voku /
portable-utf8
| @@ 2756-2803 (lines=48) @@ | ||
| 2753 | * <strong>2</strong> for UTF-16BE. |
|
| 2754 | * </p> |
|
| 2755 | */ |
|
| 2756 | public static function is_utf16($str) |
|
| 2757 | { |
|
| 2758 | $str = self::remove_bom($str); |
|
| 2759 | ||
| 2760 | if (self::is_binary($str)) { |
|
| 2761 | ||
| 2762 | $maybeUTF16LE = 0; |
|
| 2763 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16LE'); |
|
| 2764 | if ($test) { |
|
| 2765 | $test2 = \mb_convert_encoding($test, 'UTF-16LE', 'UTF-8'); |
|
| 2766 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16LE'); |
|
| 2767 | if ($test3 === $test) { |
|
| 2768 | $strChars = self::count_chars($str, true); |
|
| 2769 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2770 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2771 | $maybeUTF16LE++; |
|
| 2772 | } |
|
| 2773 | } |
|
| 2774 | } |
|
| 2775 | } |
|
| 2776 | ||
| 2777 | $maybeUTF16BE = 0; |
|
| 2778 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16BE'); |
|
| 2779 | if ($test) { |
|
| 2780 | $test2 = \mb_convert_encoding($test, 'UTF-16BE', 'UTF-8'); |
|
| 2781 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16BE'); |
|
| 2782 | if ($test3 === $test) { |
|
| 2783 | $strChars = self::count_chars($str, true); |
|
| 2784 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2785 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2786 | $maybeUTF16BE++; |
|
| 2787 | } |
|
| 2788 | } |
|
| 2789 | } |
|
| 2790 | } |
|
| 2791 | ||
| 2792 | if ($maybeUTF16BE !== $maybeUTF16LE) { |
|
| 2793 | if ($maybeUTF16LE > $maybeUTF16BE) { |
|
| 2794 | return 1; |
|
| 2795 | } else { |
|
| 2796 | return 2; |
|
| 2797 | } |
|
| 2798 | } |
|
| 2799 | ||
| 2800 | } |
|
| 2801 | ||
| 2802 | return false; |
|
| 2803 | } |
|
| 2804 | ||
| 2805 | /** |
|
| 2806 | * Check if the string is UTF-32. |
|
| @@ 2816-2863 (lines=48) @@ | ||
| 2813 | * <strong>2</strong> for UTF-32BE. |
|
| 2814 | * </p> |
|
| 2815 | */ |
|
| 2816 | public static function is_utf32($str) |
|
| 2817 | { |
|
| 2818 | $str = self::remove_bom($str); |
|
| 2819 | ||
| 2820 | if (self::is_binary($str)) { |
|
| 2821 | ||
| 2822 | $maybeUTF32LE = 0; |
|
| 2823 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32LE'); |
|
| 2824 | if ($test) { |
|
| 2825 | $test2 = \mb_convert_encoding($test, 'UTF-32LE', 'UTF-8'); |
|
| 2826 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32LE'); |
|
| 2827 | if ($test3 === $test) { |
|
| 2828 | $strChars = self::count_chars($str, true); |
|
| 2829 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2830 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2831 | $maybeUTF32LE++; |
|
| 2832 | } |
|
| 2833 | } |
|
| 2834 | } |
|
| 2835 | } |
|
| 2836 | ||
| 2837 | $maybeUTF32BE = 0; |
|
| 2838 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32BE'); |
|
| 2839 | if ($test) { |
|
| 2840 | $test2 = \mb_convert_encoding($test, 'UTF-32BE', 'UTF-8'); |
|
| 2841 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32BE'); |
|
| 2842 | if ($test3 === $test) { |
|
| 2843 | $strChars = self::count_chars($str, true); |
|
| 2844 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2845 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2846 | $maybeUTF32BE++; |
|
| 2847 | } |
|
| 2848 | } |
|
| 2849 | } |
|
| 2850 | } |
|
| 2851 | ||
| 2852 | if ($maybeUTF32BE !== $maybeUTF32LE) { |
|
| 2853 | if ($maybeUTF32LE > $maybeUTF32BE) { |
|
| 2854 | return 1; |
|
| 2855 | } else { |
|
| 2856 | return 2; |
|
| 2857 | } |
|
| 2858 | } |
|
| 2859 | ||
| 2860 | } |
|
| 2861 | ||
| 2862 | return false; |
|
| 2863 | } |
|
| 2864 | ||
| 2865 | /** |
|
| 2866 | * Checks whether the passed string contains only byte sequences that appear valid UTF-8 characters. |
|
