Skip to content

feat: add bulk insertion to deletion vector #1578

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
81 changes: 80 additions & 1 deletion crates/iceberg/src/delete_vector.rs
Original file line number Diff line number Diff line change
Expand Up @@ -21,14 +21,16 @@ use roaring::RoaringTreemap;
use roaring::bitmap::Iter;
use roaring::treemap::BitmapIter;

use crate::{Error, ErrorKind, Result};

#[derive(Debug, Default)]
pub struct DeleteVector {
inner: RoaringTreemap,
}

impl DeleteVector {
#[allow(unused)]
pub(crate) fn new(roaring_treemap: RoaringTreemap) -> DeleteVector {
pub fn new(roaring_treemap: RoaringTreemap) -> DeleteVector {
DeleteVector {
inner: roaring_treemap,
}
Expand All @@ -43,6 +45,25 @@ impl DeleteVector {
self.inner.insert(pos)
}

/// Marks the given `positions` as deleted and returns the number of elements appended.
///
/// The input slice must be strictly ordered in ascending order, and every value must be greater than all existing values already in the set.
///
/// # Errors
///
/// Returns an error if the precondition is not met.
#[allow(dead_code)]
pub fn insert_positions(&mut self, positions: &[u64]) -> Result<usize> {
if let Err(err) = self.inner.append(positions.iter().copied()) {
return Err(Error::new(
ErrorKind::PreconditionFailed,
"failed to marks rows as deleted".to_string(),
)
.with_source(err));
}
Ok(positions.len())
}

#[allow(unused)]
pub fn len(&self) -> u64 {
self.inner.len()
Expand Down Expand Up @@ -120,3 +141,61 @@ impl BitOrAssign for DeleteVector {
self.inner.bitor_assign(&other.inner);
}
}

#[cfg(test)]
mod tests {
use super::*;

#[test]
fn test_insertion_and_iteration() {
let mut dv = DeleteVector::default();
assert!(dv.insert(42));
assert!(dv.insert(100));
assert!(!dv.insert(42));

let mut items: Vec<u64> = dv.iter().collect();
items.sort();
assert_eq!(items, vec![42, 100]);
assert_eq!(dv.len(), 2);
}

#[test]
fn test_successful_insert_positions() {
let mut dv = DeleteVector::default();
let positions = vec![1, 2, 3, 1000, 1 << 33];
assert_eq!(dv.insert_positions(&positions).unwrap(), 5);

let mut collected: Vec<u64> = dv.iter().collect();
collected.sort();
assert_eq!(collected, positions);
}

/// Testing scenario: bulk insertion fails because input positions are not strictly increasing.
#[test]
fn test_failed_insertion_unsorted_elements() {
let mut dv = DeleteVector::default();
let positions = vec![1, 3, 5, 4];
let res = dv.insert_positions(&positions);
assert!(res.is_err());
}

/// Testing scenario: bulk insertion fails because input positions have intersection with existing ones.
#[test]
fn test_failed_insertion_with_intersection() {
let mut dv = DeleteVector::default();
let positions = vec![1, 3, 5];
assert_eq!(dv.insert_positions(&positions).unwrap(), 3);

let res = dv.insert_positions(&[2, 4]);
assert!(res.is_err());
}

/// Testing scenario: bulk insertion fails because input positions have duplicates.
#[test]
fn test_failed_insertion_duplicate_elements() {
let mut dv = DeleteVector::default();
let positions = vec![1, 3, 5, 5];
let res = dv.insert_positions(&positions);
assert!(res.is_err());
}
}
Loading