[GLUTEN-1632][CH]Daily Update Clickhouse Version (20250207) (#8681)

* [GLUTEN-1632][CH]Daily Update Clickhouse Version (20250207)

* Fix build due to ClickHouse/ClickHouse#75299

* Fix build due to ClickHouse/ClickHouse#75636

---------

Co-authored-by: kyligence-git <gluten@kyligence.io>
Co-authored-by: Chang Chen <baibaichen@gmail.com>

Author: 3 people

cpp-ch/clickhouse.version

@@ -1,3 +1,3 @@
 CH_ORG=Kyligence
-CH_BRANCH=rebase_ch/20250205
-CH_COMMIT=c1451130e6d
+CH_BRANCH=rebase_ch/20250207
+CH_COMMIT=b6c11f40aed

cpp-ch/local-engine/Common/ChunkBuffer.cpp

@@ -16,6 +16,8 @@
  */
 #include "ChunkBuffer.h"
 
+#include <Columns/IColumn.h>
+
 namespace local_engine
 {
 void ChunkBuffer::add(DB::Chunk & columns, int start, int end)

cpp-ch/local-engine/Functions/FunctionsBloomFilter.h

@@ -18,7 +18,6 @@
 
 #include <cstddef>
 #include <memory>
-#include <type_traits>
 #include <AggregateFunctions/AggregateFunctionFactory.h>
 #include <AggregateFunctions/AggregateFunctionGroupBloomFilter.h>
 #include <AggregateFunctions/IAggregateFunction_fwd.h>
@@ -31,6 +30,7 @@
 #include <Columns/IColumn.h>
 #include <Core/TypeId.h>
 #include <DataTypes/DataTypeAggregateFunction.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <DataTypes/IDataType.h>
 #include <Functions/FunctionHelpers.h>

cpp-ch/local-engine/Functions/SparkArrayFlatten.cpp

@@ -14,12 +14,13 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-#include <Functions/IFunction.h>
-#include <Functions/FunctionFactory.h>
-#include <Functions/FunctionHelpers.h>
-#include <DataTypes/DataTypeArray.h>
 #include <Columns/ColumnArray.h>
 #include <Columns/ColumnNullable.h>
+#include <DataTypes/DataTypeArray.h>
+#include <DataTypes/DataTypeNullable.h>
+#include <Functions/FunctionFactory.h>
+#include <Functions/FunctionHelpers.h>
+#include <Functions/IFunction.h>
 
 
 namespace DB

cpp-ch/local-engine/Functions/SparkFunctionArraySort.cpp

@@ -14,18 +14,18 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-#include <Functions/FunctionHelpers.h>
-#include <Functions/FunctionFactory.h>
 #include <Columns/ColumnArray.h>
 #include <Columns/ColumnFunction.h>
 #include <Columns/ColumnNullable.h>
-#include <Common/Exception.h>
 #include <DataTypes/DataTypeArray.h>
 #include <DataTypes/DataTypeFunction.h>
 #include <DataTypes/DataTypeLowCardinality.h>
-#include <Poco/Logger.h>
-#include <Common/logger_useful.h>
+#include <DataTypes/DataTypeNullable.h>
+#include <Functions/FunctionFactory.h>
+#include <Functions/FunctionHelpers.h>
 #include <base/sort.h>
+#include <Common/Exception.h>
+#include <Common/logger_useful.h>
 
 namespace DB::ErrorCodes
 {

cpp-ch/local-engine/Functions/SparkFunctionCheckDecimalOverflow.cpp

@@ -16,16 +16,17 @@
  */
 #include "SparkFunctionCheckDecimalOverflow.h"
 
+#include <typeinfo>
 #include <Columns/ColumnDecimal.h>
 #include <Columns/ColumnNullable.h>
 #include <Columns/ColumnsNumber.h>
 #include <Core/DecimalFunctions.h>
+#include <Core/callOnTypeIndex.h>
 #include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypesDecimal.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionHelpers.h>
 #include <Functions/IFunction.h>
-#include <typeinfo>
 
 namespace DB
 {

cpp-ch/local-engine/Functions/SparkFunctionFloor.h

@@ -18,6 +18,7 @@
 
 #include <Columns/ColumnNullable.h>
 #include <Columns/ColumnVector.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <DataTypes/IDataType.h>
 #include <Functions/FunctionFactory.h>

cpp-ch/local-engine/Functions/SparkFunctionMakeDecimal.cpp

@@ -16,6 +16,8 @@
  */
 #include <Columns/ColumnNullable.h>
 #include <Core/DecimalFunctions.h>
+#include <Core/callOnTypeIndex.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypesDecimal.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionHelpers.h>

cpp-ch/local-engine/Functions/SparkFunctionMapToString.h

@@ -15,10 +15,11 @@
  * limitations under the License.
  */
 #pragma once
-#include <memory>
+
 #include <Columns/ColumnMap.h>
 #include <Columns/ColumnNullable.h>
 #include <Columns/ColumnStringHelpers.h>
+#include <Columns/ColumnTuple.h>
 #include <Columns/ColumnsNumber.h>
 #include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypeString.h>

cpp-ch/local-engine/Functions/SparkFunctionToDateTime.h

@@ -19,6 +19,7 @@
 #include <Columns/ColumnsDateTime.h>
 #include <Columns/ColumnsNumber.h>
 #include <DataTypes/DataTypeDateTime64.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionHelpers.h>
 #include <Functions/extractTimeZoneFromFunctionArguments.h>

cpp-ch/local-engine/Functions/SparkFunctionTupleElement.cpp

@@ -16,17 +16,18 @@
  */
 #include <memory>
 #include <Columns/ColumnArray.h>
+#include <Columns/ColumnNullable.h>
 #include <Columns/ColumnString.h>
 #include <Columns/ColumnTuple.h>
 #include <Columns/ColumnsNumber.h>
 #include <DataTypes/DataTypeArray.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypeTuple.h>
 #include <DataTypes/IDataType.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionHelpers.h>
 #include <Functions/IFunction.h>
 #include <Common/assert_cast.h>
-#include "Columns/ColumnNullable.h"
 
 
 namespace DB

cpp-ch/local-engine/Functions/SparkFunctionUnscaleValue.cpp

@@ -15,6 +15,7 @@
  * limitations under the License.
  */
 #include <Columns/ColumnConst.h>
+#include <Core/callOnTypeIndex.h>
 #include <DataTypes/DataTypesDecimal.h>
 #include <Functions/FunctionFactory.h>
 #include <Functions/FunctionHelpers.h>

cpp-ch/local-engine/Operator/AdvancedExpandStep.cpp

@@ -16,8 +16,9 @@
  */
 
 #include "AdvancedExpandStep.h"
+
+#include <Columns/ColumnAggregateFunction.h>
 #include <Columns/ColumnNullable.h>
-#include <Columns/ColumnsNumber.h>
 #include <Columns/IColumn.h>
 #include <Core/Settings.h>
 #include <DataTypes/DataTypeNullable.h>
@@ -27,14 +28,11 @@
 #include <Interpreters/castColumn.h>
 #include <Operator/StreamingAggregatingStep.h>
 #include <Processors/ResizeProcessor.h>
-#include <Processors/Transforms/ExpressionTransform.h>
 #include <QueryPipeline/Pipe.h>
 #include <QueryPipeline/QueryPipelineBuilder.h>
+#include <Poco/Logger.h>
 #include <Common/AggregateUtil.h>
 #include <Common/CHUtil.h>
-#include <Common/WeakHash.h>
-
-#include <Poco/Logger.h>
 #include <Common/logger_useful.h>
 
 namespace local_engine

cpp-ch/local-engine/Operator/PartitionColumnFillingTransform.cpp

@@ -15,8 +15,9 @@
  * limitations under the License.
  */
 #include "PartitionColumnFillingTransform.h"
-#include <Columns/ColumnNullable.h>
+
 #include <Columns/ColumnsNumber.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <Functions/FunctionHelpers.h>
 #include <IO/ReadBufferFromString.h>

cpp-ch/local-engine/Operator/ReplicateRowsStep.cpp

@@ -16,8 +16,7 @@
  */
 #include "ReplicateRowsStep.h"
 
-#include <iostream>
-
+#include <Columns/IColumn.h>
 #include <QueryPipeline/QueryPipelineBuilder.h>
 
 namespace DB

cpp-ch/local-engine/Operator/WindowGroupLimitStep.cpp

@@ -17,6 +17,7 @@
 
 #include "WindowGroupLimitStep.h"
 
+#include <Columns/IColumn.h>
 #include <Processors/Chunk.h>
 #include <Processors/IProcessor.h>
 #include <QueryPipeline/QueryPipelineBuilder.h>

cpp-ch/local-engine/Parser/AggregateFunctionParser.cpp

@@ -18,6 +18,7 @@
 
 #include <AggregateFunctions/AggregateFunctionFactory.h>
 #include <DataTypes/DataTypeAggregateFunction.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypeTuple.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <Functions/FunctionHelpers.h>

cpp-ch/local-engine/Parser/RelParsers/ExpandRelParser.cpp

@@ -15,8 +15,9 @@
  * limitations under the License.
  */
 #include "ExpandRelParser.h"
-#include <ratio>
+
 #include <vector>
+#include <Columns/ColumnAggregateFunction.h>
 #include <Core/Block.h>
 #include <Core/ColumnWithTypeAndName.h>
 #include <Operator/AdvancedExpandStep.h>
@@ -41,9 +42,7 @@ ExpandRelParser::ExpandRelParser(ParserContextPtr parser_context_) : RelParser(p
 void updateType(DB::DataTypePtr & type, const DB::DataTypePtr & new_type)
 {
     if (type == nullptr || (!type->isNullable() && new_type->isNullable()))
-    {
         type = new_type;
-    }
 }
 
 DB::QueryPlanPtr
@@ -91,7 +90,8 @@ ExpandField ExpandRelParser::buildExpandField(const DB::Block & header, const su
                 fields.push_back(field);
                 if (field >= header.columns())
                 {
-                    throw DB::Exception(DB::ErrorCodes::LOGICAL_ERROR, "Field index out of range: {}, header: {}", field, header.dumpStructure());
+                    throw DB::Exception(
+                        DB::ErrorCodes::LOGICAL_ERROR, "Field index out of range: {}, header: {}", field, header.dumpStructure());
                 }
                 updateType(types[i], header.getByPosition(field).type);
                 const auto & name = header.getByPosition(field).name;
@@ -128,10 +128,8 @@ ExpandField ExpandRelParser::buildExpandField(const DB::Block & header, const su
     }
 
     for (int i = 0; i < names.size(); ++i)
-    {
         if (names[i].empty())
             names[i] = getUniqueName("expand_" + std::to_string(i));
-    }
 
     ExpandField expand_field(names, types, expand_kinds, expand_fields);
     return expand_field;
@@ -144,10 +142,8 @@ bool ExpandRelParser::isLazyAggregateExpand(const substrait::ExpandRel & expand_
         return false;
     const auto & aggregate_rel = input_rel.aggregate();
     for (const auto & measure : aggregate_rel.measures())
-    {
         if (measure.measure().phase() != substrait::AggregationPhase::AGGREGATION_PHASE_INITIAL_TO_INTERMEDIATE)
             return false;
-    }
     return true;
 }
 
@@ -172,7 +168,7 @@ DB::QueryPlanPtr ExpandRelParser::lazyAggregateExpandParse(
     auto aggregate_rel = rel.expand().input().aggregate();
     auto aggregate_descriptions = buildAggregations(input_header, expand_field, aggregate_rel);
 
-    size_t  grouping_keys = aggregate_rel.groupings(0).grouping_expressions_size();
+    size_t grouping_keys = aggregate_rel.groupings(0).grouping_expressions_size();
 
     auto expand_step
         = std::make_unique<AdvancedExpandStep>(getContext(), input_header, grouping_keys, aggregate_descriptions, expand_field);
@@ -189,10 +185,8 @@ DB::AggregateDescriptions ExpandRelParser::buildAggregations(
     DB::AggregateDescriptions descriptions;
     DB::ColumnsWithTypeAndName aggregate_columns;
     for (const auto & col : header.getColumnsWithTypeAndName())
-    {
         if (typeid_cast<const DB::ColumnAggregateFunction *>(col.column.get()))
             aggregate_columns.push_back(col);
-    }
 
     for (size_t i = 0; i < aggregate_rel.measures_size(); ++i)
     {

cpp-ch/local-engine/Parser/RelParsers/ReadRelParser.cpp

@@ -19,6 +19,7 @@
 #include <memory>
 #include <Core/Block.h>
 #include <Core/Settings.h>
+#include <IO/ReadBufferFromString.h>
 #include <Interpreters/Context.h>
 #include <Operator/BlocksBufferPoolTransform.h>
 #include <Parser/RelParsers/MergeTreeRelParser.h>
@@ -47,7 +48,8 @@ extern const int LOGICAL_ERROR;
 namespace local_engine
 {
 using namespace DB;
-DB::QueryPlanPtr ReadRelParser::parse(DB::QueryPlanPtr query_plan, const substrait::Rel & rel, std::list<const substrait::Rel *> & rel_stack)
+DB::QueryPlanPtr
+ReadRelParser::parse(DB::QueryPlanPtr query_plan, const substrait::Rel & rel, std::list<const substrait::Rel *> & rel_stack)
 {
     if (query_plan)
         throw DB::Exception(DB::ErrorCodes::LOGICAL_ERROR, "Source node's input plan should be null");

cpp-ch/local-engine/Shuffle/PartitionWriter.cpp

@@ -31,6 +31,7 @@
 #include <boost/algorithm/string/case_conv.hpp>
 #include <Common/Stopwatch.h>
 #include <Common/ThreadPool.h>
+#include <Common/logger_useful.h>
 
 namespace DB
 {

cpp-ch/local-engine/Shuffle/SelectorBuilder.h

@@ -17,17 +17,15 @@
 #pragma once
 #include <memory>
 #include <vector>
+#include <Columns/IColumn.h>
 #include <Core/Block.h>
-#include <Core/ColumnWithTypeAndName.h>
 #include <Core/SortDescription.h>
 #include <Functions/IFunction.h>
-#include <Interpreters/ActionsDAG.h>
 #include <Interpreters/ExpressionActions.h>
 #include <Processors/Chunk.h>
 #include <base/types.h>
 #include <substrait/plan.pb.h>
 #include <Poco/JSON/Array.h>
-#include <Common/BlockIterator.h>
 #include <Common/PODArray.h>
 
 namespace local_engine

cpp-ch/local-engine/Storages/Output/NormalFileWriter.cpp

@@ -19,6 +19,8 @@
 #include <Columns/ColumnArray.h>
 #include <Columns/ColumnConst.h>
 #include <Columns/ColumnMap.h>
+#include <Columns/ColumnTuple.h>
+#include <Interpreters/castColumn.h>
 #include <QueryPipeline/QueryPipeline.h>
 #include <Poco/URI.h>
 #include <Common/DebugUtils.h>

cpp-ch/local-engine/Storages/Output/NormalFileWriter.h

@@ -16,6 +16,7 @@
  */
 #pragma once
 
+#include <Columns/ColumnNullable.h>
 #include <Core/Block.h>
 #include <Core/Field.h>
 #include <Interpreters/Context.h>

cpp-ch/local-engine/Storages/Serializations/ExcelDecimalSerialization.h

@@ -19,6 +19,14 @@
 #include <DataTypes/Serializations/SerializationNumber.h>
 #include <Common/DateLUTImpl.h>
 
+namespace DB
+{
+namespace ErrorCodes
+{
+extern const int NOT_IMPLEMENTED;
+}
+}
+
 namespace local_engine
 {
 

cpp-ch/local-engine/Storages/Serializations/ExcelSerialization.h

@@ -26,6 +26,7 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int ATTEMPT_TO_READ_AFTER_EOF;
+    extern const int NOT_IMPLEMENTED;
 }
 }
 

cpp-ch/local-engine/Storages/SubstraitSource/FormatFile.cpp

@@ -17,6 +17,7 @@
 #include "FormatFile.h"
 #include <Core/Settings.h>
 #include <IO/ReadBufferFromFile.h>
+#include <IO/ReadBufferFromString.h>
 #include <Storages/SubstraitSource/JSONFormatFile.h>
 #include <boost/algorithm/string/case_conv.hpp>
 #include <Common/GlutenConfig.h>

cpp-ch/local-engine/tests/gtest_transformer.cpp

@@ -14,6 +14,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
+#include <Columns/IColumn.h>
 #include <Core/Field.h>
 #include <DataTypes/DataTypeFactory.h>
 #include <Operator/PartitionColumnFillingTransform.h>