/usr/share/php/Horde/String.php is in php-horde-util 2.5.7-1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 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 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 | <?php
/**
* Provides static methods for charset and locale safe string manipulation.
*
* Copyright 2003-2016 Horde LLC (http://www.horde.org/)
*
* See the enclosed file COPYING for license information (LGPL). If you
* did not receive this file, see http://www.horde.org/licenses/lgpl21.
*
* @todo Split up in Horde_String_Multibyte for multibyte-safe methods and
* Horde_String_Locale for locale-safe methods.
*
* @author Jan Schneider <jan@horde.org>
* @category Horde
* @license http://www.horde.org/licenses/lgpl21 LGPL 2.1
* @package Util
*/
class Horde_String
{
/**
* lower() cache.
*
* @var array
*/
protected static $_lowers = array();
/**
* upper() cache.
*
* @var array
*/
protected static $_uppers = array();
/**
* Converts a string from one charset to another.
*
* Uses the iconv or the mbstring extensions.
* The original string is returned if conversion failed or none
* of the extensions were available.
*
* @param mixed $input The data to be converted. If $input is an an
* array, the array's values get converted
* recursively.
* @param string $from The string's current charset.
* @param string $to The charset to convert the string to.
* @param boolean $force Force conversion?
*
* @return mixed The converted input data.
*/
public static function convertCharset($input, $from, $to, $force = false)
{
/* Don't bother converting numbers. */
if (is_numeric($input)) {
return $input;
}
/* If the from and to character sets are identical, return now. */
if (!$force && $from == $to) {
return $input;
}
$from = self::lower($from);
$to = self::lower($to);
if (!$force && $from == $to) {
return $input;
}
if (is_array($input)) {
$tmp = array();
reset($input);
while (list($key, $val) = each($input)) {
$tmp[self::_convertCharset($key, $from, $to)] = self::convertCharset($val, $from, $to, $force);
}
return $tmp;
}
if (is_object($input)) {
// PEAR_Error/Exception objects are almost guaranteed to contain
// recursion, which will cause a segfault in PHP. We should never
// reach this line, but add a check.
if (($input instanceof Exception) ||
($input instanceof PEAR_Error)) {
return '';
}
$input = clone $input;
$vars = get_object_vars($input);
while (list($key, $val) = each($vars)) {
$input->$key = self::convertCharset($val, $from, $to, $force);
}
return $input;
}
if (!is_string($input)) {
return $input;
}
return self::_convertCharset($input, $from, $to);
}
/**
* Internal function used to do charset conversion.
*
* @param string $input See self::convertCharset().
* @param string $from See self::convertCharset().
* @param string $to See self::convertCharset().
*
* @return string The converted string.
*/
protected static function _convertCharset($input, $from, $to)
{
/* Use utf8_[en|de]code() if possible and if the string isn't too
* large (less than 16 MB = 16 * 1024 * 1024 = 16777216 bytes) - these
* functions use more memory. */
if (Horde_Util::extensionExists('xml') &&
((strlen($input) < 16777216) ||
!Horde_Util::extensionExists('iconv') ||
!Horde_Util::extensionExists('mbstring'))) {
if (($to == 'utf-8') &&
in_array($from, array('iso-8859-1', 'us-ascii', 'utf-8'))) {
return utf8_encode($input);
}
if (($from == 'utf-8') &&
in_array($to, array('iso-8859-1', 'us-ascii', 'utf-8'))) {
return utf8_decode($input);
}
}
/* Try UTF7-IMAP conversions. */
if (($from == 'utf7-imap') || ($to == 'utf7-imap')) {
try {
if ($from == 'utf7-imap') {
return self::convertCharset(Horde_Imap_Client_Utf7imap::Utf7ImapToUtf8($input), 'UTF-8', $to);
} else {
if ($from == 'utf-8') {
$conv = $input;
} else {
$conv = self::convertCharset($input, $from, 'UTF-8');
}
return Horde_Imap_Client_Utf7imap::Utf8ToUtf7Imap($conv);
}
} catch (Horde_Imap_Client_Exception $e) {
return $input;
}
}
/* Try iconv with transliteration. */
if (Horde_Util::extensionExists('iconv')) {
unset($php_errormsg);
ini_set('track_errors', 1);
$out = @iconv($from, $to . '//TRANSLIT', $input);
$errmsg = isset($php_errormsg);
ini_restore('track_errors');
if (!$errmsg && $out !== false) {
return $out;
}
}
/* Try mbstring. */
if (Horde_Util::extensionExists('mbstring')) {
$out = @mb_convert_encoding($input, $to, self::_mbstringCharset($from));
if (!empty($out)) {
return $out;
}
}
return $input;
}
/**
* Makes a string lowercase.
*
* @param string $string The string to be converted.
* @param boolean $locale If true the string will be converted based on
* a given charset, locale independent else.
* @param string $charset If $locale is true, the charset to use when
* converting.
*
* @return string The string with lowercase characters.
*/
public static function lower($string, $locale = false, $charset = null)
{
if ($locale) {
if (Horde_Util::extensionExists('mbstring')) {
if (is_null($charset)) {
throw new InvalidArgumentException('$charset argument must not be null');
}
$ret = @mb_strtolower($string, self::_mbstringCharset($charset));
if (!empty($ret)) {
return $ret;
}
}
return strtolower($string);
}
if (!isset(self::$_lowers[$string])) {
$language = setlocale(LC_CTYPE, 0);
setlocale(LC_CTYPE, 'C');
self::$_lowers[$string] = strtolower($string);
setlocale(LC_CTYPE, $language);
}
return self::$_lowers[$string];
}
/**
* Makes a string uppercase.
*
* @param string $string The string to be converted.
* @param boolean $locale If true the string will be converted based on a
* given charset, locale independent else.
* @param string $charset If $locale is true, the charset to use when
* converting. If not provided the current charset.
*
* @return string The string with uppercase characters.
*/
public static function upper($string, $locale = false, $charset = null)
{
if ($locale) {
if (Horde_Util::extensionExists('mbstring')) {
if (is_null($charset)) {
throw new InvalidArgumentException('$charset argument must not be null');
}
$ret = @mb_strtoupper($string, self::_mbstringCharset($charset));
if (!empty($ret)) {
return $ret;
}
}
return strtoupper($string);
}
if (!isset(self::$_uppers[$string])) {
$language = setlocale(LC_CTYPE, 0);
setlocale(LC_CTYPE, 'C');
self::$_uppers[$string] = strtoupper($string);
setlocale(LC_CTYPE, $language);
}
return self::$_uppers[$string];
}
/**
* Returns a string with the first letter capitalized if it is
* alphabetic.
*
* @param string $string The string to be capitalized.
* @param boolean $locale If true the string will be converted based on a
* given charset, locale independent else.
* @param string $charset The charset to use, defaults to current charset.
*
* @return string The capitalized string.
*/
public static function ucfirst($string, $locale = false, $charset = null)
{
if ($locale) {
if (is_null($charset)) {
throw new InvalidArgumentException('$charset argument must not be null');
}
$first = self::substr($string, 0, 1, $charset);
if (self::isAlpha($first, $charset)) {
$string = self::upper($first, true, $charset) . self::substr($string, 1, null, $charset);
}
} else {
$string = self::upper(substr($string, 0, 1), false) . substr($string, 1);
}
return $string;
}
/**
* Returns a string with the first letter of each word capitalized if it is
* alphabetic.
*
* Sentences are splitted into words at whitestrings.
*
* @param string $string The string to be capitalized.
* @param boolean $locale If true the string will be converted based on a
* given charset, locale independent else.
* @param string $charset The charset to use, defaults to current charset.
*
* @return string The capitalized string.
*/
public static function ucwords($string, $locale = false, $charset = null)
{
$words = preg_split('/(\s+)/', $string, -1, PREG_SPLIT_DELIM_CAPTURE);
for ($i = 0, $c = count($words); $i < $c; $i += 2) {
$words[$i] = self::ucfirst($words[$i], $locale, $charset);
}
return implode('', $words);
}
/**
* Returns part of a string.
*
* @param string $string The string to be converted.
* @param integer $start The part's start position, zero based.
* @param integer $length The part's length.
* @param string $charset The charset to use when calculating the part's
* position and length, defaults to current
* charset.
*
* @return string The string's part.
*/
public static function substr($string, $start, $length = null,
$charset = 'UTF-8')
{
if (is_null($length)) {
$length = self::length($string, $charset) - $start;
}
if ($length === 0) {
return '';
}
$error = false;
/* Try mbstring. */
if (Horde_Util::extensionExists('mbstring')) {
$ret = @mb_substr($string, $start, $length, self::_mbstringCharset($charset));
/* mb_substr() returns empty string on failure. */
if (strlen($ret)) {
return $ret;
}
$error = true;
}
/* Try iconv. */
if (Horde_Util::extensionExists('iconv')) {
$ret = @iconv_substr($string, $start, $length, $charset);
/* iconv_substr() returns false on failure. */
if ($ret !== false) {
return $ret;
}
$error = true;
}
/* Try intl. */
if (Horde_Util::extensionExists('intl')) {
$ret = self::convertCharset(
@grapheme_substr(
self::convertCharset($string, $charset, 'UTF-8'),
$start,
$length
),
'UTF-8',
$charset
);
/* grapheme_substr() returns false on failure. */
if ($ret !== false) {
return $ret;
}
$error = true;
}
return $error
? ''
: substr($string, $start, $length);
}
/**
* Returns the character (not byte) length of a string.
*
* @param string $string The string to return the length of.
* @param string $charset The charset to use when calculating the string's
* length.
*
* @return integer The string's length.
*/
public static function length($string, $charset = 'UTF-8')
{
$charset = self::lower($charset);
if ($charset == 'utf-8' || $charset == 'utf8') {
return strlen(utf8_decode($string));
}
if (Horde_Util::extensionExists('mbstring')) {
$ret = @mb_strlen($string, self::_mbstringCharset($charset));
if (!empty($ret)) {
return $ret;
}
}
if (Horde_Util::extensionExists('intl')) {
return grapheme_strlen(
self::convertCharset($string, $charset, 'UTF-8')
);
}
return strlen($string);
}
/**
* Returns the numeric position of the first occurrence of $needle
* in the $haystack string.
*
* @param string $haystack The string to search through.
* @param string $needle The string to search for.
* @param integer $offset Character in $haystack to start searching at.
* @param string $charset Charset of $needle.
*
* @return integer The position of first occurrence.
*/
public static function pos(
$haystack, $needle, $offset = 0, $charset = 'UTF-8'
)
{
return self::_pos($haystack, $needle, $offset, $charset, 'strpos');
}
/**
* Returns the numeric position of the first case-insensitive occurrence
* of $needle in the $haystack string.
*
* @since 2.5.0
*
* @param string $haystack The string to search through.
* @param string $needle The string to search for.
* @param integer $offset Character in $haystack to start searching at.
* @param string $charset Charset of $needle.
*
* @return integer The position of first case-insensitive occurrence.
*/
public static function ipos(
$haystack, $needle, $offset = 0, $charset = 'UTF-8'
)
{
return self::_pos($haystack, $needle, $offset, $charset, 'stripos');
}
/**
* Returns the numeric position of the last occurrence of $needle
* in the $haystack string.
*
* @param string $haystack The string to search through.
* @param string $needle The string to search for.
* @param integer $offset Character in $haystack to start searching at.
* @param string $charset Charset of $needle.
*
* @return integer The position of last occurrence.
*/
public static function rpos(
$haystack, $needle, $offset = 0, $charset = 'UTF-8'
)
{
return self::_pos($haystack, $needle, $offset, $charset, 'strrpos');
}
/**
* Returns the numeric position of the last case-insensitive occurrence of
* $needle in the $haystack string.
*
* @since 2.5.0
*
* @param string $haystack The string to search through.
* @param string $needle The string to search for.
* @param integer $offset Character in $haystack to start searching at.
* @param string $charset Charset of $needle.
*
* @return integer The position of last case-insensitive occurrence.
*/
public static function ripos(
$haystack, $needle, $offset = 0, $charset = 'UTF-8'
)
{
return self::_pos($haystack, $needle, $offset, $charset, 'strripos');
}
/**
* Perform string position searches.
*
* @param string $haystack The string to search through.
* @param string $needle The string to search for.
* @param integer $offset Character in $haystack to start searching at.
* @param string $charset Charset of $needle.
* @param string $func Function to use.
*
* @return integer The position of occurrence.
*
*/
protected static function _pos(
$haystack, $needle, $offset, $charset, $func
)
{
if (Horde_Util::extensionExists('mbstring')) {
$track_errors = ini_set('track_errors', 1);
$ret = @call_user_func('mb_' . $func, $haystack, $needle, $offset, self::_mbstringCharset($charset));
ini_set('track_errors', $track_errors);
if (!isset($php_errormsg)) {
return $ret;
}
}
if (Horde_Util::extensionExists('intl')) {
$track_errors = ini_set('track_errors', 1);
$ret = self::convertCharset(
@call_user_func(
'grapheme_' . $func,
self::convertCharset($haystack, $charset, 'UTF-8'),
self::convertCharset($needle, $charset, 'UTF-8'),
$offset
),
'UTF-8',
$charset
);
ini_set('track_errors', $track_errors);
if (!isset($php_errormsg)) {
return $ret;
}
}
return $func($haystack, $needle, $offset);
}
/**
* Returns a string padded to a certain length with another string.
* This method behaves exactly like str_pad() but is multibyte safe.
*
* @param string $input The string to be padded.
* @param integer $length The length of the resulting string.
* @param string $pad The string to pad the input string with. Must
* be in the same charset like the input string.
* @param const $type The padding type. One of STR_PAD_LEFT,
* STR_PAD_RIGHT, or STR_PAD_BOTH.
* @param string $charset The charset of the input and the padding
* strings.
*
* @return string The padded string.
*/
public static function pad($input, $length, $pad = ' ',
$type = STR_PAD_RIGHT, $charset = 'UTF-8')
{
$mb_length = self::length($input, $charset);
$sb_length = strlen($input);
$pad_length = self::length($pad, $charset);
/* Return if we already have the length. */
if ($mb_length >= $length) {
return $input;
}
/* Shortcut for single byte strings. */
if ($mb_length == $sb_length && $pad_length == strlen($pad)) {
return str_pad($input, $length, $pad, $type);
}
switch ($type) {
case STR_PAD_LEFT:
$left = $length - $mb_length;
$output = self::substr(str_repeat($pad, ceil($left / $pad_length)), 0, $left, $charset) . $input;
break;
case STR_PAD_BOTH:
$left = floor(($length - $mb_length) / 2);
$right = ceil(($length - $mb_length) / 2);
$output = self::substr(str_repeat($pad, ceil($left / $pad_length)), 0, $left, $charset) .
$input .
self::substr(str_repeat($pad, ceil($right / $pad_length)), 0, $right, $charset);
break;
case STR_PAD_RIGHT:
$right = $length - $mb_length;
$output = $input . self::substr(str_repeat($pad, ceil($right / $pad_length)), 0, $right, $charset);
break;
}
return $output;
}
/**
* Wraps the text of a message.
*
* @param string $string String containing the text to wrap.
* @param integer $width Wrap the string at this number of
* characters.
* @param string $break Character(s) to use when breaking lines.
* @param boolean $cut Whether to cut inside words if a line
* can't be wrapped.
* @param boolean $line_folding Whether to apply line folding rules per
* RFC 822 or similar. The correct break
* characters including leading whitespace
* have to be specified too.
*
* @return string String containing the wrapped text.
*/
public static function wordwrap($string, $width = 75, $break = "\n",
$cut = false, $line_folding = false)
{
$wrapped = '';
while (self::length($string, 'UTF-8') > $width) {
$line = self::substr($string, 0, $width, 'UTF-8');
$string = self::substr($string, self::length($line, 'UTF-8'), null, 'UTF-8');
// Make sure we didn't cut a word, unless we want hard breaks
// anyway.
if (!$cut && preg_match('/^(.+?)((\s|\r?\n).*)/us', $string, $match)) {
$line .= $match[1];
$string = $match[2];
}
// Wrap at existing line breaks.
if (preg_match('/^(.*?)(\r?\n)(.*)$/su', $line, $match)) {
$wrapped .= $match[1] . $match[2];
$string = $match[3] . $string;
continue;
}
// Wrap at the last colon or semicolon followed by a whitespace if
// doing line folding.
if ($line_folding &&
preg_match('/^(.*?)(;|:)(\s+.*)$/u', $line, $match)) {
$wrapped .= $match[1] . $match[2] . $break;
$string = $match[3] . $string;
continue;
}
// Wrap at the last whitespace of $line.
$sub = $line_folding
? '(.+[^\s])'
: '(.*)';
if (preg_match('/^' . $sub . '(\s+)(.*)$/u', $line, $match)) {
$wrapped .= $match[1] . $break;
$string = ($line_folding ? $match[2] : '') . $match[3] . $string;
continue;
}
// Hard wrap if necessary.
if ($cut) {
$wrapped .= $line . $break;
continue;
}
$wrapped .= $line;
}
return $wrapped . $string;
}
/**
* Wraps the text of a message.
*
* @param string $text String containing the text to wrap.
* @param integer $length Wrap $text at this number of characters.
* @param string $break_char Character(s) to use when breaking lines.
* @param boolean $quote Ignore lines that are wrapped with the '>'
* character (RFC 2646)? If true, we don't
* remove any padding whitespace at the end of
* the string.
*
* @return string String containing the wrapped text.
*/
public static function wrap($text, $length = 80, $break_char = "\n",
$quote = false)
{
$paragraphs = array();
foreach (preg_split('/\r?\n/', $text) as $input) {
if ($quote && (strpos($input, '>') === 0)) {
$line = $input;
} else {
/* We need to handle the Usenet-style signature line
* separately; since the space after the two dashes is
* REQUIRED, we don't want to trim the line. */
if ($input != '-- ') {
$input = rtrim($input);
}
$line = self::wordwrap($input, $length, $break_char);
}
$paragraphs[] = $line;
}
return implode($break_char, $paragraphs);
}
/**
* Return a truncated string, suitable for notifications.
*
* @param string $text The original string.
* @param integer $length The maximum length.
*
* @return string The truncated string, if longer than $length.
*/
public static function truncate($text, $length = 100)
{
return (self::length($text) > $length)
? rtrim(self::substr($text, 0, $length - 3)) . '...'
: $text;
}
/**
* Return an abbreviated string, with characters in the middle of the
* excessively long string replaced by '...'.
*
* @param string $text The original string.
* @param integer $length The length at which to abbreviate.
*
* @return string The abbreviated string, if longer than $length.
*/
public static function abbreviate($text, $length = 20)
{
return (self::length($text) > $length)
? rtrim(self::substr($text, 0, round(($length - 3) / 2))) . '...' . ltrim(self::substr($text, (($length - 3) / 2) * -1))
: $text;
}
/**
* Returns the common leading part of two strings.
*
* @param string $str1 A string.
* @param string $str2 Another string.
*
* @return string The start of $str1 and $str2 that is identical in both.
*/
public static function common($str1, $str2)
{
for ($result = '', $i = 0;
isset($str1[$i]) && isset($str2[$i]) && $str1[$i] == $str2[$i];
$i++) {
$result .= $str1[$i];
}
return $result;
}
/**
* Returns true if the every character in the parameter is an alphabetic
* character.
*
* @param string $string The string to test.
* @param string $charset The charset to use when testing the string.
*
* @return boolean True if the parameter was alphabetic only.
*/
public static function isAlpha($string, $charset)
{
if (!Horde_Util::extensionExists('mbstring')) {
return ctype_alpha($string);
}
$charset = self::_mbstringCharset($charset);
$old_charset = mb_regex_encoding();
if ($charset != $old_charset) {
@mb_regex_encoding($charset);
}
$alpha = !@mb_ereg_match('[^[:alpha:]]', $string);
if ($charset != $old_charset) {
@mb_regex_encoding($old_charset);
}
return $alpha;
}
/**
* Returns true if ever character in the parameter is a lowercase letter in
* the current locale.
*
* @param string $string The string to test.
* @param string $charset The charset to use when testing the string.
*
* @return boolean True if the parameter was lowercase.
*/
public static function isLower($string, $charset)
{
return ((self::lower($string, true, $charset) === $string) &&
self::isAlpha($string, $charset));
}
/**
* Returns true if every character in the parameter is an uppercase letter
* in the current locale.
*
* @param string $string The string to test.
* @param string $charset The charset to use when testing the string.
*
* @return boolean True if the parameter was uppercase.
*/
public static function isUpper($string, $charset)
{
return ((self::upper($string, true, $charset) === $string) &&
self::isAlpha($string, $charset));
}
/**
* Performs a multibyte safe regex match search on the text provided.
*
* @param string $text The text to search.
* @param array $regex The regular expressions to use, without perl
* regex delimiters (e.g. '/' or '|').
* @param string $charset The character set of the text.
*
* @return array The matches array from the first regex that matches.
*/
public static function regexMatch($text, $regex, $charset = null)
{
if (!empty($charset)) {
$regex = self::convertCharset($regex, $charset, 'utf-8');
$text = self::convertCharset($text, $charset, 'utf-8');
}
$matches = array();
foreach ($regex as $val) {
if (preg_match('/' . $val . '/u', $text, $matches)) {
break;
}
}
if (!empty($charset)) {
$matches = self::convertCharset($matches, 'utf-8', $charset);
}
return $matches;
}
/**
* Check to see if a string is valid UTF-8.
*
* @param string $text The text to check.
*
* @return boolean True if valid UTF-8.
*/
public static function validUtf8($text)
{
$text = strval($text);
for ($i = 0, $len = strlen($text); $i < $len; ++$i) {
$c = ord($text[$i]);
if ($c > 128) {
if ($c > 247) {
// STD 63 (RFC 3629) eliminates 5 & 6-byte characters.
return false;
} elseif ($c > 239) {
$j = 3;
} elseif ($c > 223) {
$j = 2;
} elseif ($c > 191) {
$j = 1;
} else {
return false;
}
if (($i + $j) > $len) {
return false;
}
do {
$c = ord($text[++$i]);
if (($c < 128) || ($c > 191)) {
return false;
}
} while (--$j);
}
}
return true;
}
/**
* Workaround charsets that don't work with mbstring functions.
*
* @param string $charset The original charset.
*
* @return string The charset to use with mbstring functions.
*/
protected static function _mbstringCharset($charset)
{
/* mbstring functions do not handle the 'ks_c_5601-1987' &
* 'ks_c_5601-1989' charsets. However, these charsets are used, for
* example, by various versions of Outlook to send Korean characters.
* Use UHC (CP949) encoding instead. See, e.g.,
* http://lists.w3.org/Archives/Public/ietf-charsets/2001AprJun/0030.html */
return in_array(self::lower($charset), array('ks_c_5601-1987', 'ks_c_5601-1989'))
? 'UHC'
: $charset;
}
/**
* Strip UTF-8 byte order mark (BOM) from string data.
*
* @param string $str Input string (UTF-8).
*
* @return string Stripped string (UTF-8).
*/
public static function trimUtf8Bom($str)
{
return (substr($str, 0, 3) == pack('CCC', 239, 187, 191))
? substr($str, 3)
: $str;
}
}
|