Skip to content

GH-47105: [Statistics][C++] Implement Statistics specification attribute ARROW:row_count:approximate #48266

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kou merged 1 commit into from
Dec 3, 2025
Merged

GH-47105: [Statistics][C++] Implement Statistics specification attribute ARROW:row_count:approximate #48266

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions cpp/src/arrow/array/array_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3909,6 +3909,7 @@ class TestArrayDataStatistics : public ::testing::Test {
public:
void SetUp() {
valids_ = {1, 0, 1, 1};
row_count_ = static_cast<int64_t>(valids_.size());
null_count_ = std::count(valids_.begin(), valids_.end(), 0);
distinct_count_ = 3.0;
max_byte_width_ = 4.0;
Expand All @@ -3921,6 +3922,7 @@ class TestArrayDataStatistics : public ::testing::Test {
data_ = ArrayData::Make(int32(), values_.size(), {null_buffer_, values_buffer_},
null_count_);
data_->statistics = std::make_shared<ArrayStatistics>();
data_->statistics->row_count = row_count_;
data_->statistics->null_count = null_count_;
data_->statistics->distinct_count = distinct_count_;
data_->statistics->max_byte_width = max_byte_width_;
Expand All @@ -3934,6 +3936,7 @@ class TestArrayDataStatistics : public ::testing::Test {

protected:
std::vector<uint8_t> valids_;
int64_t row_count_;
int64_t null_count_;
double distinct_count_;
double max_byte_width_;
Expand All @@ -3950,6 +3953,9 @@ TEST_F(TestArrayDataStatistics, MoveConstructor) {
ArrayData copied_data(*data_);
ArrayData moved_data(std::move(copied_data));

ASSERT_TRUE(moved_data.statistics->row_count.has_value());
ASSERT_EQ(row_count_, std::get<int64_t>(moved_data.statistics->row_count.value()));

ASSERT_TRUE(moved_data.statistics->null_count.has_value());
ASSERT_EQ(null_count_, std::get<int64_t>(moved_data.statistics->null_count.value()));

Expand Down Expand Up @@ -3980,6 +3986,9 @@ TEST_F(TestArrayDataStatistics, MoveConstructor) {
TEST_F(TestArrayDataStatistics, CopyConstructor) {
ArrayData copied_data(*data_);

ASSERT_TRUE(copied_data.statistics->row_count.has_value());
ASSERT_EQ(row_count_, std::get<int64_t>(copied_data.statistics->row_count.value()));

ASSERT_TRUE(copied_data.statistics->null_count.has_value());
ASSERT_EQ(null_count_, std::get<int64_t>(copied_data.statistics->null_count.value()));

Expand Down Expand Up @@ -4012,6 +4021,9 @@ TEST_F(TestArrayDataStatistics, MoveAssignment) {
ArrayData moved_data;
moved_data = std::move(copied_data);

ASSERT_TRUE(moved_data.statistics->row_count.has_value());
ASSERT_EQ(row_count_, std::get<int64_t>(moved_data.statistics->row_count.value()));

ASSERT_TRUE(moved_data.statistics->null_count.has_value());
ASSERT_EQ(null_count_, std::get<int64_t>(moved_data.statistics->null_count.value()));

Expand Down Expand Up @@ -4043,6 +4055,9 @@ TEST_F(TestArrayDataStatistics, CopyAssignment) {
ArrayData copied_data;
copied_data = *data_;

ASSERT_TRUE(copied_data.statistics->row_count.has_value());
ASSERT_EQ(row_count_, std::get<int64_t>(copied_data.statistics->row_count.value()));

ASSERT_TRUE(copied_data.statistics->null_count.has_value());
ASSERT_EQ(null_count_, std::get<int64_t>(copied_data.statistics->null_count.value()));

Expand Down Expand Up @@ -4074,6 +4089,9 @@ TEST_F(TestArrayDataStatistics, CopyTo) {
ASSERT_OK_AND_ASSIGN(auto copied_data,
data_->CopyTo(arrow::default_cpu_memory_manager()));

ASSERT_TRUE(copied_data->statistics->row_count.has_value());
ASSERT_EQ(row_count_, std::get<int64_t>(copied_data->statistics->row_count.value()));

ASSERT_TRUE(copied_data->statistics->null_count.has_value());
ASSERT_EQ(null_count_, std::get<int64_t>(copied_data->statistics->null_count.value()));

Expand Down
6 changes: 6 additions & 0 deletions cpp/src/arrow/array/statistics.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,12 @@ struct ARROW_EXPORT ArrayStatistics {
return std::visit(visitor, value.value());
}

/// \brief The number of rows, may not be set
/// Note: when set to `int64_t`, it represents `exact_row_count`,
/// and when set to `double`, it represents `approximate_row_count`.
/// Note: this value is not used by \ref arrow::RecordBatch::MakeStatisticsArray.
std::optional<CountType> row_count = std::nullopt;

/// \brief The number of null values, may not be set
/// Note: when set to `int64_t`, it represents `exact_null_count`,
/// and when set to `double`, it represents `approximate_null_count`.
Expand Down
28 changes: 28 additions & 0 deletions cpp/src/arrow/array/statistics_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,22 @@

namespace arrow {

TEST(TestArrayStatistics, RowCountExact) {
ArrayStatistics statistics;
ASSERT_FALSE(statistics.row_count.has_value());
statistics.row_count = 45;
ASSERT_TRUE(statistics.row_count.has_value());
ASSERT_EQ(45, std::get<int64_t>(statistics.row_count.value()));
}

TEST(TestArrayStatistics, RowCountApproximate) {
ArrayStatistics statistics;
ASSERT_FALSE(statistics.row_count.has_value());
statistics.row_count = 45.0;
ASSERT_TRUE(statistics.row_count.has_value());
ASSERT_DOUBLE_EQ(45.0, std::get<double>(statistics.row_count.value()));
}

TEST(TestArrayStatistics, NullCountExact) {
ArrayStatistics statistics;
ASSERT_FALSE(statistics.null_count.has_value());
Expand Down Expand Up @@ -114,6 +130,18 @@ TEST(TestArrayStatistics, Equals) {

ASSERT_EQ(statistics1, statistics2);

// Test ROW_COUNT_EXACT
statistics1.row_count = 45;
ASSERT_NE(statistics1, statistics2);
statistics2.row_count = 45;
ASSERT_EQ(statistics1, statistics2);

// Test ROW_COUNT_APPROXIMATE
statistics1.row_count = 45.0;
ASSERT_NE(statistics1, statistics2);
statistics2.row_count = 45.0;
ASSERT_EQ(statistics1, statistics2);

// Test NULL_COUNT_EXACT
statistics1.null_count = 29;
ASSERT_NE(statistics1, statistics2);
Expand Down
4 changes: 3 additions & 1 deletion cpp/src/arrow/compare.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1563,7 +1563,9 @@ bool ArrayStatisticsOptionalValueEquals(const std::optional<Type>& left,

bool ArrayStatisticsEqualsImpl(const ArrayStatistics& left, const ArrayStatistics& right,
const EqualOptions& equal_options) {
return ArrayStatisticsOptionalValueEquals(left.null_count, right.null_count,
return ArrayStatisticsOptionalValueEquals(left.row_count, right.row_count,
equal_options) &&
ArrayStatisticsOptionalValueEquals(left.null_count, right.null_count,
equal_options) &&
ArrayStatisticsOptionalValueEquals(left.distinct_count, right.distinct_count,
equal_options) &&
Expand Down
Loading