php whitespace regexp warning

php_whitespace_regexp.php

<?php

/*

  http://php.net/manual/en/regexp.reference.escape.php

  The "whitespace" characters are HT (9), LF (10), FF (12), CR (13), and space (32).
  However, if locale-specific matching is happening, characters with code points in
  the range 128-255 may also be considered as whitespace characters,
  for instance, NBSP (A0).
  
  如何指定 locale，参看我之前提交给 phabricator 的一个 bug: https://secure.phabricator.com/D14441
  
*/



/*
  Get all whitespace characters that "\s" will match.

  Result:

  0x09
  0x0A
  0x0C
  0x0D
  0x20
  0x85 => 1000 0101
  0xA0 => 1010 0000
 */
print_r(whitespace_characters_in_ascii('/\s/'));


/*

  http://php.net/manual/en/function.utf8-encode.php

  bytes bits  representation
  1     7     0bbbbbbb
  2     11    110bbbbb 10bbbbbb
  3     16    1110bbbb 10bbbbbb 10bbbbbb
  4     21    11110bbb 10bbbbbb 10bbbbbb 10bbbbbb

  So if you are using regexp "/\s/", any character
  contains 0x85 or 0xA0 bit sequences will by matched.

  For example:
 */

// 忠 => E5 BF A0 => 11100101 10111111 10100000
echo preg_match('/\s/', '忠') . "\n";  // => 1
echo preg_match('/\s/', '濠') . "\n";  // => 1
echo preg_match('/\s/', '翠') . "\n";  // => 1
echo preg_match('/\s/', '迠') . "\n";  // => 1


/*
  We should only match whitespace character in 0bbbbbbb,
  So the best way is not using "\s", but using "[\t\n\f\r ]"
*/
print_r(whitespace_characters_in_ascii('/[\t\n\f\r ]/'));




function whitespace_characters_in_ascii ($whitespace_regexp) {
  $result = array();
  for ($i = 0; $i <= 255; $i++) {
    if (preg_match($whitespace_regexp, chr($i))) {
      $hex = sprintf("0x%02X", $i);
      array_push($result, $hex);
    }
  }
  return $result;
}