snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-30 09:04:59 +08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Remove unused term matching strategies

Browse Source
This commit is contained in:
Loïc Lecrenier 2023-02-21 09:40:41 +01:00
parent 1d937f831b
commit 2d88089129
2 changed files with 1 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
milli/src/search/mod.rs
View File

@ -36,6 +36,7 @@ mod distinct;
pub mod facet;
mod fst_utils;
mod matches;
pub mod new;
mod query_tree;
pub struct Search<'a> {
@ -344,14 +345,6 @@ pub enum CriterionImplementationStrategy {
pub enum TermsMatchingStrategy {
// remove last word first
Last,
// remove first word first
First,
// remove more frequent word first
Frequency,
// remove smallest word first
Size,
// only one of the word is mandatory
Any,
// all words are mandatory
All,
}

37
milli/src/search/query_tree.rs
View File

@ -487,49 +487,12 @@ fn create_query_tree(
for _ in 0..=remove_count {
let pos = match terms_matching_strategy {
TermsMatchingStrategy::All => return ngrams(ctx, authorize_typos, &query, false),
TermsMatchingStrategy::Any => {
let operation = Operation::Or(
true,
vec![
// branch allowing matching documents to contains any query word.
ngrams(ctx, authorize_typos, &query, true)?,
// branch forcing matching documents to contains all the query words,
// keeping this documents of the top of the resulted list.
ngrams(ctx, authorize_typos, &query, false)?,
],
);
return Ok(operation);
}
TermsMatchingStrategy::Last => query
.iter()
.enumerate()
.filter(|(_, part)| !part.is_phrase())
.last()
.map(|(pos, _)| pos),
TermsMatchingStrategy::First => {
query.iter().enumerate().find(|(_, part)| !part.is_phrase()).map(|(pos, _)| pos)
}
TermsMatchingStrategy::Size => query
.iter()
.enumerate()
.filter(|(_, part)| !part.is_phrase())
.min_by_key(|(_, part)| match part {
PrimitiveQueryPart::Word(s, _) => s.len(),
_ => unreachable!(),
})
.map(|(pos, _)| pos),
TermsMatchingStrategy::Frequency => query
.iter()
.enumerate()
.filter(|(_, part)| !part.is_phrase())
.max_by_key(|(_, part)| match part {
PrimitiveQueryPart::Word(s, _) => {
ctx.word_documents_count(s).unwrap_or_default().unwrap_or(u64::max_value())
}
_ => unreachable!(),
})
.map(|(pos, _)| pos),
};
// compute and push the current branch on the front