thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-24 08:32:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Extending arrayEnumerateUniq.

Browse Source 
https://github.com/yandex/ClickHouse/issues/2934
This commit is contained in:
Amos Bird 2018-08-28 15:30:44 +08:00
parent 9cdd576332
commit a4dfe0ae38
5 changed files with 218 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
dbms/src/Functions/CMakeLists.txt
View File

@ -40,6 +40,7 @@ generate_function_register(Array
FunctionCountEqual
FunctionArrayEnumerate
FunctionArrayEnumerateUniq
FunctionArrayEnumerateDense
FunctionArrayUniq
FunctionArrayDistinct
FunctionEmptyArrayUInt8

160
dbms/src/Functions/FunctionsArray.cpp
View File

@ -1503,19 +1503,22 @@ void FunctionArrayDistinct::executeHashed(
}
}
/// Implementation of FunctionArrayEnumerateUniq.
/// Implementation of FunctionArrayEnumerateExtended.
FunctionPtr FunctionArrayEnumerateUniq::create(const Context &)
template <typename Derived>
FunctionPtr FunctionArrayEnumerateExtended<Derived>::create(const Context &)
{
return std::make_shared<FunctionArrayEnumerateUniq>();
return std::make_shared<Derived>();
}
String FunctionArrayEnumerateUniq::getName() const
template <typename Derived>
String FunctionArrayEnumerateExtended<Derived>::getName() const
{
return name;
return Derived::name;
}
DataTypePtr FunctionArrayEnumerateUniq::getReturnTypeImpl(const DataTypes & arguments) const
template <typename Derived>
DataTypePtr FunctionArrayEnumerateExtended<Derived>::getReturnTypeImpl(const DataTypes & arguments) const
{
if (arguments.size() == 0)
throw Exception("Number of arguments for function " + getName() + " doesn't match: passed "
@ -1533,7 +1536,8 @@ DataTypePtr FunctionArrayEnumerateUniq::getReturnTypeImpl(const DataTypes & argu
return std::make_shared<DataTypeArray>(std::make_shared<DataTypeUInt32>());
}
void FunctionArrayEnumerateUniq::executeImpl(Block & block, const ColumnNumbers & arguments, size_t result, size_t /*input_rows_count*/)
template <typename Derived>
void FunctionArrayEnumerateExtended<Derived>::executeImpl(Block & block, const ColumnNumbers & arguments, size_t result, size_t /*input_rows_count*/)
{
const ColumnArray::Offsets * offsets = nullptr;
ColumnRawPtrs data_columns;
@ -1620,8 +1624,9 @@ void FunctionArrayEnumerateUniq::executeImpl(Block & block, const ColumnNumbers
}
template <typename Derived>
template <typename T>
bool FunctionArrayEnumerateUniq::executeNumber(const ColumnArray * array, const IColumn * null_map, ColumnUInt32::Container & res_values)
bool FunctionArrayEnumerateExtended<Derived>::executeNumber(const ColumnArray * array, const IColumn * null_map, ColumnUInt32::Container & res_values)
{
const IColumn * inner_col;
@ -1649,6 +1654,9 @@ bool FunctionArrayEnumerateUniq::executeNumber(const ColumnArray * array, const
ValuesToIndices indices;
size_t prev_off = 0;
if constexpr (std::is_same_v<Derived, FunctionArrayEnumerateUniq>)
{
// Unique
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
@ -1663,10 +1671,38 @@ bool FunctionArrayEnumerateUniq::executeNumber(const ColumnArray * array, const
}
prev_off = off;
}
} else {
// Dense
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
size_t rank = 0;
UInt32 null_index = 0;
size_t off = offsets[i];
for (size_t j = prev_off; j < off; ++j)
{
if (null_map_data && ((*null_map_data)[j] == 1))
{
if (!null_index)
null_index = ++rank;
res_values[j] = null_index;
}
else
{
auto & idx = indices[values[j]];
if (!idx)
idx = ++rank;
res_values[j] = idx;
}
}
prev_off = off;
}
}
return true;
}
bool FunctionArrayEnumerateUniq::executeString(const ColumnArray * array, const IColumn * null_map, ColumnUInt32::Container & res_values)
template <typename Derived>
bool FunctionArrayEnumerateExtended<Derived>::executeString(const ColumnArray * array, const IColumn * null_map, ColumnUInt32::Container & res_values)
{
const IColumn * inner_col;
@ -1693,6 +1729,9 @@ bool FunctionArrayEnumerateUniq::executeString(const ColumnArray * array, const
null_map_data = &static_cast<const ColumnUInt8 *>(null_map)->getData();
ValuesToIndices indices;
if constexpr (std::is_same_v<Derived, FunctionArrayEnumerateUniq>)
{
// Unique
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
@ -1707,10 +1746,38 @@ bool FunctionArrayEnumerateUniq::executeString(const ColumnArray * array, const
}
prev_off = off;
}
} else {
// Dense
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
size_t rank = 0;
UInt32 null_index = 0;
size_t off = offsets[i];
for (size_t j = prev_off; j < off; ++j)
{
if (null_map_data && ((*null_map_data)[j] == 1))
{
if (!null_index)
null_index = ++rank;
res_values[j] = null_index;
}
else
{
auto & idx = indices[nested->getDataAt(j)];
if (!idx)
idx = ++rank;
res_values[j] = idx;
}
}
prev_off = off;
}
}
return true;
}
bool FunctionArrayEnumerateUniq::execute128bit(
template <typename Derived>
bool FunctionArrayEnumerateExtended<Derived>::execute128bit(
const ColumnArray::Offsets & offsets,
const ColumnRawPtrs & columns,
const ColumnRawPtrs & null_maps,
@ -1739,6 +1806,9 @@ bool FunctionArrayEnumerateUniq::execute128bit(
ValuesToIndices indices;
size_t prev_off = 0;
if constexpr (std::is_same_v<Derived, FunctionArrayEnumerateUniq>)
{
// Unique
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
@ -1769,11 +1839,54 @@ bool FunctionArrayEnumerateUniq::execute128bit(
}
prev_off = off;
}
} else {
// Dense
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
size_t off = offsets[i];
size_t rank = 0;
for (size_t j = prev_off; j < off; ++j)
{
if (has_nullable_columns)
{
KeysNullMap<UInt128> bitmap{};
for (size_t i = 0; i < columns.size(); ++i)
{
if (null_maps[i])
{
const auto & null_map = static_cast<const ColumnUInt8 &>(*null_maps[i]).getData();
if (null_map[j] == 1)
{
size_t bucket = i / 8;
size_t offset = i % 8;
bitmap[bucket] |= UInt8(1) << offset;
}
}
}
auto &idx = indices[packFixed<UInt128>(j, count, columns, key_sizes, bitmap)];
if (!idx)
idx = ++rank;
res_values[j] = idx;
}
else
{
auto &idx = indices[packFixed<UInt128>(j, count, columns, key_sizes)];;
if (!idx)
idx = ++rank;
res_values[j] = idx;
}
}
prev_off = off;
}
}
return true;
}
void FunctionArrayEnumerateUniq::executeHashed(
template <typename Derived>
void FunctionArrayEnumerateExtended<Derived>::executeHashed(
const ColumnArray::Offsets & offsets,
const ColumnRawPtrs & columns,
ColumnUInt32::Container & res_values)
@ -1785,6 +1898,9 @@ void FunctionArrayEnumerateUniq::executeHashed(
ValuesToIndices indices;
size_t prev_off = 0;
if constexpr (std::is_same_v<Derived, FunctionArrayEnumerateUniq>)
{
// Unique
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
@ -1796,6 +1912,28 @@ void FunctionArrayEnumerateUniq::executeHashed(
prev_off = off;
}
}
else
{
// Dense
for (size_t i = 0; i < offsets.size(); ++i)
{
indices.clear();
size_t off = offsets[i];
size_t rank = 0;
for (size_t j = prev_off; j < off; ++j)
{
auto & idx = indices[hash128(j, count, columns)];
if (!idx)
idx = ++rank;
res_values[j] = idx;
}
prev_off = off;
}
}
}
template class FunctionArrayEnumerateExtended<FunctionArrayEnumerateUniq>;
template class FunctionArrayEnumerateExtended<FunctionArrayEnumerateDense>;
/// Implementation of FunctionEmptyArrayToSingle.

19
dbms/src/Functions/FunctionsArray.h
View File

@ -1260,10 +1260,10 @@ private:
};
class FunctionArrayEnumerateUniq : public IFunction
template <typename Derived>
class FunctionArrayEnumerateExtended : public IFunction
{
public:
static constexpr auto name = "arrayEnumerateUniq";
static FunctionPtr create(const Context & context);
String getName() const override;
@ -1298,6 +1298,21 @@ private:
ColumnUInt32::Container & res_values);
};
class FunctionArrayEnumerateUniq : public FunctionArrayEnumerateExtended<FunctionArrayEnumerateUniq>
{
using Base = FunctionArrayEnumerateExtended<FunctionArrayEnumerateUniq>;
public:
static constexpr auto name = "arrayEnumerateUniq";
using Base::create;
};
class FunctionArrayEnumerateDense : public FunctionArrayEnumerateExtended<FunctionArrayEnumerateDense>
{
using Base = FunctionArrayEnumerateExtended<FunctionArrayEnumerateDense>;
public:
static constexpr auto name = "arrayEnumerateDense";
using Base::create;
};
template <typename Type> struct TypeToColumnType { using ColumnType = ColumnVector<Type>; };
template <> struct TypeToColumnType<String> { using ColumnType = ColumnString; };

2
dbms/tests/queries/0_stateless/00710_array_enumerate_dense.reference Normal file
View File

@ -0,0 +1,2 @@
[1,2,3,1]
[1,2,1]

5
dbms/tests/queries/0_stateless/00710_array_enumerate_dense.sql Normal file
View File

@ -0,0 +1,5 @@
-- empty result set
SELECT a FROM (SELECT groupArray(intDiv(number, 54321)) AS a, arrayUniq(a) AS u, arrayEnumerateDense(a) AS arr FROM (SELECT number FROM system.numbers LIMIT 1000000) GROUP BY intHash32(number) % 100000) where u <> arrayReverseSort(arr)[1];
SELECT arrayEnumerateDense([[1], [2], [34], [1]]);
SELECT arrayEnumerateDense([(1, 2), (3, 4), (1, 2)]);