File: citext_utf8.sql

package info (click to toggle)
postgresql-18 18~beta3-1
  • links: PTS, VCS
  • area: main
  • in suites: experimental
  • size: 155,816 kB
  • sloc: ansic: 993,154; sql: 127,411; perl: 58,874; xml: 30,905; yacc: 21,023; lex: 9,000; makefile: 6,880; sh: 5,353; cpp: 984; python: 710; asm: 40; sed: 3
file content (61 lines) | stat: -rw-r--r-- 2,394 bytes parent folder | download | duplicates (3)
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
/*
 * This test must be run in a database with UTF-8 encoding
 * and a Unicode-aware locale.
 *
 * Also disable this file for ICU, because the test for the
 * Turkish dotted I is not correct for many ICU locales. citext always
 * uses the default collation, so it's not easy to restrict the test
 * to the "tr-TR-x-icu" collation where it will succeed.
 *
 * Also disable for Windows.  It fails similarly, at least in some locales.
 */

SELECT getdatabaseencoding() <> 'UTF8' OR
       version() ~ '(Visual C\+\+|mingw32|windows)' OR
       (SELECT (datlocprovider = 'c' AND datctype = 'C') OR datlocprovider = 'i'
        FROM pg_database
        WHERE datname=current_database())
       AS skip_test \gset
\if :skip_test
\quit
\endif

set client_encoding = utf8;

-- CREATE EXTENSION IF NOT EXISTS citext;

-- Multibyte sanity tests.
SELECT 'À'::citext =  'À'::citext AS t;
SELECT 'À'::citext =  'à'::citext AS t;
SELECT 'À'::text   =  'à'::text   AS f; -- text wins.
SELECT 'À'::citext <> 'B'::citext AS t;

-- Test combining characters making up canonically equivalent strings.
SELECT 'Ä'::text   <> 'Ä'::text   AS t;
SELECT 'Ä'::citext <> 'Ä'::citext AS t;

-- Test the Turkish dotted I. The lowercase is a single byte while the
-- uppercase is multibyte. This is why the comparison code can't be optimized
-- to compare string lengths.
SELECT 'i'::citext = 'İ'::citext AS t;

-- Regression.
SELECT 'láska'::citext <> 'laská'::citext AS t;

SELECT 'Ask Bjørn Hansen'::citext = 'Ask Bjørn Hansen'::citext AS t;
SELECT 'Ask Bjørn Hansen'::citext = 'ASK BJØRN HANSEN'::citext AS t;
SELECT 'Ask Bjørn Hansen'::citext <> 'Ask Bjorn Hansen'::citext AS t;
SELECT 'Ask Bjørn Hansen'::citext <> 'ASK BJORN HANSEN'::citext AS t;
SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjørn Hansen'::citext) = 0 AS t;
SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ask bjørn hansen'::citext) = 0 AS t;
SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'ASK BJØRN HANSEN'::citext) = 0 AS t;
SELECT citext_cmp('Ask Bjørn Hansen'::citext, 'Ask Bjorn Hansen'::citext) > 0 AS t;
SELECT citext_cmp('Ask Bjorn Hansen'::citext, 'Ask Bjørn Hansen'::citext) < 0 AS t;

-- Test ~<~ and ~<=~
SELECT 'à'::citext ~<~  'À'::citext AS f;
SELECT 'à'::citext ~<=~ 'À'::citext AS t;

-- Test ~>~ and ~>=~
SELECT 'à'::citext ~>~  'À'::citext AS f;
SELECT 'à'::citext ~>=~ 'À'::citext AS t;