rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-10-29 06:56:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove union wrapping for single-terms

Browse Source 
search-benchmark-game shows TOP_100_COUNT regression on queries tagged intersection_union.

The regression came from allowing single-term boolean unions to become TermUnion for Block-WAND. https://github.com/quickwit-oss/tantivy/pull/2915
When such a scorer is used as the optional side of RequiredOptionalScorer, boxing converted the lone term into BufferedUnionScorer.

Keep the TermUnion representation available for pruning collection, but unwrap one-term unions when boxing or doing non-pruning iteration.
This commit is contained in:
pascal
2026-06-29 19:33:50 +02:00
committed by PSeitz
parent 02e34508e2
commit 874d54a63a
1 changed files with 26 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/query/boolean_query/boolean_weight.rs
+26 -12
View File
@@ -91,10 +91,14 @@ fn into_box_scorer<TScoreCombiner: ScoreCombiner>(
num_docs: u32,
) -> Box<dyn Scorer> {
match scorer {
SpecializedScorer::TermUnion(term_scorers) => {
let union_scorer =
BufferedUnionScorer::build(term_scorers, score_combiner_fn, num_docs);
Box::new(union_scorer)
SpecializedScorer::TermUnion(mut term_scorers) => {
if term_scorers.len() == 1 {
Box::new(term_scorers.pop().unwrap())
} else {
let union_scorer =
BufferedUnionScorer::build(term_scorers, score_combiner_fn, num_docs);
Box::new(union_scorer)
}
}
SpecializedScorer::TermIntersection(term_scorers) => {
let boxed_scorers: Vec<Box<dyn Scorer>> = term_scorers
@@ -504,10 +508,15 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
let scorer = self.complex_scorer(reader, 1.0, &self.score_combiner_fn)?;
let num_docs = reader.num_docs();
match scorer {
SpecializedScorer::TermUnion(term_scorers) => {
let mut union_scorer =
BufferedUnionScorer::build(term_scorers, &self.score_combiner_fn, num_docs);
for_each_scorer(&mut union_scorer, callback);
SpecializedScorer::TermUnion(mut term_scorers) => {
if term_scorers.len() == 1 {
let mut term_scorer = term_scorers.pop().unwrap();
for_each_scorer(&mut term_scorer, callback);
} else {
let mut union_scorer =
BufferedUnionScorer::build(term_scorers, &self.score_combiner_fn, num_docs);
for_each_scorer(&mut union_scorer, callback);
}
}
SpecializedScorer::TermIntersection(term_scorers) => {
let boxed_scorers: Vec<Box<dyn Scorer>> = term_scorers
@@ -534,10 +543,15 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
let mut buffer = [0u32; COLLECT_BLOCK_BUFFER_LEN];
match scorer {
SpecializedScorer::TermUnion(term_scorers) => {
let mut union_scorer =
BufferedUnionScorer::build(term_scorers, &self.score_combiner_fn, num_docs);
for_each_docset_buffered(&mut union_scorer, &mut buffer, callback);
SpecializedScorer::TermUnion(mut term_scorers) => {
if term_scorers.len() == 1 {
let mut term_scorer = term_scorers.pop().unwrap();
for_each_docset_buffered(&mut term_scorer, &mut buffer, callback);
} else {
let mut union_scorer =
BufferedUnionScorer::build(term_scorers, &self.score_combiner_fn, num_docs);
for_each_docset_buffered(&mut union_scorer, &mut buffer, callback);
}
}
SpecializedScorer::TermIntersection(term_scorers) => {
let boxed_scorers: Vec<Box<dyn Scorer>> = term_scorers