andishgar commented on code in PR #46031:
URL: https://github.com/apache/arrow/pull/46031#discussion_r2055921650
##########
cpp/src/arrow/record_batch_test.cc:
##########
@@ -1423,35 +1452,132 @@ TEST_F(TestRecordBatch,
MakeStatisticsArrayMaxApproximate) {
AssertArraysEqual(*expected_statistics_array, *statistics_array, true);
}
-TEST_F(TestRecordBatch, MakeStatisticsArrayString) {
- auto schema =
- ::arrow::schema({field("no-statistics", boolean()), field("string",
utf8())});
- auto no_statistics_array = ArrayFromJSON(boolean(), "[true, false, true]");
- auto string_array_data = ArrayFromJSON(utf8(), "[\"a\", null,
\"c\"]")->data()->Copy();
- string_array_data->statistics = std::make_shared<ArrayStatistics>();
- string_array_data->statistics->is_max_exact = true;
- string_array_data->statistics->max = "c";
- auto string_array = MakeArray(std::move(string_array_data));
- auto batch = RecordBatch::Make(schema, string_array->length(),
- {no_statistics_array, string_array});
+template <typename DataType>
+class TestRecordBatchMakeStatisticsArrayStringBase {
+ public:
+ std::shared_ptr<::arrow::DataType> type(int32_t byte_width = 1) {
+ if constexpr (std::is_same_v<DataType, FixedSizeBinaryType>) {
+ return fixed_size_binary(byte_width);
+ } else {
+ return TypeTraits<DataType>::type_singleton();
+ }
+ }
+ std::shared_ptr<Array> GenerateString(
+ const std::shared_ptr<::arrow::DataType>& data_type) {
+ if (data_type->id() == Type::FIXED_SIZE_BINARY) {
+ auto byte_width = data_type->byte_width();
+ auto a = std::string(byte_width, 'a');
+ auto b = std::string(byte_width, 'b');
+ auto c = std::string(byte_width, 'c');
+ std::stringstream ss;
+ ss << R"([")" << a << R"(",")" << b << R"(",")" << c << R"("])";
+ return ArrayFromJSON(data_type, ss.str());
+ }
+ return ArrayFromJSON(data_type, R"(["a","b","c"])");
+ }
+};
+template <typename DataType>
+class TestRecordBatchMakeStatisticsArrayEachStringType
+ : public TestRecordBatchMakeStatisticsArrayStringBase<DataType>,
+ public ::testing::Test {
+ public:
+ void TestEachType() {
+ auto schema = ::arrow::schema(
+ {field("no-statistics", boolean()), field("string", this->type())});
+ auto no_statistics_array = ArrayFromJSON(boolean(), "[true, false, true]");
+ auto string_array_data =
this->GenerateString(this->type())->data()->Copy();
+ string_array_data->statistics = std::make_shared<ArrayStatistics>();
+ string_array_data->statistics->is_max_exact = true;
+ string_array_data->statistics->max = "c";
+ auto string_array = MakeArray(std::move(string_array_data));
+ auto batch = RecordBatch::Make(schema, string_array->length(),
+ {no_statistics_array, string_array});
+
+ ASSERT_OK_AND_ASSIGN(auto statistics_array, batch->MakeStatisticsArray());
+
+ ASSERT_OK_AND_ASSIGN(auto expected_statistics_array,
+ MakeStatisticsArray("[null, 1]",
+ {{
+
ARROW_STATISTICS_KEY_ROW_COUNT_EXACT,
+ },
+ {
+
ARROW_STATISTICS_KEY_MAX_VALUE_EXACT,
+ }},
+ {{
+
ArrayStatistics::ValueType{int64_t{3}},
+ },
+ {
+
ArrayStatistics::ValueType{"c"},
+ }},
+ {null(), this->type()}));
+ AssertArraysEqual(*expected_statistics_array, *statistics_array, true);
+ }
+};
- ASSERT_OK_AND_ASSIGN(auto statistics_array, batch->MakeStatisticsArray());
+class TestRecordBatchMakeStatisticsArrayFixedSizeBinaryCombination
+ : public TestRecordBatchMakeStatisticsArrayStringBase<FixedSizeBinaryType>,
+ public ::testing::Test {
+ public:
+ void TestCombination(int32_t byte_width_1, int32_t byte_width_2) {
+ auto f0 = GenerateString(type(byte_width_1));
+ f0->data()->statistics = std::make_shared<ArrayStatistics>();
+ f0->data()->statistics->max = std::string(byte_width_1, 'c');
+
+ auto f1 = ArrayFromJSON(int64(), R"([1, 2, 3])");
+
+ auto f2 = GenerateString(type(byte_width_2));
+ f2->data()->statistics = std::make_shared<ArrayStatistics>();
+ f2->data()->statistics->max = std::string(byte_width_2, 'c');
+
+ auto schema = ::arrow::schema({field("f0", type(byte_width_1)),
field("f1", int64()),
+ field("f2",
fixed_size_binary(byte_width_2))});
+ auto batch = RecordBatch::Make(schema, f0->length(), {f0, f1, f2});
+ ASSERT_OK_AND_ASSIGN(auto statistics_array, batch->MakeStatisticsArray());
+ ASSERT_OK_AND_ASSIGN(
+ auto expected_statistics_array,
+ MakeStatisticsArray(
+ "[null, 0, 2]",
+ {{
+ ARROW_STATISTICS_KEY_ROW_COUNT_EXACT,
+ },
+ {
+ ARROW_STATISTICS_KEY_MAX_VALUE_APPROXIMATE,
+ },
+ {
+ ARROW_STATISTICS_KEY_MAX_VALUE_APPROXIMATE,
+ }},
+ {{
+ ArrayStatistics::ValueType{int64_t{3}},
+ },
+ {
+ ArrayStatistics::ValueType{std::string(byte_width_1, 'c')},
+ },
+ {
+ ArrayStatistics::ValueType{std::string(byte_width_2, 'c')},
+ }},
+ {null(), type(byte_width_1), fixed_size_binary(byte_width_2)}));
+
+ AssertArraysEqual(*expected_statistics_array, *statistics_array, true);
+ }
+};
- ASSERT_OK_AND_ASSIGN(auto expected_statistics_array,
- MakeStatisticsArray("[null, 1]",
- {{
-
ARROW_STATISTICS_KEY_ROW_COUNT_EXACT,
- },
- {
-
ARROW_STATISTICS_KEY_MAX_VALUE_EXACT,
- }},
- {{
-
ArrayStatistics::ValueType{int64_t{3}},
- },
- {
-
ArrayStatistics::ValueType{"c"},
- }}));
- AssertArraysEqual(*expected_statistics_array, *statistics_array, true);
+TYPED_TEST_SUITE(TestRecordBatchMakeStatisticsArrayEachStringType,
+ AllBinaryOrBinrayViewLikeArrowTypes);
+
+TYPED_TEST(TestRecordBatchMakeStatisticsArrayEachStringType, EachType) {
+ this->TestEachType();
+}
+
+// Validates that the union array creates two distinct child arrays for two
+// FixedSizeBinaryArrays with unequal byte widths.
+TEST_F(TestRecordBatchMakeStatisticsArrayFixedSizeBinaryCombination,
CheckDifferentSize) {
+ this->TestCombination(1, 2);
+}
Review Comment:
Apologies for my confusion, and thank you for your thorough explanation.
I will send a commit to apply changes soon.
--
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.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
