| @@ 2908-2955 (lines=48) @@ | ||
| 2905 | * <strong>2</strong> for UTF-16BE. |
|
| 2906 | * </p> |
|
| 2907 | */ |
|
| 2908 | public static function is_utf16($str) |
|
| 2909 | { |
|
| 2910 | $str = self::remove_bom($str); |
|
| 2911 | ||
| 2912 | if (self::is_binary($str) === true) { |
|
| 2913 | ||
| 2914 | $maybeUTF16LE = 0; |
|
| 2915 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16LE'); |
|
| 2916 | if ($test) { |
|
| 2917 | $test2 = \mb_convert_encoding($test, 'UTF-16LE', 'UTF-8'); |
|
| 2918 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16LE'); |
|
| 2919 | if ($test3 === $test) { |
|
| 2920 | $strChars = self::count_chars($str, true); |
|
| 2921 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2922 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2923 | $maybeUTF16LE++; |
|
| 2924 | } |
|
| 2925 | } |
|
| 2926 | } |
|
| 2927 | } |
|
| 2928 | ||
| 2929 | $maybeUTF16BE = 0; |
|
| 2930 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-16BE'); |
|
| 2931 | if ($test) { |
|
| 2932 | $test2 = \mb_convert_encoding($test, 'UTF-16BE', 'UTF-8'); |
|
| 2933 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-16BE'); |
|
| 2934 | if ($test3 === $test) { |
|
| 2935 | $strChars = self::count_chars($str, true); |
|
| 2936 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2937 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2938 | $maybeUTF16BE++; |
|
| 2939 | } |
|
| 2940 | } |
|
| 2941 | } |
|
| 2942 | } |
|
| 2943 | ||
| 2944 | if ($maybeUTF16BE !== $maybeUTF16LE) { |
|
| 2945 | if ($maybeUTF16LE > $maybeUTF16BE) { |
|
| 2946 | return 1; |
|
| 2947 | } else { |
|
| 2948 | return 2; |
|
| 2949 | } |
|
| 2950 | } |
|
| 2951 | ||
| 2952 | } |
|
| 2953 | ||
| 2954 | return false; |
|
| 2955 | } |
|
| 2956 | ||
| 2957 | /** |
|
| 2958 | * Check if the string is UTF-32. |
|
| @@ 2968-3015 (lines=48) @@ | ||
| 2965 | * <strong>2</strong> for UTF-32BE. |
|
| 2966 | * </p> |
|
| 2967 | */ |
|
| 2968 | public static function is_utf32($str) |
|
| 2969 | { |
|
| 2970 | $str = self::remove_bom($str); |
|
| 2971 | ||
| 2972 | if (self::is_binary($str) === true) { |
|
| 2973 | ||
| 2974 | $maybeUTF32LE = 0; |
|
| 2975 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32LE'); |
|
| 2976 | if ($test) { |
|
| 2977 | $test2 = \mb_convert_encoding($test, 'UTF-32LE', 'UTF-8'); |
|
| 2978 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32LE'); |
|
| 2979 | if ($test3 === $test) { |
|
| 2980 | $strChars = self::count_chars($str, true); |
|
| 2981 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2982 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2983 | $maybeUTF32LE++; |
|
| 2984 | } |
|
| 2985 | } |
|
| 2986 | } |
|
| 2987 | } |
|
| 2988 | ||
| 2989 | $maybeUTF32BE = 0; |
|
| 2990 | $test = \mb_convert_encoding($str, 'UTF-8', 'UTF-32BE'); |
|
| 2991 | if ($test) { |
|
| 2992 | $test2 = \mb_convert_encoding($test, 'UTF-32BE', 'UTF-8'); |
|
| 2993 | $test3 = \mb_convert_encoding($test2, 'UTF-8', 'UTF-32BE'); |
|
| 2994 | if ($test3 === $test) { |
|
| 2995 | $strChars = self::count_chars($str, true); |
|
| 2996 | foreach (self::count_chars($test3, true) as $test3char => $test3charEmpty) { |
|
| 2997 | if (in_array($test3char, $strChars, true) === true) { |
|
| 2998 | $maybeUTF32BE++; |
|
| 2999 | } |
|
| 3000 | } |
|
| 3001 | } |
|
| 3002 | } |
|
| 3003 | ||
| 3004 | if ($maybeUTF32BE !== $maybeUTF32LE) { |
|
| 3005 | if ($maybeUTF32LE > $maybeUTF32BE) { |
|
| 3006 | return 1; |
|
| 3007 | } else { |
|
| 3008 | return 2; |
|
| 3009 | } |
|
| 3010 | } |
|
| 3011 | ||
| 3012 | } |
|
| 3013 | ||
| 3014 | return false; |
|
| 3015 | } |
|
| 3016 | ||
| 3017 | /** |
|
| 3018 | * Checks whether the passed string contains only byte sequences that appear valid UTF-8 characters. |
|