From f0faa111d73c8512c1f88009f0ecfd1a804de45c Mon Sep 17 00:00:00 2001
From: Kruglov Pavel <48961922+Avogar@users.noreply.github.com>
Date: Thu, 25 Jul 2024 23:19:58 +0200
Subject: [PATCH 1/2] Fix wrong usage of
 input_format_max_bytes_to_read_for_schema_inference

---
 src/Formats/FormatFactory.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/Formats/FormatFactory.cpp b/src/Formats/FormatFactory.cpp
index 1271cdfb7ad..e8956159714 100644
--- a/src/Formats/FormatFactory.cpp
+++ b/src/Formats/FormatFactory.cpp
@@ -253,7 +253,7 @@ 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;

From d041df80aa112920f28d74ed26a0c8381808dafc Mon Sep 17 00:00:00 2001
From: avogar <avogar@clickhouse.com>
Date: Fri, 26 Jul 2024 12:14:26 +0000
Subject: [PATCH 2/2] Add test

---
 ..._to_read_for_schema_inference_in_cache.reference |  2 ++
 ...x_bytes_to_read_for_schema_inference_in_cache.sh | 13 +++++++++++++
 2 files changed, 15 insertions(+)
 create mode 100644 tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.reference
 create mode 100755 tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.sh

diff --git a/tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.reference b/tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.reference
new file mode 100644
index 00000000000..cd109daac52
--- /dev/null
+++ b/tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.reference
@@ -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
diff --git a/tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.sh b/tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.sh
new file mode 100755
index 00000000000..8a77538f592
--- /dev/null
+++ b/tests/queries/0_stateless/03212_max_bytes_to_read_for_schema_inference_in_cache.sh
@@ -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
+