Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
singlestore-labs
GitHub Repository: singlestore-labs/singlestoredb-python
 Path: blob/main/singlestoredb/mysql/charset.py
469 views
1
from typing import Dict

2
from typing import Optional

3


4
MBLENGTH = {8: 1, 33: 3, 88: 2, 91: 2}

5


6


7
class Charset:

8


9
    def __init__(self, id: int, name: str, collation: str, is_default: str):

10
        self.id, self.name, self.collation = id, name, collation

11
        self.is_default = is_default == 'Yes'

12


13
    def __repr__(self) -> str:

14
        return 'Charset(id=%s, name=%r, collation=%r)' % (

15
            self.id,

16
            self.name,

17
            self.collation,

18
        )

19


20
    @property

21
    def encoding(self) -> str:

22
        name = self.name

23
        if name in ('utf8mb4', 'utf8mb3'):

24
            return 'utf8'

25
        if name == 'latin1':

26
            return 'cp1252'

27
        if name == 'koi8r':

28
            return 'koi8_r'

29
        if name == 'koi8u':

30
            return 'koi8_u'

31
        return name

32


33
    @property

34
    def is_binary(self) -> bool:

35
        return self.id == 63

36


37


38
class Charsets:

39


40
    def __init__(self) -> None:

41
        self._by_id: Dict[int, Charset] = {}

42
        self._by_name: Dict[str, Charset] = {}

43


44
    def add(self, c: Charset) -> None:

45
        self._by_id[c.id] = c

46
        if c.is_default:

47
            self._by_name[c.name] = c

48


49
    def by_id(self, id: int) -> Charset:

50
        return self._by_id[id]

51


52
    def by_name(self, name: str) -> Optional[Charset]:

53
        return self._by_name.get(name.lower())

54


55


56
_charsets = Charsets()

57


58
# Generated with:

59
#

60
# mysql -N -s -e "select id, character_set_name, collation_name, is_default

61
# from information_schema.collations order by id;" | python -c "import sys

62
# for l in sys.stdin.readlines():

63
#         id, name, collation, is_default  = l.split(chr(9))

64
#         print '_charsets.add(Charset(%s, \'%s\', \'%s\', \'%s\'))' \

65
#                 % (id, name, collation, is_default.strip())

66
# "

67
#

68
#

69
_charsets.add(Charset(1, 'big5', 'big5_chinese_ci', 'Yes'))

70
_charsets.add(Charset(2, 'latin2', 'latin2_czech_cs', ''))

71
_charsets.add(Charset(3, 'dec8', 'dec8_swedish_ci', 'Yes'))

72
_charsets.add(Charset(4, 'cp850', 'cp850_general_ci', 'Yes'))

73
_charsets.add(Charset(5, 'latin1', 'latin1_german1_ci', ''))

74
_charsets.add(Charset(6, 'hp8', 'hp8_english_ci', 'Yes'))

75
_charsets.add(Charset(7, 'koi8r', 'koi8r_general_ci', 'Yes'))

76
_charsets.add(Charset(8, 'latin1', 'latin1_swedish_ci', 'Yes'))

77
_charsets.add(Charset(9, 'latin2', 'latin2_general_ci', 'Yes'))

78
_charsets.add(Charset(10, 'swe7', 'swe7_swedish_ci', 'Yes'))

79
_charsets.add(Charset(11, 'ascii', 'ascii_general_ci', 'Yes'))

80
_charsets.add(Charset(12, 'ujis', 'ujis_japanese_ci', 'Yes'))

81
_charsets.add(Charset(13, 'sjis', 'sjis_japanese_ci', 'Yes'))

82
_charsets.add(Charset(14, 'cp1251', 'cp1251_bulgarian_ci', ''))

83
_charsets.add(Charset(15, 'latin1', 'latin1_danish_ci', ''))

84
_charsets.add(Charset(16, 'hebrew', 'hebrew_general_ci', 'Yes'))

85
_charsets.add(Charset(18, 'tis620', 'tis620_thai_ci', 'Yes'))

86
_charsets.add(Charset(19, 'euckr', 'euckr_korean_ci', 'Yes'))

87
_charsets.add(Charset(20, 'latin7', 'latin7_estonian_cs', ''))

88
_charsets.add(Charset(21, 'latin2', 'latin2_hungarian_ci', ''))

89
_charsets.add(Charset(22, 'koi8u', 'koi8u_general_ci', 'Yes'))

90
_charsets.add(Charset(23, 'cp1251', 'cp1251_ukrainian_ci', ''))

91
_charsets.add(Charset(24, 'gb2312', 'gb2312_chinese_ci', 'Yes'))

92
_charsets.add(Charset(25, 'greek', 'greek_general_ci', 'Yes'))

93
_charsets.add(Charset(26, 'cp1250', 'cp1250_general_ci', 'Yes'))

94
_charsets.add(Charset(27, 'latin2', 'latin2_croatian_ci', ''))

95
_charsets.add(Charset(28, 'gbk', 'gbk_chinese_ci', 'Yes'))

96
_charsets.add(Charset(29, 'cp1257', 'cp1257_lithuanian_ci', ''))

97
_charsets.add(Charset(30, 'latin5', 'latin5_turkish_ci', 'Yes'))

98
_charsets.add(Charset(31, 'latin1', 'latin1_german2_ci', ''))

99
_charsets.add(Charset(32, 'armscii8', 'armscii8_general_ci', 'Yes'))

100
_charsets.add(Charset(33, 'utf8', 'utf8_general_ci', 'Yes'))

101
_charsets.add(Charset(34, 'cp1250', 'cp1250_czech_cs', ''))

102
_charsets.add(Charset(36, 'cp866', 'cp866_general_ci', 'Yes'))

103
_charsets.add(Charset(37, 'keybcs2', 'keybcs2_general_ci', 'Yes'))

104
_charsets.add(Charset(38, 'macce', 'macce_general_ci', 'Yes'))

105
_charsets.add(Charset(39, 'macroman', 'macroman_general_ci', 'Yes'))

106
_charsets.add(Charset(40, 'cp852', 'cp852_general_ci', 'Yes'))

107
_charsets.add(Charset(41, 'latin7', 'latin7_general_ci', 'Yes'))

108
_charsets.add(Charset(42, 'latin7', 'latin7_general_cs', ''))

109
_charsets.add(Charset(43, 'macce', 'macce_bin', ''))

110
_charsets.add(Charset(44, 'cp1250', 'cp1250_croatian_ci', ''))

111
_charsets.add(Charset(45, 'utf8mb4', 'utf8mb4_general_ci', 'Yes'))

112
_charsets.add(Charset(46, 'utf8mb4', 'utf8mb4_bin', ''))

113
_charsets.add(Charset(47, 'latin1', 'latin1_bin', ''))

114
_charsets.add(Charset(48, 'latin1', 'latin1_general_ci', ''))

115
_charsets.add(Charset(49, 'latin1', 'latin1_general_cs', ''))

116
_charsets.add(Charset(50, 'cp1251', 'cp1251_bin', ''))

117
_charsets.add(Charset(51, 'cp1251', 'cp1251_general_ci', 'Yes'))

118
_charsets.add(Charset(52, 'cp1251', 'cp1251_general_cs', ''))

119
_charsets.add(Charset(53, 'macroman', 'macroman_bin', ''))

120
_charsets.add(Charset(57, 'cp1256', 'cp1256_general_ci', 'Yes'))

121
_charsets.add(Charset(58, 'cp1257', 'cp1257_bin', ''))

122
_charsets.add(Charset(59, 'cp1257', 'cp1257_general_ci', 'Yes'))

123
_charsets.add(Charset(63, 'binary', 'binary', 'Yes'))

124
_charsets.add(Charset(64, 'armscii8', 'armscii8_bin', ''))

125
_charsets.add(Charset(65, 'ascii', 'ascii_bin', ''))

126
_charsets.add(Charset(66, 'cp1250', 'cp1250_bin', ''))

127
_charsets.add(Charset(67, 'cp1256', 'cp1256_bin', ''))

128
_charsets.add(Charset(68, 'cp866', 'cp866_bin', ''))

129
_charsets.add(Charset(69, 'dec8', 'dec8_bin', ''))

130
_charsets.add(Charset(70, 'greek', 'greek_bin', ''))

131
_charsets.add(Charset(71, 'hebrew', 'hebrew_bin', ''))

132
_charsets.add(Charset(72, 'hp8', 'hp8_bin', ''))

133
_charsets.add(Charset(73, 'keybcs2', 'keybcs2_bin', ''))

134
_charsets.add(Charset(74, 'koi8r', 'koi8r_bin', ''))

135
_charsets.add(Charset(75, 'koi8u', 'koi8u_bin', ''))

136
_charsets.add(Charset(76, 'utf8', 'utf8_tolower_ci', ''))

137
_charsets.add(Charset(77, 'latin2', 'latin2_bin', ''))

138
_charsets.add(Charset(78, 'latin5', 'latin5_bin', ''))

139
_charsets.add(Charset(79, 'latin7', 'latin7_bin', ''))

140
_charsets.add(Charset(80, 'cp850', 'cp850_bin', ''))

141
_charsets.add(Charset(81, 'cp852', 'cp852_bin', ''))

142
_charsets.add(Charset(82, 'swe7', 'swe7_bin', ''))

143
_charsets.add(Charset(83, 'utf8', 'utf8_bin', ''))

144
_charsets.add(Charset(84, 'big5', 'big5_bin', ''))

145
_charsets.add(Charset(85, 'euckr', 'euckr_bin', ''))

146
_charsets.add(Charset(86, 'gb2312', 'gb2312_bin', ''))

147
_charsets.add(Charset(87, 'gbk', 'gbk_bin', ''))

148
_charsets.add(Charset(88, 'sjis', 'sjis_bin', ''))

149
_charsets.add(Charset(89, 'tis620', 'tis620_bin', ''))

150
_charsets.add(Charset(91, 'ujis', 'ujis_bin', ''))

151
_charsets.add(Charset(92, 'geostd8', 'geostd8_general_ci', 'Yes'))

152
_charsets.add(Charset(93, 'geostd8', 'geostd8_bin', ''))

153
_charsets.add(Charset(94, 'latin1', 'latin1_spanish_ci', ''))

154
_charsets.add(Charset(95, 'cp932', 'cp932_japanese_ci', 'Yes'))

155
_charsets.add(Charset(96, 'cp932', 'cp932_bin', ''))

156
_charsets.add(Charset(97, 'eucjpms', 'eucjpms_japanese_ci', 'Yes'))

157
_charsets.add(Charset(98, 'eucjpms', 'eucjpms_bin', ''))

158
_charsets.add(Charset(99, 'cp1250', 'cp1250_polish_ci', ''))

159
_charsets.add(Charset(192, 'utf8', 'utf8_unicode_ci', ''))

160
_charsets.add(Charset(193, 'utf8', 'utf8_icelandic_ci', ''))

161
_charsets.add(Charset(194, 'utf8', 'utf8_latvian_ci', ''))

162
_charsets.add(Charset(195, 'utf8', 'utf8_romanian_ci', ''))

163
_charsets.add(Charset(196, 'utf8', 'utf8_slovenian_ci', ''))

164
_charsets.add(Charset(197, 'utf8', 'utf8_polish_ci', ''))

165
_charsets.add(Charset(198, 'utf8', 'utf8_estonian_ci', ''))

166
_charsets.add(Charset(199, 'utf8', 'utf8_spanish_ci', ''))

167
_charsets.add(Charset(200, 'utf8', 'utf8_swedish_ci', ''))

168
_charsets.add(Charset(201, 'utf8', 'utf8_turkish_ci', ''))

169
_charsets.add(Charset(202, 'utf8', 'utf8_czech_ci', ''))

170
_charsets.add(Charset(203, 'utf8', 'utf8_danish_ci', ''))

171
_charsets.add(Charset(204, 'utf8', 'utf8_lithuanian_ci', ''))

172
_charsets.add(Charset(205, 'utf8', 'utf8_slovak_ci', ''))

173
_charsets.add(Charset(206, 'utf8', 'utf8_spanish2_ci', ''))

174
_charsets.add(Charset(207, 'utf8', 'utf8_roman_ci', ''))

175
_charsets.add(Charset(208, 'utf8', 'utf8_persian_ci', ''))

176
_charsets.add(Charset(209, 'utf8', 'utf8_esperanto_ci', ''))

177
_charsets.add(Charset(210, 'utf8', 'utf8_hungarian_ci', ''))

178
_charsets.add(Charset(211, 'utf8', 'utf8_sinhala_ci', ''))

179
_charsets.add(Charset(212, 'utf8', 'utf8_german2_ci', ''))

180
_charsets.add(Charset(213, 'utf8', 'utf8_croatian_ci', ''))

181
_charsets.add(Charset(214, 'utf8', 'utf8_unicode_520_ci', ''))

182
_charsets.add(Charset(215, 'utf8', 'utf8_vietnamese_ci', ''))

183
_charsets.add(Charset(223, 'utf8', 'utf8_general_mysql500_ci', ''))

184
_charsets.add(Charset(224, 'utf8mb4', 'utf8mb4_unicode_ci', ''))

185
_charsets.add(Charset(225, 'utf8mb4', 'utf8mb4_icelandic_ci', ''))

186
_charsets.add(Charset(226, 'utf8mb4', 'utf8mb4_latvian_ci', ''))

187
_charsets.add(Charset(227, 'utf8mb4', 'utf8mb4_romanian_ci', ''))

188
_charsets.add(Charset(228, 'utf8mb4', 'utf8mb4_slovenian_ci', ''))

189
_charsets.add(Charset(229, 'utf8mb4', 'utf8mb4_polish_ci', ''))

190
_charsets.add(Charset(230, 'utf8mb4', 'utf8mb4_estonian_ci', ''))

191
_charsets.add(Charset(231, 'utf8mb4', 'utf8mb4_spanish_ci', ''))

192
_charsets.add(Charset(232, 'utf8mb4', 'utf8mb4_swedish_ci', ''))

193
_charsets.add(Charset(233, 'utf8mb4', 'utf8mb4_turkish_ci', ''))

194
_charsets.add(Charset(234, 'utf8mb4', 'utf8mb4_czech_ci', ''))

195
_charsets.add(Charset(235, 'utf8mb4', 'utf8mb4_danish_ci', ''))

196
_charsets.add(Charset(236, 'utf8mb4', 'utf8mb4_lithuanian_ci', ''))

197
_charsets.add(Charset(237, 'utf8mb4', 'utf8mb4_slovak_ci', ''))

198
_charsets.add(Charset(238, 'utf8mb4', 'utf8mb4_spanish2_ci', ''))

199
_charsets.add(Charset(239, 'utf8mb4', 'utf8mb4_roman_ci', ''))

200
_charsets.add(Charset(240, 'utf8mb4', 'utf8mb4_persian_ci', ''))

201
_charsets.add(Charset(241, 'utf8mb4', 'utf8mb4_esperanto_ci', ''))

202
_charsets.add(Charset(242, 'utf8mb4', 'utf8mb4_hungarian_ci', ''))

203
_charsets.add(Charset(243, 'utf8mb4', 'utf8mb4_sinhala_ci', ''))

204
_charsets.add(Charset(244, 'utf8mb4', 'utf8mb4_german2_ci', ''))

205
_charsets.add(Charset(245, 'utf8mb4', 'utf8mb4_croatian_ci', ''))

206
_charsets.add(Charset(246, 'utf8mb4', 'utf8mb4_unicode_520_ci', ''))

207
_charsets.add(Charset(247, 'utf8mb4', 'utf8mb4_vietnamese_ci', ''))

208
_charsets.add(Charset(248, 'gb18030', 'gb18030_chinese_ci', 'Yes'))

209
_charsets.add(Charset(249, 'gb18030', 'gb18030_bin', ''))

210
_charsets.add(Charset(250, 'gb18030', 'gb18030_unicode_520_ci', ''))

211
_charsets.add(Charset(255, 'utf8mb4', 'utf8mb4_0900_ai_ci', ''))

212


213
charset_by_name = _charsets.by_name

214
charset_by_id = _charsets.by_id

215


216