Skip to content

branch-4.0: [opt](varbinary) support multi_distinct_count about varbinary and add conf mapping iceberg uuid #59406 #59483

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

Merged
yiguolei merged 1 commit into from
Dec 31, 2025
+17 −8
Merged

branch-4.0: [opt](varbinary) support multi_distinct_count about varbinary and add conf mapping iceberg uuid #59406 #59483

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
6 changes: 3 additions & 3 deletions be/src/vec/aggregate_functions/aggregate_function_uniq.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,9 +40,9 @@ AggregateFunctionPtr create_aggregate_function_uniq(const std::string& name,
return creator_with_type_list<
TYPE_BOOLEAN, TYPE_TINYINT, TYPE_SMALLINT, TYPE_INT, TYPE_BIGINT, TYPE_LARGEINT,
TYPE_DECIMAL32, TYPE_DECIMAL64, TYPE_DECIMAL128I, TYPE_DECIMAL256, TYPE_VARCHAR,
TYPE_ARRAY, TYPE_FLOAT, TYPE_DOUBLE, TYPE_DATEV2, TYPE_DATETIMEV2,
TYPE_TIMESTAMPTZ>::create<AggregateFunctionUniq, Data>(argument_types,
result_is_nullable, attr);
TYPE_ARRAY, TYPE_FLOAT, TYPE_DOUBLE, TYPE_DATEV2, TYPE_DATETIMEV2, TYPE_TIMESTAMPTZ,
TYPE_VARBINARY>::create<AggregateFunctionUniq, Data>(argument_types, result_is_nullable,
attr);
}

void register_aggregate_function_uniq(AggregateFunctionSimpleFactory& factory) {
Expand Down
9 changes: 5 additions & 4 deletions be/src/vec/aggregate_functions/aggregate_function_uniq.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
#include <vector>

#include "common/compiler_util.h" // IWYU pragma: keep
#include "runtime/primitive_type.h"
#include "vec/aggregate_functions/aggregate_function.h"
#include "vec/columns/column.h"
#include "vec/columns/column_vector.h"
Expand Down Expand Up @@ -56,7 +57,7 @@ class ColumnDecimal;

template <PrimitiveType T>
struct AggregateFunctionUniqExactData {
static constexpr bool is_string_key = is_string_type(T);
static constexpr bool is_string_key = is_string_type(T) || is_varbinary(T);
using Key = std::conditional_t<
is_string_key, UInt128,
std::conditional_t<T == TYPE_ARRAY, UInt64,
Expand Down Expand Up @@ -91,7 +92,7 @@ namespace detail {
template <PrimitiveType T, typename Data>
struct OneAdder {
static void ALWAYS_INLINE add(Data& data, const IColumn& column, size_t row_num) {
if constexpr (is_string_type(T)) {
if constexpr (is_string_type(T) || is_varbinary(T)) {
StringRef value = column.get_data_at(row_num);
data.set.insert(Data::get_key(value));
} else if constexpr (T == TYPE_ARRAY) {
Expand Down Expand Up @@ -119,7 +120,7 @@ class AggregateFunctionUniq final
NotNullableAggregateFunction {
public:
using KeyType =
std::conditional_t<is_string_type(T), UInt128,
std::conditional_t<is_string_type(T) || is_varbinary(T), UInt128,
std::conditional_t<T == TYPE_ARRAY, UInt64,
typename PrimitiveTypeTraits<T>::ColumnItemType>>;
AggregateFunctionUniq(const DataTypes& argument_types_)
Expand All @@ -138,7 +139,7 @@ class AggregateFunctionUniq final

static ALWAYS_INLINE const KeyType* get_keys(std::vector<KeyType>& keys_container,
const IColumn& column, size_t batch_size) {
if constexpr (is_string_type(T)) {
if constexpr (is_string_type(T) || is_varbinary(T)) {
keys_container.resize(batch_size);
for (size_t i = 0; i != batch_size; ++i) {
StringRef value = column.get_data_at(i);
Expand Down
2 changes: 1 addition & 1 deletion fe/fe-core/src/main/java/org/apache/doris/datasource/iceberg/IcebergUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -572,7 +572,7 @@ private static Type icebergPrimitiveTypeToDorisType(org.apache.iceberg.types.Typ
case STRING:
return Type.STRING;
case UUID:
return ScalarType.createVarbinaryType(16);
return enableMappingVarbinary ? ScalarType.createVarbinaryType(16) : Type.STRING;
case BINARY:
return enableMappingVarbinary ? ScalarType.createVarbinaryType(VarBinaryType.MAX_VARBINARY_LENGTH)
: Type.STRING;
Expand Down
Binary file modified regression-test/data/external_table_p0/iceberg/test_iceberg_varbinary.out
View file
Open in desktop
Binary file not shown.
8 changes: 8 additions & 0 deletions regression-test/suites/external_table_p0/iceberg/test_iceberg_varbinary.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,4 +149,12 @@ suite("test_iceberg_varbinary", "p0,external,doris,external_docker,external_dock
qt_select19 """
select * from test_ice_uuid_parquet_write_with_mapping order by id;
"""

qt_select21 """
select multi_distinct_count(col2),multi_distinct_count(col1) from test_ice_uuid_orc;
"""

qt_select22 """
select multi_distinct_count(col2),multi_distinct_count(col1) from test_ice_uuid_parquet;
"""
}
Loading