voku /
portable-utf8
| @@ 2565-2612 (lines=48) @@ | ||
| 2562 | * <strong>2</strong> for UTF-16BE. |
|
| 2563 | * </p> |
|
| 2564 | */ |
|
| 2565 | public static function is_utf16($str) |
|
| 2566 | { |
|
| 2567 | $str = self::remove_bom($str); |
|
| 2568 | ||
| 2569 | if (self::is_binary($str)) { |
|
| 2570 | ||
| 2571 | $maybeUTF16LE = 0; |
|
| 2572 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16LE'); |
|
| 2573 | if ($test) { |
|
| 2574 | $test2 = \mb_convert_encoding($test, 'UTF-16LE', 'UTF-8'); |
|
| 2575 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16LE'); |
|
| 2576 | if ($test3 === $test) { |
|
| 2577 | $strChars = self::count_chars($str, true); |
|
| 2578 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2579 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2580 | $maybeUTF16LE++; |
|
| 2581 | } |
|
| 2582 | } |
|
| 2583 | } |
|
| 2584 | } |
|
| 2585 | ||
| 2586 | $maybeUTF16BE = 0; |
|
| 2587 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16BE'); |
|
| 2588 | if ($test) { |
|
| 2589 | $test2 = \mb_convert_encoding($test, 'UTF-16BE', 'UTF-8'); |
|
| 2590 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16BE'); |
|
| 2591 | if ($test3 === $test) { |
|
| 2592 | $strChars = self::count_chars($str, true); |
|
| 2593 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2594 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2595 | $maybeUTF16BE++; |
|
| 2596 | } |
|
| 2597 | } |
|
| 2598 | } |
|
| 2599 | } |
|
| 2600 | ||
| 2601 | if ($maybeUTF16BE !== $maybeUTF16LE) { |
|
| 2602 | if ($maybeUTF16LE > $maybeUTF16BE) { |
|
| 2603 | return 1; |
|
| 2604 | } else { |
|
| 2605 | return 2; |
|
| 2606 | } |
|
| 2607 | } |
|
| 2608 | ||
| 2609 | } |
|
| 2610 | ||
| 2611 | return false; |
|
| 2612 | } |
|
| 2613 | ||
| 2614 | /** |
|
| 2615 | * Check if the string is UTF-32. |
|
| @@ 2625-2672 (lines=48) @@ | ||
| 2622 | * <strong>2</strong> for UTF-32BE. |
|
| 2623 | * </p> |
|
| 2624 | */ |
|
| 2625 | public static function is_utf32($str) |
|
| 2626 | { |
|
| 2627 | $str = self::remove_bom($str); |
|
| 2628 | ||
| 2629 | if (self::is_binary($str)) { |
|
| 2630 | ||
| 2631 | $maybeUTF32LE = 0; |
|
| 2632 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32LE'); |
|
| 2633 | if ($test) { |
|
| 2634 | $test2 = \mb_convert_encoding($test, 'UTF-32LE', 'UTF-8'); |
|
| 2635 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32LE'); |
|
| 2636 | if ($test3 === $test) { |
|
| 2637 | $strChars = self::count_chars($str, true); |
|
| 2638 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2639 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2640 | $maybeUTF32LE++; |
|
| 2641 | } |
|
| 2642 | } |
|
| 2643 | } |
|
| 2644 | } |
|
| 2645 | ||
| 2646 | $maybeUTF32BE = 0; |
|
| 2647 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32BE'); |
|
| 2648 | if ($test) { |
|
| 2649 | $test2 = \mb_convert_encoding($test, 'UTF-32BE', 'UTF-8'); |
|
| 2650 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32BE'); |
|
| 2651 | if ($test3 === $test) { |
|
| 2652 | $strChars = self::count_chars($str, true); |
|
| 2653 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2654 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2655 | $maybeUTF32BE++; |
|
| 2656 | } |
|
| 2657 | } |
|
| 2658 | } |
|
| 2659 | } |
|
| 2660 | ||
| 2661 | if ($maybeUTF32BE !== $maybeUTF32LE) { |
|
| 2662 | if ($maybeUTF32LE > $maybeUTF32BE) { |
|
| 2663 | return 1; |
|
| 2664 | } else { |
|
| 2665 | return 2; |
|
| 2666 | } |
|
| 2667 | } |
|
| 2668 | ||
| 2669 | } |
|
| 2670 | ||
| 2671 | return false; |
|
| 2672 | } |
|
| 2673 | ||
| 2674 | /** |
|
| 2675 | * Checks whether the passed string contains only byte sequences that appear valid UTF-8 characters. |
|
