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
|
--
-- encoding-sensitive tests for json and jsonb
--
-- We provide expected-results files for UTF8 (json_encoding.out)
-- and for SQL_ASCII (json_encoding_1.out). Skip otherwise.
SELECT getdatabaseencoding() NOT IN ('UTF8', 'SQL_ASCII')
AS skip_test \gset
\if :skip_test
\quit
\endif
SELECT getdatabaseencoding(); -- just to label the results files
getdatabaseencoding
---------------------
UTF8
(1 row)
-- first json
-- basic unicode input
SELECT '"\u"'::json; -- ERROR, incomplete escape
ERROR: invalid input syntax for type json
LINE 1: SELECT '"\u"'::json;
^
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u"
SELECT '"\u00"'::json; -- ERROR, incomplete escape
ERROR: invalid input syntax for type json
LINE 1: SELECT '"\u00"'::json;
^
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u00"
SELECT '"\u000g"'::json; -- ERROR, g is not a hex digit
ERROR: invalid input syntax for type json
LINE 1: SELECT '"\u000g"'::json;
^
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u000g...
SELECT '"\u0000"'::json; -- OK, legal escape
json
----------
"\u0000"
(1 row)
SELECT '"\uaBcD"'::json; -- OK, uppercase and lower case both OK
json
----------
"\uaBcD"
(1 row)
-- handling of unicode surrogate pairs
select json '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8;
correct_in_utf8
----------------------------
"\ud83d\ude04\ud83d\udc36"
(1 row)
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
ERROR: invalid input syntax for type json
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ud83d\ud83d...
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ude04...
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ud83dX...
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ude04...
--handling of simple unicode escapes
select json '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
correct_in_utf8
---------------------------------------
{ "a": "the Copyright \u00a9 sign" }
(1 row)
select json '{ "a": "dollar \u0024 character" }' as correct_everywhere;
correct_everywhere
-------------------------------------
{ "a": "dollar \u0024 character" }
(1 row)
select json '{ "a": "dollar \\u0024 character" }' as not_an_escape;
not_an_escape
--------------------------------------
{ "a": "dollar \\u0024 character" }
(1 row)
select json '{ "a": "null \u0000 escape" }' as not_unescaped;
not_unescaped
--------------------------------
{ "a": "null \u0000 escape" }
(1 row)
select json '{ "a": "null \\u0000 escape" }' as not_an_escape;
not_an_escape
---------------------------------
{ "a": "null \\u0000 escape" }
(1 row)
select json '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
correct_in_utf8
----------------------
the Copyright © sign
(1 row)
select json '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
correct_everywhere
--------------------
dollar $ character
(1 row)
select json '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
not_an_escape
-------------------------
dollar \u0024 character
(1 row)
select json '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
ERROR: unsupported Unicode escape sequence
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a": "null \u0000...
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
null \u0000 escape
(1 row)
-- then jsonb
-- basic unicode input
SELECT '"\u"'::jsonb; -- ERROR, incomplete escape
ERROR: invalid input syntax for type json
LINE 1: SELECT '"\u"'::jsonb;
^
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u"
SELECT '"\u00"'::jsonb; -- ERROR, incomplete escape
ERROR: invalid input syntax for type json
LINE 1: SELECT '"\u00"'::jsonb;
^
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u00"
SELECT '"\u000g"'::jsonb; -- ERROR, g is not a hex digit
ERROR: invalid input syntax for type json
LINE 1: SELECT '"\u000g"'::jsonb;
^
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u000g...
SELECT '"\u0045"'::jsonb; -- OK, legal escape
jsonb
-------
"E"
(1 row)
SELECT '"\u0000"'::jsonb; -- ERROR, we don't support U+0000
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT '"\u0000"'::jsonb;
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: "\u0000...
-- use octet_length here so we don't get an odd unicode char in the
-- output
SELECT octet_length('"\uaBcD"'::jsonb::text); -- OK, uppercase and lower case both OK
octet_length
--------------
5
(1 row)
-- handling of unicode surrogate pairs
SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a')::text) AS correct_in_utf8;
correct_in_utf8
-----------------
10
(1 row)
SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a';
^
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ud83d\ud83d...
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ude04...
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ud83dX" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ud83dX...
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
ERROR: invalid input syntax for type json
LINE 1: SELECT jsonb '{ "a": "\ude04X" }' -> 'a';
^
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a": "\ude04...
-- handling of simple unicode escapes
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
correct_in_utf8
-------------------------------
{"a": "the Copyright © sign"}
(1 row)
SELECT jsonb '{ "a": "dollar \u0024 character" }' as correct_everywhere;
correct_everywhere
-----------------------------
{"a": "dollar $ character"}
(1 row)
SELECT jsonb '{ "a": "dollar \\u0024 character" }' as not_an_escape;
not_an_escape
-----------------------------------
{"a": "dollar \\u0024 character"}
(1 row)
SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a": "null \u0000...
SELECT jsonb '{ "a": "null \\u0000 escape" }' as not_an_escape;
not_an_escape
------------------------------
{"a": "null \\u0000 escape"}
(1 row)
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
correct_in_utf8
----------------------
the Copyright © sign
(1 row)
SELECT jsonb '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
correct_everywhere
--------------------
dollar $ character
(1 row)
SELECT jsonb '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
not_an_escape
-------------------------
dollar \u0024 character
(1 row)
SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fai...
^
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a": "null \u0000...
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
null \u0000 escape
(1 row)
|
