Compare commits

..

1 Commits

Author SHA1 Message Date
Pascal Seitz
b1e4c3a966 make get_term_info_async pub 2026-06-25 09:55:59 +01:00
3 changed files with 40 additions and 43 deletions

View File

@@ -283,7 +283,8 @@ impl InvertedIndexReader {
#[cfg(feature = "quickwit")]
impl InvertedIndexReader {
pub(crate) async fn get_term_info_async(&self, term: &Term) -> io::Result<Option<TermInfo>> {
/// Resolves a `Term` to its [`TermInfo`] asynchronously, if present in the dictionary.
pub async fn get_term_info_async(&self, term: &Term) -> io::Result<Option<TermInfo>> {
self.termdict.get_async(term.serialized_value_bytes()).await
}
@@ -336,23 +337,38 @@ impl InvertedIndexReader {
pub async fn warm_postings(&self, term: &Term, with_positions: bool) -> io::Result<bool> {
let term_info_opt: Option<TermInfo> = self.get_term_info_async(term).await?;
if let Some(term_info) = term_info_opt {
let postings = self
.postings_file_slice
.read_bytes_slice_async(term_info.postings_range.clone());
if with_positions {
let positions = self
.positions_file_slice
.read_bytes_slice_async(term_info.positions_range.clone());
futures_util::future::try_join(postings, positions).await?;
} else {
postings.await?;
}
self.warm_postings_from_term_info(&term_info, with_positions)
.await?;
Ok(true)
} else {
Ok(false)
}
}
/// Warmup a block postings given a `TermInfo`.
/// This method is for an advanced usage only.
///
/// Use this when the [`TermInfo`] is already known (e.g. resolved via
/// [`Self::get_term_info_async`]) to avoid a redundant dictionary lookup.
pub async fn warm_postings_from_term_info(
&self,
term_info: &TermInfo,
with_positions: bool,
) -> io::Result<()> {
let postings = self
.postings_file_slice
.read_bytes_slice_async(term_info.postings_range.clone());
if with_positions {
let positions = self
.positions_file_slice
.read_bytes_slice_async(term_info.positions_range.clone());
futures_util::future::try_join(postings, positions).await?;
} else {
postings.await?;
}
Ok(())
}
/// Warmup a block postings given a range of `Term`s.
/// This method is for an advanced usage only.
///

View File

@@ -91,14 +91,10 @@ fn into_box_scorer<TScoreCombiner: ScoreCombiner>(
num_docs: u32,
) -> Box<dyn Scorer> {
match 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::TermUnion(term_scorers) => {
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
@@ -508,15 +504,10 @@ 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(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::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::TermIntersection(term_scorers) => {
let boxed_scorers: Vec<Box<dyn Scorer>> = term_scorers
@@ -543,15 +534,10 @@ impl<TScoreCombiner: ScoreCombiner + Sync> Weight for BooleanWeight<TScoreCombin
let mut buffer = [0u32; COLLECT_BLOCK_BUFFER_LEN];
match scorer {
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::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::TermIntersection(term_scorers) => {
let boxed_scorers: Vec<Box<dyn Scorer>> = term_scorers

View File

@@ -55,11 +55,6 @@ pub struct BufferedUnionScorer<TScorer, TScoreCombiner = DoNothingCombiner> {
num_docs: u32,
}
// Keep this helper out-of-line. When LLVM inlines it into
// `BufferedUnionScorer::advance`, the full traversal path used by combined
// collectors such as `(TopDocs, Count)` becomes sensitive to unrelated codegen
// changes and regresses on large unions.
#[inline(never)]
fn refill<TScorer: Scorer, TScoreCombiner: ScoreCombiner>(
scorers: &mut Vec<TScorer>,
bitsets: &mut [TinySet; HORIZON_NUM_TINYBITSETS],