What is the problem the feature request solves?

In CometBatchIterator we export the schema with each batch via Arrow FFI:

          val arrowSchema = ArrowSchema.wrap(schemaAddrs(index))
          val arrowArray = ArrowArray.wrap(arrayAddrs(index))
          Data.exportVector(
            allocator,
            getFieldVector(valueVector, "export"),
            provider,
            arrowArray,
            arrowSchema)

Exporting the schema seems quite expensive since it involves string copies and memory allocation. It gets more expensive for complex schemas, especially when nested types are involved.

Internally in Data.exportVector, the schema is exported with:

exportField(allocator, vector.getField(), provider, outSchema);

I wonder if we could refactor CometBatchIterator to just export the schema once, with the first batch, and then have the native side re-use that schema for subsequent batches.

Describe the potential solution

No response

Additional context

No response