vinodkc commented on code in PR #58024:
URL: https://github.com/apache/spark/pull/58024#discussion_r4474125314
##########
sql/core/src/test/resources/sql-tests/inputs/json-functions.sql:
##########
@@ -335,3 +335,133 @@ select json_object('a' VALUE '{"b":1}');
select json_object('a' VALUE 1 RETURNING INT);
-- JSON_OBJECT error: malformed FORMAT JSON value
select json_object('a' VALUE '{bad' FORMAT JSON);
+
+-- IS [NOT] JSON
+-- basic well-formedness
+select '{"a":1}' IS JSON;
+select '[1,2]' IS JSON;
+select '42' IS JSON;
+select '"hello"' IS JSON;
+select 'not json' IS JSON;
+select '' IS JSON;
+-- IS NOT JSON
+select '{"a":1}' IS NOT JSON;
+select 'bad' IS NOT JSON;
+-- NULL propagates
+select cast(null as string) IS JSON;
+select cast(null as string) IS NOT JSON;
+-- shape qualifiers
+select '{"a":1}' IS JSON OBJECT;
+select '[1,2]' IS JSON OBJECT;
+select '[1,2]' IS JSON ARRAY;
+select '{"a":1}' IS JSON ARRAY;
+-- IS JSON VALUE: any valid JSON value (including objects and arrays)
+select '42' IS JSON VALUE;
+select '"hello"' IS JSON VALUE;
+select '{"a":1}' IS JSON VALUE;
+select '[1,2]' IS JSON VALUE;
+select 'bad' IS JSON VALUE;
+-- IS JSON SCALAR: only primitives (string, number, boolean, null -- not
object/array)
+select '42' IS JSON SCALAR;
+select '"hello"' IS JSON SCALAR;
+select 'true' IS JSON SCALAR;
+select 'false' IS JSON SCALAR;
+select '[1]' IS JSON SCALAR;
+select '{"a":1}' IS JSON SCALAR;
+-- IS NOT JSON with shape qualifiers
+select '{"a":1}' IS NOT JSON OBJECT;
+select '[1,2]' IS NOT JSON ARRAY;
+select '{"a":1}' IS NOT JSON VALUE;
+select 'bad' IS NOT JSON VALUE;
+select '{"a":1}' IS NOT JSON SCALAR;
+select '42' IS NOT JSON SCALAR;
+-- JSON null literal is valid JSON and counts as a scalar
+select 'null' IS JSON;
+select 'null' IS JSON SCALAR;
+select 'null' IS JSON VALUE;
+select 'null' IS JSON OBJECT;
+-- strict ANSI parsing: Hive-style leniency (single quotes) is rejected
+select '{''a'':1}' IS JSON;
+select '[''a'', ''b'']' IS JSON;
+-- trailing content after a well-formed value is rejected
+select '1 2' IS JSON;
+select '{} []' IS JSON;
+-- other parser extensions are rejected: comments, unquoted names,
NaN/Infinity, leading zeros
+select '/* c */ {}' IS JSON, '{a:1}' IS JSON, 'NaN' IS JSON, 'Infinity' IS
JSON, '01' IS JSON;
+-- whitespace-only input is not a JSON value
+select ' ' IS JSON;
+-- duplicate field names are accepted
+select '{"a":1,"a":2}' IS JSON OBJECT;
+-- input beyond the parser limits raises an error, like parse_json
+select concat(repeat('[', 1001), repeat(']', 1001)) IS JSON;
+-- a shape mismatch is decided by the first token even for over-limit input:
an over-long root
+-- number is neither an object nor an array, so those shapes return false
instead of raising
+select repeat('9', 1001) IS JSON OBJECT, repeat('9', 1001) IS JSON ARRAY;
+-- structurally malformed containers are rejected: truncated input, trailing
commas, missing
+-- values, and a mismatched closer
+select '{' IS JSON, '[1,' IS JSON, '{"a"' IS JSON;
+select '[1,]' IS JSON ARRAY, '{"a":1,}' IS JSON OBJECT, '[1,,2]' IS JSON
ARRAY, '[1}' IS JSON ARRAY;
+-- input that is not valid UTF-8 is rejected (lone continuation byte, encoded
surrogate)
+select cast(X'228022' AS STRING) IS JSON;
+select cast(X'22EDA08022' AS STRING) IS JSON;
+-- unpaired surrogate escapes are rejected in values and field names, also
when nested
+select '"\\uD835"' IS JSON;
+select '"\\uDC00"' IS JSON SCALAR;
+select '{"\\uD835":1}' IS JSON OBJECT;
+select '[{"a":["\\uDC00"]}]' IS JSON ARRAY;
+select '"\\uD835\\uDC00"' IS JSON;
+-- shift operators after the ARRAY qualifier
+select '[1]' IS JSON ARRAY, 8 >> 1, 8 >>> 1;
+-- collated and trim-collated operands behave like STRING
+select '{"a":1}' COLLATE UTF8_LCASE IS JSON OBJECT, '[1] ' COLLATE
UTF8_LCASE_RTRIM IS JSON ARRAY;
+select 'bad' COLLATE UNICODE IS JSON;
+-- by default a CHAR/VARCHAR cast target is rewritten to STRING at parse time,
so this case
+-- exercises a STRING operand
+select cast('[1]' AS VARCHAR(10)) IS JSON ARRAY;
+-- with first-class CHAR/VARCHAR types (preserveCharVarcharTypeInfo or
standard semantics), the
+-- cast keeps its type, so IS JSON gets a real VARCHAR or CHAR operand
Review Comment:
Fixed.
The comments now describe each config separately:
preserveCharVarcharTypeInfo keeps the CHAR/VARCHAR type, while standard
semantics keeps the type at parse time but type coercion promotes the operand
to STRING. A CHAR case was added to the standard-semantics block, and the
analyzer golden pins the cast(cast(... as char(10)) as string) promotion.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
