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
|
/*
* This test must be run in a database with UTF-8 encoding,
* because other encodings don't support all the characters used.
*/
SELECT getdatabaseencoding() <> 'UTF8'
AS skip_test \gset
\if :skip_test
\quit
\endif
CREATE EXTENSION unaccent;
SET client_encoding TO 'UTF8';
SELECT unaccent('foobar');
unaccent
----------
foobar
(1 row)
SELECT unaccent('ёлка');
unaccent
----------
елка
(1 row)
SELECT unaccent('ЁЖИК');
unaccent
----------
ЕЖИК
(1 row)
SELECT unaccent('˃˖˗˜');
unaccent
----------
>+-~
(1 row)
SELECT unaccent('À'); -- Remove combining diacritical 0x0300
unaccent
----------
A
(1 row)
SELECT unaccent('℃℉'); -- degree signs
unaccent
----------
°C°F
(1 row)
SELECT unaccent('℗'); -- sound recording copyright
unaccent
----------
(P)
(1 row)
SELECT unaccent('1½'); -- math expression with whitespace
unaccent
----------
1 1/2
(1 row)
SELECT unaccent('〝'); -- quote
unaccent
----------
"
(1 row)
SELECT unaccent('unaccent', 'foobar');
unaccent
----------
foobar
(1 row)
SELECT unaccent('unaccent', 'ёлка');
unaccent
----------
елка
(1 row)
SELECT unaccent('unaccent', 'ЁЖИК');
unaccent
----------
ЕЖИК
(1 row)
SELECT unaccent('unaccent', '˃˖˗˜');
unaccent
----------
>+-~
(1 row)
SELECT unaccent('unaccent', 'À');
unaccent
----------
A
(1 row)
SELECT unaccent('unaccent', '℃℉');
unaccent
----------
°C°F
(1 row)
SELECT unaccent('unaccent', '℗');
unaccent
----------
(P)
(1 row)
SELECT unaccent('unaccent', '1½');
unaccent
----------
1 1/2
(1 row)
SELECT unaccent('unaccent', '〝');
unaccent
----------
"
(1 row)
SELECT ts_lexize('unaccent', 'foobar');
ts_lexize
-----------
(1 row)
SELECT ts_lexize('unaccent', 'ёлка');
ts_lexize
-----------
{елка}
(1 row)
SELECT ts_lexize('unaccent', 'ЁЖИК');
ts_lexize
-----------
{ЕЖИК}
(1 row)
SELECT ts_lexize('unaccent', '˃˖˗˜');
ts_lexize
-----------
{>+-~}
(1 row)
SELECT ts_lexize('unaccent', 'À');
ts_lexize
-----------
{A}
(1 row)
SELECT ts_lexize('unaccent', '℃℉');
ts_lexize
-----------
{°C°F}
(1 row)
SELECT ts_lexize('unaccent', '℗');
ts_lexize
-----------
{(P)}
(1 row)
SELECT ts_lexize('unaccent', '1½');
ts_lexize
-----------
{"1 1/2"}
(1 row)
SELECT ts_lexize('unaccent', '〝');
ts_lexize
-----------
{"\""}
(1 row)
-- Controversial case. Black-Letter Capital H (U+210C) is translated by
-- Latin-ASCII.xml as 'x', but it should be 'H'.
SELECT unaccent('ℌ');
unaccent
----------
x
(1 row)
|
