database/postgres
database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-05-03 22:24:49 +03:00
Code

Factor out encoding specific tests for json

Browse Source 
This lets us remove the large alternative results files for the main
json and jsonb tests, which makes modifying those tests simpler for
committers and patch submitters.

Backpatch to 9.4 for jsonb and 9.3 for json.
This commit is contained in:
Andrew Dunstan 2015-10-07 17:41:45 -04:00
parent fc95734a14
commit 48a78d80c8
11 changed files with 564 additions and 5362 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

113
src/test/regress/expected/json.out
View File

@ -42,36 +42,7 @@ LINE 1: SELECT '"\v"'::json;
^
DETAIL: Escape sequence "\v" is invalid.
CONTEXT: JSON data, line 1: "\v...
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)
-- see json_encoding test for input with unicode escapes
-- Numbers.
SELECT '1'::json; -- OK
json
@ -1419,88 +1390,6 @@ select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":[100,200,3
{"z":true} | 3 | Fri Jan 20 10:42:53 2012
(2 rows)
-- 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":...
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":...
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":...
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":...
--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":...
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
null \u0000 escape
(1 row)
--json_typeof() function
select value, json_typeof(value)
from (values (json '123.4'),

1726
src/test/regress/expected/json_1.out
View File

File diff suppressed because it is too large Load Diff

247
src/test/regress/expected/json_encoding.out Normal file
View File

@ -0,0 +1,247 @@
-- encoding-sensitive tests for json and jsonb
-- 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":...
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":...
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":...
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":...
--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":...
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: ...
-- 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":...
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":...
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":...
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":...
-- 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":...
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":...
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
null \u0000 escape
(1 row)

243
src/test/regress/expected/json_encoding_1.out Normal file
View File

@ -0,0 +1,243 @@
-- encoding-sensitive tests for json and jsonb
-- 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;
ERROR: unsupported Unicode escape sequence
DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
CONTEXT: JSON data, line 1: { "a":...
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":...
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":...
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":...
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":...
--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;
ERROR: unsupported Unicode escape sequence
DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
CONTEXT: JSON data, line 1: { "a":...
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":...
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: ...
-- 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
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT octet_length('"\uaBcD"'::jsonb::text);
^
DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
CONTEXT: JSON data, line 1: ...
-- handling of unicode surrogate pairs
SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a')::text) AS correct_in_utf8;
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc3...
^
DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
CONTEXT: JSON data, line 1: { "a":...
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":...
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":...
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":...
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":...
-- handling of simple unicode escapes
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as corr...
^
DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
CONTEXT: JSON data, line 1: { "a":...
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":...
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;
ERROR: unsupported Unicode escape sequence
LINE 1: SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' ->> 'a'...
^
DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
CONTEXT: JSON data, line 1: { "a":...
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":...
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
null \u0000 escape
(1 row)

131
src/test/regress/expected/jsonb.out
View File

@ -42,44 +42,7 @@ LINE 1: SELECT '"\v"'::jsonb;
^
DETAIL: Escape sequence "\v" is invalid.
CONTEXT: JSON data, line 1: "\v...
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: ...
-- 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)
-- see json_encoding test for input with unicode escapes
-- Numbers.
SELECT '1'::jsonb; -- OK
jsonb
@ -1981,98 +1944,6 @@ SELECT * FROM jsonb_populate_recordset(row('def',99,NULL)::jbpop,'[{"a":[100,200
{"z": true} | 3 | Fri Jan 20 10:42:53 2012
(2 rows)
-- 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":...
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":...
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":...
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":...
-- 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":...
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":...
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
not_an_escape
--------------------
null \u0000 escape
(1 row)
-- jsonb_to_record and jsonb_to_recordset
select * from jsonb_to_record('{"a":1,"b":"foo","c":"bar"}')
as x(a int, b text, d text);

3336
src/test/regress/expected/jsonb_1.out
View File

File diff suppressed because it is too large Load Diff

2
src/test/regress/parallel_schedule
View File

@ -97,7 +97,7 @@ test: rules
# ----------
# Another group of parallel tests
# ----------
test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock json jsonb indirect_toast equivclass
test: select_views portals_p2 foreign_key cluster dependency guc bitmapops combocid tsearch tsdicts foreign_data window xmlmap functional_deps advisory_lock json jsonb json_encoding indirect_toast equivclass
# ----------
# Another group of parallel tests
# NB: temp.sql does a reconnect which transiently uses 2 connections,

1
src/test/regress/serial_schedule
View File

@ -134,6 +134,7 @@ test: functional_deps
test: advisory_lock
test: json
test: jsonb
test: json_encoding
test: indirect_toast
test: equivclass
test: plancache

28
src/test/regress/sql/json.sql
View File

@ -7,11 +7,7 @@ SELECT '"abc
def"'::json; -- ERROR, unescaped newline in string constant
SELECT '"\n\"\\"'::json; -- OK, legal escapes
SELECT '"\v"'::json; -- ERROR, not a valid JSON escape
SELECT '"\u"'::json; -- ERROR, incomplete escape
SELECT '"\u00"'::json; -- ERROR, incomplete escape
SELECT '"\u000g"'::json; -- ERROR, g is not a hex digit
SELECT '"\u0000"'::json; -- OK, legal escape
SELECT '"\uaBcD"'::json; -- OK, uppercase and lower case both OK
-- see json_encoding test for input with unicode escapes
-- Numbers.
SELECT '1'::json; -- OK
@ -405,28 +401,6 @@ select * from json_populate_recordset(null::jpop,'[{"a":"blurfl","x":43.2},{"b":
select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":"blurfl","x":43.2},{"b":3,"c":"2012-01-20 10:42:53"}]') q;
select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]') q;
-- handling of unicode surrogate pairs
select json '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8;
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
--handling of simple unicode escapes
select json '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
select json '{ "a": "dollar \u0024 character" }' as correct_everywhere;
select json '{ "a": "dollar \\u0024 character" }' as not_an_escape;
select json '{ "a": "null \u0000 escape" }' as not_unescaped;
select json '{ "a": "null \\u0000 escape" }' as not_an_escape;
select json '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
select json '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
select json '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
select json '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
--json_typeof() function
select value, json_typeof(value)
from (values (json '123.4'),

68
src/test/regress/sql/json_encoding.sql Normal file
View File

@ -0,0 +1,68 @@
-- encoding-sensitive tests for json and jsonb
-- first json
-- basic unicode input
SELECT '"\u"'::json; -- ERROR, incomplete escape
SELECT '"\u00"'::json; -- ERROR, incomplete escape
SELECT '"\u000g"'::json; -- ERROR, g is not a hex digit
SELECT '"\u0000"'::json; -- OK, legal escape
SELECT '"\uaBcD"'::json; -- OK, uppercase and lower case both OK
-- handling of unicode surrogate pairs
select json '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8;
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
--handling of simple unicode escapes
select json '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
select json '{ "a": "dollar \u0024 character" }' as correct_everywhere;
select json '{ "a": "dollar \\u0024 character" }' as not_an_escape;
select json '{ "a": "null \u0000 escape" }' as not_unescaped;
select json '{ "a": "null \\u0000 escape" }' as not_an_escape;
select json '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
select json '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
select json '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
select json '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
-- then jsonb
-- basic unicode input
SELECT '"\u"'::jsonb; -- ERROR, incomplete escape
SELECT '"\u00"'::jsonb; -- ERROR, incomplete escape
SELECT '"\u000g"'::jsonb; -- ERROR, g is not a hex digit
SELECT '"\u0045"'::jsonb; -- OK, legal escape
SELECT '"\u0000"'::jsonb; -- ERROR, we don't support U+0000
-- 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
-- handling of unicode surrogate pairs
SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a')::text) AS correct_in_utf8;
SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
-- handling of simple unicode escapes
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
SELECT jsonb '{ "a": "dollar \u0024 character" }' as correct_everywhere;
SELECT jsonb '{ "a": "dollar \\u0024 character" }' as not_an_escape;
SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
SELECT jsonb '{ "a": "null \\u0000 escape" }' as not_an_escape;
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
SELECT jsonb '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
SELECT jsonb '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;

31
src/test/regress/sql/jsonb.sql
View File

@ -7,14 +7,7 @@ SELECT '"abc
def"'::jsonb; -- ERROR, unescaped newline in string constant
SELECT '"\n\"\\"'::jsonb; -- OK, legal escapes
SELECT '"\v"'::jsonb; -- ERROR, not a valid JSON escape
SELECT '"\u"'::jsonb; -- ERROR, incomplete escape
SELECT '"\u00"'::jsonb; -- ERROR, incomplete escape
SELECT '"\u000g"'::jsonb; -- ERROR, g is not a hex digit
SELECT '"\u0045"'::jsonb; -- OK, legal escape
SELECT '"\u0000"'::jsonb; -- ERROR, we don't support U+0000
-- 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
-- see json_encoding test for input with unicode escapes
-- Numbers.
SELECT '1'::jsonb; -- OK
@ -494,28 +487,6 @@ SELECT * FROM jsonb_populate_recordset(NULL::jbpop,'[{"a":"blurfl","x":43.2},{"b
SELECT * FROM jsonb_populate_recordset(row('def',99,NULL)::jbpop,'[{"a":"blurfl","x":43.2},{"b":3,"c":"2012-01-20 10:42:53"}]') q;
SELECT * FROM jsonb_populate_recordset(row('def',99,NULL)::jbpop,'[{"a":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]') q;
-- handling of unicode surrogate pairs
SELECT octet_length((jsonb '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a')::text) AS correct_in_utf8;
SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
-- handling of simple unicode escapes
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' as correct_in_utf8;
SELECT jsonb '{ "a": "dollar \u0024 character" }' as correct_everywhere;
SELECT jsonb '{ "a": "dollar \\u0024 character" }' as not_an_escape;
SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
SELECT jsonb '{ "a": "null \\u0000 escape" }' as not_an_escape;
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
SELECT jsonb '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
SELECT jsonb '{ "a": "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
-- jsonb_to_record and jsonb_to_recordset
select * from jsonb_to_record('{"a":1,"b":"foo","c":"bar"}')