Файл: sys/inc/utf8_convert_case.php
Строк: 74
<?php
/**
* Конвертирует регистр букв в строке в кодировке UTF-8
*
* @param string $s строка
* @param int $mode {CASE_LOWER|CASE_UPPER}
* @return string
* @link http://www.unicode.org/charts/PDF/U0400.pdf
*
* @author Nasibullin Rinat <n a s i b u l l i n at starlink ru>
* @charset ANSI
* @link http://ru.wikipedia.org/wiki/ISO_639-1
* @version 1.2.3
*/
function utf8_convert_case($s, $mode)
{
/**
* UTF-8 Case lookup table
*
* This lookuptable defines the upper case letters to their correspponding
* lower case letter in UTF-8
*
* @author Andreas Gohr <andi@splitbrain.org>
*/
/***
$UTF8_LOWER_TO_UPPER = array(
0x0061=>0x0041, 0x03C6=>0x03A6, 0x0163=>0x0162, 0x00E5=>0x00C5, 0x0062=>0x0042,
0x013A=>0x0139, 0x00E1=>0x00C1, 0x0142=>0x0141, 0x03CD=>0x038E, 0x0101=>0x0100,
0x0491=>0x0490, 0x03B4=>0x0394, 0x015B=>0x015A, 0x0064=>0x0044, 0x03B3=>0x0393,
0x00F4=>0x00D4, 0x044A=>0x042A, 0x0439=>0x0419, 0x0113=>0x0112, 0x043C=>0x041C,
0x015F=>0x015E, 0x0144=>0x0143, 0x00EE=>0x00CE, 0x045E=>0x040E, 0x044F=>0x042F,
0x03BA=>0x039A, 0x0155=>0x0154, 0x0069=>0x0049, 0x0073=>0x0053, 0x1E1F=>0x1E1E,
0x0135=>0x0134, 0x0447=>0x0427, 0x03C0=>0x03A0, 0x0438=>0x0418, 0x00F3=>0x00D3,
0x0440=>0x0420, 0x0454=>0x0404, 0x0435=>0x0415, 0x0449=>0x0429, 0x014B=>0x014A,
0x0431=>0x0411, 0x0459=>0x0409, 0x1E03=>0x1E02, 0x00F6=>0x00D6, 0x00F9=>0x00D9,
0x006E=>0x004E, 0x0451=>0x0401, 0x03C4=>0x03A4, 0x0443=>0x0423, 0x015D=>0x015C,
0x0453=>0x0403, 0x03C8=>0x03A8, 0x0159=>0x0158, 0x0067=>0x0047, 0x00E4=>0x00C4,
0x03AC=>0x0386, 0x03AE=>0x0389, 0x0167=>0x0166, 0x03BE=>0x039E, 0x0165=>0x0164,
0x0117=>0x0116, 0x0109=>0x0108, 0x0076=>0x0056, 0x00FE=>0x00DE, 0x0157=>0x0156,
0x00FA=>0x00DA, 0x1E61=>0x1E60, 0x1E83=>0x1E82, 0x00E2=>0x00C2, 0x0119=>0x0118,
0x0146=>0x0145, 0x0070=>0x0050, 0x0151=>0x0150, 0x044E=>0x042E, 0x0129=>0x0128,
0x03C7=>0x03A7, 0x013E=>0x013D, 0x0442=>0x0422, 0x007A=>0x005A, 0x0448=>0x0428,
0x03C1=>0x03A1, 0x1E81=>0x1E80, 0x016D=>0x016C, 0x00F5=>0x00D5, 0x0075=>0x0055,
0x0177=>0x0176, 0x00FC=>0x00DC, 0x1E57=>0x1E56, 0x03C3=>0x03A3, 0x043A=>0x041A,
0x006D=>0x004D, 0x016B=>0x016A, 0x0171=>0x0170, 0x0444=>0x0424, 0x00EC=>0x00CC,
0x0169=>0x0168, 0x03BF=>0x039F, 0x006B=>0x004B, 0x00F2=>0x00D2, 0x00E0=>0x00C0,
0x0434=>0x0414, 0x03C9=>0x03A9, 0x1E6B=>0x1E6A, 0x00E3=>0x00C3, 0x044D=>0x042D,
0x0436=>0x0416, 0x01A1=>0x01A0, 0x010D=>0x010C, 0x011D=>0x011C, 0x00F0=>0x00D0,
0x013C=>0x013B, 0x045F=>0x040F, 0x045A=>0x040A, 0x00E8=>0x00C8, 0x03C5=>0x03A5,
0x0066=>0x0046, 0x00FD=>0x00DD, 0x0063=>0x0043, 0x021B=>0x021A, 0x00EA=>0x00CA,
0x03B9=>0x0399, 0x017A=>0x0179, 0x00EF=>0x00CF, 0x01B0=>0x01AF, 0x0065=>0x0045,
0x03BB=>0x039B, 0x03B8=>0x0398, 0x03BC=>0x039C, 0x045C=>0x040C, 0x043F=>0x041F,
0x044C=>0x042C, 0x00FE=>0x00DE, 0x00F0=>0x00D0, 0x1EF3=>0x1EF2, 0x0068=>0x0048,
0x00EB=>0x00CB, 0x0111=>0x0110, 0x0433=>0x0413, 0x012F=>0x012E, 0x00E6=>0x00C6,
0x0078=>0x0058, 0x0161=>0x0160, 0x016F=>0x016E, 0x03B1=>0x0391, 0x0457=>0x0407,
0x0173=>0x0172, 0x00FF=>0x0178, 0x006F=>0x004F, 0x043B=>0x041B, 0x03B5=>0x0395,
0x0445=>0x0425, 0x0121=>0x0120, 0x017E=>0x017D, 0x017C=>0x017B, 0x03B6=>0x0396,
0x03B2=>0x0392, 0x03AD=>0x0388, 0x1E85=>0x1E84, 0x0175=>0x0174, 0x0071=>0x0051,
0x0437=>0x0417, 0x1E0B=>0x1E0A, 0x0148=>0x0147, 0x0105=>0x0104, 0x0458=>0x0408,
0x014D=>0x014C, 0x00ED=>0x00CD, 0x0079=>0x0059, 0x010B=>0x010A, 0x03CE=>0x038F,
0x0072=>0x0052, 0x0430=>0x0410, 0x0455=>0x0405, 0x0452=>0x0402, 0x0127=>0x0126,
0x0137=>0x0136, 0x012B=>0x012A, 0x03AF=>0x038A, 0x044B=>0x042B, 0x006C=>0x004C,
0x03B7=>0x0397, 0x0125=>0x0124, 0x0219=>0x0218, 0x00FB=>0x00DB, 0x011F=>0x011E,
0x043E=>0x041E, 0x1E41=>0x1E40, 0x03BD=>0x039D, 0x0107=>0x0106, 0x03CB=>0x03AB,
0x0446=>0x0426, 0x00FE=>0x00DE, 0x00E7=>0x00C7, 0x03CA=>0x03AA, 0x0441=>0x0421,
0x0432=>0x0412, 0x010F=>0x010E, 0x00F8=>0x00D8, 0x0077=>0x0057, 0x011B=>0x011A,
0x0074=>0x0054, 0x006A=>0x004A, 0x045B=>0x040B, 0x0456=>0x0406, 0x0103=>0x0102,
0x03BB=>0x039B, 0x00F1=>0x00D1, 0x043D=>0x041D, 0x03CC=>0x038C, 0x00E9=>0x00C9,
0x00F0=>0x00D0, 0x0457=>0x0407, 0x0123=>0x0122,
);
***/
/**
* UTF-8 array of common special characters
*
* This array should contain all special characters (not a letter or digit)
* defined in the various local charsets - it's not a complete list of non-alphanum
* characters in UTF-8. It's not perfect but should match most cases of special
* chars.
*
* The controlchars 0x00 to 0x19 are _not_ included in this array. The space 0x20 is!
*
* @author Andreas Gohr <andi@splitbrain.org>
* @see utf8_stripspecials()
*/
/***
$UTF8_SPECIAL_CHARS = array(
0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023,
0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d,
0x002e, 0x002f, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x005b,
0x005c, 0x005d, 0x005e, 0x005f, 0x0060, 0x007b, 0x007c, 0x007d, 0x007e,
0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088,
0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092,
0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c,
0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6,
0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0,
0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba,
0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00d7, 0x00f7, 0x02c7, 0x02d8, 0x02d9,
0x02da, 0x02db, 0x02dc, 0x02dd, 0x0300, 0x0301, 0x0303, 0x0309, 0x0323, 0x0384,
0x0385, 0x0387, 0x03b2, 0x03c6, 0x03d1, 0x03d2, 0x03d5, 0x03d6, 0x05b0, 0x05b1,
0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc,
0x05bd, 0x05be, 0x05bf, 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f3, 0x05f4, 0x060c,
0x061b, 0x061f, 0x0640, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, 0x0650, 0x0651,
0x0652, 0x066a, 0x0e3f, 0x200c, 0x200d, 0x200e, 0x200f, 0x2013, 0x2014, 0x2015,
0x2017, 0x2018, 0x2019, 0x201a, 0x201c, 0x201d, 0x201e, 0x2020, 0x2021, 0x2022,
0x2026, 0x2030, 0x2032, 0x2033, 0x2039, 0x203a, 0x2044, 0x20a7, 0x20aa, 0x20ab,
0x20ac, 0x2116, 0x2118, 0x2122, 0x2126, 0x2135, 0x2190, 0x2191, 0x2192, 0x2193,
0x2194, 0x2195, 0x21b5, 0x21d0, 0x21d1, 0x21d2, 0x21d3, 0x21d4, 0x2200, 0x2202,
0x2203, 0x2205, 0x2206, 0x2207, 0x2208, 0x2209, 0x220b, 0x220f, 0x2211, 0x2212,
0x2215, 0x2217, 0x2219, 0x221a, 0x221d, 0x221e, 0x2220, 0x2227, 0x2228, 0x2229,
0x222a, 0x222b, 0x2234, 0x223c, 0x2245, 0x2248, 0x2260, 0x2261, 0x2264, 0x2265,
0x2282, 0x2283, 0x2284, 0x2286, 0x2287, 0x2295, 0x2297, 0x22a5, 0x22c5, 0x2310,
0x2320, 0x2321, 0x2329, 0x232a, 0x2469, 0x2500, 0x2502, 0x250c, 0x2510, 0x2514,
0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2550, 0x2551, 0x2552, 0x2553,
0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d,
0x255e, 0x255f, 0x2560, 0x2561, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567,
0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590,
0x2591, 0x2592, 0x2593, 0x25a0, 0x25b2, 0x25bc, 0x25c6, 0x25ca, 0x25cf, 0x25d7,
0x2605, 0x260e, 0x261b, 0x261e, 0x2660, 0x2663, 0x2665, 0x2666, 0x2701, 0x2702,
0x2703, 0x2704, 0x2706, 0x2707, 0x2708, 0x2709, 0x270c, 0x270d, 0x270e, 0x270f,
0x2710, 0x2711, 0x2712, 0x2713, 0x2714, 0x2715, 0x2716, 0x2717, 0x2718, 0x2719,
0x271a, 0x271b, 0x271c, 0x271d, 0x271e, 0x271f, 0x2720, 0x2721, 0x2722, 0x2723,
0x2724, 0x2725, 0x2726, 0x2727, 0x2729, 0x272a, 0x272b, 0x272c, 0x272d, 0x272e,
0x272f, 0x2730, 0x2731, 0x2732, 0x2733, 0x2734, 0x2735, 0x2736, 0x2737, 0x2738,
0x2739, 0x273a, 0x273b, 0x273c, 0x273d, 0x273e, 0x273f, 0x2740, 0x2741, 0x2742,
0x2743, 0x2744, 0x2745, 0x2746, 0x2747, 0x2748, 0x2749, 0x274a, 0x274b, 0x274d,
0x274f, 0x2750, 0x2751, 0x2752, 0x2756, 0x2758, 0x2759, 0x275a, 0x275b, 0x275c,
0x275d, 0x275e, 0x2761, 0x2762, 0x2763, 0x2764, 0x2765, 0x2766, 0x2767, 0x277f,
0x2789, 0x2793, 0x2794, 0x2798, 0x2799, 0x279a, 0x279b, 0x279c, 0x279d, 0x279e,
0x279f, 0x27a0, 0x27a1, 0x27a2, 0x27a3, 0x27a4, 0x27a5, 0x27a6, 0x27a7, 0x27a8,
0x27a9, 0x27aa, 0x27ab, 0x27ac, 0x27ad, 0x27ae, 0x27af, 0x27b1, 0x27b2, 0x27b3,
0x27b4, 0x27b5, 0x27b6, 0x27b7, 0x27b8, 0x27b9, 0x27ba, 0x27bb, 0x27bc, 0x27bd,
0x27be, 0xf6d9, 0xf6da, 0xf6db, 0xf8d7, 0xf8d8, 0xf8d9, 0xf8da, 0xf8db, 0xf8dc,
0xf8dd, 0xf8de, 0xf8df, 0xf8e0, 0xf8e1, 0xf8e2, 0xf8e3, 0xf8e4, 0xf8e5, 0xf8e6,
0xf8e7, 0xf8e8, 0xf8e9, 0xf8ea, 0xf8eb, 0xf8ec, 0xf8ed, 0xf8ee, 0xf8ef, 0xf8f0,
0xf8f1, 0xf8f2, 0xf8f3, 0xf8f4, 0xf8f5, 0xf8f6, 0xf8f7, 0xf8f8, 0xf8f9, 0xf8fa,
0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d,
);
***/
#таблица конвертации регистра
static $trans = array(
#CASE_UPPER => CASE_LOWER
#en (английский латиница)
"x41" => "x61", #a
"x42" => "x62", #b
"x43" => "x63", #c
"x44" => "x64", #d
"x45" => "x65", #e
"x46" => "x66", #f
"x47" => "x67", #g
"x48" => "x68", #h
"x49" => "x69", #i
"x4a" => "x6a", #j
"x4b" => "x6b", #k
"x4c" => "x6c", #l
"x4d" => "x6d", #m
"x4e" => "x6e", #n
"x4f" => "x6f", #o
"x50" => "x70", #p
"x51" => "x71", #q
"x52" => "x72", #r
"x53" => "x73", #s
"x54" => "x74", #t
"x55" => "x75", #u
"x57" => "x77", #w
"x56" => "x76", #v
"x58" => "x78", #x
"x59" => "x79", #y
"x5a" => "x7a", #z
#ru (русский кириллица)
"xd0x81" => "xd1x91", #ё
"xd0x90" => "xd0xb0", #а
"xd0x91" => "xd0xb1", #б
"xd0x92" => "xd0xb2", #в
"xd0x93" => "xd0xb3", #г
"xd0x94" => "xd0xb4", #д
"xd0x95" => "xd0xb5", #е
"xd0x96" => "xd0xb6", #ж
"xd0x97" => "xd0xb7", #з
"xd0x98" => "xd0xb8", #и
"xd0x99" => "xd0xb9", #й
"xd0x9a" => "xd0xba", #к
"xd0x9b" => "xd0xbb", #л
"xd0x9c" => "xd0xbc", #м
"xd0x9d" => "xd0xbd", #н
"xd0x9e" => "xd0xbe", #о
"xd0x9f" => "xd0xbf", #п
"xd0xa0" => "xd1x80", #р
"xd0xa1" => "xd1x81", #с
"xd0xa2" => "xd1x82", #т
"xd0xa3" => "xd1x83", #у
"xd0xa4" => "xd1x84", #ф
"xd0xa5" => "xd1x85", #х
"xd0xa6" => "xd1x86", #ц
"xd0xa7" => "xd1x87", #ч
"xd0xa8" => "xd1x88", #ш
"xd0xa9" => "xd1x89", #щ
"xd0xaa" => "xd1x8a", #ъ
"xd0xab" => "xd1x8b", #ы
"xd0xac" => "xd1x8c", #ь
"xd0xad" => "xd1x8d", #э
"xd0xae" => "xd1x8e", #ю
"xd0xaf" => "xd1x8f", #я
#tt (татарский, башкирский кириллица)
"xd2x96" => "xd2x97", #ж с хвостиком Җ => җ
"xd2xa2" => "xd2xa3", #н с хвостиком Ң => ң
"xd2xae" => "xd2xaf", #y Ү => ү
"xd2xba" => "xd2xbb", #h мягкое Һ => һ
"xd3x98" => "xd3x99", #э Ә => ә
"xd3xa8" => "xd3xa9", #o перечеркнутое Ө => ө
#uk (украинский кириллица)
"xd2x90" => "xd2x91", #г с хвостиком
"xd0x84" => "xd1x94", #э зеркальное отражение
"xd0x86" => "xd1x96", #и с одной точкой
"xd0x87" => "xd1x97", #и с двумя точками
#be (белорусский кириллица)
"xd0x8e" => "xd1x9e", #у с подковой над буквой
#tr,de,es (турецкий, немецкий, испанский, французский латиница)
"xc3x84" => "xc3xa4", #a умляут Ä => ä (турецкий)
"xc3x87" => "xc3xa7", #c с хвостиком Ç => ç (турецкий, французский)
"xc3x91" => "xc3xb1", #n с тильдой Ñ => ñ (турецкий, испанский)
"xc3x96" => "xc3xb6", #o умляут Ö => ö (турецкий)
"xc3x9c" => "xc3xbc", #u умляут Ü => ü (турецкий, французский)
"xc4x9e" => "xc4x9f", #g умляут Ğ => ğ (турецкий)
"xc4xb0" => "xc4xb1", #i c точкой и без İ => ı (турецкий)
"xc5x9e" => "xc5x9f", #s с хвостиком Ş => ş (турецкий)
#hr (хорватский латиница)
"xc4x8c" => "xc4x8d", #c с подковой над буквой
"xc4x86" => "xc4x87", #c с ударением
"xc4x90" => "xc4x91", #d перечеркнутое
"xc5xa0" => "xc5xa1", #s с подковой над буквой
"xc5xbd" => "xc5xbe", #z с подковой над буквой
#fr (французский латиница)
"xc3x80" => "xc3xa0", #a с ударением в др. сторону
"xc3x82" => "xc3xa2", #a с крышкой
"xc3x86" => "xc3xa6", #ae совмещенное
"xc3x88" => "xc3xa8", #e с ударением в др. сторону
"xc3x89" => "xc3xa9", #e с ударением
"xc3x8a" => "xc3xaa", #e с крышкой
"xc3x8b" => "xc3xab", #ё
"xc3x8e" => "xc3xae", #i с крышкой
"xc3x8f" => "xc3xaf", #i умляут
"xc3x94" => "xc3xb4", #o с крышкой
"xc5x92" => "xc5x93", #ce совмещенное
"xc3x99" => "xc3xb9", #u с ударением в др. сторону
"xc3x9b" => "xc3xbb", #u с крышкой
"xc5xb8" => "xc3xbf", #y умляут
#xx (другой язык)
#"" => "", #
);
#d($trans);
#вариант с str_replace() должен работать быстрее, чем с strtr()
if ($mode == CASE_UPPER) {
if (function_exists('mb_strtoupper')) {
return mb_strtoupper($s, 'utf-8');
}
if (preg_match('/^[x00-x7e]*$/', $s)) {
return strtoupper($s);
} #может, так быстрее? (:TODO:)
strtr($s, array_flip($trans));
#$s = str_replace(array_values($trans), array_keys($trans), $s);
} elseif ($mode == CASE_LOWER) {
if (function_exists('mb_strtolower')) {
return mb_strtolower($s, 'utf-8');
}
if (preg_match('/^[x00-x7e]*$/', $s)) {
return strtolower($s);
} #может, так быстрее? (:TODO:)
strtr($s, $trans);
#$s = str_replace(array_keys($trans), array_values($trans), $s);
} else {
trigger_error('Parameter 2 should be a constant of CASE_LOWER or CASE_UPPER!', E_USER_WARNING);
return $s;
}
return $s;
}
function utf8_lowercase($s)
{
return utf8_convert_case($s, CASE_LOWER);
}
function utf8_uppercase($s)
{
return utf8_convert_case($s, CASE_UPPER);
}