MaxGekk 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_r395990987
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
##########
@@ -781,3 +783,64 @@ case class SchemaOfJson(
override def prettyName: String = "schema_of_json"
}
+
+/**
+ * A function which returns all the keys of outer JSON object.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(json_object) - returns all the keys of outer JSON object.",
+ arguments = """
+ Arguments:
+ * json_object - A JSON object is required as argument. `Null` is
returned, if an invalid JSON
+ string is given. `Analysis Exception` is thrown, if null string or
JSON array is given.
+ """,
+ 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 {
+ override def dataType: DataType = ArrayType(StringType)
+ override def nullable: Boolean = true
+ override def prettyName: String = "json_object_keys"
+
+ private lazy val json = child.eval().asInstanceOf[UTF8String]
+
+ override def eval(input: InternalRow): Any = {
+ try {
+
Utils.tryWithResource(CreateJacksonParser.utf8String(SharedFactory.jsonFactory,
json)) {
+ parser => getJsonKeys(parser, input)
+ }
+ } catch {
+ case _: JsonProcessingException => null
+ }
+ }
+
+ private def getJsonKeys(parser: JsonParser, input: InternalRow): Any = {
+ var arrayBufferOfKeys = ArrayBuffer.empty[UTF8String]
+ // this handles `NULL` case
+ if (parser.nextToken() == null) {
+ throw new AnalysisException(s"$prettyName expect a JSON object but
nothing is provided.")
Review comment:
Is the exception thrown at analysis phase? I think `AnalysisException`
should be replaced by `RuntimeException`.
----------------------------------------------------------------
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]
