bojana-db commented on code in PR #58281:
URL: https://github.com/apache/spark/pull/58281#discussion_r3940726815
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/variant/variantExpressions.scala:
##########
@@ -1000,6 +1000,192 @@ object VariantDelete {
}
}
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = "_FUNC_(v, path1[, path2, ...]) - Keeps only the fields or array
elements of a variant " +
+ "at the given JSONPath locations, preserving their enclosing structure;
kept array elements " +
+ "are compacted into a new array in their original order. If no path
matches, an object or " +
+ "array input yields an empty object or array, while a scalar or
variant-null input is " +
+ "unchanged. Returns NULL if `v` is NULL; NULL paths are skipped.",
+ arguments = """
+ Arguments:
+ * v - A variant value to project.
+ * path1, path2, ... - One or more string expressions, each evaluating to
a JSONPath
+ identifying a substructure to keep. A valid path should start with
`$` and is followed by
+ zero or more segments like `[123]`, `.name`, `['name']`, or
`["name"]`.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(parse_json('{"a": 1, "b": 2, "c": 3}'), '$.a', '$.c');
+ {"a":1,"c":3}
+ > SELECT _FUNC_(parse_json('{"a": {"b": 1, "c": 2}, "d": 3}'), '$.a.b');
+ {"a":{"b":1}}
+ > SELECT _FUNC_(parse_json('[10, 20, 30, 40]'), '$[0]', '$[2]');
+ [10,30]
+ > SELECT _FUNC_(parse_json('{"a": 1, "b": 2}'), NULL, '$.a',
'$.missing');
+ {"a":1}
+ > SELECT _FUNC_(parse_json('{"a": {"b": 1}}'), '$.a.x');
+ {}
+ > SELECT _FUNC_(parse_json('42'), '$.a');
+ 42
+ > SELECT _FUNC_(NULL, '$.a');
+ NULL
+ """,
+ since = "4.4.0",
+ group = "variant_funcs"
+)
+// scalastyle:on line.size.limit
+case class VariantPick(children: Seq[Expression])
+ extends Expression
+ with ExpectsInputTypes {
+
+ override def dataType: DataType = VariantType
+
+ override def nullable: Boolean = children.headOption.forall(_.nullable)
Review Comment:
This is done in order to match other engines. NULL paths in variadic
functions are always skipped, rather than nulling the whole output.
--
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]
