searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-03 11:57:07 +02:00
Code Issues Releases Wiki Activity

Fix the processed distance algorithm

Browse source
This commit is contained in:
Clément Renault 2019-12-07 13:32:43 +01:00
parent 0f698d6bd9
commit 22b19c0d93
No known key found for this signature in database
GPG key ID: 0151CDAB43460DAE
2 changed files with 27 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

24
meilisearch-core/src/bucket_sort.rs
View file

@ -1,4 +1,5 @@
use std::ops::Deref;
use std::fmt;
use std::borrow::Cow;
use std::cmp::Ordering;
use std::collections::HashSet;
@ -145,7 +146,6 @@ pub struct RawDocument<'a, 'tag> {
pub raw_matches: &'a mut [BareMatch<'tag>],
pub processed_matches: Vec<SimpleMatch>,
/// The list of minimum `distance` found
/// where the `query_index` is the index
pub processed_distances: Vec<Option<u8>>,
}
@ -157,6 +157,17 @@ pub struct BareMatch<'tag> {
pub postings_list: Idx32<'tag>,
}
impl fmt::Debug for BareMatch<'_> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.debug_struct("BareMatch")
.field("document_id", &self.document_id)
.field("query_index", &self.query_index)
.field("distance", &self.distance)
.field("is_exact", &self.is_exact)
.finish()
}
}
// TODO remove that
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
pub struct SimpleMatch {
@ -238,14 +249,11 @@ fn fetch_matches<'txn, 'tag>(
for (query_index, automaton) in automatons.iter().enumerate() {
let before_dfa = Instant::now();
let dfa = automaton.dfa();
let QueryWordAutomaton { query, is_exact, is_prefix, .. } = automaton;
let QueryWordAutomaton { query, is_exact, is_prefix, phrase_query } = automaton;
dfa_time += before_dfa.elapsed();
let mut number_of_words = 0;
let before_fst_search = Instant::now();
let mut stream = words.search(&dfa).into_stream();
debug!("fst search took {:.02?}", before_fst_search.elapsed());
// while let Some(input) = stream.next() {
loop {
@ -272,7 +280,7 @@ fn fetch_matches<'txn, 'tag>(
let posting_list_index = arena.add(postings_list_view.range(offset, group.len()));
let document_id = group[0].document_id;
let stuffed = BareMatch {
let bare_match = BareMatch {
document_id,
query_index: query_index as u16,
distance,
@ -280,7 +288,7 @@ fn fetch_matches<'txn, 'tag>(
postings_list: posting_list_index,
};
total_postings_lists.push(stuffed);
total_postings_lists.push(bare_match);
offset += group.len();
}
}
@ -434,7 +442,7 @@ fn construct_automatons2(
}
}
if n == 1 {
if false && n == 1 {
if let Some((left, right)) = split_best_frequency(reader, &normalized, postings_lists_store)? {
let mut left_automaton = QueryWordAutomaton::exact(left);
left_automaton.phrase_query = Some((0, 2));