iRakson commented on a change in pull request #27836: [SPARK-31009][SQL]
Support json_object_keys function
URL: https://github.com/apache/spark/pull/27836#discussion_r405338801
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
##########
@@ -796,3 +797,67 @@ case class SchemaOfJson(
override def prettyName: String = "schema_of_json"
}
+
+/**
+ * A function which returns all the keys of the outmost JSON object.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(json_object) - returns all the keys of the outmost JSON
object as an array.",
+ arguments = """
+ Arguments:
+ * json_object - A JSON object. If a valid JSON object is given, all the
keys of the outmost
+ object will be returned as an array. If it is any other valid JSON
string, an invalid JSON
+ string or an empty string, the function returns null.
+ """,
+ examples = """
+ Examples:
+ > Select _FUNC_('{}');
+ []
+ > Select _FUNC_('{"key": "value"}');
+ ["key"]
+ > Select _FUNC_('{"f1":"abc","f2":{"f3":"a", "f4":"b"}}');
+ ["f1","f2"]
+ """,
+ since = "3.1.0")
+case class JsonObjectKeys(child: Expression) extends UnaryExpression with
CodegenFallback
+ with ExpectsInputTypes {
+
+ override def inputTypes: Seq[DataType] = Seq(StringType)
+ override def dataType: DataType = ArrayType(StringType)
+ override def nullable: Boolean = true
+ override def prettyName: String = "json_object_keys"
+
+ override def eval(input: InternalRow): Any = {
+ val json = child.eval(input).asInstanceOf[UTF8String]
+ // return null for `NULL` input
+ if(json == null) {
+ return null
+ }
+
+ try {
+
Utils.tryWithResource(CreateJacksonParser.utf8String(SharedFactory.jsonFactory,
json)) {
+ parser => getJsonKeys(parser, input)
+ }
+ } catch {
+ case _: JsonProcessingException => null
Review comment:
Yes, `nextToken()` throws `IOException`. I will update it with other
changes.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
