Skip to content
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

GH-44579: [C++] Use array type to compute min/max statistics Arrow type #45094

Merged
merged 1 commit into from
Dec 31, 2024
Merged

GH-44579: [C++] Use array type to compute min/max statistics Arrow type #45094

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
64 changes: 57 additions & 7 deletions cpp/src/arrow/array/statistics.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
#include <string>
#include <variant>

#include "arrow/type_fwd.h"
#include "arrow/type.h"
#include "arrow/util/visibility.h"

namespace arrow {
Expand All @@ -34,22 +34,38 @@ namespace arrow {
/// as Apache Parquet may have statistics. Statistics associated with
/// data source can be read unified API via this class.
struct ARROW_EXPORT ArrayStatistics {
/// \brief The type for maximum and minimum values. If the target
/// value exists, one of them is used. `std::nullopt` is used
/// otherwise.
using ValueType = std::variant<bool, int64_t, uint64_t, double, std::string>;

static const std::shared_ptr<DataType>& ValueToArrowType(
const std::optional<ValueType>& value) {
const std::optional<ValueType>& value,
const std::shared_ptr<DataType>& array_type) {
if (!value.has_value()) {
return null();
}

struct Visitor {
const std::shared_ptr<DataType>& array_type;

const std::shared_ptr<DataType>& operator()(const bool&) { return boolean(); }
const std::shared_ptr<DataType>& operator()(const int64_t&) { return int64(); }
const std::shared_ptr<DataType>& operator()(const uint64_t&) { return uint64(); }
const std::shared_ptr<DataType>& operator()(const double&) { return float64(); }
// GH-44579: How to support binary data?
const std::shared_ptr<DataType>& operator()(const std::string&) { return utf8(); }
} visitor;
const std::shared_ptr<DataType>& operator()(const std::string&) {
switch (array_type->id()) {
case Type::STRING:
case Type::BINARY:
case Type::FIXED_SIZE_BINARY:
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we use arrow::binary() or arrow::large_binary() for Type::FIXED_SIZE_BINARY?
Approximate min/max values may not be a fixed size binary...?

case Type::LARGE_STRING:
case Type::LARGE_BINARY:
return array_type;
default:
return utf8();
}
}
} visitor{array_type};
return std::visit(visitor, value.value());
}

Expand All @@ -62,15 +78,49 @@ struct ARROW_EXPORT ArrayStatistics {
/// \brief The minimum value, may not be set
std::optional<ValueType> min = std::nullopt;

const std::shared_ptr<DataType>& MinArrowType() { return ValueToArrowType(min); }
/// \brief Compute Arrow type of the minimum value.
///
/// If \ref ValueType is `std::string`, `array_type` may be
/// used. If `array_type` is a binary-like type such as \ref
/// arrow::binary and \ref arrow::large_utf8, `array_type` is
/// returned. \ref arrow::utf8 is returned otherwise.
///
/// If \ref ValueType isn't `std::string`, `array_type` isn't used.
///
/// \param array_type The Arrow type of the associated array.
///
/// \return \ref arrow::null if the minimum value is `std::nullopt`,
/// Arrow type based on \ref ValueType of the \ref min
/// otherwise.
const std::shared_ptr<DataType>& MinArrowType(
const std::shared_ptr<DataType>& array_type) {
return ValueToArrowType(min, array_type);
}

/// \brief Whether the minimum value is exact or not
bool is_min_exact = false;

/// \brief The maximum value, may not be set
std::optional<ValueType> max = std::nullopt;

const std::shared_ptr<DataType>& MaxArrowType() { return ValueToArrowType(max); }
/// \brief Compute Arrow type of the maximum value.
///
/// If \ref ValueType is `std::string`, `array_type` may be
/// used. If `array_type` is a binary-like type such as \ref
/// arrow::binary and \ref arrow::large_utf8, `array_type` is
/// returned. \ref arrow::utf8 is returned otherwise.
///
/// If \ref ValueType isn't `std::string`, `array_type` isn't used.
///
/// \param array_type The Arrow type of the associated array.
///
/// \return \ref arrow::null if the maximum value is `std::nullopt`,
/// Arrow type based on \ref ValueType of the \ref max
/// otherwise.
const std::shared_ptr<DataType>& MaxArrowType(
const std::shared_ptr<DataType>& array_type) {
return ValueToArrowType(max, array_type);
}

/// \brief Whether the maximum value is exact or not
bool is_max_exact = false;
Expand Down
8 changes: 5 additions & 3 deletions cpp/src/arrow/record_batch.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -493,8 +493,10 @@ Status EnumerateStatistics(const RecordBatch& record_batch, OnStatistics on_stat
RETURN_NOT_OK(on_statistics(statistics));
statistics.start_new_column = false;

const auto num_fields = record_batch.schema()->num_fields();
const auto& schema = record_batch.schema();
const auto num_fields = schema->num_fields();
for (int nth_column = 0; nth_column < num_fields; ++nth_column) {
const auto& field = schema->field(nth_column);
auto column_statistics = record_batch.column(nth_column)->statistics();
if (!column_statistics) {
continue;
Expand Down Expand Up @@ -527,7 +529,7 @@ Status EnumerateStatistics(const RecordBatch& record_batch, OnStatistics on_stat
} else {
statistics.key = ARROW_STATISTICS_KEY_MIN_VALUE_APPROXIMATE;
}
statistics.type = column_statistics->MinArrowType();
statistics.type = column_statistics->MinArrowType(field->type());
statistics.value = column_statistics->min.value();
RETURN_NOT_OK(on_statistics(statistics));
statistics.start_new_column = false;
Expand All @@ -540,7 +542,7 @@ Status EnumerateStatistics(const RecordBatch& record_batch, OnStatistics on_stat
} else {
statistics.key = ARROW_STATISTICS_KEY_MAX_VALUE_APPROXIMATE;
}
statistics.type = column_statistics->MaxArrowType();
statistics.type = column_statistics->MaxArrowType(field->type());
statistics.value = column_statistics->max.value();
RETURN_NOT_OK(on_statistics(statistics));
statistics.start_new_column = false;
Expand Down
2 changes: 1 addition & 1 deletion cpp/src/arrow/record_batch_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1116,7 +1116,7 @@ Result<std::shared_ptr<Array>> MakeStatisticsArray(
}
keys_indices.push_back(key_index);

auto values_type = ArrayStatistics::ValueToArrowType(value);
auto values_type = ArrayStatistics::ValueToArrowType(value, arrow::null());
int8_t values_type_code = 0;
for (; values_type_code < static_cast<int32_t>(values_types.size());
++values_type_code) {
Expand Down
Loading