searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-12-23 13:10:06 +01:00
Code Issues Releases Wiki Activity

Remove the invalid get_phrases_docids universe parameter

Browse Source
This commit is contained in:
Clément Renault 2024-07-10 10:03:00 +02:00
parent cd7a20fa32
commit 93ba051094
No known key found for this signature in database
GPG Key ID: F250A4C4E3AE5F5F
3 changed files with 12 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
milli/src/search/new/ranking_rule_graph/exactness/mod.rs
View File

@ -29,7 +29,7 @@ fn compute_docids(
let candidates = match exact_term {
// TODO I move the intersection here
ExactTerm::Phrase(phrase) => ctx.get_phrase_docids(None, phrase)? & universe,
ExactTerm::Phrase(phrase) => ctx.get_phrase_docids(phrase)? & universe,
ExactTerm::Word(word) => {
ctx.word_docids(Some(universe), Word::Original(word))?.unwrap_or_default()
}

6
milli/src/search/new/ranking_rule_graph/proximity/compute_docids.rs
View File

@ -74,7 +74,7 @@ pub fn compute_docids(
if right_derivs.len() > 1 {
let universe = &universe;
if let Some(left_phrase) = left_phrase {
if universe.is_disjoint(ctx.get_phrase_docids(None, left_phrase)?) {
if universe.is_disjoint(ctx.get_phrase_docids(left_phrase)?) {
continue;
}
} else if let Some(left_word_docids) = ctx.word_docids(Some(universe), left_word)? {
@ -126,7 +126,7 @@ fn compute_prefix_edges(
// TODO we can clearly give the universe to this method
// Unfortunately, it is deserializing/computing stuff and
// keeping the result as a materialized bitmap.
let phrase_docids = ctx.get_phrase_docids(None, phrase)?;
let phrase_docids = ctx.get_phrase_docids(phrase)?;
if !phrase_docids.is_empty() {
used_left_phrases.insert(phrase);
}
@ -184,7 +184,7 @@ fn compute_non_prefix_edges(
let mut universe = universe.clone();
for phrase in left_phrase.iter().chain(right_phrase.iter()).copied() {
universe &= ctx.get_phrase_docids(None, phrase)?;
universe &= ctx.get_phrase_docids(phrase)?;
if universe.is_empty() {
return Ok(());
}

21
milli/src/search/new/resolve_query_graph.rs
View File

@ -19,15 +19,11 @@ pub struct PhraseDocIdsCache {
}
impl<'ctx> SearchContext<'ctx> {
/// Get the document ids associated with the given phrase
pub fn get_phrase_docids(
&mut self,
universe: Option<&RoaringBitmap>,
phrase: Interned<Phrase>,
) -> Result<&RoaringBitmap> {
pub fn get_phrase_docids(&mut self, phrase: Interned<Phrase>) -> Result<&RoaringBitmap> {
if self.phrase_docids.cache.contains_key(&phrase) {
return Ok(&self.phrase_docids.cache[&phrase]);
};
let docids = compute_phrase_docids(self, universe, phrase)?;
let docids = compute_phrase_docids(self, phrase)?;
// TODO can we improve that? Because there is an issue, we keep that in cache...
let _ = self.phrase_docids.cache.insert(phrase, docids);
let docids = &self.phrase_docids.cache[&phrase];
@ -47,7 +43,7 @@ pub fn compute_query_term_subset_docids(
}
}
for phrase in term.all_phrases(ctx)? {
docids |= ctx.get_phrase_docids(None, phrase)?;
docids |= ctx.get_phrase_docids(phrase)?;
}
if let Some(prefix) = term.use_prefix_db(ctx) {
@ -80,7 +76,7 @@ pub fn compute_query_term_subset_docids_within_field_id(
// guaranteed that all of its words are within a single fid.
if let Some(word) = phrase.words(ctx).iter().flatten().next() {
if let Some(word_fid_docids) = ctx.get_db_word_fid_docids(universe, *word, fid)? {
docids |= ctx.get_phrase_docids(None, phrase)? & word_fid_docids;
docids |= ctx.get_phrase_docids(phrase)? & word_fid_docids;
}
}
}
@ -118,7 +114,7 @@ pub fn compute_query_term_subset_docids_within_position(
if let Some(word_position_docids) =
ctx.get_db_word_position_docids(universe, *word, position)?
{
docids |= ctx.get_phrase_docids(None, phrase)? & word_position_docids;
docids |= ctx.get_phrase_docids(phrase)? & word_position_docids;
}
}
}
@ -190,7 +186,6 @@ pub fn compute_query_graph_docids(
pub fn compute_phrase_docids(
ctx: &mut SearchContext<'_>,
universe: Option<&RoaringBitmap>,
phrase: Interned<Phrase>,
) -> Result<RoaringBitmap> {
let Phrase { words } = ctx.phrase_interner.get(phrase).clone();
@ -200,7 +195,7 @@ pub fn compute_phrase_docids(
}
let mut candidates = RoaringBitmap::new();
for word in words.iter().flatten().copied() {
if let Some(word_docids) = ctx.word_docids(universe, Word::Original(word))? {
if let Some(word_docids) = ctx.word_docids(None, Word::Original(word))? {
candidates |= word_docids;
} else {
return Ok(RoaringBitmap::new());
@ -224,7 +219,7 @@ pub fn compute_phrase_docids(
.filter_map(|(index, word)| word.as_ref().map(|word| (index, word)))
{
if dist == 0 {
match ctx.get_db_word_pair_proximity_docids(universe, s1, s2, 1)? {
match ctx.get_db_word_pair_proximity_docids(None, s1, s2, 1)? {
Some(m) => bitmaps.push(m),
// If there are no documents for this pair, there will be no
// results for the phrase query.
@ -234,7 +229,7 @@ pub fn compute_phrase_docids(
let mut bitmap = RoaringBitmap::new();
for dist in 0..=dist {
if let Some(m) =
ctx.get_db_word_pair_proximity_docids(universe, s1, s2, dist as u8 + 1)?
ctx.get_db_word_pair_proximity_docids(None, s1, s2, dist as u8 + 1)?
{
bitmap |= m;
}