Merge pull request #50873 from Avogar/parquet-big-integers

Fallback to parsing big integer from String instead of exception in Parquet format

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(
+                return readColumnWithStringData<arrow::BinaryArray>(arrow_column, column_name);
-                    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));
             total_size += chunk_length;
         }
     }

tests/queries/0_stateless/02786_parquet_big_integer_compatibility.reference

@@ -0,0 +1 @@
+424242424242424242424242424242424242424242424242424242

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"
+