| 1 | MBLENGTH = { |
|---|
| 2 | 8:1, |
|---|
| 3 | 33:3, |
|---|
| 4 | 88:2, |
|---|
| 5 | 91:2 |
|---|
| 6 | } |
|---|
| 7 | |
|---|
| 8 | |
|---|
| 9 | class Charset(object): |
|---|
| 10 | def __init__(self, id, name, collation, is_default): |
|---|
| 11 | self.id, self.name, self.collation = id, name, collation |
|---|
| 12 | self.is_default = is_default == 'Yes' |
|---|
| 13 | |
|---|
| 14 | def __repr__(self): |
|---|
| 15 | return "Charset(id=%s, name=%r, collation=%r)" % ( |
|---|
| 16 | self.id, self.name, self.collation) |
|---|
| 17 | |
|---|
| 18 | @property |
|---|
| 19 | def encoding(self): |
|---|
| 20 | name = self.name |
|---|
| 21 | if name == 'utf8mb4': |
|---|
| 22 | return 'utf8' |
|---|
| 23 | return name |
|---|
| 24 | |
|---|
| 25 | @property |
|---|
| 26 | def is_binary(self): |
|---|
| 27 | return self.id == 63 |
|---|
| 28 | |
|---|
| 29 | |
|---|
| 30 | class Charsets: |
|---|
| 31 | def __init__(self): |
|---|
| 32 | self._by_id = {} |
|---|
| 33 | |
|---|
| 34 | def add(self, c): |
|---|
| 35 | self._by_id[c.id] = c |
|---|
| 36 | |
|---|
| 37 | def by_id(self, id): |
|---|
| 38 | return self._by_id[id] |
|---|
| 39 | |
|---|
| 40 | def by_name(self, name): |
|---|
| 41 | name = name.lower() |
|---|
| 42 | for c in self._by_id.values(): |
|---|
| 43 | if c.name == name and c.is_default: |
|---|
| 44 | return c |
|---|
| 45 | |
|---|
| 46 | _charsets = Charsets() |
|---|
| 47 | """ |
|---|
| 48 | Generated with: |
|---|
| 49 | |
|---|
| 50 | mysql -N -s -e "select id, character_set_name, collation_name, is_default |
|---|
| 51 | from information_schema.collations order by id;" | python -c "import sys |
|---|
| 52 | for l in sys.stdin.readlines(): |
|---|
| 53 | id, name, collation, is_default = l.split(chr(9)) |
|---|
| 54 | print '_charsets.add(Charset(%s, \'%s\', \'%s\', \'%s\'))' \ |
|---|
| 55 | % (id, name, collation, is_default.strip()) |
|---|
| 56 | " |
|---|
| 57 | |
|---|
| 58 | """ |
|---|
| 59 | _charsets.add(Charset(1, 'big5', 'big5_chinese_ci', 'Yes')) |
|---|
| 60 | _charsets.add(Charset(2, 'latin2', 'latin2_czech_cs', '')) |
|---|
| 61 | _charsets.add(Charset(3, 'dec8', 'dec8_swedish_ci', 'Yes')) |
|---|
| 62 | _charsets.add(Charset(4, 'cp850', 'cp850_general_ci', 'Yes')) |
|---|
| 63 | _charsets.add(Charset(5, 'latin1', 'latin1_german1_ci', '')) |
|---|
| 64 | _charsets.add(Charset(6, 'hp8', 'hp8_english_ci', 'Yes')) |
|---|
| 65 | _charsets.add(Charset(7, 'koi8r', 'koi8r_general_ci', 'Yes')) |
|---|
| 66 | _charsets.add(Charset(8, 'latin1', 'latin1_swedish_ci', 'Yes')) |
|---|
| 67 | _charsets.add(Charset(9, 'latin2', 'latin2_general_ci', 'Yes')) |
|---|
| 68 | _charsets.add(Charset(10, 'swe7', 'swe7_swedish_ci', 'Yes')) |
|---|
| 69 | _charsets.add(Charset(11, 'ascii', 'ascii_general_ci', 'Yes')) |
|---|
| 70 | _charsets.add(Charset(12, 'ujis', 'ujis_japanese_ci', 'Yes')) |
|---|
| 71 | _charsets.add(Charset(13, 'sjis', 'sjis_japanese_ci', 'Yes')) |
|---|
| 72 | _charsets.add(Charset(14, 'cp1251', 'cp1251_bulgarian_ci', '')) |
|---|
| 73 | _charsets.add(Charset(15, 'latin1', 'latin1_danish_ci', '')) |
|---|
| 74 | _charsets.add(Charset(16, 'hebrew', 'hebrew_general_ci', 'Yes')) |
|---|
| 75 | _charsets.add(Charset(18, 'tis620', 'tis620_thai_ci', 'Yes')) |
|---|
| 76 | _charsets.add(Charset(19, 'euckr', 'euckr_korean_ci', 'Yes')) |
|---|
| 77 | _charsets.add(Charset(20, 'latin7', 'latin7_estonian_cs', '')) |
|---|
| 78 | _charsets.add(Charset(21, 'latin2', 'latin2_hungarian_ci', '')) |
|---|
| 79 | _charsets.add(Charset(22, 'koi8u', 'koi8u_general_ci', 'Yes')) |
|---|
| 80 | _charsets.add(Charset(23, 'cp1251', 'cp1251_ukrainian_ci', '')) |
|---|
| 81 | _charsets.add(Charset(24, 'gb2312', 'gb2312_chinese_ci', 'Yes')) |
|---|
| 82 | _charsets.add(Charset(25, 'greek', 'greek_general_ci', 'Yes')) |
|---|
| 83 | _charsets.add(Charset(26, 'cp1250', 'cp1250_general_ci', 'Yes')) |
|---|
| 84 | _charsets.add(Charset(27, 'latin2', 'latin2_croatian_ci', '')) |
|---|
| 85 | _charsets.add(Charset(28, 'gbk', 'gbk_chinese_ci', 'Yes')) |
|---|
| 86 | _charsets.add(Charset(29, 'cp1257', 'cp1257_lithuanian_ci', '')) |
|---|
| 87 | _charsets.add(Charset(30, 'latin5', 'latin5_turkish_ci', 'Yes')) |
|---|
| 88 | _charsets.add(Charset(31, 'latin1', 'latin1_german2_ci', '')) |
|---|
| 89 | _charsets.add(Charset(32, 'armscii8', 'armscii8_general_ci', 'Yes')) |
|---|
| 90 | _charsets.add(Charset(33, 'utf8', 'utf8_general_ci', 'Yes')) |
|---|
| 91 | _charsets.add(Charset(34, 'cp1250', 'cp1250_czech_cs', '')) |
|---|
| 92 | _charsets.add(Charset(35, 'ucs2', 'ucs2_general_ci', 'Yes')) |
|---|
| 93 | _charsets.add(Charset(36, 'cp866', 'cp866_general_ci', 'Yes')) |
|---|
| 94 | _charsets.add(Charset(37, 'keybcs2', 'keybcs2_general_ci', 'Yes')) |
|---|
| 95 | _charsets.add(Charset(38, 'macce', 'macce_general_ci', 'Yes')) |
|---|
| 96 | _charsets.add(Charset(39, 'macroman', 'macroman_general_ci', 'Yes')) |
|---|
| 97 | _charsets.add(Charset(40, 'cp852', 'cp852_general_ci', 'Yes')) |
|---|
| 98 | _charsets.add(Charset(41, 'latin7', 'latin7_general_ci', 'Yes')) |
|---|
| 99 | _charsets.add(Charset(42, 'latin7', 'latin7_general_cs', '')) |
|---|
| 100 | _charsets.add(Charset(43, 'macce', 'macce_bin', '')) |
|---|
| 101 | _charsets.add(Charset(44, 'cp1250', 'cp1250_croatian_ci', '')) |
|---|
| 102 | _charsets.add(Charset(45, 'utf8mb4', 'utf8mb4_general_ci', 'Yes')) |
|---|
| 103 | _charsets.add(Charset(46, 'utf8mb4', 'utf8mb4_bin', '')) |
|---|
| 104 | _charsets.add(Charset(47, 'latin1', 'latin1_bin', '')) |
|---|
| 105 | _charsets.add(Charset(48, 'latin1', 'latin1_general_ci', '')) |
|---|
| 106 | _charsets.add(Charset(49, 'latin1', 'latin1_general_cs', '')) |
|---|
| 107 | _charsets.add(Charset(50, 'cp1251', 'cp1251_bin', '')) |
|---|
| 108 | _charsets.add(Charset(51, 'cp1251', 'cp1251_general_ci', 'Yes')) |
|---|
| 109 | _charsets.add(Charset(52, 'cp1251', 'cp1251_general_cs', '')) |
|---|
| 110 | _charsets.add(Charset(53, 'macroman', 'macroman_bin', '')) |
|---|
| 111 | _charsets.add(Charset(54, 'utf16', 'utf16_general_ci', 'Yes')) |
|---|
| 112 | _charsets.add(Charset(55, 'utf16', 'utf16_bin', '')) |
|---|
| 113 | _charsets.add(Charset(57, 'cp1256', 'cp1256_general_ci', 'Yes')) |
|---|
| 114 | _charsets.add(Charset(58, 'cp1257', 'cp1257_bin', '')) |
|---|
| 115 | _charsets.add(Charset(59, 'cp1257', 'cp1257_general_ci', 'Yes')) |
|---|
| 116 | _charsets.add(Charset(60, 'utf32', 'utf32_general_ci', 'Yes')) |
|---|
| 117 | _charsets.add(Charset(61, 'utf32', 'utf32_bin', '')) |
|---|
| 118 | _charsets.add(Charset(63, 'binary', 'binary', 'Yes')) |
|---|
| 119 | _charsets.add(Charset(64, 'armscii8', 'armscii8_bin', '')) |
|---|
| 120 | _charsets.add(Charset(65, 'ascii', 'ascii_bin', '')) |
|---|
| 121 | _charsets.add(Charset(66, 'cp1250', 'cp1250_bin', '')) |
|---|
| 122 | _charsets.add(Charset(67, 'cp1256', 'cp1256_bin', '')) |
|---|
| 123 | _charsets.add(Charset(68, 'cp866', 'cp866_bin', '')) |
|---|
| 124 | _charsets.add(Charset(69, 'dec8', 'dec8_bin', '')) |
|---|
| 125 | _charsets.add(Charset(70, 'greek', 'greek_bin', '')) |
|---|
| 126 | _charsets.add(Charset(71, 'hebrew', 'hebrew_bin', '')) |
|---|
| 127 | _charsets.add(Charset(72, 'hp8', 'hp8_bin', '')) |
|---|
| 128 | _charsets.add(Charset(73, 'keybcs2', 'keybcs2_bin', '')) |
|---|
| 129 | _charsets.add(Charset(74, 'koi8r', 'koi8r_bin', '')) |
|---|
| 130 | _charsets.add(Charset(75, 'koi8u', 'koi8u_bin', '')) |
|---|
| 131 | _charsets.add(Charset(77, 'latin2', 'latin2_bin', '')) |
|---|
| 132 | _charsets.add(Charset(78, 'latin5', 'latin5_bin', '')) |
|---|
| 133 | _charsets.add(Charset(79, 'latin7', 'latin7_bin', '')) |
|---|
| 134 | _charsets.add(Charset(80, 'cp850', 'cp850_bin', '')) |
|---|
| 135 | _charsets.add(Charset(81, 'cp852', 'cp852_bin', '')) |
|---|
| 136 | _charsets.add(Charset(82, 'swe7', 'swe7_bin', '')) |
|---|
| 137 | _charsets.add(Charset(83, 'utf8', 'utf8_bin', '')) |
|---|
| 138 | _charsets.add(Charset(84, 'big5', 'big5_bin', '')) |
|---|
| 139 | _charsets.add(Charset(85, 'euckr', 'euckr_bin', '')) |
|---|
| 140 | _charsets.add(Charset(86, 'gb2312', 'gb2312_bin', '')) |
|---|
| 141 | _charsets.add(Charset(87, 'gbk', 'gbk_bin', '')) |
|---|
| 142 | _charsets.add(Charset(88, 'sjis', 'sjis_bin', '')) |
|---|
| 143 | _charsets.add(Charset(89, 'tis620', 'tis620_bin', '')) |
|---|
| 144 | _charsets.add(Charset(90, 'ucs2', 'ucs2_bin', '')) |
|---|
| 145 | _charsets.add(Charset(91, 'ujis', 'ujis_bin', '')) |
|---|
| 146 | _charsets.add(Charset(92, 'geostd8', 'geostd8_general_ci', 'Yes')) |
|---|
| 147 | _charsets.add(Charset(93, 'geostd8', 'geostd8_bin', '')) |
|---|
| 148 | _charsets.add(Charset(94, 'latin1', 'latin1_spanish_ci', '')) |
|---|
| 149 | _charsets.add(Charset(95, 'cp932', 'cp932_japanese_ci', 'Yes')) |
|---|
| 150 | _charsets.add(Charset(96, 'cp932', 'cp932_bin', '')) |
|---|
| 151 | _charsets.add(Charset(97, 'eucjpms', 'eucjpms_japanese_ci', 'Yes')) |
|---|
| 152 | _charsets.add(Charset(98, 'eucjpms', 'eucjpms_bin', '')) |
|---|
| 153 | _charsets.add(Charset(99, 'cp1250', 'cp1250_polish_ci', '')) |
|---|
| 154 | _charsets.add(Charset(101, 'utf16', 'utf16_unicode_ci', '')) |
|---|
| 155 | _charsets.add(Charset(102, 'utf16', 'utf16_icelandic_ci', '')) |
|---|
| 156 | _charsets.add(Charset(103, 'utf16', 'utf16_latvian_ci', '')) |
|---|
| 157 | _charsets.add(Charset(104, 'utf16', 'utf16_romanian_ci', '')) |
|---|
| 158 | _charsets.add(Charset(105, 'utf16', 'utf16_slovenian_ci', '')) |
|---|
| 159 | _charsets.add(Charset(106, 'utf16', 'utf16_polish_ci', '')) |
|---|
| 160 | _charsets.add(Charset(107, 'utf16', 'utf16_estonian_ci', '')) |
|---|
| 161 | _charsets.add(Charset(108, 'utf16', 'utf16_spanish_ci', '')) |
|---|
| 162 | _charsets.add(Charset(109, 'utf16', 'utf16_swedish_ci', '')) |
|---|
| 163 | _charsets.add(Charset(110, 'utf16', 'utf16_turkish_ci', '')) |
|---|
| 164 | _charsets.add(Charset(111, 'utf16', 'utf16_czech_ci', '')) |
|---|
| 165 | _charsets.add(Charset(112, 'utf16', 'utf16_danish_ci', '')) |
|---|
| 166 | _charsets.add(Charset(113, 'utf16', 'utf16_lithuanian_ci', '')) |
|---|
| 167 | _charsets.add(Charset(114, 'utf16', 'utf16_slovak_ci', '')) |
|---|
| 168 | _charsets.add(Charset(115, 'utf16', 'utf16_spanish2_ci', '')) |
|---|
| 169 | _charsets.add(Charset(116, 'utf16', 'utf16_roman_ci', '')) |
|---|
| 170 | _charsets.add(Charset(117, 'utf16', 'utf16_persian_ci', '')) |
|---|
| 171 | _charsets.add(Charset(118, 'utf16', 'utf16_esperanto_ci', '')) |
|---|
| 172 | _charsets.add(Charset(119, 'utf16', 'utf16_hungarian_ci', '')) |
|---|
| 173 | _charsets.add(Charset(120, 'utf16', 'utf16_sinhala_ci', '')) |
|---|
| 174 | _charsets.add(Charset(128, 'ucs2', 'ucs2_unicode_ci', '')) |
|---|
| 175 | _charsets.add(Charset(129, 'ucs2', 'ucs2_icelandic_ci', '')) |
|---|
| 176 | _charsets.add(Charset(130, 'ucs2', 'ucs2_latvian_ci', '')) |
|---|
| 177 | _charsets.add(Charset(131, 'ucs2', 'ucs2_romanian_ci', '')) |
|---|
| 178 | _charsets.add(Charset(132, 'ucs2', 'ucs2_slovenian_ci', '')) |
|---|
| 179 | _charsets.add(Charset(133, 'ucs2', 'ucs2_polish_ci', '')) |
|---|
| 180 | _charsets.add(Charset(134, 'ucs2', 'ucs2_estonian_ci', '')) |
|---|
| 181 | _charsets.add(Charset(135, 'ucs2', 'ucs2_spanish_ci', '')) |
|---|
| 182 | _charsets.add(Charset(136, 'ucs2', 'ucs2_swedish_ci', '')) |
|---|
| 183 | _charsets.add(Charset(137, 'ucs2', 'ucs2_turkish_ci', '')) |
|---|
| 184 | _charsets.add(Charset(138, 'ucs2', 'ucs2_czech_ci', '')) |
|---|
| 185 | _charsets.add(Charset(139, 'ucs2', 'ucs2_danish_ci', '')) |
|---|
| 186 | _charsets.add(Charset(140, 'ucs2', 'ucs2_lithuanian_ci', '')) |
|---|
| 187 | _charsets.add(Charset(141, 'ucs2', 'ucs2_slovak_ci', '')) |
|---|
| 188 | _charsets.add(Charset(142, 'ucs2', 'ucs2_spanish2_ci', '')) |
|---|
| 189 | _charsets.add(Charset(143, 'ucs2', 'ucs2_roman_ci', '')) |
|---|
| 190 | _charsets.add(Charset(144, 'ucs2', 'ucs2_persian_ci', '')) |
|---|
| 191 | _charsets.add(Charset(145, 'ucs2', 'ucs2_esperanto_ci', '')) |
|---|
| 192 | _charsets.add(Charset(146, 'ucs2', 'ucs2_hungarian_ci', '')) |
|---|
| 193 | _charsets.add(Charset(147, 'ucs2', 'ucs2_sinhala_ci', '')) |
|---|
| 194 | _charsets.add(Charset(159, 'ucs2', 'ucs2_general_mysql500_ci', '')) |
|---|
| 195 | _charsets.add(Charset(160, 'utf32', 'utf32_unicode_ci', '')) |
|---|
| 196 | _charsets.add(Charset(161, 'utf32', 'utf32_icelandic_ci', '')) |
|---|
| 197 | _charsets.add(Charset(162, 'utf32', 'utf32_latvian_ci', '')) |
|---|
| 198 | _charsets.add(Charset(163, 'utf32', 'utf32_romanian_ci', '')) |
|---|
| 199 | _charsets.add(Charset(164, 'utf32', 'utf32_slovenian_ci', '')) |
|---|
| 200 | _charsets.add(Charset(165, 'utf32', 'utf32_polish_ci', '')) |
|---|
| 201 | _charsets.add(Charset(166, 'utf32', 'utf32_estonian_ci', '')) |
|---|
| 202 | _charsets.add(Charset(167, 'utf32', 'utf32_spanish_ci', '')) |
|---|
| 203 | _charsets.add(Charset(168, 'utf32', 'utf32_swedish_ci', '')) |
|---|
| 204 | _charsets.add(Charset(169, 'utf32', 'utf32_turkish_ci', '')) |
|---|
| 205 | _charsets.add(Charset(170, 'utf32', 'utf32_czech_ci', '')) |
|---|
| 206 | _charsets.add(Charset(171, 'utf32', 'utf32_danish_ci', '')) |
|---|
| 207 | _charsets.add(Charset(172, 'utf32', 'utf32_lithuanian_ci', '')) |
|---|
| 208 | _charsets.add(Charset(173, 'utf32', 'utf32_slovak_ci', '')) |
|---|
| 209 | _charsets.add(Charset(174, 'utf32', 'utf32_spanish2_ci', '')) |
|---|
| 210 | _charsets.add(Charset(175, 'utf32', 'utf32_roman_ci', '')) |
|---|
| 211 | _charsets.add(Charset(176, 'utf32', 'utf32_persian_ci', '')) |
|---|
| 212 | _charsets.add(Charset(177, 'utf32', 'utf32_esperanto_ci', '')) |
|---|
| 213 | _charsets.add(Charset(178, 'utf32', 'utf32_hungarian_ci', '')) |
|---|
| 214 | _charsets.add(Charset(179, 'utf32', 'utf32_sinhala_ci', '')) |
|---|
| 215 | _charsets.add(Charset(192, 'utf8', 'utf8_unicode_ci', '')) |
|---|
| 216 | _charsets.add(Charset(193, 'utf8', 'utf8_icelandic_ci', '')) |
|---|
| 217 | _charsets.add(Charset(194, 'utf8', 'utf8_latvian_ci', '')) |
|---|
| 218 | _charsets.add(Charset(195, 'utf8', 'utf8_romanian_ci', '')) |
|---|
| 219 | _charsets.add(Charset(196, 'utf8', 'utf8_slovenian_ci', '')) |
|---|
| 220 | _charsets.add(Charset(197, 'utf8', 'utf8_polish_ci', '')) |
|---|
| 221 | _charsets.add(Charset(198, 'utf8', 'utf8_estonian_ci', '')) |
|---|
| 222 | _charsets.add(Charset(199, 'utf8', 'utf8_spanish_ci', '')) |
|---|
| 223 | _charsets.add(Charset(200, 'utf8', 'utf8_swedish_ci', '')) |
|---|
| 224 | _charsets.add(Charset(201, 'utf8', 'utf8_turkish_ci', '')) |
|---|
| 225 | _charsets.add(Charset(202, 'utf8', 'utf8_czech_ci', '')) |
|---|
| 226 | _charsets.add(Charset(203, 'utf8', 'utf8_danish_ci', '')) |
|---|
| 227 | _charsets.add(Charset(204, 'utf8', 'utf8_lithuanian_ci', '')) |
|---|
| 228 | _charsets.add(Charset(205, 'utf8', 'utf8_slovak_ci', '')) |
|---|
| 229 | _charsets.add(Charset(206, 'utf8', 'utf8_spanish2_ci', '')) |
|---|
| 230 | _charsets.add(Charset(207, 'utf8', 'utf8_roman_ci', '')) |
|---|
| 231 | _charsets.add(Charset(208, 'utf8', 'utf8_persian_ci', '')) |
|---|
| 232 | _charsets.add(Charset(209, 'utf8', 'utf8_esperanto_ci', '')) |
|---|
| 233 | _charsets.add(Charset(210, 'utf8', 'utf8_hungarian_ci', '')) |
|---|
| 234 | _charsets.add(Charset(211, 'utf8', 'utf8_sinhala_ci', '')) |
|---|
| 235 | _charsets.add(Charset(223, 'utf8', 'utf8_general_mysql500_ci', '')) |
|---|
| 236 | _charsets.add(Charset(224, 'utf8mb4', 'utf8mb4_unicode_ci', '')) |
|---|
| 237 | _charsets.add(Charset(225, 'utf8mb4', 'utf8mb4_icelandic_ci', '')) |
|---|
| 238 | _charsets.add(Charset(226, 'utf8mb4', 'utf8mb4_latvian_ci', '')) |
|---|
| 239 | _charsets.add(Charset(227, 'utf8mb4', 'utf8mb4_romanian_ci', '')) |
|---|
| 240 | _charsets.add(Charset(228, 'utf8mb4', 'utf8mb4_slovenian_ci', '')) |
|---|
| 241 | _charsets.add(Charset(229, 'utf8mb4', 'utf8mb4_polish_ci', '')) |
|---|
| 242 | _charsets.add(Charset(230, 'utf8mb4', 'utf8mb4_estonian_ci', '')) |
|---|
| 243 | _charsets.add(Charset(231, 'utf8mb4', 'utf8mb4_spanish_ci', '')) |
|---|
| 244 | _charsets.add(Charset(232, 'utf8mb4', 'utf8mb4_swedish_ci', '')) |
|---|
| 245 | _charsets.add(Charset(233, 'utf8mb4', 'utf8mb4_turkish_ci', '')) |
|---|
| 246 | _charsets.add(Charset(234, 'utf8mb4', 'utf8mb4_czech_ci', '')) |
|---|
| 247 | _charsets.add(Charset(235, 'utf8mb4', 'utf8mb4_danish_ci', '')) |
|---|
| 248 | _charsets.add(Charset(236, 'utf8mb4', 'utf8mb4_lithuanian_ci', '')) |
|---|
| 249 | _charsets.add(Charset(237, 'utf8mb4', 'utf8mb4_slovak_ci', '')) |
|---|
| 250 | _charsets.add(Charset(238, 'utf8mb4', 'utf8mb4_spanish2_ci', '')) |
|---|
| 251 | _charsets.add(Charset(239, 'utf8mb4', 'utf8mb4_roman_ci', '')) |
|---|
| 252 | _charsets.add(Charset(240, 'utf8mb4', 'utf8mb4_persian_ci', '')) |
|---|
| 253 | _charsets.add(Charset(241, 'utf8mb4', 'utf8mb4_esperanto_ci', '')) |
|---|
| 254 | _charsets.add(Charset(242, 'utf8mb4', 'utf8mb4_hungarian_ci', '')) |
|---|
| 255 | _charsets.add(Charset(243, 'utf8mb4', 'utf8mb4_sinhala_ci', '')) |
|---|
| 256 | _charsets.add(Charset(244, 'utf8mb4', 'utf8mb4_german2_ci', '')) |
|---|
| 257 | _charsets.add(Charset(245, 'utf8mb4', 'utf8mb4_croatian_ci', '')) |
|---|
| 258 | _charsets.add(Charset(246, 'utf8mb4', 'utf8mb4_unicode_520_ci', '')) |
|---|
| 259 | _charsets.add(Charset(247, 'utf8mb4', 'utf8mb4_vietnamese_ci', '')) |
|---|
| 260 | |
|---|
| 261 | |
|---|
| 262 | charset_by_name = _charsets.by_name |
|---|
| 263 | charset_by_id = _charsets.by_id |
|---|
| 264 | |
|---|
| 265 | |
|---|
| 266 | def charset_to_encoding(name): |
|---|
| 267 | """Convert MySQL's charset name to Python's codec name""" |
|---|
| 268 | if name == 'utf8mb4': |
|---|
| 269 | return 'utf8' |
|---|
| 270 | return name |
|---|
