summaryrefslogtreecommitdiff
path: root/src/test
diff options
context:
space:
mode:
Diffstat (limited to 'src/test')
-rw-r--r--src/test/regress/expected/json_encoding.out15
-rw-r--r--src/test/regress/expected/json_encoding_1.out39
-rw-r--r--src/test/regress/expected/json_encoding_2.out9
-rw-r--r--src/test/regress/expected/jsonpath_encoding.out15
-rw-r--r--src/test/regress/expected/jsonpath_encoding_1.out33
-rw-r--r--src/test/regress/expected/jsonpath_encoding_2.out9
-rw-r--r--src/test/regress/expected/strings.out83
-rw-r--r--src/test/regress/sql/json_encoding.sql13
-rw-r--r--src/test/regress/sql/jsonpath_encoding.sql13
-rw-r--r--src/test/regress/sql/strings.sql20
10 files changed, 215 insertions, 34 deletions
diff --git a/src/test/regress/expected/json_encoding.out b/src/test/regress/expected/json_encoding.out
index d8d34f4ff6a..f343f74fe18 100644
--- a/src/test/regress/expected/json_encoding.out
+++ b/src/test/regress/expected/json_encoding.out
@@ -1,4 +1,19 @@
+--
-- 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
diff --git a/src/test/regress/expected/json_encoding_1.out b/src/test/regress/expected/json_encoding_1.out
index 79ed78e1c5f..e2fc131b0fa 100644
--- a/src/test/regress/expected/json_encoding_1.out
+++ b/src/test/regress/expected/json_encoding_1.out
@@ -1,4 +1,19 @@
+--
-- 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
+---------------------
+ SQL_ASCII
+(1 row)
+
-- first json
-- basic unicode input
SELECT '"\u"'::json; -- ERROR, incomplete escape
@@ -33,9 +48,7 @@ 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;
-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":...
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
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.
@@ -84,9 +97,7 @@ select json '{ "a": "null \\u0000 escape" }' as not_an_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":...
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
select json '{ "a": "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
correct_everywhere
--------------------
@@ -144,18 +155,14 @@ 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
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
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
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
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';
@@ -182,11 +189,9 @@ 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
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
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
-----------------------------
@@ -212,11 +217,9 @@ SELECT jsonb '{ "a": "null \\u0000 escape" }' as not_an_escape;
(1 row)
SELECT jsonb '{ "a": "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
-ERROR: unsupported Unicode escape sequence
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
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
--------------------
diff --git a/src/test/regress/expected/json_encoding_2.out b/src/test/regress/expected/json_encoding_2.out
new file mode 100644
index 00000000000..4fc8f0241ab
--- /dev/null
+++ b/src/test/regress/expected/json_encoding_2.out
@@ -0,0 +1,9 @@
+--
+-- 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
diff --git a/src/test/regress/expected/jsonpath_encoding.out b/src/test/regress/expected/jsonpath_encoding.out
index ecffe095b59..7cbfb6abcf3 100644
--- a/src/test/regress/expected/jsonpath_encoding.out
+++ b/src/test/regress/expected/jsonpath_encoding.out
@@ -1,4 +1,19 @@
+--
-- encoding-sensitive tests for jsonpath
+--
+-- We provide expected-results files for UTF8 (jsonpath_encoding.out)
+-- and for SQL_ASCII (jsonpath_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)
+
-- checks for double-quoted values
-- basic unicode input
SELECT '"\u"'::jsonpath; -- ERROR, incomplete escape
diff --git a/src/test/regress/expected/jsonpath_encoding_1.out b/src/test/regress/expected/jsonpath_encoding_1.out
index c8cc2173a8c..005136c9657 100644
--- a/src/test/regress/expected/jsonpath_encoding_1.out
+++ b/src/test/regress/expected/jsonpath_encoding_1.out
@@ -1,4 +1,19 @@
+--
-- encoding-sensitive tests for jsonpath
+--
+-- We provide expected-results files for UTF8 (jsonpath_encoding.out)
+-- and for SQL_ASCII (jsonpath_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
+---------------------
+ SQL_ASCII
+(1 row)
+
-- checks for double-quoted values
-- basic unicode input
SELECT '"\u"'::jsonpath; -- ERROR, incomplete escape
@@ -19,16 +34,14 @@ LINE 1: SELECT '"\u0000"'::jsonpath;
^
DETAIL: \u0000 cannot be converted to text.
SELECT '"\uaBcD"'::jsonpath; -- OK, uppercase and lower case both OK
-ERROR: invalid input syntax for type jsonpath
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
LINE 1: SELECT '"\uaBcD"'::jsonpath;
^
-DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-- handling of unicode surrogate pairs
select '"\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_utf8;
-ERROR: invalid input syntax for type jsonpath
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
LINE 1: select '"\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_...
^
-DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
select '"\ud83d\ud83d"'::jsonpath; -- 2 high surrogates in a row
ERROR: invalid input syntax for type jsonpath
LINE 1: select '"\ud83d\ud83d"'::jsonpath;
@@ -51,10 +64,9 @@ LINE 1: select '"\ude04X"'::jsonpath;
DETAIL: Unicode low surrogate must follow a high surrogate.
--handling of simple unicode escapes
select '"the Copyright \u00a9 sign"'::jsonpath as correct_in_utf8;
-ERROR: invalid input syntax for type jsonpath
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
LINE 1: select '"the Copyright \u00a9 sign"'::jsonpath as correct_in...
^
-DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
select '"dollar \u0024 character"'::jsonpath as correct_everywhere;
correct_everywhere
----------------------
@@ -98,16 +110,14 @@ LINE 1: SELECT '$."\u0000"'::jsonpath;
^
DETAIL: \u0000 cannot be converted to text.
SELECT '$."\uaBcD"'::jsonpath; -- OK, uppercase and lower case both OK
-ERROR: invalid input syntax for type jsonpath
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
LINE 1: SELECT '$."\uaBcD"'::jsonpath;
^
-DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-- handling of unicode surrogate pairs
select '$."\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_in_utf8;
-ERROR: invalid input syntax for type jsonpath
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
LINE 1: select '$."\ud83d\ude04\ud83d\udc36"'::jsonpath as correct_i...
^
-DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
select '$."\ud83d\ud83d"'::jsonpath; -- 2 high surrogates in a row
ERROR: invalid input syntax for type jsonpath
LINE 1: select '$."\ud83d\ud83d"'::jsonpath;
@@ -130,10 +140,9 @@ LINE 1: select '$."\ude04X"'::jsonpath;
DETAIL: Unicode low surrogate must follow a high surrogate.
--handling of simple unicode escapes
select '$."the Copyright \u00a9 sign"'::jsonpath as correct_in_utf8;
-ERROR: invalid input syntax for type jsonpath
+ERROR: conversion between UTF8 and SQL_ASCII is not supported
LINE 1: select '$."the Copyright \u00a9 sign"'::jsonpath as correct_...
^
-DETAIL: Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
select '$."dollar \u0024 character"'::jsonpath as correct_everywhere;
correct_everywhere
------------------------
diff --git a/src/test/regress/expected/jsonpath_encoding_2.out b/src/test/regress/expected/jsonpath_encoding_2.out
new file mode 100644
index 00000000000..bb71bfe72c4
--- /dev/null
+++ b/src/test/regress/expected/jsonpath_encoding_2.out
@@ -0,0 +1,9 @@
+--
+-- encoding-sensitive tests for jsonpath
+--
+-- We provide expected-results files for UTF8 (jsonpath_encoding.out)
+-- and for SQL_ASCII (jsonpath_encoding_1.out). Skip otherwise.
+SELECT getdatabaseencoding() NOT IN ('UTF8', 'SQL_ASCII')
+ AS skip_test \gset
+\if :skip_test
+\quit
diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out
index 60cb86193c7..6c4443afcf1 100644
--- a/src/test/regress/expected/strings.out
+++ b/src/test/regress/expected/strings.out
@@ -35,6 +35,12 @@ SELECT U&'d!0061t\+000061' UESCAPE '!' AS U&"d*0061t\+000061" UESCAPE '*';
dat\+000061
(1 row)
+SELECT U&'a\\b' AS "a\b";
+ a\b
+-----
+ a\b
+(1 row)
+
SELECT U&' \' UESCAPE '!' AS "tricky";
tricky
--------
@@ -48,13 +54,15 @@ SELECT 'tricky' AS U&"\" UESCAPE '!';
(1 row)
SELECT U&'wrong: \061';
-ERROR: invalid Unicode escape value
+ERROR: invalid Unicode escape
LINE 1: SELECT U&'wrong: \061';
^
+HINT: Unicode escapes must be \XXXX or \+XXXXXX.
SELECT U&'wrong: \+0061';
-ERROR: invalid Unicode escape value
+ERROR: invalid Unicode escape
LINE 1: SELECT U&'wrong: \+0061';
^
+HINT: Unicode escapes must be \XXXX or \+XXXXXX.
SELECT U&'wrong: +0061' UESCAPE +;
ERROR: UESCAPE must be followed by a simple string literal at or near "+"
LINE 1: SELECT U&'wrong: +0061' UESCAPE +;
@@ -63,6 +71,77 @@ SELECT U&'wrong: +0061' UESCAPE '+';
ERROR: invalid Unicode escape character at or near "'+'"
LINE 1: SELECT U&'wrong: +0061' UESCAPE '+';
^
+SELECT U&'wrong: \db99';
+ERROR: invalid Unicode surrogate pair
+LINE 1: SELECT U&'wrong: \db99';
+ ^
+SELECT U&'wrong: \db99xy';
+ERROR: invalid Unicode surrogate pair
+LINE 1: SELECT U&'wrong: \db99xy';
+ ^
+SELECT U&'wrong: \db99\\';
+ERROR: invalid Unicode surrogate pair
+LINE 1: SELECT U&'wrong: \db99\\';
+ ^
+SELECT U&'wrong: \db99\0061';
+ERROR: invalid Unicode surrogate pair
+LINE 1: SELECT U&'wrong: \db99\0061';
+ ^
+SELECT U&'wrong: \+00db99\+000061';
+ERROR: invalid Unicode surrogate pair
+LINE 1: SELECT U&'wrong: \+00db99\+000061';
+ ^
+SELECT U&'wrong: \+2FFFFF';
+ERROR: invalid Unicode escape value
+LINE 1: SELECT U&'wrong: \+2FFFFF';
+ ^
+-- while we're here, check the same cases in E-style literals
+SELECT E'd\u0061t\U00000061' AS "data";
+ data
+------
+ data
+(1 row)
+
+SELECT E'a\\b' AS "a\b";
+ a\b
+-----
+ a\b
+(1 row)
+
+SELECT E'wrong: \u061';
+ERROR: invalid Unicode escape
+LINE 1: SELECT E'wrong: \u061';
+ ^
+HINT: Unicode escapes must be \uXXXX or \UXXXXXXXX.
+SELECT E'wrong: \U0061';
+ERROR: invalid Unicode escape
+LINE 1: SELECT E'wrong: \U0061';
+ ^
+HINT: Unicode escapes must be \uXXXX or \UXXXXXXXX.
+SELECT E'wrong: \udb99';
+ERROR: invalid Unicode surrogate pair at or near "'"
+LINE 1: SELECT E'wrong: \udb99';
+ ^
+SELECT E'wrong: \udb99xy';
+ERROR: invalid Unicode surrogate pair at or near "x"
+LINE 1: SELECT E'wrong: \udb99xy';
+ ^
+SELECT E'wrong: \udb99\\';
+ERROR: invalid Unicode surrogate pair at or near "\"
+LINE 1: SELECT E'wrong: \udb99\\';
+ ^
+SELECT E'wrong: \udb99\u0061';
+ERROR: invalid Unicode surrogate pair at or near "\u0061"
+LINE 1: SELECT E'wrong: \udb99\u0061';
+ ^
+SELECT E'wrong: \U0000db99\U00000061';
+ERROR: invalid Unicode surrogate pair at or near "\U00000061"
+LINE 1: SELECT E'wrong: \U0000db99\U00000061';
+ ^
+SELECT E'wrong: \U002FFFFF';
+ERROR: invalid Unicode escape value at or near "\U002FFFFF"
+LINE 1: SELECT E'wrong: \U002FFFFF';
+ ^
SET standard_conforming_strings TO off;
SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
ERROR: unsafe use of string constant with Unicode escapes
diff --git a/src/test/regress/sql/json_encoding.sql b/src/test/regress/sql/json_encoding.sql
index 87a2d564ff3..d7fac69733d 100644
--- a/src/test/regress/sql/json_encoding.sql
+++ b/src/test/regress/sql/json_encoding.sql
@@ -1,5 +1,16 @@
-
+--
-- 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
-- first json
diff --git a/src/test/regress/sql/jsonpath_encoding.sql b/src/test/regress/sql/jsonpath_encoding.sql
index 3a23b728182..55d9e30b95c 100644
--- a/src/test/regress/sql/jsonpath_encoding.sql
+++ b/src/test/regress/sql/jsonpath_encoding.sql
@@ -1,5 +1,16 @@
-
+--
-- encoding-sensitive tests for jsonpath
+--
+
+-- We provide expected-results files for UTF8 (jsonpath_encoding.out)
+-- and for SQL_ASCII (jsonpath_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
-- checks for double-quoted values
diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql
index c5cd15142a5..3e28cd198f4 100644
--- a/src/test/regress/sql/strings.sql
+++ b/src/test/regress/sql/strings.sql
@@ -21,6 +21,7 @@ SET standard_conforming_strings TO on;
SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
SELECT U&'d!0061t\+000061' UESCAPE '!' AS U&"d*0061t\+000061" UESCAPE '*';
+SELECT U&'a\\b' AS "a\b";
SELECT U&' \' UESCAPE '!' AS "tricky";
SELECT 'tricky' AS U&"\" UESCAPE '!';
@@ -30,6 +31,25 @@ SELECT U&'wrong: \+0061';
SELECT U&'wrong: +0061' UESCAPE +;
SELECT U&'wrong: +0061' UESCAPE '+';
+SELECT U&'wrong: \db99';
+SELECT U&'wrong: \db99xy';
+SELECT U&'wrong: \db99\\';
+SELECT U&'wrong: \db99\0061';
+SELECT U&'wrong: \+00db99\+000061';
+SELECT U&'wrong: \+2FFFFF';
+
+-- while we're here, check the same cases in E-style literals
+SELECT E'd\u0061t\U00000061' AS "data";
+SELECT E'a\\b' AS "a\b";
+SELECT E'wrong: \u061';
+SELECT E'wrong: \U0061';
+SELECT E'wrong: \udb99';
+SELECT E'wrong: \udb99xy';
+SELECT E'wrong: \udb99\\';
+SELECT E'wrong: \udb99\u0061';
+SELECT E'wrong: \U0000db99\U00000061';
+SELECT E'wrong: \U002FFFFF';
+
SET standard_conforming_strings TO off;
SELECT U&'d\0061t\+000061' AS U&"d\0061t\+000061";
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-01 16:35:43 +0000