From 82bcd3903ae2f0e27d58b686971958218b3aab55 Mon Sep 17 00:00:00 2001
From: Masha Basmanova <mbasmanova@fb.com>
Date: Wed, 17 Jan 2024 00:03:46 -0800
Subject: [PATCH] Fix creation of DuckDB tables with arrays of boolean, tinyint
 and smallint (#8408)

Summary:
Creating DuckDB table with a column of type array(boolean), array(tinyint) or
array(smallint) having a mix of null and non-null array elements used to fail with

```
INTERNAL Error: Assertion triggered in file "/home/runner/work/velox/velox/_build/debug/_deps/duckdb-src/src/common/types/value.cpp" on line 702: values[i].type() == values[0].type()
```

The problem is that `duckValueAt<TypeKind>` template in QueryAssertions.cpp used
to convert non-null values by calling duckdb::Value(v) API, which is not defined
for bool, int8_t and int16_t. Hence, we ended up calling a version of that API
that takes int32_t and returns a value of type INTEGER. However, code for
converting null values used duckdb::Value(type) API which takes type directly
and therefore creates values of the "right" type. When array value had a mix of
null and non-null values we ended up passing a list of elements of different
types to DuckDB and hit an assertion.

A fix implemented here is to provide explicit overrides for boolean, tinyint and smallint.

This issue happens often in join fuzzer runs.

Fixes https://github.com/facebookincubator/velox/issues/7943

Pull Request resolved: https://github.com/facebookincubator/velox/pull/8408

Reviewed By: amitkdutta

Differential Revision: D52826343

Pulled By: mbasmanova

fbshipit-source-id: 41d78f7cde95ed3f8e4b3fe3db980f5b60b52f47
---
 velox/exec/tests/utils/QueryAssertions.cpp | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/velox/exec/tests/utils/QueryAssertions.cpp b/velox/exec/tests/utils/QueryAssertions.cpp
index dfc996e2063b..e224320edaf6 100644
--- a/velox/exec/tests/utils/QueryAssertions.cpp
+++ b/velox/exec/tests/utils/QueryAssertions.cpp
@@ -39,6 +39,30 @@ ::duckdb::Value duckValueAt(const VectorPtr& vector, vector_size_t index) {
   return ::duckdb::Value(vector->as<SimpleVector<T>>()->valueAt(index));
 }
 
+template <>
+::duckdb::Value duckValueAt<TypeKind::TINYINT>(
+    const VectorPtr& vector,
+    vector_size_t index) {
+  return ::duckdb::Value::TINYINT(
+      vector->as<SimpleVector<int8_t>>()->valueAt(index));
+}
+
+template <>
+::duckdb::Value duckValueAt<TypeKind::SMALLINT>(
+    const VectorPtr& vector,
+    vector_size_t index) {
+  return ::duckdb::Value::SMALLINT(
+      vector->as<SimpleVector<int16_t>>()->valueAt(index));
+}
+
+template <>
+::duckdb::Value duckValueAt<TypeKind::BOOLEAN>(
+    const VectorPtr& vector,
+    vector_size_t index) {
+  return ::duckdb::Value::BOOLEAN(
+      vector->as<SimpleVector<bool>>()->valueAt(index));
+}
+
 template <>
 ::duckdb::Value duckValueAt<TypeKind::VARCHAR>(
     const VectorPtr& vector,