thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-09 17:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

finish dev

Browse Source
This commit is contained in:
taiyang-li 2024-09-12 10:08:52 +08:00
parent 9fc225fee3
commit e43e3d8c17
5 changed files with 2 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/Core/Settings.h
View File

@ -1267,7 +1267,6 @@ class IColumn;
M(Bool, output_format_orc_string_as_string, true, "Use ORC String type instead of Binary for String columns", 0) \
M(ORCCompression, output_format_orc_compression_method, "zstd", "Compression method for ORC output format. Supported codecs: lz4, snappy, zlib, zstd, none (uncompressed)", 0) \
M(UInt64, output_format_orc_row_index_stride, 10'000, "Target row index stride in ORC output format", 0) \
M(Double, output_format_orc_dictionary_key_size_threshold, 0.0, "For a string column in ORC output format, if the number of distinct values is greater than this fraction of the total number of non-null rows, turn off dictionary encoding. Otherwise dictionary encoding is enabled", 0) \
\
M(CapnProtoEnumComparingMode, format_capn_proto_enum_comparising_mode, FormatSettings::CapnProtoEnumComparingMode::BY_VALUES, "How to map ClickHouse Enum and CapnProto Enum", 0) \
\

3
src/Core/SettingsChangesHistory.cpp
View File

@ -96,8 +96,7 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
{"use_json_alias_for_old_object_type", true, false, "Use JSON type alias to create new JSON type"},
{"type_json_skip_duplicated_paths", false, false, "Allow to skip duplicated paths during JSON parsing"},
{"allow_experimental_vector_similarity_index", false, false, "Added new setting to allow experimental vector similarity indexes"},
{"input_format_try_infer_datetimes_only_datetime64", true, false, "Allow to infer DateTime instead of DateTime64 in data formats"},
{"output_format_orc_dictionary_key_size_threshold", 0.0, 0.0, "For a string column in ORC output format, if the number of distinct values is greater than this fraction of the total number of non-null rows, turn off dictionary encoding. Otherwise dictionary encoding is enabled"},
{"input_format_try_infer_datetimes_only_datetime64", true, false, "Allow to infer DateTime instead of DateTime64 in data formats"}
}
},
{"24.7",

1
src/Formats/FormatFactory.cpp
View File

@ -240,7 +240,6 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
format_settings.orc.output_string_as_string = settings.output_format_orc_string_as_string;
format_settings.orc.output_compression_method = settings.output_format_orc_compression_method;
format_settings.orc.output_row_index_stride = settings.output_format_orc_row_index_stride;
format_settings.orc.output_dictionary_key_size_threshold = settings.output_format_orc_dictionary_key_size_threshold;
format_settings.orc.use_fast_decoder = settings.input_format_orc_use_fast_decoder;
format_settings.orc.filter_push_down = settings.input_format_orc_filter_push_down;
format_settings.orc.reader_time_zone_name = settings.input_format_orc_reader_time_zone_name;

1
src/Formats/FormatSettings.h
View File

@ -414,7 +414,6 @@ struct FormatSettings
bool filter_push_down = true;
UInt64 output_row_index_stride = 10'000;
String reader_time_zone_name = "GMT";
double output_dictionary_key_size_threshold = 0.0;
bool dictionary_as_low_cardinality = true;
} orc{};

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

@ -78,9 +78,7 @@ void ORCOutputStream::write(const void* buf, size_t length)
}
ORCBlockOutputFormat::ORCBlockOutputFormat(WriteBuffer & out_, const Block & header_, const FormatSettings & format_settings_)
: IOutputFormat(header_, out_)
, format_settings{format_settings_}
, output_stream(out_)
: IOutputFormat(header_, out_), format_settings{format_settings_}, output_stream(out_)
{
for (const auto & type : header_.getDataTypes())
data_types.push_back(recursiveRemoveLowCardinality(type));
@ -567,7 +565,6 @@ void ORCBlockOutputFormat::prepareWriter()
schema = orc::createStructType();
options.setCompression(getORCCompression(format_settings.orc.output_compression_method));
options.setRowIndexStride(format_settings.orc.output_row_index_stride);
options.setDictionaryKeySizeThreshold(format_settings.orc.output_dictionary_key_size_threshold);
size_t columns_count = header.columns();
for (size_t i = 0; i != columns_count; ++i)
schema->addStructField(header.safeGetByPosition(i).name, getORCType(recursiveRemoveLowCardinality(data_types[i])));