snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-27 04:25:06 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

rewrite word pair distance gathering

Browse Source
This commit is contained in:
ad hoc 2022-02-03 15:01:34 +01:00
parent d852dc0d2b
commit 13de251047
No known key found for this signature in database
GPG Key ID: 4F00A782990CC643
1 changed files with 9 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
milli/src/search/criteria/mod.rs
View File

@ -1,7 +1,6 @@
use std::borrow::Cow;
use std::collections::HashMap;
use itertools::Itertools;
use roaring::RoaringBitmap;
use self::asc_desc::AscDesc;
@ -323,22 +322,18 @@ pub fn resolve_query_tree<'t>(
let winsize = words.len().min(7);
for win in words.windows(winsize) {
// Get all the word pairs and their compute their relative distance
let dists = win
.iter()
.enumerate()
.cartesian_product(win.iter().enumerate())
.filter(|(x, y)| y > x)
.map(|((pos1, s1), (pos2, s2))| (s1, s2, pos2 - pos1));
// Get all the documents with the matching distance for each word pairs.
let mut bitmaps = Vec::with_capacity(winsize.pow(2));
for (s1, s2, d) in dists {
match ctx.word_pair_proximity_docids(s1, s2, d as u8)? {
for (offset, s1) in win.iter().enumerate() {
for (dist, s2) in win.iter().skip(offset).enumerate() {
match ctx.word_pair_proximity_docids(s1, s2, dist as u8 + 1)? {
Some(m) => bitmaps.push(m),
// If there are no document for this distance, there will be no
// results for the phrase query.
None => return Ok(RoaringBitmap::new()),
}
}
}
// We sort the bitmaps so that we perform the small intersections first, which is faster.
bitmaps.sort_unstable_by(|a, b| a.len().cmp(&b.len()));