This is an automated email from the ASF dual-hosted git repository.
tustvold pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/master by this push:
new cea5146b6 Add RowSelection::iter(), Into<Vec<RowSelector>> and example
(#3173)
cea5146b6 is described below
commit cea5146b69b3413a1d5caa946e0774ec8d834e95
Author: Andrew Lamb <[email protected]>
AuthorDate: Wed Nov 23 13:56:07 2022 -0500
Add RowSelection::iter(), Into<Vec<RowSelector>> and example (#3173)
---
parquet/src/arrow/arrow_reader/selection.rs | 54 ++++++++++++++++++++++++++++-
1 file changed, 53 insertions(+), 1 deletion(-)
diff --git a/parquet/src/arrow/arrow_reader/selection.rs
b/parquet/src/arrow/arrow_reader/selection.rs
index d5c4ce5ea..487e95fcd 100644
--- a/parquet/src/arrow/arrow_reader/selection.rs
+++ b/parquet/src/arrow/arrow_reader/selection.rs
@@ -59,6 +59,30 @@ impl RowSelector {
/// A typical use-case would be using the [`PageIndex`] to filter out rows
/// that don't satisfy a predicate
///
+/// # Example
+/// ```
+/// use parquet::arrow::arrow_reader::{RowSelection, RowSelector};
+///
+/// let selectors = vec![
+/// RowSelector { row_count: 5, skip: true },
+/// RowSelector { row_count: 5, skip: false },
+/// RowSelector { row_count: 5, skip: false },
+/// RowSelector { row_count: 5, skip: true },
+/// ];
+///
+/// // Creating a selection will combine adjacent selectors
+/// let selection: RowSelection = selectors.into();
+///
+/// let expected = vec![
+/// RowSelector { row_count: 5, skip: true },
+/// RowSelector { row_count: 10, skip: false },
+/// RowSelector { row_count: 5, skip: true },
+/// ];
+///
+/// let actual: Vec<RowSelector> = selection.into();
+/// assert_eq!(actual, expected);
+/// ```
+///
/// [`PageIndex`]: [crate::file::page_index::index::PageIndex]
#[derive(Debug, Clone, Default, Eq, PartialEq)]
pub struct RowSelection {
@@ -243,7 +267,6 @@ impl RowSelection {
selectors: remaining,
}
}
-
/// Given a [`RowSelection`] computed under `self`, returns the
[`RowSelection`]
/// representing their conjunction
///
@@ -347,6 +370,12 @@ impl RowSelection {
}
self
}
+
+ /// Returns an iterator over the [`RowSelector`]s for this
+ /// [`RowSelection`].
+ pub fn iter(&self) -> impl Iterator<Item = &RowSelector> {
+ self.selectors.iter()
+ }
}
impl From<Vec<RowSelector>> for RowSelection {
@@ -355,6 +384,12 @@ impl From<Vec<RowSelector>> for RowSelection {
}
}
+impl From<RowSelection> for Vec<RowSelector> {
+ fn from(r: RowSelection) -> Self {
+ r.selectors
+ }
+}
+
impl From<RowSelection> for VecDeque<RowSelector> {
fn from(r: RowSelection) -> Self {
r.selectors.into()
@@ -789,6 +824,23 @@ mod tests {
}
}
+ #[test]
+ fn test_iter() {
+ // use the iter() API to show it does what is expected and
+ // avoid accidental deletion
+ let selectors = vec![
+ RowSelector::select(3),
+ RowSelector::skip(33),
+ RowSelector::select(4),
+ ];
+
+ let round_tripped = RowSelection::from(selectors.clone())
+ .iter()
+ .cloned()
+ .collect::<Vec<_>>();
+ assert_eq!(selectors, round_tripped);
+ }
+
#[test]
fn test_scan_ranges() {
let index = vec