thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-25 17:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix failed uts

Browse Source
This commit is contained in:
taiyang-li 2024-08-09 18:33:05 +08:00
parent ba3fa8a87f
commit dccb6bdd88
2 changed files with 17 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
src/Processors/Formats/Impl/ORCBlockOutputFormat.cpp
View File

@ -280,20 +280,28 @@ void ORCBlockOutputFormat::writeColumn(
DataTypePtr & type,
const PaddedPODArray<UInt8> * null_bytemap)
{
orc_column.numElements = column.size();
size_t rows = column.size();
orc_column.resize(rows);
orc_column.numElements = rows;
/// Calculate orc_column.hasNulls
if (null_bytemap)
{
orc_column.hasNulls = !memoryIsZero(null_bytemap->data(), 0, null_bytemap->size());
if (orc_column.hasNulls)
{
orc_column.notNull.resize(null_bytemap->size());
for (size_t i = 0; i < null_bytemap->size(); ++i)
orc_column.notNull[i] = !(*null_bytemap)[i];
}
}
else
orc_column.hasNulls = false;
/// Fill orc_column.notNull
if (orc_column.hasNulls)
{
for (size_t i = 0; i < rows; ++i)
orc_column.notNull[i] = !(*null_bytemap)[i];
}
else
{
for (size_t i = 0; i < rows; ++i)
orc_column.notNull[i] = 1;
}
/// ORC doesn't have unsigned types, so cast everything to signed and sign-extend to Int64 to
/// make the ORC library calculate min and max correctly.
switch (type->getTypeId())
@ -516,27 +524,6 @@ void ORCBlockOutputFormat::writeColumn(
}
}
size_t ORCBlockOutputFormat::getColumnSize(const IColumn & column, DataTypePtr & type)
{
if (type->getTypeId() == TypeIndex::Array)
{
auto nested_type = assert_cast<const DataTypeArray &>(*type).getNestedType();
const IColumn & nested_column = assert_cast<const ColumnArray &>(column).getData();
return std::max(column.size(), getColumnSize(nested_column, nested_type));
}
return column.size();
}
size_t ORCBlockOutputFormat::getMaxColumnSize(Chunk & chunk)
{
size_t columns_num = chunk.getNumColumns();
size_t max_column_size = 0;
for (size_t i = 0; i != columns_num; ++i)
max_column_size = std::max(max_column_size, getColumnSize(*chunk.getColumns()[i], data_types[i]));
return max_column_size;
}
void ORCBlockOutputFormat::consume(Chunk chunk)
{
if (!writer)

5
src/Processors/Formats/Impl/ORCBlockOutputFormat.h
View File

@ -69,11 +69,6 @@ private:
void writeColumn(orc::ColumnVectorBatch & orc_column, const IColumn & column, DataTypePtr & type, const PaddedPODArray<UInt8> * null_bytemap);
/// These two functions are needed to know maximum nested size of arrays to
/// create an ORC Batch with the appropriate size
size_t getColumnSize(const IColumn & column, DataTypePtr & type);
size_t getMaxColumnSize(Chunk & chunk);
void prepareWriter();
const FormatSettings format_settings;