coderfender commented on code in PR #2099: URL: https://github.com/apache/datafusion-comet/pull/2099#discussion_r2285594049
########## native/spark-expr/src/static_invoke/char_varchar_utils/read_side_padding.rs: ########## @@ -42,18 +41,48 @@ fn spark_read_side_padding2( ) -> Result<ColumnarValue, DataFusionError> { match args { [ColumnarValue::Array(array), ColumnarValue::Scalar(ScalarValue::Int32(Some(length)))] => { + let rpad_arg = RPadArgument::ConstLength(*length); match array.data_type() { - DataType::Utf8 => spark_read_side_padding_internal::<i32>(array, *length, truncate), + DataType::Utf8 => { + spark_read_side_padding_internal::<i32>(array, truncate, rpad_arg) + } DataType::LargeUtf8 => { - spark_read_side_padding_internal::<i64>(array, *length, truncate) + spark_read_side_padding_internal::<i64>(array, truncate, rpad_arg) } // Dictionary support required for SPARK-48498 DataType::Dictionary(_, value_type) => { let dict = as_dictionary_array::<Int32Type>(array); let col = if value_type.as_ref() == &DataType::Utf8 { - spark_read_side_padding_internal::<i32>(dict.values(), *length, truncate)? + spark_read_side_padding_internal::<i32>(dict.values(), truncate, rpad_arg)? } else { - spark_read_side_padding_internal::<i64>(dict.values(), *length, truncate)? + spark_read_side_padding_internal::<i64>(dict.values(), truncate, rpad_arg)? + }; + // col consists of an array, so arg of to_array() is not used. Can be anything + let values = col.to_array(0)?; + let result = DictionaryArray::try_new(dict.keys().clone(), values)?; + Ok(ColumnarValue::Array(make_array(result.into()))) + } + other => Err(DataFusionError::Internal(format!( + "Unsupported data type {other:?} for function rpad/read_side_padding", + ))), + } + } + [ColumnarValue::Array(array), ColumnarValue::Array(array_int)] => { + let rpad_arg = RPadArgument::ColArray(Arc::clone(array_int)); + match array.data_type() { + DataType::Utf8 => { + spark_read_side_padding_internal::<i32>(array, truncate, rpad_arg) + } + DataType::LargeUtf8 => { Review Comment: Thank you for sharing this @mbutrovich I will update this info in the github issue I plan to create to port these changes to data fusion crate -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org