ClickHouse/src/Processors/Formats/IInputFormat.h
李扬 465962df7f
Support orc filter push down (file + stripe + rowgroup level) (#55330)
* support orc filter push down

* update orc lib version

* replace setqueryinfo with setkeycondition

* fix issue https://github.com/ClickHouse/ClickHouse/issues/53536

* refactor source with key condition

* fix building error

* remove std::cout

* update orc

* update orc version

* fix bugs

* improve code

* upgrade orc lib

* fix code style

* change as requested

* add performance tests for orc filter push down

* add performance tests for orc filter push down

* fix all bugs

* fix default as null issue

* add uts for null as default issues

* upgrade orc lib

* fix failed orc lib uts and fix typo

* fix failed uts

* fix failed uts

* fix ast fuzzer tests

* fix bug of uint64 overflow in https://s3.amazonaws.com/clickhouse-test-reports/55330/de22fdcaea2e12c96f300e95f59beba84401712d/fuzzer_astfuzzerubsan/report.html

* fix asan fatal caused by reused column vector batch in native orc input format. refer to https://s3.amazonaws.com/clickhouse-test-reports/55330/be39d23af2d7e27f5ec7f168947cf75aeaabf674/stateless_tests__asan__[4_4].htm

* fix wrong performance tests

* disable 02892_orc_filter_pushdown on aarch64. https://s3.amazonaws.com/clickhouse-test-reports/55330/be39d23af2d7e27f5ec7f168947cf75aeaabf674/stateless_tests__aarch64_.html

* add some comments

* add some comments

* inline range::equals and range::less

* fix data race of key condition

* trigger ci
2023-10-24 12:08:17 -07:00

82 lines
2.6 KiB
C++

#pragma once
#include <Formats/ColumnMapping.h>
#include <IO/ReadBuffer.h>
#include <Interpreters/Context.h>
#include <Processors/Formats/InputFormatErrorsLogger.h>
#include <Processors/SourceWithKeyCondition.h>
#include <Storages/MergeTree/KeyCondition.h>
namespace DB
{
struct SelectQueryInfo;
using ColumnMappingPtr = std::shared_ptr<ColumnMapping>;
/** Input format is a source, that reads data from ReadBuffer.
*/
class IInputFormat : public SourceWithKeyCondition
{
protected:
ReadBuffer * in [[maybe_unused]] = nullptr;
public:
/// ReadBuffer can be nullptr for random-access formats.
IInputFormat(Block header, ReadBuffer * in_);
/** In some usecase (hello Kafka) we need to read a lot of tiny streams in exactly the same format.
* The recreating of parser for each small stream takes too long, so we introduce a method
* resetParser() which allow to reset the state of parser to continue reading of
* source stream without recreating that.
* That should be called after current buffer was fully read.
*/
virtual void resetParser();
virtual void setReadBuffer(ReadBuffer & in_);
ReadBuffer & getReadBuffer() const { chassert(in); return *in; }
virtual const BlockMissingValues & getMissingValues() const
{
static const BlockMissingValues none;
return none;
}
/// Must be called from ParallelParsingInputFormat after readSuffix
ColumnMappingPtr getColumnMapping() const { return column_mapping; }
/// Must be called from ParallelParsingInputFormat before readPrefix
void setColumnMapping(ColumnMappingPtr column_mapping_) { column_mapping = column_mapping_; }
size_t getCurrentUnitNumber() const { return current_unit_number; }
void setCurrentUnitNumber(size_t current_unit_number_) { current_unit_number = current_unit_number_; }
void addBuffer(std::unique_ptr<ReadBuffer> buffer) { owned_buffers.emplace_back(std::move(buffer)); }
void setErrorsLogger(const InputFormatErrorsLoggerPtr & errors_logger_) { errors_logger = errors_logger_; }
virtual size_t getApproxBytesReadForChunk() const { return 0; }
void needOnlyCount() { need_only_count = true; }
protected:
virtual Chunk getChunkForCount(size_t rows);
ColumnMappingPtr column_mapping{};
InputFormatErrorsLoggerPtr errors_logger;
bool need_only_count = false;
private:
/// Number of currently parsed chunk (if parallel parsing is enabled)
size_t current_unit_number = 0;
std::vector<std::unique_ptr<ReadBuffer>> owned_buffers;
};
using InputFormatPtr = std::shared_ptr<IInputFormat>;
}