1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
|
/*
* This test is for collations and character operations when using the
* builtin provider with the C.UTF-8 locale.
*/
/* skip test if not UTF8 server encoding */
SELECT getdatabaseencoding() <> 'UTF8' AS skip_test \gset
\if :skip_test
\quit
\endif
SET client_encoding TO UTF8;
--
-- Test builtin "C"
--
CREATE COLLATION regress_builtin_c (
provider = builtin, locale = 'C');
-- non-ASCII characters are unchanged
SELECT LOWER(U&'\00C1' COLLATE regress_builtin_c) = U&'\00C1';
?column?
----------
t
(1 row)
SELECT UPPER(U&'\00E1' COLLATE regress_builtin_c) = U&'\00E1';
?column?
----------
t
(1 row)
-- non-ASCII characters are not alphabetic
SELECT U&'\00C1\00E1' !~ '[[:alpha:]]' COLLATE regress_builtin_c;
?column?
----------
t
(1 row)
DROP COLLATION regress_builtin_c;
--
-- Test PG_C_UTF8
--
CREATE COLLATION regress_pg_c_utf8 (
provider = builtin, locale = 'C_UTF8'); -- fails
ERROR: invalid locale name "C_UTF8" for builtin provider
CREATE COLLATION regress_pg_c_utf8 (
provider = builtin, locale = 'C.UTF8');
DROP COLLATION regress_pg_c_utf8;
CREATE COLLATION regress_pg_c_utf8 (
provider = builtin, locale = 'C.UTF-8');
CREATE TABLE test_pg_c_utf8 (
t TEXT COLLATE PG_C_UTF8
);
INSERT INTO test_pg_c_utf8 VALUES
('abc DEF 123abc'),
('ábc sßs ßss DÉF'),
('DŽxxDŽ džxxDž Džxxdž'),
(U&'Λλ 1a \FF11a'),
('ȺȺȺ'),
('ⱥⱥⱥ'),
('ⱥȺ');
SELECT
t, lower(t), initcap(t), upper(t),
length(convert_to(t, 'UTF8')) AS t_bytes,
length(convert_to(lower(t), 'UTF8')) AS lower_t_bytes,
length(convert_to(initcap(t), 'UTF8')) AS initcap_t_bytes,
length(convert_to(upper(t), 'UTF8')) AS upper_t_bytes
FROM test_pg_c_utf8;
t | lower | initcap | upper | t_bytes | lower_t_bytes | initcap_t_bytes | upper_t_bytes
-----------------+-----------------+-----------------+-----------------+---------+---------------+-----------------+---------------
abc DEF 123abc | abc def 123abc | Abc Def 123abc | ABC DEF 123ABC | 14 | 14 | 14 | 14
ábc sßs ßss DÉF | ábc sßs ßss déf | Ábc Sßs ßss Déf | ÁBC SßS ßSS DÉF | 19 | 19 | 19 | 19
DŽxxDŽ džxxDž Džxxdž | džxxdž džxxdž džxxdž | DŽxxdž DŽxxdž DŽxxdž | DŽXXDŽ DŽXXDŽ DŽXXDŽ | 20 | 20 | 20 | 20
Λλ 1a １a | λλ 1a １a | Λλ 1a １A | ΛΛ 1A １A | 12 | 12 | 12 | 12
ȺȺȺ | ⱥⱥⱥ | Ⱥⱥⱥ | ȺȺȺ | 6 | 9 | 8 | 6
ⱥⱥⱥ | ⱥⱥⱥ | Ⱥⱥⱥ | ȺȺȺ | 9 | 9 | 8 | 6
ⱥȺ | ⱥⱥ | Ⱥⱥ | ȺȺ | 5 | 6 | 5 | 4
(7 rows)
DROP TABLE test_pg_c_utf8;
-- negative test: Final_Sigma not used for builtin locale C.UTF-8
SELECT lower('ΑΣ' COLLATE PG_C_UTF8);
lower
-------
ασ
(1 row)
SELECT lower('ΑͺΣͺ' COLLATE PG_C_UTF8);
lower
-------
αͺσͺ
(1 row)
SELECT lower('Α΄Σ΄' COLLATE PG_C_UTF8);
lower
-------
α΄σ΄
(1 row)
-- properties
SELECT 'xyz' ~ '[[:alnum:]]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT 'xyz' !~ '[[:upper:]]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT '@' !~ '[[:alnum:]]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT '=' ~ '[[:punct:]]' COLLATE PG_C_UTF8; -- symbols are punctuation in posix
?column?
----------
t
(1 row)
SELECT 'a8a' ~ '[[:digit:]]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT '൧' !~ '\d' COLLATE PG_C_UTF8; -- only 0-9 considered digits in posix
?column?
----------
t
(1 row)
-- case mapping
SELECT 'xYz' ~* 'XyZ' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT 'xAb' ~* '[W-Y]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT 'xAb' !~* '[c-d]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT 'Δ' ~* '[γ-λ]' COLLATE PG_C_UTF8;
?column?
----------
t
(1 row)
SELECT 'δ' ~* '[Γ-Λ]' COLLATE PG_C_UTF8; -- same as above with cases reversed
?column?
----------
t
(1 row)
-- case folding
select casefold('AbCd 123 #$% ıiIİ ẞ ß DŽDždž Σσς' collate PG_C_UTF8);
casefold
-------------------------------
abcd 123 #$% ıiiİ ß ß dždždž σσσ
(1 row)
--
-- Test PG_UNICODE_FAST
--
CREATE COLLATION regress_pg_unicode_fast (
provider = builtin, locale = 'unicode'); -- fails
ERROR: invalid locale name "unicode" for builtin provider
CREATE COLLATION regress_pg_unicode_fast (
provider = builtin, locale = 'PG_UNICODE_FAST');
CREATE TABLE test_pg_unicode_fast (
t TEXT COLLATE PG_UNICODE_FAST
);
INSERT INTO test_pg_unicode_fast VALUES
('abc DEF 123abc'),
('ábc sßs ßss DÉF'),
('DŽxxDŽ džxxDž Džxxdž'),
(U&'Λλ 1a \FF11a'),
('ȺȺȺ'),
('ⱥⱥⱥ'),
('ⱥȺ');
SELECT
t, lower(t), initcap(t), upper(t),
length(convert_to(t, 'UTF8')) AS t_bytes,
length(convert_to(lower(t), 'UTF8')) AS lower_t_bytes,
length(convert_to(initcap(t), 'UTF8')) AS initcap_t_bytes,
length(convert_to(upper(t), 'UTF8')) AS upper_t_bytes
FROM test_pg_unicode_fast;
t | lower | initcap | upper | t_bytes | lower_t_bytes | initcap_t_bytes | upper_t_bytes
-----------------+-----------------+------------------+-------------------+---------+---------------+-----------------+---------------
abc DEF 123abc | abc def 123abc | Abc Def 123abc | ABC DEF 123ABC | 14 | 14 | 14 | 14
ábc sßs ßss DÉF | ábc sßs ßss déf | Ábc Sßs Ssss Déf | ÁBC SSSS SSSS DÉF | 19 | 19 | 19 | 19
DŽxxDŽ džxxDž Džxxdž | džxxdž džxxdž džxxdž | Džxxdž Džxxdž Džxxdž | DŽXXDŽ DŽXXDŽ DŽXXDŽ | 20 | 20 | 20 | 20
Λλ 1a １a | λλ 1a １a | Λλ 1a １a | ΛΛ 1A １A | 12 | 12 | 12 | 12
ȺȺȺ | ⱥⱥⱥ | Ⱥⱥⱥ | ȺȺȺ | 6 | 9 | 8 | 6
ⱥⱥⱥ | ⱥⱥⱥ | Ⱥⱥⱥ | ȺȺȺ | 9 | 9 | 8 | 6
ⱥȺ | ⱥⱥ | Ⱥⱥ | ȺȺ | 5 | 6 | 5 | 4
(7 rows)
DROP TABLE test_pg_unicode_fast;
-- test Final_Sigma
SELECT lower('ΑΣ' COLLATE PG_UNICODE_FAST); -- 0391 03A3
lower
-------
ας
(1 row)
SELECT lower('ΑΣ0' COLLATE PG_UNICODE_FAST); -- 0391 03A3 0030
lower
-------
ας0
(1 row)
SELECT lower('ἈΣ̓' COLLATE PG_UNICODE_FAST); -- 0391 0343 03A3 0343
lower
-------
ἀς̓
(1 row)
SELECT lower('ᾼΣͅ' COLLATE PG_UNICODE_FAST); -- 0391 0345 03A3 0345
lower
-------
ᾳςͅ
(1 row)
-- test !Final_Sigma
SELECT lower('Σ' COLLATE PG_UNICODE_FAST); -- 03A3
lower
-------
σ
(1 row)
SELECT lower('0Σ' COLLATE PG_UNICODE_FAST); -- 0030 03A3
lower
-------
0σ
(1 row)
SELECT lower('ΑΣΑ' COLLATE PG_UNICODE_FAST); -- 0391 03A3 0391
lower
-------
ασα
(1 row)
SELECT lower('ἈΣ̓Α' COLLATE PG_UNICODE_FAST); -- 0391 0343 03A3 0343 0391
lower
-------
ἀσ̓α
(1 row)
SELECT lower('ᾼΣͅΑ' COLLATE PG_UNICODE_FAST); -- 0391 0345 03A3 0345 0391
lower
-------
ᾳσͅα
(1 row)
-- properties
SELECT 'xyz' ~ '[[:alnum:]]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT 'xyz' !~ '[[:upper:]]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT '@' !~ '[[:alnum:]]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT '=' !~ '[[:punct:]]' COLLATE PG_UNICODE_FAST; -- symbols are not punctuation
?column?
----------
t
(1 row)
SELECT 'a8a' ~ '[[:digit:]]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT '൧' ~ '\d' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
-- case mapping
SELECT 'xYz' ~* 'XyZ' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT 'xAb' ~* '[W-Y]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT 'xAb' !~* '[c-d]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT 'Δ' ~* '[γ-λ]' COLLATE PG_UNICODE_FAST;
?column?
----------
t
(1 row)
SELECT 'δ' ~* '[Γ-Λ]' COLLATE PG_UNICODE_FAST; -- same as above with cases reversed
?column?
----------
t
(1 row)
-- case folding
select casefold('AbCd 123 #$% ıiIİ ẞ ß DŽDždž Σσς' collate PG_UNICODE_FAST);
casefold
---------------------------------
abcd 123 #$% ıiii̇ ss ss dždždž σσσ
(1 row)
|
