voku /
portable-utf8
| @@ 2956-3003 (lines=48) @@ | ||
| 2953 | * <strong>2</strong> for UTF-16BE. |
|
| 2954 | * </p> |
|
| 2955 | */ |
|
| 2956 | public static function is_utf16($str) |
|
| 2957 | { |
|
| 2958 | $str = self::remove_bom($str); |
|
| 2959 | ||
| 2960 | if (self::is_binary($str) === true) { |
|
| 2961 | ||
| 2962 | $maybeUTF16LE = 0; |
|
| 2963 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16LE'); |
|
| 2964 | if ($test) { |
|
| 2965 | $test2 = \mb_convert_encoding($test, 'UTF-16LE', 'UTF-8'); |
|
| 2966 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16LE'); |
|
| 2967 | if ($test3 === $test) { |
|
| 2968 | $strChars = self::count_chars($str, true); |
|
| 2969 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2970 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2971 | $maybeUTF16LE++; |
|
| 2972 | } |
|
| 2973 | } |
|
| 2974 | } |
|
| 2975 | } |
|
| 2976 | ||
| 2977 | $maybeUTF16BE = 0; |
|
| 2978 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16BE'); |
|
| 2979 | if ($test) { |
|
| 2980 | $test2 = \mb_convert_encoding($test, 'UTF-16BE', 'UTF-8'); |
|
| 2981 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16BE'); |
|
| 2982 | if ($test3 === $test) { |
|
| 2983 | $strChars = self::count_chars($str, true); |
|
| 2984 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2985 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2986 | $maybeUTF16BE++; |
|
| 2987 | } |
|
| 2988 | } |
|
| 2989 | } |
|
| 2990 | } |
|
| 2991 | ||
| 2992 | if ($maybeUTF16BE !== $maybeUTF16LE) { |
|
| 2993 | if ($maybeUTF16LE > $maybeUTF16BE) { |
|
| 2994 | return 1; |
|
| 2995 | } |
|
| 2996 | ||
| 2997 | return 2; |
|
| 2998 | } |
|
| 2999 | ||
| 3000 | } |
|
| 3001 | ||
| 3002 | return false; |
|
| 3003 | } |
|
| 3004 | ||
| 3005 | /** |
|
| 3006 | * Check if the string is UTF-32. |
|
| @@ 3016-3063 (lines=48) @@ | ||
| 3013 | * <strong>2</strong> for UTF-32BE. |
|
| 3014 | * </p> |
|
| 3015 | */ |
|
| 3016 | public static function is_utf32($str) |
|
| 3017 | { |
|
| 3018 | $str = self::remove_bom($str); |
|
| 3019 | ||
| 3020 | if (self::is_binary($str) === true) { |
|
| 3021 | ||
| 3022 | $maybeUTF32LE = 0; |
|
| 3023 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32LE'); |
|
| 3024 | if ($test) { |
|
| 3025 | $test2 = \mb_convert_encoding($test, 'UTF-32LE', 'UTF-8'); |
|
| 3026 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32LE'); |
|
| 3027 | if ($test3 === $test) { |
|
| 3028 | $strChars = self::count_chars($str, true); |
|
| 3029 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 3030 | if (in_array($test3char, $strChars, true) === true) { |
|
| 3031 | $maybeUTF32LE++; |
|
| 3032 | } |
|
| 3033 | } |
|
| 3034 | } |
|
| 3035 | } |
|
| 3036 | ||
| 3037 | $maybeUTF32BE = 0; |
|
| 3038 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32BE'); |
|
| 3039 | if ($test) { |
|
| 3040 | $test2 = \mb_convert_encoding($test, 'UTF-32BE', 'UTF-8'); |
|
| 3041 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32BE'); |
|
| 3042 | if ($test3 === $test) { |
|
| 3043 | $strChars = self::count_chars($str, true); |
|
| 3044 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 3045 | if (in_array($test3char, $strChars, true) === true) { |
|
| 3046 | $maybeUTF32BE++; |
|
| 3047 | } |
|
| 3048 | } |
|
| 3049 | } |
|
| 3050 | } |
|
| 3051 | ||
| 3052 | if ($maybeUTF32BE !== $maybeUTF32LE) { |
|
| 3053 | if ($maybeUTF32LE > $maybeUTF32BE) { |
|
| 3054 | return 1; |
|
| 3055 | } |
|
| 3056 | ||
| 3057 | return 2; |
|
| 3058 | } |
|
| 3059 | ||
| 3060 | } |
|
| 3061 | ||
| 3062 | return false; |
|
| 3063 | } |
|
| 3064 | ||
| 3065 | /** |
|
| 3066 | * Checks whether the passed string contains only byte sequences that appear valid UTF-8 characters. |
|
