snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-10-26 05:26:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix word pair proximity

Browse Source
This commit is contained in:
ManyTheFish
2023-09-26 10:08:36 +02:00
committed by Louis Dureuil
parent 96be85396d
commit 28a8d0ccda
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs
View File

@@ -1,4 +1,3 @@
use std::cmp::Ordering;
use std::collections::{HashMap, VecDeque};
use std::fs::File;
use std::io::BufReader;
@@ -12,7 +11,7 @@ use super::helpers::{
};
use crate::error::SerializationError;
use crate::index::db_name::DOCID_WORD_POSITIONS;
use crate::proximity::{positions_proximity, MAX_DISTANCE};
use crate::proximity::{index_proximity, MAX_DISTANCE};
use crate::{DocumentId, Result};
/// Extracts the best proximity between pairs of words and the documents ids where this pair appear.
@@ -71,7 +70,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
for (position, word) in KvReaderU16::new(&value).iter() {
// drain the proximity window until the head word is considered close to the word we are inserting.
while word_positions.get(0).map_or(false, |(_w, p)| {
positions_proximity(*p as u32, position as u32) > MAX_DISTANCE
index_proximity(*p as u32, position as u32) >= MAX_DISTANCE
}) {
word_positions_into_word_pair_proximity(
&mut word_positions,
@@ -109,6 +108,7 @@ fn document_word_positions_into_sorter(
word_pair_proximity: &HashMap<(String, String), u8>,
word_pair_proximity_docids_sorter: &mut grenad::Sorter<MergeFn>,
) -> Result<()> {
puffin::profile_function!();
let mut key_buffer = Vec::new();
for ((w1, w2), prox) in word_pair_proximity {
key_buffer.clear();
@@ -127,9 +127,10 @@ fn word_positions_into_word_pair_proximity(
word_positions: &mut VecDeque<(String, u16)>,
word_pair_proximity: &mut HashMap<(String, String), u8>,
) -> Result<()> {
puffin::profile_function!();
let (head_word, head_position) = word_positions.pop_front().unwrap();
for (word, position) in word_positions.iter() {
let prox = positions_proximity(head_position as u32, *position as u32) as u8;
let prox = index_proximity(head_position as u32, *position as u32) as u8;
word_pair_proximity
.entry((head_word.clone(), word.clone()))
.and_modify(|p| {