dongjoon-hyun commented on a change in pull request #27759: [SPARK-31008][SQL]
Support json_array_length function
URL: https://github.com/apache/spark/pull/27759#discussion_r403509345
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
##########
@@ -796,3 +796,75 @@ case class SchemaOfJson(
override def prettyName: String = "schema_of_json"
}
+
+/**
+ * A function that returns the number of elements in outer JSON array.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(jsonArray) - Returns the number of elements in outer JSON
array.",
+ arguments = """
+ Arguments:
+ * jsonArray - A JSON array. An exception is thrown if any other valid
JSON strings are passed.
+ `NULL` is returned in case of an invalid JSON.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_('[1,2,3,4]');
+ 4
+ > SELECT _FUNC_('[1,2,3,{"f1":1,"f2":[5,6]},4]');
+ 5
+ > SELECT _FUNC_('[1,2');
+ NULL
+ """,
+ since = "3.1.0"
+)
+case class LengthOfJsonArray(child: Expression) extends UnaryExpression
+ with CodegenFallback with ExpectsInputTypes {
+
+ override def inputTypes: Seq[AbstractDataType] = Seq(StringType)
+ override def dataType: DataType = IntegerType
+ override def nullable: Boolean = true
+ override def prettyName: String = "json_array_length"
+
+ 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 => {
+ // return null if null array is encountered.
+ if (parser.nextToken() == null) {
+ return null
+ }
+ // Parse the array to compute its length.
+ parseCounter(parser, input)
+ }
+ }
+ } catch {
+ case _: JsonProcessingException | _: IOException => null
+ }
+ }
+
+ private def parseCounter(parser: JsonParser, input: InternalRow): Int = {
+ var length = 0;
+ // Only JSON array are supported for this function.
+ if (parser.currentToken != JsonToken.START_ARRAY) {
+ throw new IllegalArgumentException(s"$prettyName can only be called on
JSON array.")
+ }
+ // Keep traversing until the end of JSON array
+ while(parser.nextToken() != JsonToken.END_ARRAY) {
+ // Null indicates end of input.
+ if (parser.currentToken == null) {
+ throw new IllegalArgumentException("Please provide a valid JSON
array.")
+ }
+ length += 1
+ // skip all the child of inner object or array
+ parser.skipChildren()
Review comment:
Just a question. We still check the invalidity of the content inside
children because we should return `null` if there is an invalidity in there.
Did I understand correctly?
----------------------------------------------------------------
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]
