos( $email, '@', 1 ) === false ) {
3280          /** This filter is documented in wp-includes/formatting.php */
3281          return apply_filters( 'is_email', false, $email, 'email_no_at' );
3282      }
3283  
3284      // Split out the local and domain parts
3285      list( $local, $domain ) = explode( '@', $email, 2 );
3286  
3287      // LOCAL PART
3288      // Test for invalid characters
3289      if ( ! preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
3290          /** This filter is documented in wp-includes/formatting.php */
3291          return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
3292      }
3293  
3294      // DOMAIN PART
3295      // Test for sequences of periods
3296      if ( preg_match( '/\.{2,}/', $domain ) ) {
3297          /** This filter is documented in wp-includes/formatting.php */
3298          return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
3299      }
3300  
3301      // Test for leading and trailing periods and whitespace
3302      if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
3303          /** This filter is documented in wp-includes/formatting.php */
3304          return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
3305      }
3306  
3307      // Split the domain into subs
3308      $subs = explode( '.', $domain );
3309  
3310      // Assume the domain will have at least two subs
3311      if ( 2 > count( $subs ) ) {
3312          /** This filter is documented in wp-includes/formatting.php */
3313          return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
3314      }
3315  
3316      // Loop through each sub
3317      foreach ( $subs as $sub ) {
3318          // Test for leading and trailing hyphens and whitespace
3319          if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
3320              /** This filter is documented in wp-includes/formatting.php */
3321              return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
3322          }
3323  
3324          // Test for invalid characters
3325          if ( ! preg_match( '/^[a-z0-9-]+$/i', $sub ) ) {
3326              /** This filter is documented in wp-includes/formatting.php */
3327              return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
3328          }
3329      }
3330  
3331      // Congratulations your email made it!
3332      /** This filter is documented in wp-includes/formatting.php */
3333      return apply_filters( 'is_email', $email, $email, null );
3334  }
3335  
3336  /**
3337   * Convert to ASCII from email subjects.
3338   *
3339   * @since 1.2.0
3340   *
3341   * @param string $string Subject line
3342   * @return string Converted string to ASCII
3343   */
3344  function wp_iso_descrambler( $string ) {
3345      /* this may only work with iso-8859-1, I'm afraid */
3346      if ( ! preg_match( '#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches ) ) {
3347          return $string;
3348      } else {
3349          $subject = str_replace( '_', ' ', $matches[2] );
3350          return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
3351      }
3352  }
3353  
3354  /**
3355   * Helper function to convert hex encoded chars to ASCII
3356   *
3357   * @since 3.1.0
3358   * @access private
3359   *
3360   * @param array $match The preg_replace_callback matches array
3361   * @return string Converted chars
3362   */
3363  function _wp_iso_convert( $match ) {
3364      return chr( hexdec( strtolower( $match[1] ) ) );
3365  }
3366  
3367  /**
3368   * Returns a date in the GMT equivalent.
3369   *
3370   * Requires and returns a date in the Y-m-d H:i:s format. If there is a
3371   * timezone_string available, the date is assumed to be in that timezone,
3372   * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
3373   * format can be overridden using the $format parameter.
3374   *
3375   * @since 1.2.0
3376   *
3377   * @param string $string The date to be converted.
3378   * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
3379   * @return string GMT version of the date provided.
3380   */
3381  function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
3382      $tz = get_option( 'timezone_string' );
3383      if ( $tz ) {
3384          $datetime = date_create( $string, new DateTimeZone( $tz ) );
3385          if ( ! $datetime ) {
3386              return gmdate( $format, 0 );
3387          }
3388          $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
3389          $string_gmt = $datetime->format( $format );
3390      } else {
3391          if ( ! preg_match( '#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches ) ) {
3392              $datetime = strtotime( $string );
3393              if ( false === $datetime ) {
3394                  return gmdate( $format, 0 );
3395              }
3396              return gmdate( $format, $datetime );
3397          }
3398          $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
3399          $string_gmt  = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
3400      }
3401      return $string_gmt;
3402  }
3403  
3404  /**
3405   * Converts a GMT date into the correct format for the blog.
3406   *
3407   * Requires and returns a date in the Y-m-d H:i:s format. If there is a
3408   * timezone_string available, the returned date is in that timezone, otherwise
3409   * it simply adds the value of gmt_offset. Return format can be overridden
3410   * using the $format parameter
3411   *
3412   * @since 1.2.0
3413   *
3414   * @param string $string The date to be converted.
3415   * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
3416   * @return string Formatted date relative to the timezone / GMT offset.
3417   */
3418  function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
3419      $tz = get_option( 'timezone_string' );
3420      if ( $tz ) {
3421          $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
3422          if ( ! $datetime ) {
3423              return date( $format, 0 );
3424          }
3425          $datetime->setTimezone( new DateTimeZone( $tz ) );
3426          $string_localtime = $datetime->format( $format );
3427      } else {
3428          if ( ! preg_match( '#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches ) ) {
3429              return date( $format, 0 );
3430          }
3431          $string_time      = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
3432          $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
3433      }
3434      return $string_localtime;
3435  }
3436  
3437  /**
3438   * Computes an offset in seconds from an iso8601 timezone.
3439   *
3440   * @since 1.5.0
3441   *
3442   * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
3443   * @return int|float The offset in seconds.
3444   */
3445  function iso8601_timezone_to_offset( $timezone ) {
3446      // $timezone is either 'Z' or '[+|-]hhmm'
3447      if ( $timezone == 'Z' ) {
3448          $offset = 0;
3449      } else {
3450          $sign    = ( substr( $timezone, 0, 1 ) == '+' ) ? 1 : -1;
3451          $hours   = intval( substr( $timezone, 1, 2 ) );
3452          $minutes = intval( substr( $timezone, 3, 4 ) ) / 60;
3453          $offset  = $sign * HOUR_IN_SECONDS * ( $hours + $minutes );
3454      }
3455      return $offset;
3456  }
3457  
3458  /**
3459   * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
3460   *
3461   * @since 1.5.0
3462   *
3463   * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}.
3464   * @param string $timezone    Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
3465   * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
3466   */
3467  function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
3468      $timezone = strtolower( $timezone );
3469  
3470      if ( $timezone == 'gmt' ) {
3471  
3472          preg_match( '#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', $date_string, $date_bits );
3473  
3474          if ( ! empty( $date_bits[7] ) ) { // we have a timezone, so let's compute an offset
3475              $offset = iso8601_timezone_to_offset( $date_bits[7] );
3476          } else { // we don't have a timezone, so we assume user local timezone (not server's!)
3477              $offset = HOUR_IN_SECONDS * get_option( 'gmt_offset' );
3478          }
3479  
3480          $timestamp  = gmmktime( $date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1] );
3481          $timestamp -= $offset;
3482  
3483          return gmdate( 'Y-m-d H:i:s', $timestamp );
3484  
3485      } elseif ( $timezone == 'user' ) {
3486          return preg_replace( '#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', '$1-$2-$3 $4:$5:$6', $date_string );
3487      }
3488  }
3489  
3490  /**
3491   * Strips out all characters that are not allowable in an email.
3492   *
3493   * @since 1.5.0
3494   *
3495   * @param string $email Email address to filter.
3496   * @return string Filtered email address.
3497   */
3498  function sanitize_email( $email ) {
3499      // Test for the minimum length the email can be
3500      if ( strlen( $email ) < 6 ) {
3501          /**
3502           * Filters a sanitized email address.
3503           *
3504           * This filter is evaluated under several contexts, including 'email_too_short',
3505           * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3506           * 'domain_no_periods', 'domain_no_valid_subs', or no context.
3507           *
3508           * @since 2.8.0
3509           *
3510           * @param string $sanitized_email The sanitized email address.
3511           * @param string $email           The email address, as provided to sanitize_email().
3512           * @param string|null $message    A message to pass to the user. null if email is sanitized.
3513           */
3514          return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
3515      }
3516  
3517      // Test for an @ character after the first position
3518      if ( strpos( $email, '@', 1 ) === false ) {
3519          /** This filter is documented in wp-includes/formatting.php */
3520          return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
3521      }
3522  
3523      // Split out the local and domain parts
3524      list( $local, $domain ) = explode( '@', $email, 2 );
3525  
3526      // LOCAL PART
3527      // Test for invalid characters
3528      $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
3529      if ( '' === $local ) {
3530          /** This filter is documented in wp-includes/formatting.php */
3531          return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
3532      }
3533  
3534      // DOMAIN PART
3535      // Test for sequences of periods
3536      $domain = preg_replace( '/\.{2,}/', '', $domain );
3537      if ( '' === $domain ) {
3538          /** This filter is documented in wp-includes/formatting.php */
3539          return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
3540      }
3541  
3542      // Test for leading and trailing periods and whitespace
3543      $domain = trim( $domain, " \t\n\r\0\x0B." );
3544      if ( '' === $domain ) {
3545          /** This filter is documented in wp-includes/formatting.php */
3546          return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
3547      }
3548  
3549      // Split the domain into subs
3550      $subs = explode( '.', $domain );
3551  
3552      // Assume the domain will have at least two subs
3553      if ( 2 > count( $subs ) ) {
3554          /** This filter is documented in wp-includes/formatting.php */
3555          return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
3556      }
3557  
3558      // Create an array that will contain valid subs
3559      $new_subs = array();
3560  
3561      // Loop through each sub
3562      foreach ( $subs as $sub ) {
3563          // Test for leading and trailing hyphens
3564          $sub = trim( $sub, " \t\n\r\0\x0B-" );
3565  
3566          // Test for invalid characters
3567          $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
3568  
3569          // If there's anything left, add it to the valid subs
3570          if ( '' !== $sub ) {
3571              $new_subs[] = $sub;
3572          }
3573      }
3574  
3575      // If there aren't 2 or more valid subs
3576      if ( 2 > count( $new_subs ) ) {
3577          /** This filter is documented in wp-includes/formatting.php */
3578          return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
3579      }
3580  
3581      // Join valid subs into the new domain
3582      $domain = join( '.', $new_subs );
3583  
3584      // Put the email back together
3585      $sanitized_email = $local . '@' . $domain;
3586  
3587      // Congratulations your email made it!
3588      /** This filter is documented in wp-includes/formatting.php */
3589      return apply_filters( 'sanitize_email', $sanitized_email, $email, null );
3590  }
3591  
3592  /**
3593   * Determines the difference between two timestamps.
3594   *
3595   * The difference is returned in a human readable format such as "1 hour",
3596   * "5 mins", "2 days".
3597   *
3598   * @since 1.5.0
3599   *
3600   * @param int $from Unix timestamp from which the difference begins.
3601   * @param int $to   Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
3602   * @return string Human readable time difference.
3603   */
3604  function human_time_diff( $from, $to = '' ) {
3605      if ( empty( $to ) ) {
3606          $to = time();
3607      }
3608  
3609      $diff = (int) abs( $to - $from );
3610  
3611      if ( $diff < HOUR_IN_SECONDS ) {
3612          $mins = round( $diff / MINUTE_IN_SECONDS );
3613          if ( $mins <= 1 ) {
3614              $mins = 1;
3615          }
3616          /* translators: Time difference between two dates, in minutes (min=minute). %s: Number of minutes */
3617          $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
3618      } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
3619          $hours = round( $diff / HOUR_IN_SECONDS );
3620          if ( $hours <= 1 ) {
3621              $hours = 1;
3622          }
3623          /* translators: Time difference between two dates, in hours. %s: Number of hours */
3624          $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
3625      } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
3626          $days = round( $diff / DAY_IN_SECONDS );
3627          if ( $days <= 1 ) {
3628              $days = 1;
3629          }
3630          /* translators: Time difference between two dates, in days. %s: Number of days */
3631          $since = sprintf( _n( '%s day', '%s days', $days ), $days );
3632      } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
3633          $weeks = round( $diff / WEEK_IN_SECONDS );
3634          if ( $weeks <= 1 ) {
3635              $weeks = 1;
3636          }
3637          /* translators: Time difference between two dates, in weeks. %s: Number of weeks */
3638          $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
3639      } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
3640          $months = round( $diff / MONTH_IN_SECONDS );
3641          if ( $months <= 1 ) {
3642              $months = 1;
3643          }
3644          /* translators: Time difference between two dates, in months. %s: Number of months */
3645          $since = sprintf( _n( '%s month', '%s months', $months ), $months );
3646      } elseif ( $diff >= YEAR_IN_SECONDS ) {
3647          $years = round( $diff / YEAR_IN_SECONDS );
3648          if ( $years <= 1 ) {
3649              $years = 1;
3650          }
3651          /* translators: Time difference between two dates, in years. %s: Number of years */
3652          $since = sprintf( _n( '%s year', '%s years', $years ), $years );
3653      }
3654  
3655      /**
3656       * Filters the human readable difference between two timestamps.
3657       *
3658       * @since 4.0.0
3659       *
3660       * @param string $since The difference in human readable text.
3661       * @param int    $diff  The difference in seconds.
3662       * @param int    $from  Unix timestamp from which the difference begins.
3663       * @param int    $to    Unix timestamp to end the time difference.
3664       */
3665      return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
3666  }
3667  
3668  /**
3669   * Generates an excerpt from the content, if needed.
3670   *
3671   * The excerpt word amount will be 55 words and if the amount is greater than
3672   * that, then the string ' [&hellip;]' will be appended to the excerpt. If the string
3673   * is less than 55 words, then the content will be returned as is.
3674   *
3675   * The 55 word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter
3676   * The ' [&hellip;]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter
3677   *
3678   * @since 1.5.0
3679   *
3680   * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
3681   * @return string The excerpt.
3682   */
3683  function wp_trim_excerpt( $text = '' ) {
3684      $raw_excerpt = $text;
3685      if ( '' == $text ) {
3686          $text = get_the_content( '' );
3687  
3688          $text = strip_shortcodes( $text );
3689          $text = excerpt_remove_blocks( $text );
3690  
3691          /** This filter is documented in wp-includes/post-template.php */
3692          $text = apply_filters( 'the_content', $text );
3693          $text = str_replace( ']]>', ']]&gt;', $text );
3694  
3695          /**
3696           * Filters the number of words in an excerpt.
3697           *
3698           * @since 2.7.0
3699           *
3700           * @param int $number The number of words. Default 55.
3701           */
3702          $excerpt_length = apply_filters( 'excerpt_length', 55 );
3703          /**
3704           * Filters the string in the "more" link displayed after a trimmed excerpt.
3705           *
3706           * @since 2.9.0
3707           *
3708           * @param string $more_string The string shown within the more link.
3709           */
3710          $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[&hellip;]' );
3711          $text         = wp_trim_words( $text, $excerpt_length, $excerpt_more );
3712      }
3713      /**
3714       * Filters the trimmed excerpt string.
3715       *
3716       * @since 2.8.0
3717       *
3718       * @param string $text        The trimmed text.
3719       * @param string $raw_excerpt The text prior to trimming.
3720       */
3721      return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
3722  }
3723  
3724  /**
3725   * Trims text to a certain number of words.
3726   *
3727   * This function is localized. For languages that count 'words' by the individual
3728   * character (such as East Asian languages), the $num_words argument will apply
3729   * to the number of individual characters.
3730   *
3731   * @since 3.3.0
3732   *
3733   * @param string $text      Text to trim.
3734   * @param int    $num_words Number of words. Default 55.
3735   * @param string $more      Optional. What to append if $text needs to be trimmed. Default '&hellip;'.
3736   * @return string Trimmed text.
3737   */
3738  function wp_trim_words( $text, $num_words = 55, $more = null ) {
3739      if ( null === $more ) {
3740          $more = __( '&hellip;' );
3741      }
3742  
3743      $original_text = $text;
3744      $text          = wp_strip_all_tags( $text );
3745  
3746      /*
3747       * translators: If your word count is based on single characters (e.g. East Asian characters),
3748       * enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
3749       * Do not translate into your own language.
3750       */
3751      if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
3752          $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
3753          preg_match_all( '/./u', $text, $words_array );
3754          $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
3755          $sep         = '';
3756      } else {
3757          $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
3758          $sep         = ' ';
3759      }
3760  
3761      if ( count( $words_array ) > $num_words ) {
3762          array_pop( $words_array );
3763          $text = implode( $sep, $words_array );
3764          $text = $text . $more;
3765      } else {
3766          $text = implode( $sep, $words_array );
3767      }
3768  
3769      /**
3770       * Filters the text content after words have been trimmed.
3771       *
3772       * @since 3.3.0
3773       *
3774       * @param string $text          The trimmed text.
3775       * @param int    $num_words     The number of words to trim the text to. Default 55.
3776       * @param string $more          An optional string to append to the end of the trimmed text, e.g. &hellip;.
3777       * @param string $original_text The text before it was trimmed.
3778       */
3779      return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
3780  }
3781  
3782  /**
3783   * Converts named entities into numbered entities.
3784   *
3785   * @since 1.5.1
3786   *
3787   * @param string $text The text within which entities will be converted.
3788   * @return string Text with converted entities.
3789   */
3790  function ent2ncr( $text ) {
3791  
3792      /**
3793       * Filters text before named entities are converted into numbered entities.
3794       *
3795       * A non-null string must be returned for the filter to be evaluated.
3796       *
3797       * @since 3.3.0
3798       *
3799       * @param null   $converted_text The text to be converted. Default null.
3800       * @param string $text           The text prior to entity conversion.
3801       */
3802      $filtered = apply_filters( 'pre_ent2ncr', null, $text );
3803      if ( null !== $filtered ) {
3804          return $filtered;
3805      }
3806  
3807      $to_ncr = array(
3808          '&quot;'     => '&#34;',
3809          '&amp;'      => '&#38;',
3810          '&lt;'       => '&#60;',
3811          '&gt;'       => '&#62;',
3812          '|'          => '&#124;',
3813          '&nbsp;'     => '&#160;',
3814          '&iexcl;'    => '&#161;',
3815          '&cent;'     => '&#162;',
3816          '&pound;'    => '&#163;',
3817          '&curren;'   => '&#164;',
3818          '&yen;'      => '&#165;',
3819          '&brvbar;'   => '&#166;',
3820          '&brkbar;'   => '&#166;',
3821          '&sect;'     => '&#167;',
3822          '&uml;'      => '&#168;',
3823          '&die;'      => '&#168;',
3824          '&copy;'     => '&#169;',
3825          '&ordf;'     => '&#170;',
3826          '&laquo;'    => '&#171;',
3827          '&not;'      => '&#172;',
3828          '&shy;'      => '&#173;',
3829          '&reg;'      => '&#174;',
3830          '&macr;'     => '&#175;',
3831          '&hibar;'    => '&#175;',
3832          '&deg;'      => '&#176;',
3833          '&plusmn;'   => '&#177;',
3834          '&sup2;'     => '&#178;',
3835          '&sup3;'     => '&#179;',
3836          '&acute;'    => '&#180;',
3837          '&micro;'    => '&#181;',
3838          '&para;'     => '&#182;',
3839          '&middot;'   => '&#183;',
3840          '&cedil;'    => '&#184;',
3841          '&sup1;'     => '&#185;',
3842          '&ordm;'     => '&#186;',
3843          '&raquo;'    => '&#187;',
3844          '&frac14;'   => '&#188;',
3845          '&frac12;'   => '&#189;',
3846          '&frac34;'   => '&#190;',
3847          '&iquest;'   => '&#191;',
3848          '&Agrave;'   => '&#192;',
3849          '&Aacute;'   => '&#193;',
3850          '&Acirc;'    => '&#194;',
3851          '&Atilde;'   => '&#195;',
3852          '&Auml;'     => '&#196;',
3853          '&Aring;'    => '&#197;',
3854          '&AElig;'    => '&#198;',
3855          '&Ccedil;'   => '&#199;',
3856          '&Egrave;'   => '&#200;',
3857          '&Eacute;'   => '&#201;',
3858          '&Ecirc;'    => '&#202;',
3859          '&Euml;'     => '&#203;',
3860          '&Igrave;'   => '&#204;',
3861          '&Iacute;'   => '&#205;',
3862          '&Icirc;'    => '&#206;',
3863          '&Iuml;'     => '&#207;',
3864          '&ETH;'      => '&#208;',
3865          '&Ntilde;'   => '&#209;',
3866          '&Ograve;'   => '&#210;',
3867          '&Oacute;'   => '&#211;',
3868          '&Ocirc;'    => '&#212;',
3869          '&Otilde;'   => '&#213;',
3870          '&Ouml;'     => '&#214;',
3871          '&times;'    => '&#215;',
3872          '&Oslash;'   => '&#216;',
3873          '&Ugrave;'   => '&#217;',
3874          '&Uacute;'   => '&#218;',
3875          '&Ucirc;'    => '&#219;',
3876          '&Uuml;'     => '&#220;',
3877          '&Yacute;'   => '&#221;',
3878          '&THORN;'    => '&#222;',
3879          '&szlig;'    => '&#223;',
3880          '&agrave;'   => '&#224;',
3881          '&aacute;'   => '&#225;',
3882          '&acirc;'    => '&#226;',
3883          '&atilde;'   => '&#227;',
3884          '&auml;'     => '&#228;',
3885          '&aring;'    => '&#229;',
3886          '&aelig;'    => '&#230;',
3887          '&ccedil;'   => '&#231;',
3888          '&egrave;'   => '&#232;',
3889          '&eacute;'   => '&#233;',
3890          '&ecirc;'    => '&#234;',
3891          '&euml;'     => '&#235;',
3892          '&igrave;'   => '&#236;',
3893          '&iacute;'   => '&#237;',
3894          '&icirc;'    => '&#238;',
3895          '&iuml;'     => '&#239;',
3896          '&eth;'      => '&#240;',
3897          '&ntilde;'   => '&#241;',
3898          '&ograve;'   => '&#242;',
3899          '&oacute;'   => '&#243;',
3900          '&ocirc;'    => '&#244;',
3901          '&otilde;'   => '&#245;',
3902          '&ouml;'     => '&#246;',
3903          '&divide;'   => '&#247;',
3904          '&oslash;'   => '&#248;',
3905          '&ugrave;'   => '&#249;',
3906          '&uacute;'   => '&#250;',
3907          '&ucirc;'    => '&#251;',
3908          '&uuml;'     => '&#252;',
3909          '&yacute;'   => '&#253;',
3910          '&thorn;'    => '&#254;',
3911          '&yuml;'     => '&#255;',
3912          '&OElig;'    => '&#338;',
3913          '&oelig;'    => '&#339;',
3914          '&Scaron;'   => '&#352;',
3915          '&scaron;'   => '&#353;',
3916          '&Yuml;'     => '&#376;',
3917          '&fnof;'     => '&#402;',
3918          '&circ;'     => '&#710;',
3919          '&tilde;'    => '&#732;',
3920          '&Alpha;'    => '&#913;',
3921          '&Beta;'     => '&#914;',
3922          '&Gamma;'    => '&#915;',
3923          '&Delta;'    => '&#916;',
3924          '&Epsilon;'  => '&#917;',
3925          '&Zeta;'     => '&#918;',
3926          '&Eta;'      => '&#919;',
3927          '&Theta;'    => '&#920;',
3928          '&Iota;'     => '&#921;',
3929          '&Kappa;'    => '&#922;',
3930          '&Lambda;'   => '&#923;',
3931          '&Mu;'       => '&#924;',
3932          '&Nu;'       => '&#925;',
3933          '&Xi;'       => '&#926;',
3934          '&Omicron;'  => '&#927;',
3935          '&Pi;'       => '&#928;',
3936          '&Rho;'      => '&#929;',
3937          '&Sigma;'    => '&#931;',
3938          '&Tau;'      => '&#932;',
3939          '&Upsilon;'  => '&#933;',
3940          '&Phi;'      => '&#934;',
3941          '&Chi;'      => '&#935;',
3942          '&Psi;'      => '&#936;',
3943          '&Omega;'    => '&#937;',
3944          '&alpha;'    => '&#945;',
3945          '&beta;'     => '&#946;',
3946          '&gamma;'    => '&#947;',
3947          '&delta;'    => '&#948;',
3948          '&epsilon;'  => '&#949;',
3949          '&zeta;'     => '&#950;',
3950          '&eta;'      => '&#951;',
3951          '&theta;'    => '&#952;',
3952          '&iota;'     => '&#953;',
3953          '&kappa;'    => '&#954;',
3954          '&lambda;'   => '&#955;',
3955          '&mu;'       => '&#956;',
3956          '&nu;'       => '&#957;',
3957          '&xi;'       => '&#958;',
3958          '&omicron;'  => '&#959;',
3959          '&pi;'       => '&#960;',
3960          '&rho;'      => '&#961;',
3961          '&sigmaf;'   => '&#962;',
3962          '&sigma;'    => '&#963;',
3963          '&tau;'      => '&#964;',
3964          '&upsilon;'  => '&#965;',
3965          '&phi;'      => '&#966;',
3966          '&chi;'      => '&#967;',
3967          '&psi;'      => '&#968;',
3968          '&omega;'    => '&#969;',
3969          '&thetasym;' => '&#977;',
3970          '&upsih;'    => '&#978;',
3971          '&piv;'      => '&#982;',
3972          '&ensp;'     => '&#8194;',
3973          '&emsp;'     => '&#8195;',
3974          '&thinsp;'   => '&#8201;',
3975          '&zwnj;'     => '&#8204;',
3976          '&zwj;'      => '&#8205;',
3977          '&lrm;'      => '&#8206;',
3978          '&rlm;'      => '&#8207;',
3979          '&ndash;'    => '&#8211;',
3980          '&mdash;'    => '&#8212;',
3981          '&lsquo;'    => '&#8216;',
3982          '&rsquo;'    => '&#8217;',
3983          '&sbquo;'    => '&#8218;',
3984          '&ldquo;'    => '&#8220;',
3985          '&rdquo;'    => '&#8221;',
3986          '&bdquo;'    => '&#8222;',
3987          '&dagger;'   => '&#8224;',
3988          '&Dagger;'   => '&#8225;',
3989          '&bull;'     => '&#8226;',
3990          '&hellip;'   => '&#8230;',
3991          '&permil;'   => '&#8240;',
3992          '&prime;'    => '&#8242;',
3993          '&Prime;'    => '&#8243;',
3994          '&lsaquo;'   => '&#8249;',
3995          '&rsaquo;'   => '&#8250;',
3996          '&oline;'    => '&#8254;',
3997          '&frasl;'    => '&#8260;',
3998          '&euro;'     => '&#8364;',
3999          '&image;'    => '&#8465;',
4000          '&weierp;'   => '&#8472;',
4001          '&real;'     => '&#8476;',
4002          '&trade;'    => '&#8482;',
4003          '&alefsym;'  => '&#8501;',
4004          '&crarr;'    => '&#8629;',
4005          '&lArr;'     => '&#8656;',
4006          '&uArr;'     => '&#8657;',
4007          '&rArr;'     => '&#8658;',
4008          '&dArr;'     => '&#8659;',
4009          '&hArr;'     => '&#8660;',
4010          '&forall;'   => '&#8704;',
4011          '&part;'     => '&#8706;',
4012          '&exist;'    => '&#8707;',
4013          '&empty;'    => '&#8709;',
4014          '&nabla;'    => '&#8711;',
4015          '&isin;'     => '&#8712;',
4016          '&notin;'    => '&#8713;',
4017          '&ni;'       => '&#8715;',
4018          '&prod;'     => '&#8719;',
4019          '&sum;'      => '&#8721;',
4020          '&minus;'    => '&#8722;',
4021          '&lowast;'   => '&#8727;',
4022          '&radic;'    => '&#8730;',
4023          '&prop;'     => '&#8733;',
4024          '&infin;'    => '&#8734;',
4025          '&ang;'      => '&#8736;',
4026          '&and;'      => '&#8743;',
4027          '&or;'       => '&#8744;',
4028          '&cap;'      => '&#8745;',
4029          '&cup;'      => '&#8746;',
4030          '&int;'      => '&#8747;',
4031          '&there4;'   => '&#8756;',
4032          '&sim;'      => '&#8764;',
4033          '&cong;'     => '&#8773;',
4034          '&asymp;'    => '&#8776;',
4035          '&ne;'       => '&#8800;',
4036          '&equiv;'    => '&#8801;',
4037          '&le;'       => '&#8804;',
4038          '&ge;'       => '&#8805;',
4039          '&sub;'      => '&#8834;',
4040          '&sup;'      => '&#8835;',
4041          '&nsub;'     => '&#8836;',
4042          '&sube;'     => '&#8838;',
4043          '&supe;'     => '&#8839;',
4044          '&oplus;'    => '&#8853;',
4045          '&otimes;'   => '&#8855;',
4046          '&perp;'     => '&#8869;',
4047          '&sdot;'     => '&#8901;',
4048          '&lceil;'    => '&#8968;',
4049          '&rceil;'    => '&#8969;',
4050          '&lfloor;'   => '&#8970;',
4051          '&rfloor;'   => '&#8971;',
4052          '&lang;'     => '&#9001;',
4053          '&rang;'     => '&#9002;',
4054          '&larr;'     => '&#8592;',
4055          '&uarr;'     => '&#8593;',
4056          '&rarr;'     => '&#8594;',
4057          '&darr;'     => '&#8595;',
4058          '&harr;'     => '&#8596;',
4059          '&loz;'      => '&#9674;',
4060          '&spades;'   => '&#9824;',
4061          '&clubs;'    => '&#9827;',
4062          '&hearts;'   => '&#9829;',
4063          '&diams;'    => '&#9830;',
4064      );
4065  
4066      return str_replace( array_keys( $to_ncr ), array_values( $to_ncr ), $text );
4067  }
4068  
4069  /**
4070   * Formats text for the editor.
4071   *
4072   * Generally the browsers treat everything inside a textarea as text, but
4073   * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
4074   *
4075   * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
4076   * filter will be applied to an empty string.
4077   *
4078   * @since 4.3.0
4079   *
4080   * @see _WP_Editors::editor()
4081   *
4082   * @param string $text           The text to be formatted.
4083   * @param string $default_editor The default editor for the current user.
4084   *                               It is usually either 'html' or 'tinymce'.
4085   * @return string The formatted text after filter is applied.
4086   */
4087  function format_for_editor( $text, $default_editor = null ) {
4088      if ( $text ) {
4089          $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
4090      }
4091  
4092      /**
4093       * Filters the text after it is formatted for the editor.
4094       *
4095       * @since 4.3.0
4096       *
4097       * @param string $text           The formatted text.
4098       * @param string $default_editor The default editor for the current user.
4099       *                               It is usually either 'html' or 'tinymce'.
4100       */
4101      return apply_filters( 'format_for_editor', $text, $default_editor );
4102  }
4103  
4104  /**
4105   * Perform a deep string replace operation to ensure the values in $search are no longer present
4106   *
4107   * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
4108   * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
4109   * str_replace would return
4110   *
4111   * @since 2.8.1
4112   * @access private
4113   *
4114   * @param string|array $search  The value being searched for, otherwise known as the needle.
4115   *                              An array may be used to designate multiple needles.
4116   * @param string       $subject The string being searched and replaced on, otherwise known as the haystack.
4117   * @return string The string with the replaced values.
4118   */
4119  function _deep_replace( $search, $subject ) {
4120      $subject = (string) $subject;
4121  
4122      $count = 1;
4123      while ( $count ) {
4124          $subject = str_replace( $search, '', $subject, $count );
4125      }
4126  
4127      return $subject;
4128  }
4129  
4130  /**
4131   * Escapes data for use in a MySQL query.
4132   *
4133   * Usually you should prepare queries using wpdb::prepare().
4134   * Sometimes, spot-escaping is required or useful. One example
4135   * is preparing an array for use in an IN clause.
4136   *
4137   * NOTE: Since 4.8.3, '%' characters will be replaced with a placeholder string,
4138   * this prevents certain SQLi attacks from taking place. This change in behaviour
4139   * may cause issues for code that expects the return value of esc_sql() to be useable
4140   * for other purposes.
4141   *
4142   * @since 2.8.0
4143   *
4144   * @global wpdb $wpdb WordPress database abstraction object.
4145   *
4146   * @param string|array $data Unescaped data
4147   * @return string|array Escaped data
4148   */
4149  function esc_sql( $data ) {
4150      global $wpdb;
4151      return $wpdb->_escape( $data );
4152  }
4153  
4154  /**
4155   * Checks and cleans a URL.
4156   *
4157   * A number of characters are removed from the URL. If the URL is for displaying
4158   * (the default behaviour) ampersands are also replaced. The {@see 'clean_url'} filter
4159   * is applied to the returned cleaned URL.
4160   *
4161   * @since 2.8.0
4162   *
4163   * @param string $url       The URL to be cleaned.
4164   * @param array  $protocols Optional. An array of acceptable protocols.
4165   *                          Defaults to return value of wp_allowed_protocols()
4166   * @param string $_context  Private. Use esc_url_raw() for database usage.
4167   * @return string The cleaned $url after the {@see 'clean_url'} filter is applied.
4168   */
4169  function esc_url( $url, $protocols = null, $_context = 'display' ) {
4170      $original_url = $url;
4171  
4172      if ( '' == $url ) {
4173          return $url;
4174      }
4175  
4176      $url = str_replace( ' ', '%20', $url );
4177      $url = preg_replace( '|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url );
4178  
4179      if ( '' === $url ) {
4180          return $url;
4181      }
4182  
4183      if ( 0 !== stripos( $url, 'mailto:' ) ) {
4184          $strip = array( '%0d', '%0a', '%0D', '%0A' );
4185          $url   = _deep_replace( $strip, $url );
4186      }
4187  
4188      $url = str_replace( ';//', '://', $url );
4189      /* If the URL doesn't appear to contain a scheme, we
4190       * presume it needs http:// prepended (unless a relative
4191       * link starting with /, # or ? or a php file).
4192       */
4193      if ( strpos( $url, ':' ) === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
4194          ! preg_match( '/^[a-z0-9-]+?\.php/i', $url ) ) {
4195          $url = 'http://' . $url;
4196      }
4197  
4198      // Replace ampersands and single quotes only when displaying.
4199      if ( 'display' == $_context ) {
4200          $url = wp_kses_normalize_entities( $url );
4201          $url = str_replace( '&amp;', '&#038;', $url );
4202          $url = str_replace( "'", '&#039;', $url );
4203      }
4204  
4205      if ( ( false !== strpos( $url, '[' ) ) || ( false !== strpos( $url, ']' ) ) ) {
4206  
4207          $parsed = wp_parse_url( $url );
4208          $front  = '';
4209  
4210          if ( isset( $parsed['scheme'] ) ) {
4211              $front .= $parsed['scheme'] . '://';
4212          } elseif ( '/' === $url[0] ) {
4213              $front .= '//';
4214          }
4215  
4216          if ( isset( $parsed['user'] ) ) {
4217              $front .= $parsed['user'];
4218          }
4219  
4220          if ( isset( $parsed['pass'] ) ) {
4221              $front .= ':' . $parsed['pass'];
4222          }
4223  
4224          if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) {
4225              $front .= '@';
4226          }
4227  
4228          if ( isset( $parsed['host'] ) ) {
4229              $front .= $parsed['host'];
4230          }
4231  
4232          if ( isset( $parsed['port'] ) ) {
4233              $front .= ':' . $parsed['port'];
4234          }
4235  
4236          $end_dirty = str_replace( $front, '', $url );
4237          $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty );
4238          $url       = str_replace( $end_dirty, $end_clean, $url );
4239  
4240      }
4241  
4242      if ( '/' === $url[0] ) {
4243          $good_protocol_url = $url;
4244      } else {
4245          if ( ! is_array( $protocols ) ) {
4246              $protocols = wp_allowed_protocols();
4247          }
4248          $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
4249          if ( strtolower( $good_protocol_url ) != strtolower( $url ) ) {
4250              return '';
4251          }
4252      }
4253  
4254      /**
4255       * Filters a string cleaned and escaped for output as a URL.
4256       *
4257       * @since 2.3.0
4258       *
4259       * @param string $good_protocol_url The cleaned URL to be returned.
4260       * @param string $original_url      The URL prior to cleaning.
4261       * @param string $_context          If 'display', replace ampersands and single quotes only.
4262       */
4263      return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
4264  }
4265  
4266  /**
4267   * Performs esc_url() for database usage.
4268   *
4269   * @since 2.8.0
4270   *
4271   * @param string $url       The URL to be cleaned.
4272   * @param array  $protocols An array of acceptable protocols.
4273   * @return string The cleaned URL.
4274   */
4275  function esc_url_raw( $url, $protocols = null ) {
4276      return esc_url( $url, $protocols, 'db' );
4277  }
4278  
4279  /**
4280   * Convert entities, while preserving already-encoded entities.
4281   *
4282   * @link https://secure.php.net/htmlentities Borrowed from the PHP Manual user notes.
4283   *
4284   * @since 1.2.2
4285   *
4286   * @param string $myHTML The text to be converted.
4287   * @return string Converted text.
4288   */
4289  function htmlentities2( $myHTML ) {
4290      $translation_table              = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
4291      $translation_table[ chr( 38 ) ] = '&';
4292      return preg_replace( '/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/', '&amp;', strtr( $myHTML, $translation_table ) );
4293  }
4294  
4295  /**
4296   * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
4297   *
4298   * Escapes text strings for echoing in JS. It is intended to be used for inline JS
4299   * (in a tag attribute, for example onclick="..."). Note that the strings have to
4300   * be in single quotes. The {@see 'js_escape'} filter is also applied here.
4301   *
4302   * @since 2.8.0
4303   *
4304   * @param string $text The text to be escaped.
4305   * @return string Escaped text.
4306   */
4307  function esc_js( $text ) {
4308      $safe_text = wp_check_invalid_utf8( $text );
4309      $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
4310      $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
4311      $safe_text = str_replace( "\r", '', $safe_text );
4312      $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
4313      /**
4314       * Filters a string cleaned and escaped for output in JavaScript.
4315       *
4316       * Text passed to esc_js() is stripped of invalid or special characters,
4317       * and properly slashed for output.
4318       *
4319       * @since 2.0.6
4320       *
4321       * @param string $safe_text The text after it has been escaped.
4322       * @param string $text      The text prior to being escaped.
4323       */
4324      return apply_filters( 'js_escape', $safe_text, $text );
4325  }
4326  
4327  /**
4328   * Escaping for HTML blocks.
4329   *
4330   * @since 2.8.0
4331   *
4332   * @param string $text
4333   * @return string
4334   */
4335  function esc_html( $text ) {
4336      $safe_text = wp_check_invalid_utf8( $text );
4337      $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
4338      /**
4339       * Filters a string cleaned and escaped for output in HTML.
4340       *
4341       * Text passed to esc_html() is stripped of invalid or special characters
4342       * before output.
4343       *
4344       * @since 2.8.0
4345       *
4346       * @param string $safe_text The text after it has been escaped.
4347       * @param string $text      The text prior to being escaped.
4348       */
4349      return apply_filters( 'esc_html', $safe_text, $text );
4350  }
4351  
4352  /**
4353   * Escaping for HTML attributes.
4354   *
4355   * @since 2.8.0
4356   *
4357   * @param string $text
4358   * @return string
4359   */
4360  function esc_attr( $text ) {
4361      $safe_text = wp_check_invalid_utf8( $text );
4362      $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
4363      /**
4364       * Filters a string cleaned and escaped for output in an HTML attribute.
4365       *
4366       * Text passed to esc_attr() is stripped of invalid or special characters
4367       * before output.
4368       *
4369       * @since 2.0.6
4370       *
4371       * @param string $safe_text The text after it has been escaped.
4372       * @param string $text      The text prior to being escaped.
4373       */
4374      return apply_filters( 'attribute_escape', $safe_text, $text );
4375  }
4376  
4377  /**
4378   * Escaping for textarea values.
4379   *
4380   * @since 3.1.0
4381   *
4382   * @param string $text
4383   * @return string
4384   */
4385  function esc_textarea( $text ) {
4386      $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
4387      /**
4388       * Filters a string cleaned and escaped for output in a textarea element.
4389       *
4390       * @since 3.1.0
4391       *
4392       * @param string $safe_text The text after it has been escaped.
4393       * @param string $text      The text prior to being escaped.
4394       */
4395      return apply_filters( 'esc_textarea', $safe_text, $text );
4396  }
4397  
4398  /**
4399   * Escape an HTML tag name.
4400   *
4401   * @since 2.5.0
4402   *
4403   * @param string $tag_name
4404   * @return string
4405   */
4406  function tag_escape( $tag_name ) {
4407      $safe_tag = strtolower( preg_replace( '/[^a-zA-Z0-9_:]/', '', $tag_name ) );
4408      /**
4409       * Filters a string cleaned and escaped for output as an HTML tag.
4410       *
4411       * @since 2.8.0
4412       *
4413       * @param string $safe_tag The tag name after it has been escaped.
4414       * @param string $tag_name The text before it was escaped.
4415       */
4416      return apply_filters( 'tag_escape', $safe_tag, $tag_name );
4417  }
4418  
4419  /**
4420   * Convert full URL paths to absolute paths.
4421   *
4422   * Removes the http or https protocols and the domain. Keeps the path '/' at the
4423   * beginning, so it isn't a true relative link, but from the web root base.
4424   *
4425   * @since 2.1.0
4426   * @since 4.1.0 Support was added for relative URLs.
4427   *
4428   * @param string $link Full URL path.
4429   * @return string Absolute path.
4430   */
4431  function wp_make_link_relative( $link ) {
4432      return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link );
4433  }
4434  
4435  /**
4436   * Sanitises various option values based on the nature of the option.
4437   *
4438   * This is basically a switch statement which will pass $value through a number
4439   * of functions depending on the $option.
4440   *
4441   * @since 2.0.5
4442   *
4443   * @global wpdb $wpdb WordPress database abstraction object.
4444   *
4445   * @param string $option The name of the option.
4446   * @param string $value  The unsanitised value.
4447   * @return string Sanitized value.
4448   */
4449  function sanitize_option( $option, $value ) {
4450      global $wpdb;
4451  
4452      $original_value = $value;
4453      $error          = '';
4454  
4455      switch ( $option ) {
4456          case 'admin_email':
4457          case 'new_admin_email':
4458              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4459              if ( is_wp_error( $value ) ) {
4460                  $error = $value->get_error_message();
4461              } else {
4462                  $value = sanitize_email( $value );
4463                  if ( ! is_email( $value ) ) {
4464                      $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
4465                  }
4466              }
4467              break;
4468  
4469          case 'thumbnail_size_w':
4470          case 'thumbnail_size_h':
4471          case 'medium_size_w':
4472          case 'medium_size_h':
4473          case 'medium_large_size_w':
4474          case 'medium_large_size_h':
4475          case 'large_size_w':
4476          case 'large_size_h':
4477          case 'mailserver_port':
4478          case 'comment_max_links':
4479          case 'page_on_front':
4480          case 'page_for_posts':
4481          case 'rss_excerpt_length':
4482          case 'default_category':
4483          case 'default_email_category':
4484          case 'default_link_category':
4485          case 'close_comments_days_old':
4486          case 'comments_per_page':
4487          case 'thread_comments_depth':
4488          case 'users_can_register':
4489          case 'start_of_week':
4490          case 'site_icon':
4491              $value = absint( $value );
4492              break;
4493  
4494          case 'posts_per_page':
4495          case 'posts_per_rss':
4496              $value = (int) $value;
4497              if ( empty( $value ) ) {
4498                  $value = 1;
4499              }
4500              if ( $value < -1 ) {
4501                  $value = abs( $value );
4502              }
4503              break;
4504  
4505          case 'default_ping_status':
4506          case 'default_comment_status':
4507              // Options that if not there have 0 value but need to be something like "closed"
4508              if ( $value == '0' || $value == '' ) {
4509                  $value = 'closed';
4510              }
4511              break;
4512  
4513          case 'blogdescription':
4514          case 'blogname':
4515              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4516              if ( $value !== $original_value ) {
4517                  $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) );
4518              }
4519  
4520              if ( is_wp_error( $value ) ) {
4521                  $error = $value->get_error_message();
4522              } else {
4523                  $value = esc_html( $value );
4524              }
4525              break;
4526  
4527          case 'blog_charset':
4528              $value = preg_replace( '/[^a-zA-Z0-9_-]/', '', $value ); // strips slashes
4529              break;
4530  
4531          case 'blog_public':
4532              // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
4533              if ( null === $value ) {
4534                  $value = 1;
4535              } else {
4536                  $value = intval( $value );
4537              }
4538              break;
4539  
4540          case 'date_format':
4541          case 'time_format':
4542          case 'mailserver_url':
4543          case 'mailserver_login':
4544          case 'mailserver_pass':
4545          case 'upload_path':
4546              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4547              if ( is_wp_error( $value ) ) {
4548                  $error = $value->get_error_message();
4549              } else {
4550                  $value = strip_tags( $value );
4551                  $value = wp_kses_data( $value );
4552              }
4553              break;
4554  
4555          case 'ping_sites':
4556              $value = explode( "\n", $value );
4557              $value = array_filter( array_map( 'trim', $value ) );
4558              $value = array_filter( array_map( 'esc_url_raw', $value ) );
4559              $value = implode( "\n", $value );
4560              break;
4561  
4562          case 'gmt_offset':
4563              $value = preg_replace( '/[^0-9:.-]/', '', $value ); // strips slashes
4564              break;
4565  
4566          case 'siteurl':
4567              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4568              if ( is_wp_error( $value ) ) {
4569                  $error = $value->get_error_message();
4570              } else {
4571                  if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
4572                      $value = esc_url_raw( $value );
4573                  } else {
4574                      $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
4575                  }
4576              }
4577              break;
4578  
4579          case 'home':
4580              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4581              if ( is_wp_error( $value ) ) {
4582                  $error = $value->get_error_message();
4583              } else {
4584                  if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
4585                      $value = esc_url_raw( $value );
4586                  } else {
4587                      $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
4588                  }
4589              }
4590              break;
4591  
4592          case 'WPLANG':
4593              $allowed = get_available_languages();
4594              if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
4595                  $allowed[] = WPLANG;
4596              }
4597              if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
4598                  $value = get_option( $option );
4599              }
4600              break;
4601  
4602          case 'illegal_names':
4603              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4604              if ( is_wp_error( $value ) ) {
4605                  $error = $value->get_error_message();
4606              } else {
4607                  if ( ! is_array( $value ) ) {
4608                      $value = explode( ' ', $value );
4609                  }
4610  
4611                  $value = array_values( array_filter( array_map( 'trim', $value ) ) );
4612  
4613                  if ( ! $value ) {
4614                      $value = '';
4615                  }
4616              }
4617              break;
4618  
4619          case 'limited_email_domains':
4620          case 'banned_email_domains':
4621              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4622              if ( is_wp_error( $value ) ) {
4623                  $error = $value->get_error_message();
4624              } else {
4625                  if ( ! is_array( $value ) ) {
4626                      $value = explode( "\n", $value );
4627                  }
4628  
4629                  $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
4630                  $value   = array();
4631  
4632                  foreach ( $domains as $domain ) {
4633                      if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
4634                          $value[] = $domain;
4635                      }
4636                  }
4637                  if ( ! $value ) {
4638                      $value = '';
4639                  }
4640              }
4641              break;
4642  
4643          case 'timezone_string':
4644              $allowed_zones = timezone_identifiers_list();
4645              if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
4646                  $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
4647              }
4648              break;
4649  
4650          case 'permalink_structure':
4651          case 'category_base':
4652          case 'tag_base':
4653              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4654              if ( is_wp_error( $value ) ) {
4655                  $error = $value->get_error_message();
4656              } else {
4657                  $value = esc_url_raw( $value );
4658                  $value = str_replace( 'http://', '', $value );
4659              }
4660  
4661              if ( 'permalink_structure' === $option && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value ) ) {
4662                  $error = sprintf(
4663                      /* translators: %s: Codex URL */
4664                      __( 'A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>' ),
4665                      __( 'https://codex.wordpress.org/Using_Permalinks#Choosing_your_permalink_structure' )
4666                  );
4667              }
4668              break;
4669  
4670          case 'default_role':
4671              if ( ! get_role( $value ) && get_role( 'subscriber' ) ) {
4672                  $value = 'subscriber';
4673              }
4674              break;
4675  
4676          case 'moderation_keys':
4677          case 'blacklist_keys':
4678              $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4679              if ( is_wp_error( $value ) ) {
4680                  $error = $value->get_error_message();
4681              } else {
4682                  $value = explode( "\n", $value );
4683                  $value = array_filter( array_map( 'trim', $value ) );
4684                  $value = array_unique( $value );
4685                  $value = implode( "\n", $value );
4686              }
4687              break;
4688      }
4689  
4690      if ( ! empty( $error ) ) {
4691          $value = get_option( $option );
4692          if ( function_exists( 'add_settings_error' ) ) {
4693              add_settings_error( $option, "invalid_{$option}", $error );
4694          }
4695      }
4696  
4697      /**
4698       * Filters an option value following sanitization.
4699       *
4700       * @since 2.3.0
4701       * @since 4.3.0 Added the `$original_value` parameter.
4702       *
4703       * @param string $value          The sanitized option value.
4704       * @param string $option         The option name.
4705       * @param string $original_value The original value passed to the function.
4706       */
4707      return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value );
4708  }
4709  
4710  /**
4711   * Maps a function to all non-iterable elements of an array or an object.
4712   *
4713   * This is similar to `array_walk_recursive()` but acts upon objects too.
4714   *
4715   * @since 4.4.0
4716   *
4717   * @param mixed    $value    The array, object, or scalar.
4718   * @param callable $callback The function to map onto $value.
4719   * @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
4720   */
4721  function map_deep( $value, $callback ) {
4722      if ( is_array( $value ) ) {
4723          foreach ( $value as $index => $item ) {
4724              $value[ $index ] = map_deep( $item, $callback );
4725          }
4726      } elseif ( is_object( $value ) ) {
4727          $object_vars = get_object_vars( $value );
4728          foreach ( $object_vars as $property_name => $property_value ) {
4729              $value->$property_name = map_deep( $property_value, $callback );
4730          }
4731      } else {
4732          $value = call_user_func( $callback, $value );
4733      }
4734  
4735      return $value;
4736  }
4737  
4738  /**
4739   * Parses a string into variables to be stored in an array.
4740   *
4741   * Uses {@link https://secure.php.net/parse_str parse_str()} and stripslashes if
4742   * {@link https://secure.php.net/magic_quotes magic_quotes_gpc} is on.
4743   *
4744   * @since 2.2.1
4745   *
4746   * @param string $string The string to be parsed.
4747   * @param array  $array  Variables will be stored in this array.
4748   */
4749  function wp_parse_str( $string, &$array ) {
4750      parse_str( $string, $array );
4751      if ( get_magic_quotes_gpc() ) {
4752          $array = stripslashes_deep( $array );
4753      }
4754      /**
4755       * Filters the array of variables derived from a parsed string.
4756       *
4757       * @since 2.3.0
4758       *
4759       * @param array $array The array populated with variables.
4760       */
4761      $array = apply_filters( 'wp_parse_str', $array );
4762  }
4763  
4764  /**
4765   * Convert lone less than signs.
4766   *
4767   * KSES already converts lone greater than signs.
4768   *
4769   * @since 2.3.0
4770   *
4771   * @param string $text Text to be converted.
4772   * @return string Converted text.
4773   */
4774  function wp_pre_kses_less_than( $text ) {
4775      return preg_replace_callback( '%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text );
4776  }
4777  
4778  /**
4779   * Callback function used by preg_replace.
4780   *
4781   * @since 2.3.0
4782   *
4783   * @param array $matches Populated by matches to preg_replace.
4784   * @return string The text returned after esc_html if needed.
4785   */
4786  function wp_pre_kses_less_than_callback( $matches ) {
4787      if ( false === strpos( $matches[0], '>' ) ) {
4788          return esc_html( $matches[0] );
4789      }
4790      return $matches[0];
4791  }
4792  
4793  /**
4794   * WordPress implementation of PHP sprintf() with filters.
4795   *
4796   * @since 2.5.0
4797   * @link https://secure.php.net/sprintf
4798   *
4799   * @param string $pattern   The string which formatted args are inserted.
4800   * @param mixed  $args ,... Arguments to be formatted into the $pattern string.
4801   * @return string The formatted string.
4802   */
4803  function wp_sprintf( $pattern ) {
4804      $args      = func_get_args();
4805      $len       = strlen( $pattern );
4806      $start     = 0;
4807      $result    = '';
4808      $arg_index = 0;
4809      while ( $len > $start ) {
4810          // Last character: append and break
4811          if ( strlen( $pattern ) - 1 == $start ) {
4812              $result .= substr( $pattern, -1 );
4813              break;
4814          }
4815  
4816          // Literal %: append and continue
4817          if ( substr( $pattern, $start, 2 ) == '%%' ) {
4818              $start  += 2;
4819              $result .= '%';
4820              continue;
4821          }
4822  
4823          // Get fragment before next %
4824          $end = strpos( $pattern, '%', $start + 1 );
4825          if ( false === $end ) {
4826              $end = $len;
4827          }
4828          $fragment = substr( $pattern, $start, $end - $start );
4829  
4830          // Fragment has a specifier
4831          if ( $pattern[ $start ] == '%' ) {
4832              // Find numbered arguments or take the next one in order
4833              if ( preg_match( '/^%(\d+)\$/', $fragment, $matches ) ) {
4834                  $arg      = isset( $args[ $matches[1] ] ) ? $args[ $matches[1] ] : '';
4835                  $fragment = str_replace( "%{$matches[1]}$", '%', $fragment );
4836              } else {
4837                  ++$arg_index;
4838                  $arg = isset( $args[ $arg_index ] ) ? $args[ $arg_index ] : '';
4839              }
4840  
4841              /**
4842               * Filters a fragment from the pattern passed to wp_sprintf().
4843               *
4844               * If the fragment is unchanged, then sprintf() will be run on the fragment.
4845               *
4846               * @since 2.5.0
4847               *
4848               * @param string $fragment A fragment from the pattern.
4849               * @param string $arg      The argument.
4850               */
4851              $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
4852              if ( $_fragment != $fragment ) {
4853                  $fragment = $_fragment;
4854              } else {
4855                  $fragment = sprintf( $fragment, strval( $arg ) );
4856              }
4857          }
4858  
4859          // Append to result and move to next fragment
4860          $result .= $fragment;
4861          $start   = $end;
4862      }
4863      return $result;
4864  }
4865  
4866  /**
4867   * Localize list items before the rest of the content.
4868   *
4869   * The '%l' must be at the first characters can then contain the rest of the
4870   * content. The list items will have ', ', ', and', and ' and ' added depending
4871   * on the amount of list items in the $args parameter.
4872   *
4873   * @since 2.5.0
4874   *
4875   * @param string $pattern Content containing '%l' at the beginning.
4876   * @param array  $args    List items to prepend to the content and replace '%l'.
4877   * @return string Localized list items and rest of the content.
4878   */
4879  function wp_sprintf_l( $pattern, $args ) {
4880      // Not a match
4881      if ( substr( $pattern, 0, 2 ) != '%l' ) {
4882          return $pattern;
4883      }
4884  
4885      // Nothing to work with
4886      if ( empty( $args ) ) {
4887          return '';
4888      }
4889  
4890      /**
4891       * Filters the translated delimiters used by wp_sprintf_l().
4892       * Placeholders (%s) are included to assist translators and then
4893       * removed before the array of strings reaches the filter.
4894       *
4895       * Please note: Ampersands and entities should be avoided here.
4896       *
4897       * @since 2.5.0
4898       *
4899       * @param array $delimiters An array of translated delimiters.
4900       */
4901      $l = apply_filters(
4902          'wp_sprintf_l',
4903          array(
4904              /* translators: used to join items in a list with more than 2 items */
4905              'between'          => sprintf( __( '%1$s, %2$s' ), '', '' ),
4906              /* translators: used to join last two items in a list with more than 2 times */
4907              'between_last_two' => sprintf( __( '%1$s, and %2$s' ), '', '' ),
4908              /* translators: used to join items in a list with only 2 items */
4909              'between_only_two' => sprintf( __( '%1$s and %2$s' ), '', '' ),
4910          )
4911      );
4912  
4913      $args   = (array) $args;
4914      $result = array_shift( $args );
4915      if ( count( $args ) == 1 ) {
4916          $result .= $l['between_only_two'] . array_shift( $args );
4917      }
4918      // Loop when more than two args
4919      $i = count( $args );
4920      while ( $i ) {
4921          $arg = array_shift( $args );
4922          $i--;
4923          if ( 0 == $i ) {
4924              $result .= $l['between_last_two'] . $arg;
4925          } else {
4926              $result .= $l['between'] . $arg;
4927          }
4928      }
4929      return $result . substr( $pattern, 2 );
4930  }
4931  
4932  /**
4933   * Safely extracts not more than the first $count characters from html string.
4934   *
4935   * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
4936   * be counted as one character. For example &amp; will be counted as 4, &lt; as
4937   * 3, etc.
4938   *
4939   * @since 2.5.0
4940   *
4941   * @param string $str   String to get the excerpt from.
4942   * @param int    $count Maximum number of characters to take.
4943   * @param string $more  Optional. What to append if $str needs to be trimmed. Defaults to empty string.
4944   * @return string The excerpt.
4945   */
4946  function wp_html_excerpt( $str, $count, $more = null ) {
4947      if ( null === $more ) {
4948          $more = '';
4949      }
4950      $str     = wp_strip_all_tags( $str, true );
4951      $excerpt = mb_substr( $str, 0, $count );
4952      // remove part of an entity at the end
4953      $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
4954      if ( $str != $excerpt ) {
4955          $excerpt = trim( $excerpt ) . $more;
4956      }
4957      return $excerpt;
4958  }
4959  
4960  /**
4961   * Add a Base url to relative links in passed content.
4962   *
4963   * By default it supports the 'src' and 'href' attributes. However this can be
4964   * changed via the 3rd param.
4965   *
4966   * @since 2.7.0
4967   *
4968   * @global string $_links_add_base
4969   *
4970   * @param string $content String to search for links in.
4971   * @param string $base    The base URL to prefix to links.
4972   * @param array  $attrs   The attributes which should be processed.
4973   * @return string The processed content.
4974   */
4975  function links_add_base_url( $content, $base, $attrs = array( 'src', 'href' ) ) {
4976      global $_links_add_base;
4977      $_links_add_base = $base;
4978      $attrs           = implode( '|', (array) $attrs );
4979      return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
4980  }
4981  
4982  /**
4983   * Callback to add a base url to relative links in passed content.
4984   *
4985   * @since 2.7.0
4986   * @access private
4987   *
4988   * @global string $_links_add_base
4989   *
4990   * @param string $m The matched link.
4991   * @return string The processed link.
4992   */
4993  function _links_add_base( $m ) {
4994      global $_links_add_base;
4995      //1 = attribute name  2 = quotation mark  3 = URL
4996      return $m[1] . '=' . $m[2] .
4997          ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
4998              $m[3] :
4999              WP_Http::make_absolute_url( $m[3], $_links_add_base )
5000          )
5001          . $m[2];
5002  }
5003  
5004  /**
5005   * Adds a Target attribute to all links in passed content.
5006   *
5007   * This function by default only applies to `<a>` tags, however this can be
5008   * modified by the 3rd param.
5009   *
5010   * *NOTE:* Any current target attributed will be stripped and replaced.
5011   *
5012   * @since 2.7.0
5013   *
5014   * @global string $_links_add_target
5015   *
5016   * @param string $content String to search for links in.
5017   * @param string $target  The Target to add to the links.
5018   * @param array  $tags    An array of tags to apply to.
5019   * @return string The processed content.
5020   */
5021  function links_add_target( $content, $target = '_blank', $tags = array( 'a' ) ) {
5022      global $_links_add_target;
5023      $_links_add_target = $target;
5024      $tags              = implode( '|', (array) $tags );
5025      return preg_replace_callback( "!<($tags)([^>]*)>!i", '_links_add_target', $content );
5026  }
5027  
5028  /**
5029   * Callback to add a target attribute to all links in passed content.
5030   *
5031   * @since 2.7.0
5032   * @access private
5033   *
5034   * @global string $_links_add_target
5035   *
5036   * @param string $m The matched link.
5037   * @return string The processed link.
5038   */
5039  function _links_add_target( $m ) {
5040      global $_links_add_target;
5041      $tag  = $m[1];
5042      $link = preg_replace( '|( target=([\'"])(.*?)\2)|i', '', $m[2] );
5043      return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
5044  }
5045  
5046  /**
5047   * Normalize EOL characters and strip duplicate whitespace.
5048   *
5049   * @since 2.7.0
5050   *
5051   * @param string $str The string to normalize.
5052   * @return string The normalized string.
5053   */
5054  function normalize_whitespace( $str ) {
5055      $str = trim( $str );
5056      $str = str_replace( "\r", "\n", $str );
5057      $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
5058      return $str;
5059  }
5060  
5061  /**
5062   * Properly strip all HTML tags including script and style
5063   *
5064   * This differs from strip_tags() because it removes the contents of
5065   * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
5066   * will return 'something'. wp_strip_all_tags will return ''
5067   *
5068   * @since 2.9.0
5069   *
5070   * @param string $string        String containing HTML tags
5071   * @param bool   $remove_breaks Optional. Whether to remove left over line breaks and white space chars
5072   * @return string The processed string.
5073   */
5074  function wp_strip_all_tags( $string, $remove_breaks = false ) {
5075      $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
5076      $string = strip_tags( $string );
5077  
5078      if ( $remove_breaks ) {
5079          $string = preg_replace( '/[\r\n\t ]+/', ' ', $string );
5080      }
5081  
5082      return trim( $string );
5083  }
5084  
5085  /**
5086   * Sanitizes a string from user input or from the database.
5087   *
5088   * - Checks for invalid UTF-8,
5089   * - Converts single `<` characters to entities
5090   * - Strips all tags
5091   * - Removes line breaks, tabs, and extra whitespace
5092   * - Strips octets
5093   *
5094   * @since 2.9.0
5095   *
5096   * @see sanitize_textarea_field()
5097   * @see wp_check_invalid_utf8()
5098   * @see wp_strip_all_tags()
5099   *
5100   * @param string $str String to sanitize.
5101   * @return string Sanitized string.
5102   */
5103  function sanitize_text_field( $str ) {
5104      $filtered = _sanitize_text_fields( $str, false );
5105  
5106      /**
5107       * Filters a sanitized text field string.
5108       *
5109       * @since 2.9.0
5110       *
5111       * @param string $filtered The sanitized string.
5112       * @param string $str      The string prior to being sanitized.
5113       */
5114      return apply_filters( 'sanitize_text_field', $filtered, $str );
5115  }
5116  
5117  /**
5118   * Sanitizes a multiline string from user input or from the database.
5119   *
5120   * The function is like sanitize_text_field(), but preserves
5121   * new lines (\n) and other whitespace, which are legitimate
5122   * input in textarea elements.
5123   *
5124   * @see sanitize_text_field()
5125   *
5126   * @since 4.7.0
5127   *
5128   * @param string $str String to sanitize.
5129   * @return string Sanitized string.
5130   */
5131  function sanitize_textarea_field( $str ) {
5132      $filtered = _sanitize_text_fields( $str, true );
5133  
5134      /**
5135       * Filters a sanitized textarea field string.
5136       *
5137       * @since 4.7.0
5138       *
5139       * @param string $filtered The sanitized string.
5140       * @param string $str      The string prior to being sanitized.
5141       */
5142      return apply_filters( 'sanitize_textarea_field', $filtered, $str );
5143  }
5144  
5145  /**
5146   * Internal helper function to sanitize a string from user input or from the db
5147   *
5148   * @since 4.7.0
5149   * @access private
5150   *
5151   * @param string $str String to sanitize.
5152   * @param bool $keep_newlines optional Whether to keep newlines. Default: false.
5153   * @return string Sanitized string.
5154   */
5155  function _sanitize_text_fields( $str, $keep_newlines = false ) {
5156      if ( is_object( $str ) || is_array( $str ) ) {
5157          return '';
5158      }
5159  
5160      $str = (string) $str;
5161  
5162      $filtered = wp_check_invalid_utf8( $str );
5163  
5164      if ( strpos( $filtered, '<' ) !== false ) {
5165          $filtered = wp_pre_kses_less_than( $filtered );
5166          // This will strip extra whitespace for us.
5167          $filtered = wp_strip_all_tags( $filtered, false );
5168  
5169          // Use html entities in a special case to make sure no later
5170          // newline stripping stage could lead to a functional tag
5171          $filtered = str_replace( "<\n", "&lt;\n", $filtered );
5172      }
5173  
5174      if ( ! $keep_newlines ) {
5175          $filtered = preg_replace( '/[\r\n\t ]+/', ' ', $filtered );
5176      }
5177      $filtered = trim( $filtered );
5178  
5179      $found = false;
5180      while ( preg_match( '/%[a-f0-9]{2}/i', $filtered, $match ) ) {
5181          $filtered = str_replace( $match[0], '', $filtered );
5182          $found    = true;
5183      }
5184  
5185      if ( $found ) {
5186          // Strip out the whitespace that may now exist after removing the octets.
5187          $filtered = trim( preg_replace( '/ +/', ' ', $filtered ) );
5188      }
5189  
5190      return $filtered;
5191  }
5192  
5193  /**
5194   * i18n friendly version of basename()
5195   *
5196   * @since 3.1.0
5197   *
5198   * @param string $path   A path.
5199   * @param string $suffix If the filename ends in suffix this will also be cut off.
5200   * @return string
5201   */
5202  function wp_basename( $path, $suffix = '' ) {
5203      return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
5204  }
5205  
5206  // phpcs:disable WordPress.WP.CapitalPDangit.Misspelled, WordPress.NamingConventions.ValidFunctionName.FunctionNameInvalid -- 8-)
5207  /**
5208   * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
5209   *
5210   * Violating our coding standards for a good function name.
5211   *
5212   * @since 3.0.0
5213   *
5214   * @staticvar string|false $dblq
5215   *
5216   * @param string $text The text to be modified.
5217   * @return string The modified text.
5218   */
5219  function capital_P_dangit( $text ) {
5220      // Simple replacement for titles
5221      $current_filter = current_filter();
5222      if ( 'the_title' === $current_filter || 'wp_title' === $current_filter ) {
5223          return str_replace( 'Wordpress', 'WordPress', $text );
5224      }
5225      // Still here? Use the more judicious replacement
5226      static $dblq = false;
5227      if ( false === $dblq ) {
5228          $dblq = _x( '&#8220;', 'opening curly double quote' );
5229      }
5230      return str_replace(
5231          array( ' Wordpress', '&#8216;Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
5232          array( ' WordPress', '&#8216;WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
5233          $text
5234      );
5235  }
5236  // phpcs:enable
5237  
5238  /**
5239   * Sanitize a mime type
5240   *
5241   * @since 3.1.3
5242   *
5243   * @param string $mime_type Mime type
5244   * @return string Sanitized mime type
5245   */
5246  function sanitize_mime_type( $mime_type ) {
5247      $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
5248      /**
5249       * Filters a mime type following sanitization.
5250       *
5251       * @since 3.1.3
5252       *
5253       * @param string $sani_mime_type The sanitized mime type.
5254       * @param string $mime_type      The mime type prior to sanitization.
5255       */
5256      return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
5257  }
5258  
5259  /**
5260   * Sanitize space or carriage return separated URLs that are used to send trackbacks.
5261   *
5262   * @since 3.4.0
5263   *
5264   * @param string $to_ping Space or carriage return separated URLs
5265   * @return string URLs starting with the http or https protocol, separated by a carriage return.
5266   */
5267  function sanitize_trackback_urls( $to_ping ) {
5268      $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
5269      foreach ( $urls_to_ping as $k => $url ) {
5270          if ( ! preg_match( '#^https?://.#i', $url ) ) {
5271              unset( $urls_to_ping[ $k ] );
5272          }
5273      }
5274      $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
5275      $urls_to_ping = implode( "\n", $urls_to_ping );
5276      /**
5277       * Filters a list of trackback URLs following sanitization.
5278       *
5279       * The string returned here consists of a space or carriage return-delimited list
5280       * of trackback URLs.
5281       *
5282       * @since 3.4.0
5283       *
5284       * @param string $urls_to_ping Sanitized space or carriage return separated URLs.
5285       * @param string $to_ping      Space or carriage return separated URLs before sanitization.
5286       */
5287      return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
5288  }
5289  
5290  /**
5291   * Add slashes to a string or array of strings.
5292   *
5293   * This should be used when preparing data for core API that expects slashed data.
5294   * This should not be used to escape data going directly into an SQL query.
5295   *
5296   * @since 3.6.0
5297   *
5298   * @param string|array $value String or array of strings to slash.
5299   * @return string|array Slashed $value
5300   */
5301  function wp_slash( $value ) {
5302      if ( is_array( $value ) ) {
5303          foreach ( $value as $k => $v ) {
5304              if ( is_array( $v ) ) {
5305                  $value[ $k ] = wp_slash( $v );
5306              } else {
5307                  $value[ $k ] = addslashes( $v );
5308              }
5309          }
5310      } else {
5311          $value = addslashes( $value );
5312      }
5313  
5314      return $value;
5315  }
5316  
5317  /**
5318   * Remove slashes from a string or array of strings.
5319   *
5320   * This should be used to remove slashes from data passed to core API that
5321   * expects data to be unslashed.
5322   *
5323   * @since 3.6.0
5324   *
5325   * @param string|array $value String or array of strings to unslash.
5326   * @return string|array Unslashed $value
5327   */
5328  function wp_unslash( $value ) {
5329      return stripslashes_deep( $value );
5330  }
5331  
5332  /**
5333   * Extract and return the first URL from passed content.
5334   *
5335   * @since 3.6.0
5336   *
5337   * @param string $content A string which might contain a URL.
5338   * @return string|false The found URL.
5339   */
5340  function get_url_in_content( $content ) {
5341      if ( empty( $content ) ) {
5342          return false;
5343      }
5344  
5345      if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content,