snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-07-28 17:21:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Split position DB into fid and relative position DB

Browse Source
This commit is contained in:
Loïc Lecrenier
2023-03-23 09:22:01 +01:00
parent 56b7209f26
commit 9b2653427d
11 changed files with 162 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
milli/src/search/criteria/attribute.rs
View File

@ -199,7 +199,7 @@ impl<'t> Criterion for Attribute<'t> {
struct QueryPositionIterator<'t> {
#[allow(clippy::type_complexity)]
inner:
Vec<Peekable<Box<dyn Iterator<Item = heed::Result<((&'t str, u32), RoaringBitmap)>> + 't>>>,
Vec<Peekable<Box<dyn Iterator<Item = heed::Result<((&'t str, u16), RoaringBitmap)>> + 't>>>,
}
impl<'t> QueryPositionIterator<'t> {
@ -241,7 +241,7 @@ impl<'t> QueryPositionIterator<'t> {
}
impl<'t> Iterator for QueryPositionIterator<'t> {
type Item = heed::Result<(u32, RoaringBitmap)>;
type Item = heed::Result<(u16, RoaringBitmap)>;
fn next(&mut self) -> Option<Self::Item> {
// sort inner words from the closest next position to the farthest next position.
@ -281,9 +281,9 @@ impl<'t> Iterator for QueryPositionIterator<'t> {
/// A Branch is represent a possible alternative of the original query and is build with the Query Tree,
/// This branch allows us to iterate over meta-interval of positions.
struct Branch<'t> {
query_level_iterator: Vec<(u32, RoaringBitmap, Peekable<QueryPositionIterator<'t>>)>,
last_result: (u32, RoaringBitmap),
branch_size: u32,
query_level_iterator: Vec<(u16, RoaringBitmap, Peekable<QueryPositionIterator<'t>>)>,
last_result: (u16, RoaringBitmap),
branch_size: u16,
}
impl<'t> Branch<'t> {
@ -303,7 +303,7 @@ impl<'t> Branch<'t> {
let mut branch = Self {
query_level_iterator,
last_result: (0, RoaringBitmap::new()),
branch_size: flatten_branch.len() as u32,
branch_size: flatten_branch.len() as u16,
};
branch.update_last_result();
@ -342,7 +342,7 @@ impl<'t> Branch<'t> {
Some(result) => {
result.as_ref().map(|(next_pos, _)| *next_pos - *pos).unwrap_or(0)
}
None => u32::MAX,
None => u16::MAX,
}
}
})
@ -378,7 +378,8 @@ impl<'t> Branch<'t> {
fn compute_rank(&self) -> u32 {
// we compute a rank from the position.
let (pos, _) = self.last_result;
pos.saturating_sub((0..self.branch_size).sum()) * LCM_10_FIRST_NUMBERS / self.branch_size
pos.saturating_sub((0..self.branch_size).sum()) as u32 * LCM_10_FIRST_NUMBERS
/ self.branch_size as u32
}
fn cmp(&self, other: &Self) -> Ordering {

12
milli/src/search/criteria/mod.rs
View File

@ -171,7 +171,7 @@ pub trait Context<'c> {
&self,
word: &str,
in_prefix_cache: bool,
) -> heed::Result<Box<dyn Iterator<Item = heed::Result<((&'c str, u32), RoaringBitmap)>> + 'c>>;
) -> heed::Result<Box<dyn Iterator<Item = heed::Result<((&'c str, u16), RoaringBitmap)>> + 'c>>;
fn synonyms(&self, word: &str) -> heed::Result<Option<Vec<Vec<String>>>>;
fn searchable_fields_ids(&self) -> Result<Vec<FieldId>>;
fn field_id_word_count_docids(
@ -322,11 +322,11 @@ impl<'c> Context<'c> for CriteriaBuilder<'c> {
&self,
word: &str,
in_prefix_cache: bool,
) -> heed::Result<Box<dyn Iterator<Item = heed::Result<((&'c str, u32), RoaringBitmap)>> + 'c>>
) -> heed::Result<Box<dyn Iterator<Item = heed::Result<((&'c str, u16), RoaringBitmap)>> + 'c>>
{
let range = {
let left = u32::min_value();
let right = u32::max_value();
let left = u16::min_value(); // TODO: this is wrong
let right = u16::max_value(); // TODO: this is wrong
let left = (word, left);
let right = (word, right);
left..=right
@ -360,7 +360,7 @@ impl<'c> Context<'c> for CriteriaBuilder<'c> {
}
fn word_position_docids(&self, word: &str, pos: u32) -> heed::Result<Option<RoaringBitmap>> {
let key = (word, pos);
let key = (word, pos as u16); // TODO: this is wrong
self.index.word_position_docids.get(self.rtxn, &key)
}
}
@ -899,7 +899,7 @@ pub mod test {
_word: &str,
_in_prefix_cache: bool,
) -> heed::Result<
Box<dyn Iterator<Item = heed::Result<((&'c str, u32), RoaringBitmap)>> + 'c>,
Box<dyn Iterator<Item = heed::Result<((&'c str, u16), RoaringBitmap)>> + 'c>,
> {
todo!()
}