iRakson 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_r387616235
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
##########
@@ -781,3 +782,65 @@ case class SchemaOfJson(
override def prettyName: String = "schema_of_json"
}
+
+/**
+ * A function that returns number of elements in outer Json Array.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(jsonArray) - Returns length of the jsonArray",
+ arguments = """
+ jsonArray - A JSON array is required as argument. `Analysis Exception` is
thrown if any other
+ valid JSON expression is passed. `NULL` is returned in case of 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 {
+ override def dataType: DataType = IntegerType
+ override def nullable: Boolean = true
+ override def prettyName: String = "json_array_length"
+
+ override def eval(input: InternalRow): Any = {
+ @transient
+ val json = child.eval(input).asInstanceOf[UTF8String]
+ 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 => null
+ }
+ }
+
+ private def parseCounter(parser: JsonParser, input: InternalRow): Int = {
+ // Counter for length of array
+ var array_length: Int = 0;
+ // Only json array are supported for this function.
+ if (parser.getCurrentToken != JsonToken.START_ARRAY) {
+ throw new AnalysisException(s"$prettyName can only be called on Json
Array.")
+ }
+ // Keep traversing until the end of Json Array
+ while(parser.nextToken() != JsonToken.END_ARRAY) {
Review comment:
It returns null when end of input is reached.
If it returns null before returning `END_ARRAY` then our json is invalid.
Invalid input was already handled.
Anyway now i will add one more check for null.
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
