unicode.inc 14.7 KB
Newer Older
1 2 3 4 5 6 7
<?php
// $Id$

define('UNICODE_ERROR', -1);
define('UNICODE_SINGLEBYTE', 0);
define('UNICODE_MULTIBYTE', 1);

8 9 10 11 12 13 14
/**
 * Wrapper around _unicode_check().
 */
function unicode_check() {
  $GLOBALS['multibyte'] = _unicode_check();
}

15 16 17 18 19 20 21 22 23 24 25
/**
 * Perform checks about Unicode support in PHP, and set the right settings if
 * needed.
 *
 * Because Drupal needs to be able to handle text in various encodings, we do
 * not support mbstring function overloading. HTTP input/output conversion must
 * be disabled for similar reasons.
 *
 * @param $errors
 *   Whether to report any fatal errors with form_set_error().
 */
26
function _unicode_check($errors = false) {
27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79
  // Set the standard C locale to ensure consistent, ASCII-only string handling.
  setlocale(LC_CTYPE, 'C');

  // Check for outdated PCRE library
  // Note: we check if U+E2 is in the range U+E0 - U+E1. This test returns TRUE on old PCRE versions.
  if (preg_match('/[à-á]/u', 'â')) {
    if ($errors) {
      form_set_error('unicode', t('The PCRE library in your PHP installation is outdated. This will cause problems when handling Unicode text. If you are running PHP 4.3.3 or higher, make sure you are using the PCRE library supplied by PHP. Please refer to the <a href="%url">PHP PCRE documentation</a> for more information.', array('%url' => 'http://be.php.net/manual/nl/ref.pcre.php')));
    }
    return UNICODE_ERROR;
  }

  // Check for mbstring extension
  if (!function_exists('mb_strlen')) {
    return UNICODE_SINGLEBYTE;
  }

  // Check mbstring configuration
  if (ini_get('mbstring.func_overload') != 0) {
    if ($errors) {
      form_set_error('unicode', t('Multibyte string function overloading in PHP is active and must be disabled. Check the php.ini <em>mbstring.func_overload</em> setting. Please refer to the <a href="%url">PHP mbstring documentation</a> for more information.', array('%url' => 'http://www.php.net/manual/nl/ref.mbstring.php')));
    }
    return UNICODE_ERROR;
  }
  if (ini_get('mbstring.encoding_translation') != 0) {
    if ($errors) {
      form_set_error('unicode', t('Multibyte string input conversion in PHP is active and must be disabled. Check the php.ini <em>mbstring.encoding_translation</em> setting. Please refer to the <a href="%url">PHP mbstring documentation</a> for more information.', array('%url' => 'http://www.php.net/manual/nl/ref.mbstring.php')));
    }
    return UNICODE_ERROR;
  }
  if (ini_get('mbstring.http_input') != 'pass') {
    if ($errors) {
      form_set_error('unicode', t('Multibyte string input conversion in PHP is active and must be disabled. Check the php.ini <em>mbstring.http_input</em> setting. Please refer to the <a href="%url">PHP mbstring documentation</a> for more information.', array('%url' => 'http://www.php.net/manual/nl/ref.mbstring.php')));
    }
    return UNICODE_ERROR;
  }  
  if (ini_get('mbstring.http_output') != 'pass') {
    if ($errors) {
      form_set_error('unicode', t('Multibyte string output conversion in PHP is active and must be disabled. Check the php.ini <em>mbstring.http_output</em> setting. Please refer to the <a href="%url">PHP mbstring documentation</a> for more information.', array('%url' => 'http://www.php.net/manual/nl/ref.mbstring.php')));
    }
    return UNICODE_ERROR;
  }

  // Set appropriate configuration
  mb_internal_encoding('utf-8');
  mb_language('uni');
  return UNICODE_MULTIBYTE;
}

/**
 * Return the required Unicode status and errors for admin/settings.
 */
function unicode_settings() {
80
  $status = _unicode_check(true);
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451
  $options = array(UNICODE_SINGLEBYTE => t('Standard PHP: operations on Unicode strings are emulated on a best-effort basis. Install the <a href="%url">PHP mbstring extension</a> for improved Unicode support.', array('%url' => 'http://www.php.net/manual/nl/ref.mbstring.php')),
                   UNICODE_MULTIBYTE => t('Multi-byte: operations on Unicode strings are supported through the <a href="%url">PHP mbstring extension</a>.', array('%url' => 'http://www.php.net/manual/nl/ref.mbstring.php')),
                   UNICODE_ERROR => t('Invalid: the current configuration is incompatible with Drupal.'));
  return form_item(t('String handling method'), $options[$status]);
}

/**
 * Prepare a new XML parser.
 *
 * This is a wrapper around xml_parser_create() which extracts the encoding from
 * the XML data first and sets the output encoding to UTF-8. This function should
 * be used instead of xml_parser_create(), because PHP's XML parser doesn't check
 * the input encoding itself.
 *
 * This is also where unsupported encodings will be converted.
 * Callers should take this into account: $data might have been changed after
 * the call.
 *
 * @param &$data
 *   The XML data which will be parsed later.
 * @return
 *   An XML parser object.
 */
function drupal_xml_parser_create(&$data) {
  // Default XML encoding is UTF-8
  $encoding = 'utf-8';
  $bom = false;

  // Check for UTF-8 byte order mark (PHP5's XML parser doesn't handle it).
  if (!strncmp($data, "\xEF\xBB\xBF", 3)) {
    $bom = true;
    $data = substr($data, 3);
  }

  // Check for an encoding declaration in the XML prolog if no BOM was found.
  if (!$bom && ereg('^<\?xml[^>]+encoding="([^"]+)"', $data, $match)) {
    $encoding = $match[1];
  }

  // Unsupported encodings are converted here into UTF-8.
  $php_supported = array('utf-8', 'iso-8859-1', 'us-ascii');
  if (!in_array(strtolower($encoding), $php_supported)) {
    $out = drupal_convert_to_utf8($data, $encoding);
    if ($out !== false) {
      $data = $out;
      $encoding = 'utf-8';
    }
    else {
      watchdog('php', t("Could not convert XML encoding '%s' to UTF-8.", array('%s' => $encoding)), WATCHDOG_WARNING);
      return 0;
    }
  }

  $xml_parser = xml_parser_create($encoding);
  xml_parser_set_option($xml_parser, XML_OPTION_TARGET_ENCODING, 'utf-8');
  return $xml_parser;
}

/**
 * Convert data to UTF-8
 *
 * Requires the iconv, GNU recode or mbstring PHP extension.
 *
 * @param $data
 *   The data to be converted.
 * @param $encoding
 *   The encoding that the data is in
 * @return
 *   Converted data or FALSE.
 */
function drupal_convert_to_utf8($data, $encoding) {
  if (function_exists('iconv')) {
    $out = @iconv($encoding, 'utf-8', $data);
  }
  else if (function_exists('mb_convert_encoding')) {
    $out = @mb_convert_encoding($data, 'utf-8', $encoding);
  }
  else if (function_exists('recode_string')) {
    $out = @recode_string($encoding .'..utf-8', $data);
  }
  else {
    watchdog('php', t("Unsupported encoding '%s'. Please install iconv, GNU recode or mbstring for PHP.", array('%s' => $encoding)), WATCHDOG_ERROR);
    return FALSE;
  }

  return $out;
}

/**
 * Truncate a UTF-8-encoded string safely to a number of bytes.
 *
 * If the end position is in the middle of a UTF-8 sequence, it scans backwards
 * until the beginning of the byte sequence.
 *
 * Use this function whenever you want to chop off a string at an unsure
 * location. On the other hand, if you're sure that you're splitting on a
 * character boundary (e.g. after using strpos() or similar), you can safely use
 * substr() instead.
 *
 * @param $string
 *   The string to truncate.
 * @param $len
 *   An upper limit on the returned string length.
 * @param $wordsafe
 *   Flag to truncate at nearest space. Defaults to FALSE.
 * @return
 *   The truncated string.
 */
function truncate_utf8($string, $len, $wordsafe = FALSE, $dots = FALSE) {
  $slen = strlen($string);
  if ($slen <= $len) {
    return $string;
  }
  if ($wordsafe) {
    while (($string{--$len} != ' ') && ($len > 0)) {};
  }
  if ((ord($string{$len}) < 0x80) || (ord($string{$len}) >= 0xC0)) {
    return substr($string, 0, $len) . ($dots ? ' ...' : '');
  }
  while (ord($string{--$len}) < 0xC0) {};
  return substr($string, 0, $len) . ($dots ? ' ...' : '');
}

/**
 * Encodes MIME/HTTP header values that contain non-ASCII, UTF-8 encoded
 * characters.
 *
 * For example, mime_header_encode('tést.txt') returns "=?UTF-8?B?dMOpc3QudHh0?=".
 *
 * See http://www.rfc-editor.org/rfc/rfc2047.txt for more information.
 *
 * Notes:
 * - Only encode strings that contain non-ASCII characters.
 * - We progressively cut-off a chunk with truncate_utf8(). This is to ensure
 *   each chunk starts and ends on a character boundary.
 * - Using \n as the chunk separator may cause problems on some systems and may
 *   have to be changed to \r\n or \r.
 */
function mime_header_encode($string) {
  if (!preg_match('/^[\x20-\x7E]*$/', $string)) {
    $chunk_size = 47; // floor((75 - strlen("=?UTF-8?B??=")) * 0.75);
    $len = strlen($string);
    $output = '';
    while ($len > 0) {
      $chunk = truncate_utf8($string, $chunk_size);
      $output .= ' =?UTF-8?B?'. base64_encode($chunk) ."?=\n";
      $c = strlen($chunk);
      $string = substr($string, $c);
      $len -= $c;
    }
    return trim($output);
  }
  return $string;
}

/**
 * Decode all HTML entities (including numerical ones) to regular UTF-8 bytes.
 * Double-escaped entities will only be decoded once ("&amp;lt;" becomes "&lt;", not "<").
 *
 * @param $text
 *   The text to decode entities in.
 * @param $exclude
 *   An array of characters which should not be decoded. For example,
 *   array('<', '&', '"'). This affects both named and numerical entities.
 */
function decode_entities($text, $exclude = array()) {
  static $table;
  // We store named entities in a table for quick processing.
  if (!isset($table)) {
    // Get all named HTML entities.
    $table = array_flip(get_html_translation_table(HTML_ENTITIES));
    // PHP gives us ISO-8859-1 data, we need UTF-8.
    $table = array_map('utf8_encode', $table);
    // Add apostrophe (XML)
    $table['&apos;'] = "'";
  }
  $newtable = array_diff($table, $exclude);

  // Use a regexp to select all entities in one pass, to avoid decoding double-escaped entities twice.
  return preg_replace('/&(#x?)?([A-Za-z0-9]+);/e', '_decode_entities("$1", "$2", "$0", $newtable, $exclude)', $text);
}

/**
 * Helper function for decode_entities
 */
function _decode_entities($prefix, $codepoint, $original, &$table, &$exclude) {
  // Named entity
  if (!$prefix) {
    if (isset($table[$original])) {
      return $table[$original];
    }
    else {
      return $original;
    }
  }
  // Hexadecimal numerical entity
  if ($prefix == '#x') {
    $codepoint = base_convert($codepoint, 16, 10);
  }
  // Encode codepoint as UTF-8 bytes
  if ($codepoint < 0x80) {
    $str = chr($codepoint);
  }
  else if ($codepoint < 0x800) {
    $str = chr(0xC0 | ($codepoint >> 6))
         . chr(0x80 | ($codepoint & 0x3F));
  }
  else if ($codepoint < 0x10000) {
    $str = chr(0xE0 | ( $codepoint >> 12))
         . chr(0x80 | (($codepoint >> 6) & 0x3F))
         . chr(0x80 | ( $codepoint       & 0x3F));
  }
  else if ($codepoint < 0x200000) {
    $str = chr(0xF0 | ( $codepoint >> 18))
         . chr(0x80 | (($codepoint >> 12) & 0x3F))
         . chr(0x80 | (($codepoint >> 6)  & 0x3F))
         . chr(0x80 | ( $codepoint        & 0x3F));
  }
  // Check for excluded characters
  if (in_array($str, $exclude)) {
    return $original;
  }
  else {
    return $str;
  }
}

/**
 * Count the amount of characters in a UTF-8 string. This is less than or
 * equal to the byte count.
 */
function drupal_strlen($text) {
  global $multibyte;
  if ($multibyte == UNICODE_MULTIBYTE) {
    return mb_strlen($text);
  }
  else {
    // Do not count UTF-8 continuation bytes.
    return strlen(preg_replace("/[\x80-\xBF]/", '', $text));
  }
}

/**
 * Uppercase a UTF-8 string.
 */
function drupal_strtoupper($text) {
  global $multibyte;
  if ($multibyte == UNICODE_MULTIBYTE) {  
    return mb_strtoupper($text);
  }
  else {
    // Use C-locale for ASCII-only uppercase
    $text = strtoupper($text);
    // Case flip Latin-1 accented letters
    $text = preg_replace_callback('/\xC3[\xA0-\xB6\xB8-\xBE]/', '_unicode_caseflip', $text);
    return $text;
  }  
}

/**
 * Lowercase a UTF-8 string.
 */
function drupal_strtolower($text) {
  global $multibyte;
  if ($multibyte == UNICODE_MULTIBYTE) {
    return mb_strtolower($text);
  }
  else {
    // Use C-locale for ASCII-only lowercase
    $text = strtolower($text);
    // Case flip Latin-1 accented letters
    $text = preg_replace_callback('/\xC3[\x80-\x96\x98-\x9E]/', '_unicode_caseflip', $text);
    return $text;
  }  
}

/**
 * Helper function for case conversion of Latin-1.
 * Used for flipping U+C0-U+DE to U+E0-U+FD and back.
 */
function _unicode_caseflip($matches) {
  return $matches[0]{0} . chr(ord($matches[0]{1}) ^ 32);
}

/**
 * Capitalize the first letter of a UTF-8 string.
 */
function drupal_ucfirst($text) {
  // Note: no mbstring equivalent!
  return drupal_strtoupper(drupal_substr($text, 0, 1)) . drupal_substr($text, 1);
}

/**
 * Cut off a piece of a string based on character indices and counts. Follows
 * the same behaviour as PHP's own substr() function.
 *
 * Note that for cutting off a string at a known character/substring
 * location, the usage of PHP's normal strpos/substr is safe and
 * much faster.
 */
function drupal_substr($text, $start, $length = NULL) {
  global $multibyte;
  if ($multibyte == UNICODE_MULTIBYTE) {
    return $length === NULL ? mb_substr($text, $start) : mb_substr($text, $start, $length);
  }
  else {
    $strlen = strlen($text);
    // Find the starting byte offset
    if ($start > 0) {
      // Count all the continuation bytes from the start until we have found
      // $start characters
      $bytes = -1; $chars = -1;
      while ($bytes < $strlen && $chars < $start) {
        $bytes++;
        $c = ord($text{$bytes});
        if ($c < 0x80 || $c >= 0xC0) {
          $chars++;
        }
      }
    }
    else if ($start < 0) {
      // Count all the continuation bytes from the end until we have found
      // abs($start) characters
      $start = abs($start);
      $bytes = $strlen; $chars = 0;
      while ($bytes > 0 && $chars < $start) {
        $bytes--;
        $c = ord($text{$bytes});
        if ($c < 0x80 || $c >= 0xC0) {
          $chars++;
        }
      }
    }
    $istart = $bytes;

    // Find the ending byte offset
    if ($length === NULL) {
      $bytes = $strlen - 1;
    }
    else if ($length > 0) {
      // Count all the continuation bytes from the starting index until we have
      // found $length + 1 characters. Then backtrack one byte.
      $bytes = $istart; $chars = 0;
      while ($bytes < $strlen && $chars < $length) {
        $bytes++;
        $c = ord($text{$bytes});
        if ($c < 0x80 || $c >= 0xC0) {
          $chars++;
        }
      }
      $bytes--;
    }
    else if ($length < 0) {
      // Count all the continuation bytes from the end until we have found
      // abs($length) characters
      $length = abs($length);
      $bytes = $strlen - 1; $chars = 0;
      while ($bytes >= 0 && $chars < $length) {
        $c = ord($text{$bytes});
        if ($c < 0x80 || $c >= 0xC0) {
          $chars++;
        }
        $bytes--;
      }
    }
    $iend = $bytes;

    return substr($text, $istart, max(0, $iend - $istart + 1));
  }  
}