thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 00:30:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #67157 from ClickHouse/Avogar-patch-5

Browse Source 
Fix wrong usage of input_format_max_bytes_to_read_for_schema_inference in schema cache
This commit is contained in:
Kruglov Pavel 2024-07-30 10:45:36 +00:00 committed by GitHub
commit b143ce5481
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/Formats/FormatFactory.cpp
View File

@ -252,7 +252,7 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
format_settings.msgpack.number_of_columns = settings.input_format_msgpack_number_of_columns;
format_settings.msgpack.output_uuid_representation = settings.output_format_msgpack_uuid_representation;
format_settings.max_rows_to_read_for_schema_inference = settings.input_format_max_rows_to_read_for_schema_inference;
format_settings.max_bytes_to_read_for_schema_inference = settings.input_format_max_rows_to_read_for_schema_inference;
format_settings.max_bytes_to_read_for_schema_inference = settings.input_format_max_bytes_to_read_for_schema_inference;
format_settings.column_names_for_schema_inference = settings.column_names_for_schema_inference;
format_settings.schema_inference_hints = settings.schema_inference_hints;
format_settings.schema_inference_make_columns_nullable = settings.schema_inference_make_columns_nullable;

2
tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.reference Normal file
View File

@ -0,0 +1,2 @@
x Nullable(Int64)
schema_inference_hints=, max_rows_to_read_for_schema_inference=25000, max_bytes_to_read_for_schema_inference=1000, schema_inference_make_columns_nullable=true, try_infer_integers=true, try_infer_dates=true, try_infer_datetimes=true, try_infer_numbers_from_strings=false, read_bools_as_numbers=true, read_bools_as_strings=true, read_objects_as_strings=true, read_numbers_as_strings=true, read_arrays_as_strings=true, try_infer_objects_as_tuples=true, infer_incomplete_types_as_strings=true, try_infer_objects=false, use_string_type_for_ambiguous_paths_in_named_tuples_inference_from_objects=false

13
tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.sh Executable file
View File

@ -0,0 +1,13 @@
#!/usr/bin/env bash
CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
# shellcheck source=../shell_config.sh
. "$CUR_DIR"/../shell_config.sh
echo '{"x" : 42}' > $CLICKHOUSE_TEST_UNIQUE_NAME.json
$CLICKHOUSE_LOCAL -nm -q "
DESC file('$CLICKHOUSE_TEST_UNIQUE_NAME.json') SETTINGS input_format_max_bytes_to_read_for_schema_inference=1000;
SELECT additional_format_info from system.schema_inference_cache"
rm $CLICKHOUSE_TEST_UNIQUE_NAME.json