From b8bf7b93d5851f9562329ce265c002c74ece945f Mon Sep 17 00:00:00 2001
From: Yicong Huang <17627829+Yicong-Huang@users.noreply.github.com>
Date: Wed, 18 Mar 2026 07:41:11 +0000
Subject: [PATCH] test: add tests for SPARK-55056 triple nested array empty
 outer segfault

---
 python/pyspark/sql/tests/arrow/test_arrow.py  | 35 ++++++++++++++++
 .../execution/arrow/ArrowWriterSuite.scala    | 41 +++++++++++++++++++
 2 files changed, 76 insertions(+)

diff --git a/python/pyspark/sql/tests/arrow/test_arrow.py b/python/pyspark/sql/tests/arrow/test_arrow.py
index 4189860181a8d..db74f303e3d43 100644
--- a/python/pyspark/sql/tests/arrow/test_arrow.py
+++ b/python/pyspark/sql/tests/arrow/test_arrow.py
@@ -1871,6 +1871,41 @@ def test_toArrow_with_compression_codec_large_dataset(self):
                     self.assertEqual(t.num_rows, 10000)
                     self.assertEqual(t.column_names, ["id", "str_col", "mod_col"])
 
+    def test_toPandas_double_nested_array_empty_outer(self):
+        schema = StructType([StructField("data", ArrayType(ArrayType(StringType())))])
+        df = self.spark.createDataFrame([Row(data=[])], schema=schema)
+        pdf = df.toPandas()
+        self.assertEqual(len(pdf), 1)
+        self.assertEqual(len(pdf["data"][0]), 0)
+
+    def test_toPandas_array_of_map_empty_outer(self):
+        schema = StructType([StructField("data", ArrayType(MapType(StringType(), StringType())))])
+        df = self.spark.createDataFrame([Row(data=[])], schema=schema)
+        pdf = df.toPandas()
+        self.assertEqual(len(pdf), 1)
+        self.assertEqual(len(pdf["data"][0]), 0)
+
+    def test_toPandas_triple_nested_array_empty_outer(self):
+        # SPARK-55056: This used to trigger SIGSEGV before the upstream arrow-java fix.
+        # When the outer array is empty, the second-level ArrayWriter is never
+        # invoked, so its count stays 0. Arrow format requires ListArray offset
+        # buffer to have N+1 entries even when N=0, but getBufferSizeFor(0)
+        # returns 0 and the buffer is omitted in IPC serialization.
+        schema = StructType([StructField("data", ArrayType(ArrayType(ArrayType(StringType()))))])
+        df = self.spark.createDataFrame([Row(data=[])], schema=schema)
+        pdf = df.toPandas()
+        self.assertEqual(len(pdf), 1)
+        self.assertEqual(len(pdf["data"][0]), 0)
+
+    def test_toPandas_nested_array_with_map_empty_outer(self):
+        schema = StructType(
+            [StructField("data", ArrayType(ArrayType(MapType(StringType(), StringType()))))]
+        )
+        df = self.spark.createDataFrame([Row(data=[])], schema=schema)
+        pdf = df.toPandas()
+        self.assertEqual(len(pdf), 1)
+        self.assertEqual(len(pdf["data"][0]), 0)
+
 
 @unittest.skipIf(
     not have_pandas or not have_pyarrow,
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala
index 2c0c0494bbacf..c3e9af54d431e 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/arrow/ArrowWriterSuite.scala
@@ -875,4 +875,45 @@ class ArrowWriterSuite extends SparkFunSuite {
     assert(map2.keyArray().array().mkString(",") == Array(1).mkString(","))
     assert(stringRepr(map2) == Array("bob", "40").mkString(","))
   }
+
+  test("SPARK-55056: triple nested array with empty outer array") {
+    // Schema: array<array<array<string>>>
+    // This used to trigger SIGSEGV before the upstream arrow-java fix.
+    // When the outer array is empty, the second-level ArrayWriter is never
+    // invoked, so its count stays 0. Arrow format requires ListArray offset
+    // buffer to have N+1 entries even when N=0, but getBufferSizeFor(0)
+    // returns 0 and the buffer is omitted.
+    val schema = new StructType()
+      .add("data", ArrayType(ArrayType(ArrayType(StringType))))
+    val writer = ArrowWriter.create(schema, null)
+    assert(writer.schema === schema)
+
+    // Write a row with an empty outer array
+    writer.write(InternalRow(ArrayData.toArrayData(Array.empty)))
+    writer.finish()
+
+    val reader = new ArrowColumnVector(writer.root.getFieldVectors().get(0))
+    val array0 = reader.getArray(0)
+    assert(array0.numElements() === 0)
+
+    writer.root.close()
+  }
+
+  test("SPARK-55056: nested array with map inside empty outer array") {
+    // Schema: array<array<map<string, string>>>
+    val schema = new StructType()
+      .add("data", ArrayType(ArrayType(MapType(StringType, StringType))))
+    val writer = ArrowWriter.create(schema, null)
+    assert(writer.schema === schema)
+
+    // Write a row with an empty outer array
+    writer.write(InternalRow(ArrayData.toArrayData(Array.empty)))
+    writer.finish()
+
+    val reader = new ArrowColumnVector(writer.root.getFieldVectors().get(0))
+    val array0 = reader.getArray(0)
+    assert(array0.numElements() === 0)
+
+    writer.root.close()
+  }
 }