voku /
portable-utf8
| @@ 2794-2841 (lines=48) @@ | ||
| 2791 | * <strong>2</strong> for UTF-16BE. |
|
| 2792 | * </p> |
|
| 2793 | */ |
|
| 2794 | public static function is_utf16($str) |
|
| 2795 | { |
|
| 2796 | $str = self::remove_bom($str); |
|
| 2797 | ||
| 2798 | if (self::is_binary($str)) { |
|
| 2799 | ||
| 2800 | $maybeUTF16LE = 0; |
|
| 2801 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16LE'); |
|
| 2802 | if ($test) { |
|
| 2803 | $test2 = \mb_convert_encoding($test, 'UTF-16LE', 'UTF-8'); |
|
| 2804 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16LE'); |
|
| 2805 | if ($test3 === $test) { |
|
| 2806 | $strChars = self::count_chars($str, true); |
|
| 2807 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2808 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2809 | $maybeUTF16LE++; |
|
| 2810 | } |
|
| 2811 | } |
|
| 2812 | } |
|
| 2813 | } |
|
| 2814 | ||
| 2815 | $maybeUTF16BE = 0; |
|
| 2816 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16BE'); |
|
| 2817 | if ($test) { |
|
| 2818 | $test2 = \mb_convert_encoding($test, 'UTF-16BE', 'UTF-8'); |
|
| 2819 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16BE'); |
|
| 2820 | if ($test3 === $test) { |
|
| 2821 | $strChars = self::count_chars($str, true); |
|
| 2822 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2823 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2824 | $maybeUTF16BE++; |
|
| 2825 | } |
|
| 2826 | } |
|
| 2827 | } |
|
| 2828 | } |
|
| 2829 | ||
| 2830 | if ($maybeUTF16BE !== $maybeUTF16LE) { |
|
| 2831 | if ($maybeUTF16LE > $maybeUTF16BE) { |
|
| 2832 | return 1; |
|
| 2833 | } else { |
|
| 2834 | return 2; |
|
| 2835 | } |
|
| 2836 | } |
|
| 2837 | ||
| 2838 | } |
|
| 2839 | ||
| 2840 | return false; |
|
| 2841 | } |
|
| 2842 | ||
| 2843 | /** |
|
| 2844 | * Check if the string is UTF-32. |
|
| @@ 2854-2901 (lines=48) @@ | ||
| 2851 | * <strong>2</strong> for UTF-32BE. |
|
| 2852 | * </p> |
|
| 2853 | */ |
|
| 2854 | public static function is_utf32($str) |
|
| 2855 | { |
|
| 2856 | $str = self::remove_bom($str); |
|
| 2857 | ||
| 2858 | if (self::is_binary($str)) { |
|
| 2859 | ||
| 2860 | $maybeUTF32LE = 0; |
|
| 2861 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32LE'); |
|
| 2862 | if ($test) { |
|
| 2863 | $test2 = \mb_convert_encoding($test, 'UTF-32LE', 'UTF-8'); |
|
| 2864 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32LE'); |
|
| 2865 | if ($test3 === $test) { |
|
| 2866 | $strChars = self::count_chars($str, true); |
|
| 2867 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2868 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2869 | $maybeUTF32LE++; |
|
| 2870 | } |
|
| 2871 | } |
|
| 2872 | } |
|
| 2873 | } |
|
| 2874 | ||
| 2875 | $maybeUTF32BE = 0; |
|
| 2876 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32BE'); |
|
| 2877 | if ($test) { |
|
| 2878 | $test2 = \mb_convert_encoding($test, 'UTF-32BE', 'UTF-8'); |
|
| 2879 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32BE'); |
|
| 2880 | if ($test3 === $test) { |
|
| 2881 | $strChars = self::count_chars($str, true); |
|
| 2882 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2883 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2884 | $maybeUTF32BE++; |
|
| 2885 | } |
|
| 2886 | } |
|
| 2887 | } |
|
| 2888 | } |
|
| 2889 | ||
| 2890 | if ($maybeUTF32BE !== $maybeUTF32LE) { |
|
| 2891 | if ($maybeUTF32LE > $maybeUTF32BE) { |
|
| 2892 | return 1; |
|
| 2893 | } else { |
|
| 2894 | return 2; |
|
| 2895 | } |
|
| 2896 | } |
|
| 2897 | ||
| 2898 | } |
|
| 2899 | ||
| 2900 | return false; |
|
| 2901 | } |
|
| 2902 | ||
| 2903 | /** |
|
| 2904 | * Checks whether the passed string contains only byte sequences that appear valid UTF-8 characters. |
|
