--
-- encoding-sensitive tests for json and jsonb
--
SELECT getdatabaseencoding(); -- just to label the results files
-- first json
-- basic unicode input
SELECT '"\u"'::json; -- ERROR, incomplete escape
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
-- first json
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u"
-- first json
^
SELECT '"\u00"'::json; -- ERROR, incomplete escape
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT '"\u00"'::json; -- ERROR, incomplete escape
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u00"
SELECT '"\u00"'::json; -- ERROR, incomplete escape
^
SELECT '"\u000g"'::json; -- ERROR, g is not a hex digit
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT '"\u000g"'::json; -- ERROR, g is not a hex digit
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u000g...
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
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
^
-stdin-::1:1: Fatal: 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": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
^
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
^
-stdin-::1:1: Fatal: 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": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
^
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
^
-stdin-::1:1: Fatal: 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
^
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
^
-stdin-::1:1: Fatal: 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
^
--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;
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
select json '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
^
-stdin-::1:1: Fatal: 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 fails;
^
select json '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;
-- then jsonb
-- basic unicode input
SELECT '"\u"'::jsonb; -- ERROR, incomplete escape
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
-- then jsonb
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u"
-- then jsonb
^
SELECT '"\u00"'::jsonb; -- ERROR, incomplete escape
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT '"\u00"'::jsonb; -- ERROR, incomplete escape
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u00"
SELECT '"\u00"'::jsonb; -- ERROR, incomplete escape
^
SELECT '"\u000g"'::jsonb; -- ERROR, g is not a hex digit
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT '"\u000g"'::jsonb; -- ERROR, g is not a hex digit
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: "\u" must be followed by four hexadecimal digits.
CONTEXT: JSON data, line 1: "\u000g...
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
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT '"\u0000"'::jsonb; -- ERROR, we don't support U+0000
^
-stdin-::1:1: Fatal: ERROR: unsupported Unicode escape sequence
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: ...
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
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: Unicode high surrogate must not follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
SELECT jsonb '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
^
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
SELECT jsonb '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
^
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
SELECT jsonb '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
^
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT jsonb '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate
^
-stdin-::1:1: Fatal: ERROR: invalid input syntax for type json
DETAIL: Unicode low surrogate must follow a high surrogate.
CONTEXT: JSON data, line 1: { "a":...
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;
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT jsonb '{ "a": "null \u0000 escape" }' as fails;
^
-stdin-::1:1: Fatal: ERROR: unsupported Unicode escape sequence
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
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;
-stdin-:: Fatal: Execution
-stdin-::1:1: Fatal: Execution of node: Result
SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
^
-stdin-::1:1: Fatal: ERROR: unsupported Unicode escape sequence
DETAIL: \u0000 cannot be converted to text.
CONTEXT: JSON data, line 1: { "a":...
SELECT jsonb '{ "a": "null \u0000 escape" }' ->> 'a' as fails;
^
SELECT jsonb '{ "a": "null \\u0000 escape" }' ->> 'a' as not_an_escape;