searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-26 14:54:27 +01:00
Code Issues Releases Wiki Activity

Merge #4858

Browse Source 
4858: also intersect the universe for searchOnAttributes r=irevoire a=dureuill

# Pull Request

## Related issue
Fixes #4857 

## What does this PR do?
- intersect with the universe (which does not contain the filtered out ids) when looking up documents for words, even when using `searchOnAttributes`


Co-authored-by: Louis Dureuil <louis@meilisearch.com>
This commit is contained in:
meili-bors[bot] 2024-08-07 13:15:26 +00:00 committed by GitHub
commit b44e17c4c3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 24 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
milli/src/search/new/db_cache.rs
View File

@ -110,18 +110,18 @@ impl<'ctx> DatabaseCache<'ctx> {
.map_err(Into::into) .map_err(Into::into)
} }
fn get_value_from_keys<'v, K1, KC, DC>( fn get_value_from_keys<'v, K1, KC>(
txn: &'ctx RoTxn<'_>, txn: &'ctx RoTxn<'_>,
cache_key: K1, cache_key: K1,
db_keys: &'v [KC::EItem], db_keys: &'v [KC::EItem],
cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>, cache: &mut FxHashMap<K1, Option<Cow<'ctx, [u8]>>>,
db: Database<KC, Bytes>, db: Database<KC, Bytes>,
universe: Option<&RoaringBitmap>,
merger: MergeFn, merger: MergeFn,
) -> Result<Option<DC::DItem>> ) -> Result<Option<RoaringBitmap>>
where where
K1: Copy + Eq + Hash, K1: Copy + Eq + Hash,
KC: BytesEncode<'v>, KC: BytesEncode<'v>,
DC: BytesDecodeOwned,
KC::EItem: Sized, KC::EItem: Sized,
{ {
if let Entry::Vacant(entry) = cache.entry(cache_key) { if let Entry::Vacant(entry) = cache.entry(cache_key) {
@ -146,16 +146,22 @@ impl<'ctx> DatabaseCache<'ctx> {
entry.insert(bitmap_ptr); entry.insert(bitmap_ptr);
} }
match cache.get(&cache_key).unwrap() { let bitmap_bytes = match cache.get(&cache_key).unwrap() {
Some(Cow::Borrowed(bytes)) => DC::bytes_decode_owned(bytes) Some(Cow::Borrowed(bytes)) => bytes,
Some(Cow::Owned(bytes)) => bytes.as_slice(),
None => return Ok(None),
};
match (bitmap_bytes, universe) {
(bytes, Some(universe)) => {
CboRoaringBitmapCodec::intersection_with_serialized(bytes, universe)
.map(Some)
.map_err(Into::into)
}
(bytes, None) => CboRoaringBitmapCodec::bytes_decode_owned(bytes)
.map(Some) .map(Some)
.map_err(heed::Error::Decoding) .map_err(heed::Error::Decoding)
.map_err(Into::into), .map_err(Into::into),
Some(Cow::Owned(bytes)) => DC::bytes_decode_owned(bytes)
.map(Some)
.map_err(heed::Error::Decoding)
.map_err(Into::into),
None => Ok(None),
} }
} }
} }
@ -207,12 +213,13 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> = let keys: Vec<_> =
restricted_fids.tolerant.iter().map(|(fid, _)| (interned, *fid)).collect(); restricted_fids.tolerant.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>( DatabaseCache::get_value_from_keys::<_, _>(
self.txn, self.txn,
word, word,
&keys[..], &keys[..],
&mut self.db_cache.word_docids, &mut self.db_cache.word_docids,
self.index.word_fid_docids.remap_data_type::<Bytes>(), self.index.word_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps, merge_cbo_roaring_bitmaps,
) )
} }
@ -238,12 +245,13 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> = let keys: Vec<_> =
restricted_fids.exact.iter().map(|(fid, _)| (interned, *fid)).collect(); restricted_fids.exact.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>( DatabaseCache::get_value_from_keys::<_, _>(
self.txn, self.txn,
word, word,
&keys[..], &keys[..],
&mut self.db_cache.exact_word_docids, &mut self.db_cache.exact_word_docids,
self.index.word_fid_docids.remap_data_type::<Bytes>(), self.index.word_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps, merge_cbo_roaring_bitmaps,
) )
} }
@ -294,12 +302,13 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> = let keys: Vec<_> =
restricted_fids.tolerant.iter().map(|(fid, _)| (interned, *fid)).collect(); restricted_fids.tolerant.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>( DatabaseCache::get_value_from_keys::<_, _>(
self.txn, self.txn,
prefix, prefix,
&keys[..], &keys[..],
&mut self.db_cache.word_prefix_docids, &mut self.db_cache.word_prefix_docids,
self.index.word_prefix_fid_docids.remap_data_type::<Bytes>(), self.index.word_prefix_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps, merge_cbo_roaring_bitmaps,
) )
} }
@ -325,12 +334,13 @@ impl<'ctx> SearchContext<'ctx> {
let keys: Vec<_> = let keys: Vec<_> =
restricted_fids.exact.iter().map(|(fid, _)| (interned, *fid)).collect(); restricted_fids.exact.iter().map(|(fid, _)| (interned, *fid)).collect();
DatabaseCache::get_value_from_keys::<_, _, CboRoaringBitmapCodec>( DatabaseCache::get_value_from_keys::<_, _>(
self.txn, self.txn,
prefix, prefix,
&keys[..], &keys[..],
&mut self.db_cache.exact_word_prefix_docids, &mut self.db_cache.exact_word_prefix_docids,
self.index.word_prefix_fid_docids.remap_data_type::<Bytes>(), self.index.word_prefix_fid_docids.remap_data_type::<Bytes>(),
universe,
merge_cbo_roaring_bitmaps, merge_cbo_roaring_bitmaps,
) )
} }