Merge pull request #51195 from ClickHouse/backport/23.5/50873

Backport #50873 to 23.5: Fallback to parsing big integer from String instead of exception in Parquet format
ClickHouse · Jun 21, 2023 · 4fa10a8 · 4fa10a8
2 parents 416c535 + d79a81a
commit 4fa10a8
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 6 deletions.
diff --git a/src/Processors/Formats/Impl/ArrowColumnToCHColumn.cpp b/src/Processors/Formats/Impl/ArrowColumnToCHColumn.cpp
@@ -202,13 +202,10 @@ static ColumnWithTypeAndName readColumnWithBigNumberFromBinaryData(std::shared_p
 
         for (size_t i = 0; i != chunk_length; ++i)
         {
+            /// If at least one value size is not equal to the size if big integer, fallback to reading String column and further cast to result type.
             if (!chunk.IsNull(i) && chunk.value_length(i) != sizeof(ValueType))
-                throw Exception(
-                    ErrorCodes::BAD_ARGUMENTS,
-                    "Cannot insert data into {} column from binary value, expected data with size {}, got {}",
-                    column_type->getName(),
-                    sizeof(ValueType),
-                    chunk.value_length(i));
+                return readColumnWithStringData<arrow::BinaryArray>(arrow_column, column_name);
+
             total_size += chunk_length;
         }
     }

diff --git a/tests/queries/0_stateless/02786_parquet_big_integer_compatibility.reference b/tests/queries/0_stateless/02786_parquet_big_integer_compatibility.reference
@@ -0,0 +1 @@
+424242424242424242424242424242424242424242424242424242
diff --git a/tests/queries/0_stateless/02786_parquet_big_integer_compatibility.sh b/tests/queries/0_stateless/02786_parquet_big_integer_compatibility.sh
@@ -0,0 +1,9 @@
+#!/usr/bin/env bash
+# Tags: no-fasttest
+
+CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CUR_DIR"/../shell_config.sh
+
+$CLICKHOUSE_LOCAL -q "select toString(424242424242424242424242424242424242424242424242424242::UInt256) as x format Parquet" | $CLICKHOUSE_LOCAL --input-format=Parquet --structure='x UInt256' -q "select * from table"
+