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

Jump to bottom

Add support for Date/DateTime datatypes to arrayMin/Max, arrayDifference functions #48445

Merged
merged 4 commits into from
Apr 12, 2023
Merged

Add support for Date/DateTime datatypes to arrayMin/Max, arrayDifference functions #48445

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0dfcc84
Add support for Date/Datetime datatypes to arrayMin, arrayMax, arrayD…
evillique Apr 6, 2023
9508653
Fix style
evillique Apr 6, 2023
7161d3d
Fixes
evillique Apr 7, 2023
6debacc
Fix build
evillique Apr 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
11 changes: 11 additions & 0 deletions src/DataTypes/DataTypeDateTime64.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ namespace DB
namespace ErrorCodes
{
extern const int ARGUMENT_OUT_OF_BOUND;
extern const int LOGICAL_ERROR;
}

static constexpr UInt32 max_scale = 9;
Expand Down Expand Up @@ -56,4 +57,14 @@ SerializationPtr DataTypeDateTime64::doGetDefaultSerialization() const
return std::make_shared<SerializationDateTime64>(scale, *this);
}

std::string getDateTimeTimezone(const IDataType & data_type)
{
if (const auto * type = typeid_cast<const DataTypeDateTime *>(&data_type))
return type->hasExplicitTimeZone() ? type->getTimeZone().getTimeZone() : std::string();
if (const auto * type = typeid_cast<const DataTypeDateTime64 *>(&data_type))
return type->hasExplicitTimeZone() ? type->getTimeZone().getTimeZone() : std::string();

throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot get time zone from type {}", data_type.getName());
}

}
2 changes: 2 additions & 0 deletions src/DataTypes/DataTypeDateTime64.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,5 +41,7 @@ class DataTypeDateTime64 final : public DataTypeDecimalBase<DateTime64>, public
SerializationPtr doGetDefaultSerialization() const override;
};

std::string getDateTimeTimezone(const IDataType & data_type);

}

4 changes: 4 additions & 0 deletions src/DataTypes/IDataType.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -556,6 +556,7 @@ inline bool isNullableOrLowCardinalityNullable(const DataTypePtr & data_type)
template <typename DataType> constexpr bool IsDataTypeDecimal = false;
template <typename DataType> constexpr bool IsDataTypeNumber = false;
template <typename DataType> constexpr bool IsDataTypeDateOrDateTime = false;
template <typename DataType> constexpr bool IsDataTypeDate = false;
template <typename DataType> constexpr bool IsDataTypeEnum = false;

template <typename DataType> constexpr bool IsDataTypeDecimalOrNumber = IsDataTypeDecimal<DataType> || IsDataTypeNumber<DataType>;
Expand All @@ -576,6 +577,9 @@ template <> inline constexpr bool IsDataTypeDecimal<DataTypeDateTime64> = true;

template <typename T> constexpr bool IsDataTypeNumber<DataTypeNumber<T>> = true;

template <> inline constexpr bool IsDataTypeDate<DataTypeDate> = true;
template <> inline constexpr bool IsDataTypeDate<DataTypeDate32> = true;

template <> inline constexpr bool IsDataTypeDateOrDateTime<DataTypeDate> = true;
template <> inline constexpr bool IsDataTypeDateOrDateTime<DataTypeDate32> = true;
template <> inline constexpr bool IsDataTypeDateOrDateTime<DataTypeDateTime> = true;
Expand Down
64 changes: 48 additions & 16 deletions src/Functions/array/arrayAggregation.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,9 @@
#include <Columns/ColumnsNumber.h>

#include <DataTypes/DataTypeArray.h>
#include <DataTypes/DataTypeDate.h>
#include <DataTypes/DataTypeDate32.h>
#include <DataTypes/DataTypeDateTime.h>
#include <DataTypes/DataTypeDateTime64.h>
#include <DataTypes/DataTypesDecimal.h>
#include <DataTypes/DataTypesNumber.h>
Expand Down Expand Up @@ -81,9 +84,10 @@ struct ArrayAggregateResultImpl<ArrayElement, AggregateOperation::sum>
std::conditional_t<std::is_same_v<ArrayElement, Decimal64>, Decimal128,
std::conditional_t<std::is_same_v<ArrayElement, Decimal128>, Decimal128,
std::conditional_t<std::is_same_v<ArrayElement, Decimal256>, Decimal256,
std::conditional_t<std::is_same_v<ArrayElement, DateTime64>, Decimal128,
std::conditional_t<std::is_floating_point_v<ArrayElement>, Float64,
std::conditional_t<std::is_signed_v<ArrayElement>, Int64,
UInt64>>>>>>>>>>;
UInt64>>>>>>>>>>>;
};

template <typename ArrayElement, AggregateOperation operation>
Expand All @@ -108,26 +112,53 @@ struct ArrayAggregateImpl
using Types = std::decay_t<decltype(types)>;
using DataType = typename Types::LeftType;

if constexpr (aggregate_operation == AggregateOperation::average || aggregate_operation == AggregateOperation::product)
if constexpr (!IsDataTypeDateOrDateTime<DataType>)
{
result = std::make_shared<DataTypeFloat64>();
if constexpr (aggregate_operation == AggregateOperation::average || aggregate_operation == AggregateOperation::product)
{
result = std::make_shared<DataTypeFloat64>();

return true;
}
else if constexpr (IsDataTypeNumber<DataType>)
{
using NumberReturnType = ArrayAggregateResult<typename DataType::FieldType, aggregate_operation>;
result = std::make_shared<DataTypeNumber<NumberReturnType>>();
return true;
}
else if constexpr (IsDataTypeNumber<DataType>)
{
using NumberReturnType = ArrayAggregateResult<typename DataType::FieldType, aggregate_operation>;
result = std::make_shared<DataTypeNumber<NumberReturnType>>();

return true;
return true;
}
else if constexpr (IsDataTypeDecimal<DataType>)
{
using DecimalReturnType = ArrayAggregateResult<typename DataType::FieldType, aggregate_operation>;
UInt32 scale = getDecimalScale(*expression_return);
result = std::make_shared<DataTypeDecimal<DecimalReturnType>>(DecimalUtils::max_precision<DecimalReturnType>, scale);

return true;
}
}
else if constexpr (IsDataTypeDecimal<DataType> && !IsDataTypeDateOrDateTime<DataType>)
else if constexpr (aggregate_operation == AggregateOperation::max || aggregate_operation == AggregateOperation::min)
{
using DecimalReturnType = ArrayAggregateResult<typename DataType::FieldType, aggregate_operation>;
UInt32 scale = getDecimalScale(*expression_return);
result = std::make_shared<DataTypeDecimal<DecimalReturnType>>(DecimalUtils::max_precision<DecimalReturnType>, scale);
if constexpr (IsDataTypeDate<DataType>)
{
result = std::make_shared<DataType>();

return true;
return true;
}
else if constexpr (!IsDataTypeDecimal<DataType>)
{
std::string timezone = getDateTimeTimezone(*expression_return);
result = std::make_shared<DataTypeDateTime>(timezone);

return true;
}
else
{
std::string timezone = getDateTimeTimezone(*expression_return);
UInt32 scale = getDecimalScale(*expression_return);
result = std::make_shared<DataTypeDateTime64>(scale, timezone);

return true;
}
}

return false;
Expand Down Expand Up @@ -370,7 +401,8 @@ struct ArrayAggregateImpl
executeType<Decimal32>(mapped, offsets, res) ||
executeType<Decimal64>(mapped, offsets, res) ||
executeType<Decimal128>(mapped, offsets, res) ||
executeType<Decimal256>(mapped, offsets, res))
executeType<Decimal256>(mapped, offsets, res) ||
executeType<DateTime64>(mapped, offsets, res))
{
return res;
}
Expand Down
15 changes: 12 additions & 3 deletions src/Functions/array/arrayDifference.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,10 +35,10 @@ struct ArrayDifferenceImpl
if (which.isUInt8() || which.isInt8())
return std::make_shared<DataTypeArray>(std::make_shared<DataTypeInt16>());

if (which.isUInt16() || which.isInt16())
if (which.isUInt16() || which.isInt16() || which.isDate())
return std::make_shared<DataTypeArray>(std::make_shared<DataTypeInt32>());

if (which.isUInt32() || which.isUInt64() || which.isInt32() || which.isInt64())
if (which.isUInt32() || which.isUInt64() || which.isInt32() || which.isInt64() || which.isDate32() || which.isDateTime())
return std::make_shared<DataTypeArray>(std::make_shared<DataTypeInt64>());

if (which.isFloat32() || which.isFloat64())
Expand All @@ -47,6 +47,14 @@ struct ArrayDifferenceImpl
if (which.isDecimal())
return std::make_shared<DataTypeArray>(expression_return);

if (which.isDateTime64())
{
UInt32 scale = getDecimalScale(*expression_return);
UInt32 precision = getDecimalPrecision(*expression_return);

return std::make_shared<DataTypeArray>(std::make_shared<DataTypeDecimal<Decimal64>>(precision, scale));
}

throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "arrayDifference cannot process values of type {}", expression_return->getName());
}

Expand Down Expand Up @@ -146,7 +154,8 @@ struct ArrayDifferenceImpl
executeType<Decimal32, Decimal32>(mapped, array, res) ||
executeType<Decimal64, Decimal64>(mapped, array, res) ||
executeType<Decimal128, Decimal128>(mapped, array, res) ||
executeType<Decimal256, Decimal256>(mapped, array, res))
executeType<Decimal256, Decimal256>(mapped, array, res) ||
executeType<DateTime64, Decimal64>(mapped, array, res))
return res;
else
throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Unexpected column for arrayDifference: {}", mapped->getName());
Expand Down
4 changes: 4 additions & 0 deletions tests/queries/0_stateless/01602_array_aggregation.reference
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,10 @@ Table array decimal avg
3.5
0
2
2023-04-05 00:25:24 2023-04-05 00:25:23 [0,1]
2023-04-05 00:25:24.124 2023-04-05 00:25:23.123 [0,1.001]
2023-04-06 2023-04-05 [0,1]
2023-04-06 2023-04-05 [0,1]
Types of aggregation result array min
Int8 Int16 Int32 Int64
UInt8 UInt16 UInt32 UInt64
Expand Down
5 changes: 5 additions & 0 deletions tests/queries/0_stateless/01602_array_aggregation.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,11 @@ SELECT arrayAvg(x) FROM test_aggregation;

DROP TABLE test_aggregation;

WITH ['2023-04-05 00:25:23', '2023-04-05 00:25:24']::Array(DateTime) AS dt SELECT arrayMax(dt), arrayMin(dt), arrayDifference(dt);
WITH ['2023-04-05 00:25:23.123', '2023-04-05 00:25:24.124']::Array(DateTime64(3)) AS dt SELECT arrayMax(dt), arrayMin(dt), arrayDifference(dt);
WITH ['2023-04-05', '2023-04-06']::Array(Date) AS d SELECT arrayMax(d), arrayMin(d), arrayDifference(d);
WITH ['2023-04-05', '2023-04-06']::Array(Date32) AS d SELECT arrayMax(d), arrayMin(d), arrayDifference(d);

SELECT 'Types of aggregation result array min';
SELECT toTypeName(arrayMin([toInt8(0)])), toTypeName(arrayMin([toInt16(0)])), toTypeName(arrayMin([toInt32(0)])), toTypeName(arrayMin([toInt64(0)]));
SELECT toTypeName(arrayMin([toUInt8(0)])), toTypeName(arrayMin([toUInt16(0)])), toTypeName(arrayMin([toUInt32(0)])), toTypeName(arrayMin([toUInt64(0)]));
Expand Down