alamb commented on code in PR #7502:
URL: https://github.com/apache/arrow-rs/pull/7502#discussion_r2093305576
##########
parquet/src/arrow/arrow_reader/mod.rs:
##########
@@ -905,116 +899,37 @@ impl ParquetRecordBatchReader {
let array_reader =
build_array_reader(levels.levels.as_ref(), &ProjectionMask::all(),
row_groups)?;
+ let read_plan = ReadPlanBuilder::new(batch_size)
+ .with_selection(selection)
+ .build();
+
Ok(Self {
- batch_size,
array_reader,
schema: Arc::new(Schema::new(levels.fields.clone())),
- selection: selection.map(|s| s.trim().into()),
+ read_plan,
})
}
/// Create a new [`ParquetRecordBatchReader`] that will read at most
`batch_size` rows at
/// a time from [`ArrayReader`] based on the configured `selection`. If
`selection` is `None`
/// all rows will be returned
- pub(crate) fn new(
- batch_size: usize,
- array_reader: Box<dyn ArrayReader>,
- selection: Option<RowSelection>,
- ) -> Self {
+ pub(crate) fn new(array_reader: Box<dyn ArrayReader>, read_plan: ReadPlan)
-> Self {
let schema = match array_reader.get_data_type() {
ArrowType::Struct(ref fields) => Schema::new(fields.clone()),
_ => unreachable!("Struct array reader's data type is not
struct!"),
};
Self {
- batch_size,
array_reader,
schema: Arc::new(schema),
- selection: selection.map(|s| s.trim().into()),
+ read_plan,
}
}
-}
-/// Returns `true` if `selection` is `None` or selects some rows
-pub(crate) fn selects_any(selection: Option<&RowSelection>) -> bool {
Review Comment:
this code is moved into `ReadPlanBuilder`
--
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...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
