voku /
portable-utf8
| @@ 2892-2939 (lines=48) @@ | ||
| 2889 | * <strong>2</strong> for UTF-16BE. |
|
| 2890 | * </p> |
|
| 2891 | */ |
|
| 2892 | public static function is_utf16($str) |
|
| 2893 | { |
|
| 2894 | $str = self::remove_bom($str); |
|
| 2895 | ||
| 2896 | if (self::is_binary($str) === true) { |
|
| 2897 | ||
| 2898 | $maybeUTF16LE = 0; |
|
| 2899 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16LE'); |
|
| 2900 | if ($test) { |
|
| 2901 | $test2 = \mb_convert_encoding($test, 'UTF-16LE', 'UTF-8'); |
|
| 2902 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16LE'); |
|
| 2903 | if ($test3 === $test) { |
|
| 2904 | $strChars = self::count_chars($str, true); |
|
| 2905 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2906 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2907 | $maybeUTF16LE++; |
|
| 2908 | } |
|
| 2909 | } |
|
| 2910 | } |
|
| 2911 | } |
|
| 2912 | ||
| 2913 | $maybeUTF16BE = 0; |
|
| 2914 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16BE'); |
|
| 2915 | if ($test) { |
|
| 2916 | $test2 = \mb_convert_encoding($test, 'UTF-16BE', 'UTF-8'); |
|
| 2917 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16BE'); |
|
| 2918 | if ($test3 === $test) { |
|
| 2919 | $strChars = self::count_chars($str, true); |
|
| 2920 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2921 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2922 | $maybeUTF16BE++; |
|
| 2923 | } |
|
| 2924 | } |
|
| 2925 | } |
|
| 2926 | } |
|
| 2927 | ||
| 2928 | if ($maybeUTF16BE !== $maybeUTF16LE) { |
|
| 2929 | if ($maybeUTF16LE > $maybeUTF16BE) { |
|
| 2930 | return 1; |
|
| 2931 | } else { |
|
| 2932 | return 2; |
|
| 2933 | } |
|
| 2934 | } |
|
| 2935 | ||
| 2936 | } |
|
| 2937 | ||
| 2938 | return false; |
|
| 2939 | } |
|
| 2940 | ||
| 2941 | /** |
|
| 2942 | * Check if the string is UTF-32. |
|
| @@ 2952-2999 (lines=48) @@ | ||
| 2949 | * <strong>2</strong> for UTF-32BE. |
|
| 2950 | * </p> |
|
| 2951 | */ |
|
| 2952 | public static function is_utf32($str) |
|
| 2953 | { |
|
| 2954 | $str = self::remove_bom($str); |
|
| 2955 | ||
| 2956 | if (self::is_binary($str) === true) { |
|
| 2957 | ||
| 2958 | $maybeUTF32LE = 0; |
|
| 2959 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32LE'); |
|
| 2960 | if ($test) { |
|
| 2961 | $test2 = \mb_convert_encoding($test, 'UTF-32LE', 'UTF-8'); |
|
| 2962 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32LE'); |
|
| 2963 | if ($test3 === $test) { |
|
| 2964 | $strChars = self::count_chars($str, true); |
|
| 2965 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2966 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2967 | $maybeUTF32LE++; |
|
| 2968 | } |
|
| 2969 | } |
|
| 2970 | } |
|
| 2971 | } |
|
| 2972 | ||
| 2973 | $maybeUTF32BE = 0; |
|
| 2974 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32BE'); |
|
| 2975 | if ($test) { |
|
| 2976 | $test2 = \mb_convert_encoding($test, 'UTF-32BE', 'UTF-8'); |
|
| 2977 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32BE'); |
|
| 2978 | if ($test3 === $test) { |
|
| 2979 | $strChars = self::count_chars($str, true); |
|
| 2980 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2981 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2982 | $maybeUTF32BE++; |
|
| 2983 | } |
|
| 2984 | } |
|
| 2985 | } |
|
| 2986 | } |
|
| 2987 | ||
| 2988 | if ($maybeUTF32BE !== $maybeUTF32LE) { |
|
| 2989 | if ($maybeUTF32LE > $maybeUTF32BE) { |
|
| 2990 | return 1; |
|
| 2991 | } else { |
|
| 2992 | return 2; |
|
| 2993 | } |
|
| 2994 | } |
|
| 2995 | ||
| 2996 | } |
|
| 2997 | ||
| 2998 | return false; |
|
| 2999 | } |
|
| 3000 | ||
| 3001 | /** |
|
| 3002 | * Checks whether the passed string contains only byte sequences that appear valid UTF-8 characters. |
|
