Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/18655#discussion_r129488362
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowConvertersSuite.scala
---
@@ -857,6 +857,449 @@ class ArrowConvertersSuite extends SharedSQLContext
with BeforeAndAfterAll {
collectAndValidate(df, json, "nanData-floating_point.json")
}
+ test("array type conversion") {
+ val json =
+ s"""
+ |{
+ | "schema" : {
+ | "fields" : [ {
+ | "name" : "a_arr",
+ | "nullable" : true,
+ | "type" : {
+ | "name" : "list"
+ | },
+ | "children" : [ {
+ | "name" : "element",
+ | "nullable" : false,
+ | "type" : {
+ | "name" : "int",
+ | "bitWidth" : 32,
+ | "isSigned" : true
+ | },
+ | "children" : [ ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "DATA",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | } ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "OFFSET",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | }, {
+ | "name" : "b_arr",
+ | "nullable" : true,
+ | "type" : {
+ | "name" : "list"
+ | },
+ | "children" : [ {
+ | "name" : "element",
+ | "nullable" : false,
+ | "type" : {
+ | "name" : "int",
+ | "bitWidth" : 32,
+ | "isSigned" : true
+ | },
+ | "children" : [ ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "DATA",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | } ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "OFFSET",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | }, {
+ | "name" : "c_arr",
+ | "nullable" : true,
+ | "type" : {
+ | "name" : "list"
+ | },
+ | "children" : [ {
+ | "name" : "element",
+ | "nullable" : true,
+ | "type" : {
+ | "name" : "int",
+ | "bitWidth" : 32,
+ | "isSigned" : true
+ | },
+ | "children" : [ ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "DATA",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | } ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "OFFSET",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | }, {
+ | "name" : "d_arr",
+ | "nullable" : true,
+ | "type" : {
+ | "name" : "list"
+ | },
+ | "children" : [ {
+ | "name" : "element",
+ | "nullable" : true,
+ | "type" : {
+ | "name" : "list"
+ | },
+ | "children" : [ {
+ | "name" : "element",
+ | "nullable" : false,
+ | "type" : {
+ | "name" : "int",
+ | "bitWidth" : 32,
+ | "isSigned" : true
+ | },
+ | "children" : [ ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "DATA",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | } ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "OFFSET",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | } ],
+ | "typeLayout" : {
+ | "vectors" : [ {
+ | "type" : "VALIDITY",
+ | "typeBitWidth" : 1
+ | }, {
+ | "type" : "OFFSET",
+ | "typeBitWidth" : 32
+ | } ]
+ | }
+ | } ]
+ | },
+ | "batches" : [ {
+ | "count" : 4,
+ | "columns" : [ {
+ | "name" : "a_arr",
+ | "count" : 4,
+ | "VALIDITY" : [ 1, 1, 1, 1 ],
+ | "OFFSET" : [ 0, 2, 4, 4, 5 ],
+ | "children" : [ {
+ | "name" : "element",
+ | "count" : 5,
+ | "VALIDITY" : [ 1, 1, 1, 1, 1 ],
+ | "DATA" : [ 1, 2, 3, 4, 5 ]
+ | } ]
+ | }, {
+ | "name" : "b_arr",
+ | "count" : 4,
+ | "VALIDITY" : [ 1, 0, 1, 0 ],
+ | "OFFSET" : [ 0, 2, 2, 2, 2 ],
+ | "children" : [ {
+ | "name" : "element",
+ | "count" : 2,
+ | "VALIDITY" : [ 1, 1 ],
+ | "DATA" : [ 1, 2 ]
+ | } ]
+ | }, {
+ | "name" : "c_arr",
+ | "count" : 4,
+ | "VALIDITY" : [ 1, 1, 1, 1 ],
+ | "OFFSET" : [ 0, 2, 4, 4, 5 ],
+ | "children" : [ {
+ | "name" : "element",
+ | "count" : 5,
+ | "VALIDITY" : [ 1, 1, 1, 0, 1 ],
+ | "DATA" : [ 1, 2, 3, 0, 5 ]
+ | } ]
+ | }, {
+ | "name" : "d_arr",
+ | "count" : 4,
+ | "VALIDITY" : [ 1, 1, 1, 1 ],
+ | "OFFSET" : [ 0, 1, 3, 3, 4 ],
+ | "children" : [ {
+ | "name" : "element",
+ | "count" : 4,
+ | "VALIDITY" : [ 1, 1, 1, 1 ],
+ | "OFFSET" : [ 0, 2, 3, 3, 4 ],
+ | "children" : [ {
+ | "name" : "element",
+ | "count" : 4,
+ | "VALIDITY" : [ 1, 1, 1, 1 ],
+ | "DATA" : [ 1, 2, 3, 5 ]
+ | } ]
+ | } ]
+ | } ]
+ | } ]
+ |}
+ """.stripMargin
+
+ val a_arr = Seq(Seq(1, 2), Seq(3, 4), Seq(), Seq(5))
+ val b_arr = Seq(Some(Seq(1, 2)), None, Some(Seq()), None)
+ val c_arr = Seq(Seq(Some(1), Some(2)), Seq(Some(3), None), Seq(),
Seq(Some(5)))
+ val d_arr = Seq(Seq(Seq(1, 2)), Seq(Seq(3), Seq()), Seq(), Seq(Seq(5)))
--- End diff --
Thanks, I'll modify it.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
