thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-21 23:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #26334 from ryzuo/ryzuo

Browse Source 
Implementation of window function nth_value
This commit is contained in:
Alexander Kuzmenkov 2021-07-27 15:02:29 +03:00 committed by GitHub
commit 7e737d9568
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 165 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
src/Processors/Transforms/WindowTransform.cpp
View File

@ -1619,6 +1619,74 @@ struct WindowFunctionLagLeadInFrame final : public WindowFunction
}
};
struct WindowFunctionNthValue final : public WindowFunction
{
WindowFunctionNthValue(const std::string & name_,
const DataTypes & argument_types_, const Array & parameters_)
: WindowFunction(name_, argument_types_, parameters_)
{
if (!parameters.empty())
{
throw Exception(ErrorCodes::BAD_ARGUMENTS,
"Function {} cannot be parameterized", name_);
}
if (argument_types.size() != 2)
{
throw Exception(ErrorCodes::BAD_ARGUMENTS,
"Function '{}' accepts 2 arguments, {} given",
name_, argument_types.size());
}
}
DataTypePtr getReturnType() const override
{ return argument_types[0]; }
bool allocatesMemoryInArena() const override { return false; }
void windowInsertResultInto(const WindowTransform * transform,
size_t function_index) override
{
const auto & current_block = transform->blockAt(transform->current_row);
IColumn & to = *(current_block.output_columns[function_index]);
const auto & workspace = transform->workspaces[function_index];
int64_t offset = (*current_block.input_columns[
workspace.argument_column_indices[1]])[
transform->current_row.row].get<Int64>() - 1;
if (offset < 0)
{
throw Exception(ErrorCodes::BAD_ARGUMENTS,
"The offset for function {} must be non-negative, {} given",
getName(), offset);
}
if (offset > INT_MAX)
{
throw Exception(ErrorCodes::BAD_ARGUMENTS,
"The offset for function {} must be less than {}, {} given",
getName(), INT_MAX, offset);
}
const auto [target_row, offset_left] = transform->moveRowNumber(transform->frame_start, offset);
if (offset_left != 0
|| target_row < transform->frame_start
|| transform->frame_end <= target_row)
{
// Offset is outside the frame.
to.insertDefault();
}
else
{
// Offset is inside the frame.
to.insertFrom(*transform->blockAt(target_row).input_columns[
workspace.argument_column_indices[0]],
target_row.row);
}
}
};
void registerWindowFunctions(AggregateFunctionFactory & factory)
{
// Why didn't I implement lag/lead yet? Because they are a mess. I imagine
@ -1682,6 +1750,13 @@ void registerWindowFunctions(AggregateFunctionFactory & factory)
return std::make_shared<WindowFunctionLagLeadInFrame<true>>(
name, argument_types, parameters);
}, properties});
factory.registerFunction("nth_value", {[](const std::string & name,
const DataTypes & argument_types, const Array & parameters, const Settings *)
{
return std::make_shared<WindowFunctionNthValue>(
name, argument_types, parameters);
}, properties});
}
}

56
tests/queries/0_stateless/01591_window_functions.reference
View File

@ -1095,6 +1095,62 @@ order by number
7 6 8
8 7 9
9 8 9
-- nth_value without specific frame range given
select
number,
nth_value(number, 1) over w as firstValue,
nth_value(number, 2) over w as secondValue,
nth_value(number, 3) over w as thirdValue,
nth_value(number, 4) over w as fourthValue
from numbers(10)
window w as (order by number)
order by number
;
0 0 0 0 0
1 0 1 0 0
2 0 1 2 0
3 0 1 2 3
4 0 1 2 3
5 0 1 2 3
6 0 1 2 3
7 0 1 2 3
8 0 1 2 3
9 0 1 2 3
-- nth_value with frame range specified
select
number,
nth_value(number, 1) over w as firstValue,
nth_value(number, 2) over w as secondValue,
nth_value(number, 3) over w as thirdValue,
nth_value(number, 4) over w as fourthValue
from numbers(10)
window w as (order by number range between 1 preceding and 1 following)
order by number
;
0 0 1 0 0
1 0 1 2 0
2 1 2 3 0
3 2 3 4 0
4 3 4 5 0
5 4 5 6 0
6 5 6 7 0
7 6 7 8 0
8 7 8 9 0
9 8 9 0 0
-- to make nth_value return null for out-of-frame rows, cast the argument to
-- Nullable; otherwise, it returns default values.
SELECT
number,
nth_value(toNullable(number), 1) OVER w as firstValue,
nth_value(toNullable(number), 3) OVER w as thridValue
FROM numbers(5)
WINDOW w AS (ORDER BY number ASC)
;
0 0 \N
1 0 \N
2 0 2
3 0 2
4 0 2
-- In this case, we had a problem with PartialSortingTransform returning zero-row
-- chunks for input chunks w/o columns.
select count() over () from numbers(4) where number < 2;

34
tests/queries/0_stateless/01591_window_functions.sql
View File

@ -403,6 +403,40 @@ window w as (order by number range between 1 preceding and 1 following)
order by number
;
-- nth_value without specific frame range given
select
number,
nth_value(number, 1) over w as firstValue,
nth_value(number, 2) over w as secondValue,
nth_value(number, 3) over w as thirdValue,
nth_value(number, 4) over w as fourthValue
from numbers(10)
window w as (order by number)
order by number
;
-- nth_value with frame range specified
select
number,
nth_value(number, 1) over w as firstValue,
nth_value(number, 2) over w as secondValue,
nth_value(number, 3) over w as thirdValue,
nth_value(number, 4) over w as fourthValue
from numbers(10)
window w as (order by number range between 1 preceding and 1 following)
order by number
;
-- to make nth_value return null for out-of-frame rows, cast the argument to
-- Nullable; otherwise, it returns default values.
SELECT
number,
nth_value(toNullable(number), 1) OVER w as firstValue,
nth_value(toNullable(number), 3) OVER w as thridValue
FROM numbers(5)
WINDOW w AS (ORDER BY number ASC)
;
-- In this case, we had a problem with PartialSortingTransform returning zero-row
-- chunks for input chunks w/o columns.
select count() over () from numbers(4) where number < 2;