1
-- source include/have_ucs2.inc
2
-- source include/have_utf32.inc
5
DROP TABLE IF EXISTS t1;
9
set collation_connection=utf32_unicode_ci;
10
select hex('a'), hex('a ');
11
-- source include/endspace.inc
14
# Bug #6787 LIKE not working properly with _ and utf8 data
16
select 'c' like '\_' as want0;
19
# Bug #5679 utf8_unicode_ci LIKE--trailing % doesn't equal zero characters
23
) ENGINE=MyISAM DEFAULT CHARACTER SET utf32 COLLATE=utf32_unicode_ci;
24
INSERT INTO t VALUES ('a'),('ab'),('aba');
25
ALTER TABLE t ADD INDEX (c);
26
SELECT c FROM t WHERE c LIKE 'a%';
30
create table t1 (c1 char(10) character set utf32 collate utf32_bin);
35
insert into t1 values ('A'),('a');
36
insert into t1 values ('B'),('b');
37
insert into t1 values ('C'),('c');
38
insert into t1 values ('D'),('d');
39
insert into t1 values ('E'),('e');
40
insert into t1 values ('F'),('f');
41
insert into t1 values ('G'),('g');
42
insert into t1 values ('H'),('h');
43
insert into t1 values ('I'),('i');
44
insert into t1 values ('J'),('j');
45
insert into t1 values ('K'),('k');
46
insert into t1 values ('L'),('l');
47
insert into t1 values ('M'),('m');
48
insert into t1 values ('N'),('n');
49
insert into t1 values ('O'),('o');
50
insert into t1 values ('P'),('p');
51
insert into t1 values ('Q'),('q');
52
insert into t1 values ('R'),('r');
53
insert into t1 values ('S'),('s');
54
insert into t1 values ('T'),('t');
55
insert into t1 values ('U'),('u');
56
insert into t1 values ('V'),('v');
57
insert into t1 values ('W'),('w');
58
insert into t1 values ('X'),('x');
59
insert into t1 values ('Y'),('y');
60
insert into t1 values ('Z'),('z');
65
insert into t1 values (_ucs2 0x00e0),(_ucs2 0x00c0);
66
insert into t1 values (_ucs2 0x00e1),(_ucs2 0x00c1);
67
insert into t1 values (_ucs2 0x00e2),(_ucs2 0x00c2);
68
insert into t1 values (_ucs2 0x00e3),(_ucs2 0x00c3);
69
insert into t1 values (_ucs2 0x00e4),(_ucs2 0x00c4);
70
insert into t1 values (_ucs2 0x00e5),(_ucs2 0x00c5);
71
insert into t1 values (_ucs2 0x00e6),(_ucs2 0x00c6);
72
insert into t1 values (_ucs2 0x00e7),(_ucs2 0x00c7);
73
insert into t1 values (_ucs2 0x00e8),(_ucs2 0x00c8);
74
insert into t1 values (_ucs2 0x00e9),(_ucs2 0x00c9);
75
insert into t1 values (_ucs2 0x00ea),(_ucs2 0x00ca);
76
insert into t1 values (_ucs2 0x00eb),(_ucs2 0x00cb);
77
insert into t1 values (_ucs2 0x00ec),(_ucs2 0x00cc);
78
insert into t1 values (_ucs2 0x00ed),(_ucs2 0x00cd);
79
insert into t1 values (_ucs2 0x00ee),(_ucs2 0x00ce);
80
insert into t1 values (_ucs2 0x00ef),(_ucs2 0x00cf);
82
insert into t1 values (_ucs2 0x00f0),(_ucs2 0x00d0);
83
insert into t1 values (_ucs2 0x00f1),(_ucs2 0x00d1);
84
insert into t1 values (_ucs2 0x00f2),(_ucs2 0x00d2);
85
insert into t1 values (_ucs2 0x00f3),(_ucs2 0x00d3);
86
insert into t1 values (_ucs2 0x00f4),(_ucs2 0x00d4);
87
insert into t1 values (_ucs2 0x00f5),(_ucs2 0x00d5);
88
insert into t1 values (_ucs2 0x00f6),(_ucs2 0x00d6);
89
insert into t1 values (_ucs2 0x00f7),(_ucs2 0x00d7);
90
insert into t1 values (_ucs2 0x00f8),(_ucs2 0x00d8);
91
insert into t1 values (_ucs2 0x00f9),(_ucs2 0x00d9);
92
insert into t1 values (_ucs2 0x00fa),(_ucs2 0x00da);
93
insert into t1 values (_ucs2 0x00fb),(_ucs2 0x00db);
94
insert into t1 values (_ucs2 0x00fc),(_ucs2 0x00dc);
95
insert into t1 values (_ucs2 0x00fd),(_ucs2 0x00dd);
96
insert into t1 values (_ucs2 0x00fe),(_ucs2 0x00de);
97
insert into t1 values (_ucs2 0x00ff),(_ucs2 0x00df);
100
# Latin extended-A, 0100-017F
102
insert into t1 values (_ucs2 0x0100),(_ucs2 0x0101),(_ucs2 0x0102),(_ucs2 0x0103);
103
insert into t1 values (_ucs2 0x0104),(_ucs2 0x0105),(_ucs2 0x0106),(_ucs2 0x0107);
104
insert into t1 values (_ucs2 0x0108),(_ucs2 0x0109),(_ucs2 0x010a),(_ucs2 0x010b);
105
insert into t1 values (_ucs2 0x010c),(_ucs2 0x010d),(_ucs2 0x010e),(_ucs2 0x010f);
106
insert into t1 values (_ucs2 0x0110),(_ucs2 0x0111),(_ucs2 0x0112),(_ucs2 0x0113);
107
insert into t1 values (_ucs2 0x0114),(_ucs2 0x0115),(_ucs2 0x0116),(_ucs2 0x0117);
108
insert into t1 values (_ucs2 0x0118),(_ucs2 0x0119),(_ucs2 0x011a),(_ucs2 0x011b);
109
insert into t1 values (_ucs2 0x011c),(_ucs2 0x011d),(_ucs2 0x011e),(_ucs2 0x011f);
110
insert into t1 values (_ucs2 0x0120),(_ucs2 0x0121),(_ucs2 0x0122),(_ucs2 0x0123);
111
insert into t1 values (_ucs2 0x0124),(_ucs2 0x0125),(_ucs2 0x0126),(_ucs2 0x0127);
112
insert into t1 values (_ucs2 0x0128),(_ucs2 0x0129),(_ucs2 0x012a),(_ucs2 0x012b);
113
insert into t1 values (_ucs2 0x012c),(_ucs2 0x012d),(_ucs2 0x012e),(_ucs2 0x012f);
114
insert into t1 values (_ucs2 0x0130),(_ucs2 0x0131),(_ucs2 0x0132),(_ucs2 0x0133);
115
insert into t1 values (_ucs2 0x0134),(_ucs2 0x0135),(_ucs2 0x0136),(_ucs2 0x0137);
116
insert into t1 values (_ucs2 0x0138),(_ucs2 0x0139),(_ucs2 0x013a),(_ucs2 0x013b);
117
insert into t1 values (_ucs2 0x013c),(_ucs2 0x013d),(_ucs2 0x013e),(_ucs2 0x013f);
118
insert into t1 values (_ucs2 0x0140),(_ucs2 0x0141),(_ucs2 0x0142),(_ucs2 0x0143);
119
insert into t1 values (_ucs2 0x0144),(_ucs2 0x0145),(_ucs2 0x0146),(_ucs2 0x0147);
120
insert into t1 values (_ucs2 0x0148),(_ucs2 0x0149),(_ucs2 0x014a),(_ucs2 0x014b);
121
insert into t1 values (_ucs2 0x014c),(_ucs2 0x014d),(_ucs2 0x014e),(_ucs2 0x014f);
122
insert into t1 values (_ucs2 0x0150),(_ucs2 0x0151),(_ucs2 0x0152),(_ucs2 0x0153);
123
insert into t1 values (_ucs2 0x0154),(_ucs2 0x0155),(_ucs2 0x0156),(_ucs2 0x0157);
124
insert into t1 values (_ucs2 0x0158),(_ucs2 0x0159),(_ucs2 0x015a),(_ucs2 0x015b);
125
insert into t1 values (_ucs2 0x015c),(_ucs2 0x015d),(_ucs2 0x015e),(_ucs2 0x015f);
126
insert into t1 values (_ucs2 0x0160),(_ucs2 0x0161),(_ucs2 0x0162),(_ucs2 0x0163);
127
insert into t1 values (_ucs2 0x0164),(_ucs2 0x0165),(_ucs2 0x0166),(_ucs2 0x0167);
128
insert into t1 values (_ucs2 0x0168),(_ucs2 0x0169),(_ucs2 0x016a),(_ucs2 0x016b);
129
insert into t1 values (_ucs2 0x016c),(_ucs2 0x016d),(_ucs2 0x016e),(_ucs2 0x016f);
130
insert into t1 values (_ucs2 0x0170),(_ucs2 0x0171),(_ucs2 0x0172),(_ucs2 0x0173);
131
insert into t1 values (_ucs2 0x0174),(_ucs2 0x0175),(_ucs2 0x0176),(_ucs2 0x0177);
132
insert into t1 values (_ucs2 0x0178),(_ucs2 0x0179),(_ucs2 0x017a),(_ucs2 0x017b);
133
insert into t1 values (_ucs2 0x017c),(_ucs2 0x017d),(_ucs2 0x017e),(_ucs2 0x017f);
136
# Latin extended-B, 0180-024F
138
insert into t1 values (_ucs2 0x0180),(_ucs2 0x0181),(_ucs2 0x0182),(_ucs2 0x0183);
139
insert into t1 values (_ucs2 0x0184),(_ucs2 0x0185),(_ucs2 0x0186),(_ucs2 0x0187);
140
insert into t1 values (_ucs2 0x0188),(_ucs2 0x0189),(_ucs2 0x018a),(_ucs2 0x018b);
141
insert into t1 values (_ucs2 0x018c),(_ucs2 0x018d),(_ucs2 0x018e),(_ucs2 0x018f);
142
insert into t1 values (_ucs2 0x0190),(_ucs2 0x0191),(_ucs2 0x0192),(_ucs2 0x0193);
143
insert into t1 values (_ucs2 0x0194),(_ucs2 0x0195),(_ucs2 0x0196),(_ucs2 0x0197);
144
insert into t1 values (_ucs2 0x0198),(_ucs2 0x0199),(_ucs2 0x019a),(_ucs2 0x019b);
145
insert into t1 values (_ucs2 0x019c),(_ucs2 0x019d),(_ucs2 0x019e),(_ucs2 0x019f);
146
insert into t1 values (_ucs2 0x01a0),(_ucs2 0x01a1),(_ucs2 0x01a2),(_ucs2 0x01a3);
147
insert into t1 values (_ucs2 0x01a4),(_ucs2 0x01a5),(_ucs2 0x01a6),(_ucs2 0x01a7);
148
insert into t1 values (_ucs2 0x01a8),(_ucs2 0x01a9),(_ucs2 0x01aa),(_ucs2 0x01ab);
149
insert into t1 values (_ucs2 0x01ac),(_ucs2 0x01ad),(_ucs2 0x01ae),(_ucs2 0x01af);
150
insert into t1 values (_ucs2 0x01b0),(_ucs2 0x01b1),(_ucs2 0x01b2),(_ucs2 0x01b3);
151
insert into t1 values (_ucs2 0x01b4),(_ucs2 0x01b5),(_ucs2 0x01b6),(_ucs2 0x01b7);
152
insert into t1 values (_ucs2 0x01b8),(_ucs2 0x01b9),(_ucs2 0x01ba),(_ucs2 0x01bb);
153
insert into t1 values (_ucs2 0x01bc),(_ucs2 0x01bd),(_ucs2 0x01be),(_ucs2 0x01bf);
154
insert into t1 values (_ucs2 0x01c0),(_ucs2 0x01c1),(_ucs2 0x01c2),(_ucs2 0x01c3);
155
insert into t1 values (_ucs2 0x01c4),(_ucs2 0x01c5),(_ucs2 0x01c6),(_ucs2 0x01c7);
156
insert into t1 values (_ucs2 0x01c8),(_ucs2 0x01c9),(_ucs2 0x01ca),(_ucs2 0x01cb);
157
insert into t1 values (_ucs2 0x01cc),(_ucs2 0x01cd),(_ucs2 0x01ce),(_ucs2 0x01cf);
158
insert into t1 values (_ucs2 0x01d0),(_ucs2 0x01d1),(_ucs2 0x01d2),(_ucs2 0x01d3);
159
insert into t1 values (_ucs2 0x01d4),(_ucs2 0x01d5),(_ucs2 0x01d6),(_ucs2 0x01d7);
160
insert into t1 values (_ucs2 0x01d8),(_ucs2 0x01d9),(_ucs2 0x01da),(_ucs2 0x01db);
161
insert into t1 values (_ucs2 0x01dc),(_ucs2 0x01dd),(_ucs2 0x01de),(_ucs2 0x01df);
162
insert into t1 values (_ucs2 0x01e0),(_ucs2 0x01e1),(_ucs2 0x01e2),(_ucs2 0x01e3);
163
insert into t1 values (_ucs2 0x01e4),(_ucs2 0x01e5),(_ucs2 0x01e6),(_ucs2 0x01e7);
164
insert into t1 values (_ucs2 0x01e8),(_ucs2 0x01e9),(_ucs2 0x01ea),(_ucs2 0x01eb);
165
insert into t1 values (_ucs2 0x01ec),(_ucs2 0x01ed),(_ucs2 0x01ee),(_ucs2 0x01ef);
166
insert into t1 values (_ucs2 0x01f0),(_ucs2 0x01f1),(_ucs2 0x01f2),(_ucs2 0x01f3);
167
insert into t1 values (_ucs2 0x01f4),(_ucs2 0x01f5),(_ucs2 0x01f6),(_ucs2 0x01f7);
168
insert into t1 values (_ucs2 0x01f8),(_ucs2 0x01f9),(_ucs2 0x01fa),(_ucs2 0x01fb);
169
insert into t1 values (_ucs2 0x01fc),(_ucs2 0x01fd),(_ucs2 0x01fe),(_ucs2 0x01ff);
172
insert into t1 values ('AA'),('Aa'),('aa'),('aA');
173
insert into t1 values ('CH'),('Ch'),('ch'),('cH');
174
insert into t1 values ('DZ'),('Dz'),('dz'),('dZ');
175
insert into t1 values ('IJ'),('Ij'),('ij'),('iJ');
176
insert into t1 values ('LJ'),('Lj'),('lj'),('lJ');
177
insert into t1 values ('LL'),('Ll'),('ll'),('lL');
178
insert into t1 values ('NJ'),('Nj'),('nj'),('nJ');
179
insert into t1 values ('OE'),('Oe'),('oe'),('oE');
180
insert into t1 values ('SS'),('Ss'),('ss'),('sS');
181
insert into t1 values ('RR'),('Rr'),('rr'),('rR');
183
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_unicode_ci;
184
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_icelandic_ci;
185
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_latvian_ci;
186
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_romanian_ci;
187
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_slovenian_ci;
188
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_polish_ci;
189
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_estonian_ci;
190
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_spanish_ci;
191
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_swedish_ci;
192
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_turkish_ci;
193
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_czech_ci;
194
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_danish_ci;
195
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_lithuanian_ci;
196
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_slovak_ci;
197
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_spanish2_ci;
198
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_roman_ci;
199
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_esperanto_ci;
200
select group_concat(c1 order by binary c1 separator '') from t1 group by c1 collate utf32_hungarian_ci;
209
CREATE TABLE t1 (c varchar(200) CHARACTER SET utf32 COLLATE utf32_general_ci NOT NULL, INDEX (c));
210
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B403B11F770308);
212
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025 COLLATE utf32_general_ci;
213
INSERT INTO t1 VALUES (CONVERT(_ucs2 0x039C03C903B4 USING utf8));
215
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025
216
COLLATE utf32_general_ci ORDER BY c;
219
CREATE TABLE t1 (c varchar(200) CHARACTER SET utf32 COLLATE utf32_unicode_ci NOT NULL, INDEX (c));
220
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B403B11F770308);
222
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025 COLLATE utf32_unicode_ci;
223
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B4);
225
SELECT * FROM t1 WHERE c LIKE _utf32 0x0000039C00000025
226
COLLATE utf32_unicode_ci ORDER BY c;
229
CREATE TABLE t1 (c varchar(200) CHARACTER SET utf32 COLLATE utf32_unicode_ci NOT NULL, INDEX (c));
230
INSERT INTO t1 VALUES (_ucs2 0x039C03C903B403B11F770308);
232
SELECT * FROM t1 WHERE c LIKE CONVERT(_ucs2 0x039C0025 USING utf32) COLLATE utf32_unicode_ci;
233
INSERT INTO t1 VALUES (CONVERT(_ucs2 0x039C03C903B4 USING utf8));
235
SELECT * FROM t1 WHERE c LIKE CONVERT(_ucs2 0x039C0025 USING utf32)
236
COLLATE utf32_unicode_ci ORDER BY c;
241
SET @test_character_set='utf32';
242
SET @test_collation='utf32_swedish_ci';
243
-- source include/ctype_common.inc
246
SET collation_connection='utf32_unicode_ci';
247
-- source include/ctype_filesort.inc
248
-- source include/ctype_like_escape.inc
250
--echo End of 4.1 tests
253
# Check UPPER/LOWER changing length
255
# Result shorter than argument
256
CREATE TABLE t1 (id int, a varchar(30) character set utf32);
257
INSERT INTO t1 VALUES (1, _ucs2 0x01310069), (2, _ucs2 0x01310131);
258
INSERT INTO t1 VALUES (3, _ucs2 0x00690069), (4, _ucs2 0x01300049);
259
INSERT INTO t1 VALUES (5, _ucs2 0x01300130), (6, _ucs2 0x00490049);
260
SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu
262
ALTER TABLE t1 MODIFY a VARCHAR(30) character set utf32 collate utf32_turkish_ci;
263
SELECT a, length(a) la, @l:=lower(a) l, length(@l) ll, @u:=upper(a) u, length(@u) lu
268
# Bug #27079 Crash while grouping empty ucs2 strings
271
c1 text character set utf32 collate utf32_polish_ci NOT NULL
273
insert into t1 values (''),('a');
274
SELECT COUNT(*), c1 FROM t1 GROUP BY c1;
275
DROP TABLE IF EXISTS t1;
277
--echo End of 5.1 tests
279
set collation_connection=utf32_unicode_ci;
280
--source include/weight_string.inc
281
select hex(weight_string(_utf32 0x10000 collate utf32_unicode_ci));
282
select hex(weight_string(_utf32 0x10001 collate utf32_unicode_ci));
283
--source include/weight_string_l1.inc
285
set @@collation_connection=utf32_czech_ci;
286
--source include/weight_string_chde.inc
289
# Test basic regex functionality
291
set collation_connection=utf32_unicode_ci;
292
--source include/ctype_regex.inc
295
--echo End of 5.2 tests