thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-25 09:02:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add estimateCardinalityInPermutedRange for ColumnFixedString

Browse Source
This commit is contained in:
Igor Markelov 2024-05-26 17:05:56 +00:00
parent 9d7c470d4e
commit 9202e46ff5
2 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/Columns/ColumnFixedString.cpp
View File

@ -5,6 +5,7 @@
#include <IO/WriteHelpers.h> #include <IO/WriteHelpers.h>
#include <Common/Arena.h> #include <Common/Arena.h>
#include <Common/HashTable/Hash.h> #include <Common/HashTable/Hash.h>
#include <Common/HashTable/StringHashSet.h>
#include <Common/SipHash.h> #include <Common/SipHash.h>
#include <Common/WeakHash.h> #include <Common/WeakHash.h>
#include <Common/assert_cast.h> #include <Common/assert_cast.h>
@ -200,6 +201,24 @@ void ColumnFixedString::updatePermutation(IColumn::PermutationSortDirection dire
updatePermutationImpl(limit, res, equal_ranges, ComparatorDescendingStable(*this), comparator_equal, DefaultSort(), DefaultPartialSort()); updatePermutationImpl(limit, res, equal_ranges, ComparatorDescendingStable(*this), comparator_equal, DefaultSort(), DefaultPartialSort());
} }
size_t ColumnFixedString::estimateCardinalityInPermutedRange(const Permutation & permutation, const EqualRange & equal_range) const
{
const size_t range_size = equal_range.size();
if (range_size <= 1)
return range_size;
/// TODO use sampling if the range is too large (e.g. 16k elements, but configurable)
StringHashSet elements;
bool inserted = false;
for (size_t i = equal_range.from; i < equal_range.to; ++i)
{
size_t id = permutation[i];
StringRef ref = getDataAt(id);
elements.emplace(ref, inserted);
}
return elements.size();
}
void ColumnFixedString::insertRangeFrom(const IColumn & src, size_t start, size_t length) void ColumnFixedString::insertRangeFrom(const IColumn & src, size_t start, size_t length)
{ {
const ColumnFixedString & src_concrete = assert_cast<const ColumnFixedString &>(src); const ColumnFixedString & src_concrete = assert_cast<const ColumnFixedString &>(src);

2
src/Columns/ColumnFixedString.h
View File

@ -142,6 +142,8 @@ public:
void updatePermutation(IColumn::PermutationSortDirection direction, IColumn::PermutationSortStability stability, void updatePermutation(IColumn::PermutationSortDirection direction, IColumn::PermutationSortStability stability,
size_t limit, int nan_direction_hint, Permutation & res, EqualRanges & equal_ranges) const override; size_t limit, int nan_direction_hint, Permutation & res, EqualRanges & equal_ranges) const override;
size_t estimateCardinalityInPermutedRange(const Permutation & permutation, const EqualRange & equal_range) const override;
void insertRangeFrom(const IColumn & src, size_t start, size_t length) override; void insertRangeFrom(const IColumn & src, size_t start, size_t length) override;
ColumnPtr filter(const IColumn::Filter & filt, ssize_t result_size_hint) const override; ColumnPtr filter(const IColumn::Filter & filt, ssize_t result_size_hint) const override;