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
|
/*
* 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
set client_encoding = utf8;
set standard_conforming_strings = on;
-- Run the Tcl test cases that require Unicode
-- expectMatch 9.44 EMP* {a[\u00fe-\u0507][\u00ff-\u0300]b} \
-- "a\u0102\u02ffb" "a\u0102\u02ffb"
select * from test_regex('a[\u00fe-\u0507][\u00ff-\u0300]b', E'a\u0102\u02ffb', 'EMP*');
test_regex
----------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT}
{aĂ˿b}
(2 rows)
-- expectMatch 13.27 P "a\\U00001234x" "a\u1234x" "a\u1234x"
select * from test_regex('a\U00001234x', E'a\u1234x', 'P');
test_regex
-------------------
{0,REG_UNONPOSIX}
{aሴx}
(2 rows)
-- expectMatch 13.28 P {a\U00001234x} "a\u1234x" "a\u1234x"
select * from test_regex('a\U00001234x', E'a\u1234x', 'P');
test_regex
-------------------
{0,REG_UNONPOSIX}
{aሴx}
(2 rows)
-- expectMatch 13.29 P "a\\U0001234x" "a\u1234x" "a\u1234x"
-- Tcl has relaxed their code to allow 1-8 hex digits, but Postgres hasn't
select * from test_regex('a\U0001234x', E'a\u1234x', 'P');
ERROR: invalid regular expression: invalid escape \ sequence
-- expectMatch 13.30 P {a\U0001234x} "a\u1234x" "a\u1234x"
-- Tcl has relaxed their code to allow 1-8 hex digits, but Postgres hasn't
select * from test_regex('a\U0001234x', E'a\u1234x', 'P');
ERROR: invalid regular expression: invalid escape \ sequence
-- expectMatch 13.31 P "a\\U000012345x" "a\u12345x" "a\u12345x"
select * from test_regex('a\U000012345x', E'a\u12345x', 'P');
test_regex
-------------------
{0,REG_UNONPOSIX}
{aሴ5x}
(2 rows)
-- expectMatch 13.32 P {a\U000012345x} "a\u12345x" "a\u12345x"
select * from test_regex('a\U000012345x', E'a\u12345x', 'P');
test_regex
-------------------
{0,REG_UNONPOSIX}
{aሴ5x}
(2 rows)
-- expectMatch 13.33 P "a\\U1000000x" "a\ufffd0x" "a\ufffd0x"
-- Tcl allows this as a standalone character, but Postgres doesn't
select * from test_regex('a\U1000000x', E'a\ufffd0x', 'P');
ERROR: invalid regular expression: invalid escape \ sequence
-- expectMatch 13.34 P {a\U1000000x} "a\ufffd0x" "a\ufffd0x"
-- Tcl allows this as a standalone character, but Postgres doesn't
select * from test_regex('a\U1000000x', E'a\ufffd0x', 'P');
ERROR: invalid regular expression: invalid escape \ sequence
-- Additional tests, not derived from Tcl
-- Exercise logic around high character ranges a bit more
select * from test_regex('a
[\u1000-\u1100]*
[\u3000-\u3100]*
[\u1234-\u25ff]+
[\u2000-\u35ff]*
[\u2600-\u2f00]*
\u1236\u1236x',
E'a\u1234\u1236\u1236x', 'xEMP');
test_regex
----------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT}
{aሴሶሶx}
(2 rows)
select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
E'\u1500\u1237', 'ELMP');
test_regex
----------------------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT,REG_ULOCALE}
{ᔀሷ}
(2 rows)
select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
E'A\u1239', 'ELMP');
test_regex
----------------------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT,REG_ULOCALE}
(1 row)
select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
E'\u1500\u1237', 'iELMP');
test_regex
----------------------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT,REG_ULOCALE}
{ᔀሷ}
(2 rows)
-- systematically test char classes
select * from test_regex('[[:alnum:]]+', E'x*\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{x}
(2 rows)
select * from test_regex('[[:alpha:]]+', E'x*\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{x}
(2 rows)
select * from test_regex('[[:ascii:]]+', E'x\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{x}
(2 rows)
select * from test_regex('[[:blank:]]+', E'x \t\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{" "}
(2 rows)
select * from test_regex('[[:cntrl:]]+', E'x\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
(1 row)
select * from test_regex('[[:digit:]]+', E'x9\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{9}
(2 rows)
select * from test_regex('[[:graph:]]+', E'x\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{xᔀሷ}
(2 rows)
select * from test_regex('[[:lower:]]+', E'x\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{x}
(2 rows)
select * from test_regex('[[:print:]]+', E'x\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{xᔀሷ}
(2 rows)
select * from test_regex('[[:punct:]]+', E'x.\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{.}
(2 rows)
select * from test_regex('[[:space:]]+', E'x \t\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{" "}
(2 rows)
select * from test_regex('[[:upper:]]+', E'xX\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{X}
(2 rows)
select * from test_regex('[[:xdigit:]]+', E'xa9\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{a9}
(2 rows)
select * from test_regex('[[:word:]]+', E'x_*\u1500\u1237', 'L');
test_regex
-----------------
{0,REG_ULOCALE}
{x_}
(2 rows)
|
