dwsmith1983 commented on code in PR #5654:
URL: https://github.com/apache/datafusion-comet/pull/5654#discussion_r4100226456
##########
native/core/src/parquet/parquet_support.rs:
##########
@@ -162,43 +169,330 @@ impl SparkParquetOptions {
/// Spark-compatible cast implementation. Defers to DataFusion's cast where
that is known
/// to be compatible, and returns an error when a not supported and not
DF-compatible cast
-/// is requested.
+/// is requested. Resolves the nested field mapping for this one value; a
per-file caller
+/// resolves once and uses [`spark_parquet_convert_with_mapping`] for every
batch.
pub fn spark_parquet_convert(
arg: ColumnarValue,
data_type: &DataType,
parquet_options: &SparkParquetOptions,
+) -> DataFusionResult<ColumnarValue> {
+ let mapping =
+ resolve_field_mapping(&arg.data_type(), data_type,
parquet_options).map_err(spark_error)?;
+ spark_parquet_convert_with_mapping(arg, data_type, &mapping,
parquet_options)
+}
+
+/// [`spark_parquet_convert`] with a mapping already resolved for the value's
type.
+pub(crate) fn spark_parquet_convert_with_mapping(
+ arg: ColumnarValue,
+ data_type: &DataType,
+ mapping: &FieldMapping,
+ parquet_options: &SparkParquetOptions,
) -> DataFusionResult<ColumnarValue> {
match arg {
- ColumnarValue::Array(array) =>
Ok(ColumnarValue::Array(parquet_convert_array(
+ ColumnarValue::Array(array) => Ok(ColumnarValue::Array(convert_array(
array,
data_type,
+ mapping,
parquet_options,
+ None,
)?)),
ColumnarValue::Scalar(scalar) => {
// Note that normally CAST(scalar) should be fold in Spark JVM
side. However, for
// some cases e.g., scalar subquery, Spark will not fold it, so we
need to handle it
// here.
let array = scalar.to_array()?;
let scalar = ScalarValue::try_from_array(
- &parquet_convert_array(array, data_type, parquet_options)?,
+ &convert_array(array, data_type, mapping, parquet_options,
None)?,
0,
)?;
Ok(ColumnarValue::Scalar(scalar))
}
}
}
-fn parquet_convert_array(
- array: ArrayRef,
+/// Wrap a [`SparkError`] the way every native operator surfaces it to the JVM.
+pub(crate) fn spark_error(error: SparkError) -> DataFusionError {
+ DataFusionError::External(Box::new(error))
+}
+
+/// Outcome of matching one requested id or name against a struct's file
fields: the last
+/// file field that matched and whether more than one did. A plain `Copy`
value, so resolving
+/// a wide struct allocates nothing per id or per name; the matched names are
only gathered
+/// when an ambiguity is reported.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) struct FieldMatch {
Review Comment:
Done as sketched. `from_id_to_index` is a `HashMap<i32, Option<usize>>`
filled with `map.entry(id).and_modify(|m| *m = None).or_insert(Some(i))`, and
the id arm raises `DuplicateFieldByFieldId` on `Some(None)` with the matched
names from `field_names_with_id`. `FieldMatch`, `record_field_match` and their
test are gone.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
