rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-06-05 01:50:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

use binary search instead of linear for get_val in merge (#1548)

Browse Source 
* use binary search instead of linear for get_val in merge

* use partition_point
This commit is contained in:
PSeitz
2022-09-26 08:42:33 +08:00
committed by GitHub
parent ea8e6d7b1d
commit 21e0adefda
1 changed files with 3 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/indexer/sorted_doc_id_multivalue_column.rs
View File

@@ -72,13 +72,9 @@ impl<'a> SortedDocIdMultiValueColumn<'a> {
impl<'a> Column for SortedDocIdMultiValueColumn<'a> {
fn get_val(&self, pos: u64) -> u64 {
// use the offsets index to find the doc_id which will contain the position.
// the offsets are strictly increasing so we can do a simple search on it.
let new_doc_id: DocId = self
.offsets
.iter()
.position(|&offset| offset > pos)
.expect("pos is out of bounds") as DocId
- 1u32;
// the offsets are strictly increasing so we can do a binary search on it.
let new_doc_id: DocId = self.offsets.partition_point(|&offset| offset <= pos) as DocId - 1; // Offsets start at 0, so -1 is safe
// now we need to find the position of `pos` in the multivalued bucket
let num_pos_covered_until_now = self.offsets[new_doc_id as usize];