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

wip: Impl a basic tree traversing

Browse source
This commit is contained in:
Clément Renault 2020-01-07 18:23:55 +01:00
parent 6e1f4af833
commit fbcec2975d
4 changed files with 76 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

19
meilisearch-core/src/bucket_sort.rs
View file

@ -15,7 +15,7 @@ use levenshtein_automata::DFA;
use log::debug;
use meilisearch_tokenizer::{is_cjk, split_query_string};
use meilisearch_types::DocIndex;
use sdset::{Set, SetBuf};
use sdset::{Set, SetBuf, SetOperation};
use slice_group_by::{GroupBy, GroupByMut};
use crate::automaton::NGRAMS;
@ -28,7 +28,7 @@ use crate::distinct_map::{BufferedDistinctMap, DistinctMap};
use crate::raw_document::RawDocument;
use crate::{database::MainT, reordered_attrs::ReorderedAttrs};
use crate::{store, Document, DocumentId, MResult};
use crate::query_tree::create_query_tree;
use crate::query_tree::{create_query_tree, traverse_query_tree, QueryResult};
pub fn bucket_sort<'c, FI>(
reader: &heed::RoTxn<MainT>,
@ -50,6 +50,21 @@ where
let operation = create_query_tree(reader, postings_lists_store, synonyms_store, query).unwrap();
println!("{:?}", operation);
let QueryResult { docids, queries } = traverse_query_tree(reader, postings_lists_store, &operation).unwrap();
println!("found {} documents", docids.len());
println!("number of postings {:?}", queries.len());
let before = Instant::now();
for (query, matches) in queries {
let op = sdset::duo::IntersectionByKey::new(&matches, &docids, |d| d.document_id, Clone::clone);
let buf: SetBuf<DocIndex> = op.into_set_buf();
if !buf.is_empty() {
println!("{:?} gives {} matches", query, buf.len());
}
}
println!("matches cleaned in {:.02?}", before.elapsed());
// We delegate the filter work to the distinct query builder,
// specifying a distinct rule that has no effect.
if filter.is_some() {