mirror of
https://github.com/meilisearch/meilisearch.git
synced 2025-09-14 00:36:25 +00:00
Move crates under a sub folder to clean up the code
This commit is contained in:
Clément Renault
159
crates/milli/src/search/new/tests/attribute_fid.rs
Normal file
159
crates/milli/src/search/new/tests/attribute_fid.rs
Normal file
@ -0,0 +1,159 @@
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::{db_snap, Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec![
|
||||
"title".to_owned(),
|
||||
"description".to_owned(),
|
||||
"plot".to_owned(),
|
||||
]);
|
||||
s.set_criteria(vec![Criterion::Attribute]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"title": "",
|
||||
"description": "",
|
||||
"plot": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"title": "",
|
||||
"description": "the quick brown foxes jump over the lazy dog",
|
||||
"plot": "",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "the quick brown fox jumps over the lazy dog",
|
||||
"description": "",
|
||||
"plot": "",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "the",
|
||||
"description": "quick brown fox jumps over the lazy dog",
|
||||
"plot": "",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "the quick",
|
||||
"description": "brown fox jumps over the lazy dog",
|
||||
"plot": "",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "the quick brown",
|
||||
"description": "fox jumps over the lazy dog",
|
||||
"plot": "",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "the quick brown fox",
|
||||
"description": "jumps over the lazy dog",
|
||||
"plot": "",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"title": "the quick",
|
||||
"description": "brown fox jumps",
|
||||
"plot": "over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"title": "the quick brown",
|
||||
"description": "fox",
|
||||
"plot": "jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"title": "the quick brown",
|
||||
"description": "fox jumps",
|
||||
"plot": "over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"title": "",
|
||||
"description": "the quick brown fox",
|
||||
"plot": "jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"title": "the quick",
|
||||
"description": "",
|
||||
"plot": "brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"title": "",
|
||||
"description": "the quickbrownfox",
|
||||
"plot": "jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"title": "",
|
||||
"description": "the quick brown fox",
|
||||
"plot": "jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"title": "",
|
||||
"description": "the quickbrownfox",
|
||||
"plot": "jumps overthelazy dog",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_attribute_fid_simple() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_attribute_fid_ngrams() {
|
||||
let index = create_index();
|
||||
db_snap!(index, fields_ids_map, @r###"
|
||||
0 id |
|
||||
1 title |
|
||||
2 description |
|
||||
3 plot |
|
||||
"###);
|
||||
db_snap!(index, searchable_fields, @r###"["title", "description", "plot"]"###);
|
||||
db_snap!(index, fieldids_weights_map, @r###"
|
||||
fid weight
|
||||
1 0 |
|
||||
2 1 |
|
||||
3 2 |
|
||||
"###);
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
}
|
||||
196
crates/milli/src/search/new/tests/attribute_position.rs
Normal file
196
crates/milli/src/search/new/tests/attribute_position.rs
Normal file
@ -0,0 +1,196 @@
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::{db_snap, Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec![
|
||||
"text".to_owned(),
|
||||
"text2".to_owned(),
|
||||
"other".to_owned(),
|
||||
]);
|
||||
s.set_criteria(vec![Criterion::Attribute]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "do you know about the quick and talented brown fox",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "do you know about the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quick and talented brown fox",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "fox brown quick the",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "quick a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
brown",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
quickbrown",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
quick brown",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
|
||||
quickbrown",
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"text": "quick brown",
|
||||
"text2": "brown quick",
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"text": "quickbrown",
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"text": "quick brown",
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"text": "quickbrown",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_attribute_position_simple() {
|
||||
let index = create_index();
|
||||
|
||||
db_snap!(index, word_position_docids, @"1ad58847d772924d8aab5e92be8cf0cc");
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("quick brown");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
}
|
||||
#[test]
|
||||
fn test_attribute_position_repeated() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("a a a a a");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_attribute_position_different_fields() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("quick brown");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_attribute_position_ngrams() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("quick brown");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
}
|
||||
429
crates/milli/src/search/new/tests/cutoff.rs
Normal file
429
crates/milli/src/search/new/tests/cutoff.rs
Normal file
@ -0,0 +1,429 @@
|
||||
//! This module test the search cutoff and ensure a few things:
|
||||
//! 1. A basic test works and mark the search as degraded
|
||||
//! 2. A test that ensure the filters are affectively applied even with a cutoff of 0
|
||||
//! 3. A test that ensure the cutoff works well with the ranking scores
|
||||
|
||||
use std::time::Duration;
|
||||
|
||||
use big_s::S;
|
||||
use maplit::hashset;
|
||||
use meili_snap::snapshot;
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::score_details::{ScoreDetails, ScoringStrategy};
|
||||
use crate::{Criterion, Filter, Search, TimeBudget};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_filterable_fields(hashset! { S("id") });
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// reverse the ID / insertion order so we see better what was sorted from what got the insertion order ordering
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 4,
|
||||
"text": "hella puppo kefir",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "hella puppy kefir",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "hello",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "hello puppy",
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"text": "hello puppy kefir",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn basic_degraded_search() {
|
||||
let index = create_index();
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut search = Search::new(&rtxn, &index);
|
||||
search.query("hello puppy kefir");
|
||||
search.limit(3);
|
||||
search.time_budget(TimeBudget::new(Duration::from_millis(0)));
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
assert!(result.degraded);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn degraded_search_cannot_skip_filter() {
|
||||
let index = create_index();
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut search = Search::new(&rtxn, &index);
|
||||
search.query("hello puppy kefir");
|
||||
search.limit(100);
|
||||
search.time_budget(TimeBudget::new(Duration::from_millis(0)));
|
||||
let filter_condition = Filter::from_str("id > 2").unwrap().unwrap();
|
||||
search.filter(filter_condition);
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
assert!(result.degraded);
|
||||
snapshot!(format!("{:?}\n{:?}", result.candidates, result.documents_ids), @r###"
|
||||
RoaringBitmap<[0, 1]>
|
||||
[0, 1]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[allow(clippy::format_collect)] // the test is already quite big
|
||||
fn degraded_search_and_score_details() {
|
||||
let index = create_index();
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut search = Search::new(&rtxn, &index);
|
||||
search.query("hello puppy kefir");
|
||||
search.limit(4);
|
||||
search.scoring_strategy(ScoringStrategy::Detailed);
|
||||
search.time_budget(TimeBudget::max());
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
|
||||
IDs: [4, 1, 0, 3]
|
||||
Scores: 1.0000 0.9167 0.8333 0.6667
|
||||
Score Details:
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// Do ONE loop iteration. Not much can be deduced, almost everyone matched the words first bucket.
|
||||
search.time_budget(TimeBudget::max().with_stop_after(1));
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
|
||||
IDs: [0, 1, 4, 2]
|
||||
Scores: 0.6667 0.6667 0.6667 0.0000
|
||||
Score Details:
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
[
|
||||
Skipped,
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// Do TWO loop iterations. The first document should be entirely sorted
|
||||
search.time_budget(TimeBudget::max().with_stop_after(2));
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
|
||||
IDs: [4, 0, 1, 2]
|
||||
Scores: 1.0000 0.6667 0.6667 0.0000
|
||||
Score Details:
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
[
|
||||
Skipped,
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// Do THREE loop iterations. The second document should be entirely sorted as well
|
||||
search.time_budget(TimeBudget::max().with_stop_after(3));
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
|
||||
IDs: [4, 1, 0, 2]
|
||||
Scores: 1.0000 0.9167 0.6667 0.0000
|
||||
Score Details:
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
[
|
||||
Skipped,
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// Do FOUR loop iterations. The third document should be entirely sorted as well
|
||||
// The words bucket have still not progressed thus the last document doesn't have any info yet.
|
||||
search.time_budget(TimeBudget::max().with_stop_after(4));
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
|
||||
IDs: [4, 1, 0, 2]
|
||||
Scores: 1.0000 0.9167 0.8333 0.0000
|
||||
Score Details:
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Skipped,
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// After SIX loop iteration. The words ranking rule gave us a new bucket.
|
||||
// Since we reached the limit we were able to early exit without checking the typo ranking rule.
|
||||
search.time_budget(TimeBudget::max().with_stop_after(6));
|
||||
|
||||
let result = search.execute().unwrap();
|
||||
snapshot!(format!("IDs: {:?}\nScores: {}\nScore Details:\n{:#?}", result.documents_ids, result.document_scores.iter().map(|scores| format!("{:.4} ", ScoreDetails::global_score(scores.iter()))).collect::<String>(), result.document_scores), @r###"
|
||||
IDs: [4, 1, 0, 3]
|
||||
Scores: 1.0000 0.9167 0.8333 0.3333
|
||||
Score Details:
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Skipped,
|
||||
],
|
||||
]
|
||||
"###);
|
||||
}
|
||||
634
crates/milli/src/search/new/tests/distinct.rs
Normal file
634
crates/milli/src/search/new/tests/distinct.rs
Normal file
@ -0,0 +1,634 @@
|
||||
/*!
|
||||
This module tests the "distinct attribute" feature, and its
|
||||
interaction with other ranking rules.
|
||||
|
||||
1. no duplicate distinct attributes are ever returned
|
||||
2. only the best document (according to the search rules) for each distinct value appears in the result
|
||||
3. if a document does not have a distinct attribute, then the distinct rule does not apply to it
|
||||
|
||||
It doesn't test properly:
|
||||
- combination of distinct + exhaustive_nbr_hits (because we know it's incorrect)
|
||||
- distinct attributes with arrays (because we know it's incorrect as well)
|
||||
*/
|
||||
|
||||
use std::collections::HashSet;
|
||||
|
||||
use big_s::S;
|
||||
use heed::RoTxn;
|
||||
use maplit::hashset;
|
||||
|
||||
use super::collect_field_values;
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::{AscDesc, Criterion, Index, Member, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_sortable_fields(hashset! { S("rank1"), S("letter") });
|
||||
s.set_distinct_field("letter".to_owned());
|
||||
s.set_criteria(vec![Criterion::Words]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"letter": "A",
|
||||
"rank1": 0,
|
||||
"text": "the quick brown fox jamps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"letter": "A",
|
||||
"rank1": 1,
|
||||
"text": "the quick brown fox jumpes over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"letter": "B",
|
||||
"rank1": 0,
|
||||
"text": "the quick brown foxjumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"letter": "B",
|
||||
"rank1": 1,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"letter": "B",
|
||||
"rank1": 2,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"letter": "C",
|
||||
"rank1": 0,
|
||||
"text": "the quickbrownfox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"letter": "C",
|
||||
"rank1": 1,
|
||||
"text": "the quick brown fox jumpss over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"letter": "C",
|
||||
"rank1": 2,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"letter": "D",
|
||||
"rank1": 0,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"letter": "E",
|
||||
"rank1": 0,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"letter": "E",
|
||||
"rank1": 1,
|
||||
"text": "the quackbrown foxjunps over",
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"letter": "E",
|
||||
"rank1": 2,
|
||||
"text": "the quicko browno fox junps over",
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"letter": "E",
|
||||
"rank1": 3,
|
||||
"text": "the quicko browno fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"letter": "E",
|
||||
"rank1": 4,
|
||||
"text": "the quick brewn fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"letter": "E",
|
||||
"rank1": 5,
|
||||
"text": "the quick brown fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 15,
|
||||
"letter": "F",
|
||||
"rank1": 0,
|
||||
"text": "the quick brownf fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 16,
|
||||
"letter": "F",
|
||||
"rank1": 1,
|
||||
"text": "the quic brown fox jamps over",
|
||||
},
|
||||
{
|
||||
"id": 17,
|
||||
"letter": "F",
|
||||
"rank1": 2,
|
||||
"text": "thequick browns fox jimps",
|
||||
},
|
||||
{
|
||||
"id": 18,
|
||||
"letter": "G",
|
||||
"rank1": 0,
|
||||
"text": "the qick brown fox jumps",
|
||||
},
|
||||
{
|
||||
"id": 19,
|
||||
"letter": "G",
|
||||
"rank1": 1,
|
||||
"text": "the quick brownfoxjumps",
|
||||
},
|
||||
{
|
||||
"id": 20,
|
||||
"letter": "H",
|
||||
"rank1": 0,
|
||||
"text": "the quick brow fox jumps",
|
||||
},
|
||||
{
|
||||
"id": 21,
|
||||
"letter": "I",
|
||||
"rank1": 0,
|
||||
"text": "the quick brown fox jpmps",
|
||||
},
|
||||
{
|
||||
"id": 22,
|
||||
"letter": "I",
|
||||
"rank1": 1,
|
||||
"text": "the quick brown fox jumps",
|
||||
},
|
||||
{
|
||||
"id": 23,
|
||||
"letter": "I",
|
||||
"rank1": 2,
|
||||
"text": "the quick",
|
||||
},
|
||||
{
|
||||
"id": 24,
|
||||
"rank1": 0,
|
||||
"text": "the quick",
|
||||
},
|
||||
{
|
||||
"id": 25,
|
||||
"rank1": 1,
|
||||
"text": "the quick brown",
|
||||
},
|
||||
{
|
||||
"id": 26,
|
||||
"rank1": 2,
|
||||
"text": "the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 26,
|
||||
"rank1": 3,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn verify_distinct(
|
||||
index: &Index,
|
||||
txn: &RoTxn<'_>,
|
||||
distinct: Option<&str>,
|
||||
docids: &[u32],
|
||||
) -> Vec<String> {
|
||||
let vs = collect_field_values(
|
||||
index,
|
||||
txn,
|
||||
distinct.or_else(|| index.distinct_field(txn).unwrap()).unwrap(),
|
||||
docids,
|
||||
);
|
||||
|
||||
let mut unique = HashSet::new();
|
||||
for v in vs.iter() {
|
||||
if v == "__does_not_exist__" {
|
||||
continue;
|
||||
}
|
||||
assert!(unique.insert(v.clone()));
|
||||
}
|
||||
|
||||
vs
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_placeholder_no_ranking_rules() {
|
||||
let index = create_index();
|
||||
|
||||
// Set the letter as filterable and unset the distinct attribute.
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_filterable_fields(hashset! { S("letter") });
|
||||
s.reset_distinct_field();
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.distinct(S("letter"));
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 2, 5, 8, 9, 15, 18, 20, 21, 24, 25, 26]");
|
||||
let distinct_values = verify_distinct(&index, &txn, Some("letter"), &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"A\"",
|
||||
"\"B\"",
|
||||
"\"C\"",
|
||||
"\"D\"",
|
||||
"\"E\"",
|
||||
"\"F\"",
|
||||
"\"G\"",
|
||||
"\"H\"",
|
||||
"\"I\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_at_search_placeholder_no_ranking_rules() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let s = Search::new(&txn, &index);
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 2, 5, 8, 9, 15, 18, 20, 21, 24, 25, 26]");
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"A\"",
|
||||
"\"B\"",
|
||||
"\"C\"",
|
||||
"\"D\"",
|
||||
"\"E\"",
|
||||
"\"F\"",
|
||||
"\"G\"",
|
||||
"\"H\"",
|
||||
"\"I\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_placeholder_sort() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Sort]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("rank1")))]);
|
||||
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[14, 26, 4, 7, 17, 23, 1, 19, 25, 8, 20, 24]");
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"E\"",
|
||||
"__does_not_exist__",
|
||||
"\"B\"",
|
||||
"\"C\"",
|
||||
"\"F\"",
|
||||
"\"I\"",
|
||||
"\"A\"",
|
||||
"\"G\"",
|
||||
"__does_not_exist__",
|
||||
"\"D\"",
|
||||
"\"H\"",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
let rank_values = collect_field_values(&index, &txn, "rank1", &documents_ids);
|
||||
insta::assert_debug_snapshot!(rank_values, @r###"
|
||||
[
|
||||
"5",
|
||||
"3",
|
||||
"2",
|
||||
"2",
|
||||
"2",
|
||||
"2",
|
||||
"1",
|
||||
"1",
|
||||
"1",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("letter")))]);
|
||||
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[21, 20, 18, 15, 9, 8, 5, 2, 0, 24, 25, 26]");
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"I\"",
|
||||
"\"H\"",
|
||||
"\"G\"",
|
||||
"\"F\"",
|
||||
"\"E\"",
|
||||
"\"D\"",
|
||||
"\"C\"",
|
||||
"\"B\"",
|
||||
"\"A\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
let rank_values = collect_field_values(&index, &txn, "rank1", &documents_ids);
|
||||
insta::assert_debug_snapshot!(rank_values, @r###"
|
||||
[
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"1",
|
||||
"3",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.sort_criteria(vec![
|
||||
AscDesc::Desc(Member::Field(S("letter"))),
|
||||
AscDesc::Desc(Member::Field(S("rank1"))),
|
||||
]);
|
||||
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[23, 20, 19, 17, 14, 8, 7, 4, 1, 26, 25, 24]");
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"I\"",
|
||||
"\"H\"",
|
||||
"\"G\"",
|
||||
"\"F\"",
|
||||
"\"E\"",
|
||||
"\"D\"",
|
||||
"\"C\"",
|
||||
"\"B\"",
|
||||
"\"A\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
let rank_values = collect_field_values(&index, &txn, "rank1", &documents_ids);
|
||||
insta::assert_debug_snapshot!(rank_values, @r###"
|
||||
[
|
||||
"2",
|
||||
"0",
|
||||
"1",
|
||||
"2",
|
||||
"5",
|
||||
"0",
|
||||
"2",
|
||||
"2",
|
||||
"1",
|
||||
"3",
|
||||
"1",
|
||||
"0",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_words() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 2, 26, 5, 8, 9, 15, 18, 20, 21, 25, 24]");
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"A\"",
|
||||
"\"B\"",
|
||||
"__does_not_exist__",
|
||||
"\"C\"",
|
||||
"\"D\"",
|
||||
"\"E\"",
|
||||
"\"F\"",
|
||||
"\"G\"",
|
||||
"\"H\"",
|
||||
"\"I\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
let text_values = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(text_values, @r###"
|
||||
[
|
||||
"\"the quick brown fox jamps over the lazy dog\"",
|
||||
"\"the quick brown foxjumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quickbrownfox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brownf fox jumps over\"",
|
||||
"\"the qick brown fox jumps\"",
|
||||
"\"the quick brow fox jumps\"",
|
||||
"\"the quick brown fox jpmps\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quick\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_sort_words() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Sort, Criterion::Words, Criterion::Desc(S("rank1"))]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("letter")))]);
|
||||
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[22, 20, 19, 16, 9, 8, 7, 3, 1, 26, 25, 24]");
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"I\"",
|
||||
"\"H\"",
|
||||
"\"G\"",
|
||||
"\"F\"",
|
||||
"\"E\"",
|
||||
"\"D\"",
|
||||
"\"C\"",
|
||||
"\"B\"",
|
||||
"\"A\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
|
||||
let rank_values = collect_field_values(&index, &txn, "rank1", &documents_ids);
|
||||
insta::assert_debug_snapshot!(rank_values, @r###"
|
||||
[
|
||||
"1",
|
||||
"0",
|
||||
"1",
|
||||
"1",
|
||||
"0",
|
||||
"0",
|
||||
"2",
|
||||
"1",
|
||||
"1",
|
||||
"3",
|
||||
"1",
|
||||
"0",
|
||||
]
|
||||
"###);
|
||||
|
||||
let text_values = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(text_values, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brow fox jumps\"",
|
||||
"\"the quick brownfoxjumps\"",
|
||||
"\"the quic brown fox jamps over\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumpes over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quick\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_all_candidates() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Sort]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("rank1")))]);
|
||||
s.exhaustive_number_hits(true);
|
||||
|
||||
let SearchResult { documents_ids, candidates, .. } = s.execute().unwrap();
|
||||
let candidates = candidates.iter().collect::<Vec<_>>();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[14, 26, 4, 7, 17, 23, 1, 19, 25, 8, 20, 24]");
|
||||
// This is incorrect, but unfortunately impossible to do better efficiently.
|
||||
insta::assert_snapshot!(format!("{candidates:?}"), @"[1, 4, 7, 8, 14, 17, 19, 20, 23, 24, 25, 26]");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_distinct_typo() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3, 26, 0, 7, 8, 9, 15, 22, 18, 20, 25, 24]");
|
||||
|
||||
let distinct_values = verify_distinct(&index, &txn, None, &documents_ids);
|
||||
insta::assert_debug_snapshot!(distinct_values, @r###"
|
||||
[
|
||||
"\"B\"",
|
||||
"__does_not_exist__",
|
||||
"\"A\"",
|
||||
"\"C\"",
|
||||
"\"D\"",
|
||||
"\"E\"",
|
||||
"\"F\"",
|
||||
"\"I\"",
|
||||
"\"G\"",
|
||||
"\"H\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
|
||||
let text_values = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(text_values, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jamps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brownf fox jumps over\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the qick brown fox jumps\"",
|
||||
"\"the quick brow fox jumps\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quick\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
920
crates/milli/src/search/new/tests/exactness.rs
Normal file
920
crates/milli/src/search/new/tests/exactness.rs
Normal file
@ -0,0 +1,920 @@
|
||||
/*!
|
||||
This module tests the following properties about the exactness ranking rule:
|
||||
|
||||
- it sorts documents as follows:
|
||||
1. documents which have an attribute which is equal to the whole query
|
||||
2. documents which have an attribute which start with the whole query
|
||||
3. documents which contain the most exact words from the query
|
||||
|
||||
- the `exactness` ranking rule must be preceded by the `words` ranking rule
|
||||
|
||||
- if `words` has already removed terms from the query, then exactness will sort documents as follows:
|
||||
1. those that have an attribute which is equal to the whole remaining query, if this query does not have any "gap"
|
||||
2. those that have an attribute which start with the whole remaining query, if this query does not have any "gap"
|
||||
3. those that contain the most exact words from the remaining query
|
||||
|
||||
- if it is followed by other graph-based ranking rules (`typo`, `proximity`, `attribute`).
|
||||
Then these rules will only work with
|
||||
1. the exact terms selected by `exactness
|
||||
2. the full query term otherwise
|
||||
*/
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index_simple_ordered() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quick",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "the quick brown",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "the quick brown fox jumps",
|
||||
},
|
||||
|
||||
{
|
||||
"id": 6,
|
||||
"text": "the quick brown fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the quick brown fox jumps over the",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_simple_reversed() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "dog",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
}
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_simple_random() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "over",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "jump dog",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "brown the lazy",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "jump dog quick the",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "fox the lazy dog brown",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "jump fox quick lazy the dog",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the dog brown over jumps quick lazy",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the jumps dog quick over brown lazy fox",
|
||||
}
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_attribute_starts_with() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "what a lovely view from this balcony, I love it",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "this balcony is overlooking the sea",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "this balcony",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "over looking the sea is a beautiful balcony",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "a beautiful balcony is overlooking the sea",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "overlooking the sea is a beautiful balcony, I love it",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "overlooking the sea is a beautiful balcony",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "overlooking",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_simple_ordered_with_typos() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quack",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "the quack briwn",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the quack briwn fox",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "the quack briwn fox jlmps",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "the quack briwn fox jlmps over",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the quack briwn fox jlmps over the",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the quack briwn fox jlmps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quack briwn fox jlmps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"text": "",
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"text": "the",
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"text": "the quick",
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"text": "the quick brown",
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"text": "the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 15,
|
||||
"text": "the quick brown fox jumps",
|
||||
},
|
||||
|
||||
{
|
||||
"id": 16,
|
||||
"text": "the quick brown fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 17,
|
||||
"text": "the quick brown fox jumps over the",
|
||||
},
|
||||
{
|
||||
"id": 18,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 19,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_with_varying_proximities() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness, Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "lazy jumps dog brown quick the over fox the",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the quick brown fox jumps over the very lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "dog brown quick the over fox the lazy",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the quick brown fox over the very lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "the quick brown fox over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "brown quick the over fox",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the very quick brown fox over"
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the quick brown fox over",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_with_typo_and_prefix() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "expraordinarily quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "extraordinarily quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "extra quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "expraordinarily quack brown fox",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "expraordinapily quick brown fox",
|
||||
}
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_index_all_equal_except_proximity_between_ignored_terms() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Exactness, Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "lazy jumps dog brown quick the over fox the"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "lazy jumps dog brown quick the over fox the. quack briwn jlmps",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "lazy jumps dog brown quick the over fox the. quack briwn jlmps overt",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_simple_ordered() {
|
||||
let index = create_index_simple_ordered();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quick\"",
|
||||
"\"the\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_simple_reversed() {
|
||||
let index = create_index_simple_reversed();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"quick brown fox jumps over the lazy dog\"",
|
||||
"\"the lazy dog\"",
|
||||
"\"over the lazy dog\"",
|
||||
"\"jumps over the lazy dog\"",
|
||||
"\"fox jumps over the lazy dog\"",
|
||||
"\"brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"quick brown fox jumps over the lazy dog\"",
|
||||
"\"the lazy dog\"",
|
||||
"\"over the lazy dog\"",
|
||||
"\"jumps over the lazy dog\"",
|
||||
"\"fox jumps over the lazy dog\"",
|
||||
"\"brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_simple_random() {
|
||||
let index = create_index_simple_random();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the jumps dog quick over brown lazy fox\"",
|
||||
"\"the dog brown over jumps quick lazy\"",
|
||||
"\"jump dog quick the\"",
|
||||
"\"jump fox quick lazy the dog\"",
|
||||
"\"brown the lazy\"",
|
||||
"\"fox the lazy dog brown\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_attribute_starts_with_simple() {
|
||||
let index = create_index_attribute_starts_with();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("this balcony");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"this balcony\"",
|
||||
"\"this balcony is overlooking the sea\"",
|
||||
"\"what a lovely view from this balcony, I love it\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_attribute_starts_with_phrase() {
|
||||
let index = create_index_attribute_starts_with();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("\"overlooking the sea\" is a beautiful balcony");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"overlooking the sea is a beautiful balcony\"",
|
||||
"\"overlooking the sea is a beautiful balcony, I love it\"",
|
||||
"\"a beautiful balcony is overlooking the sea\"",
|
||||
"\"this balcony is overlooking the sea\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("overlooking the sea is a beautiful balcony");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"overlooking the sea is a beautiful balcony\"",
|
||||
"\"overlooking the sea is a beautiful balcony, I love it\"",
|
||||
"\"a beautiful balcony is overlooking the sea\"",
|
||||
"\"over looking the sea is a beautiful balcony\"",
|
||||
"\"this balcony is overlooking the sea\"",
|
||||
"\"overlooking\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_all_candidates_with_typo() {
|
||||
let index = create_index_attribute_starts_with();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("overlocking the sea is a beautiful balcony");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
// "overlooking" is returned here because the term matching strategy allows it
|
||||
// but it has the worst exactness score (0 exact words)
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"a beautiful balcony is overlooking the sea\"",
|
||||
"\"overlooking the sea is a beautiful balcony, I love it\"",
|
||||
"\"overlooking the sea is a beautiful balcony\"",
|
||||
"\"this balcony is overlooking the sea\"",
|
||||
"\"overlooking\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_after_words() {
|
||||
let index = create_index_simple_ordered_with_typos();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quack briwn fox jlmps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quack briwn fox jlmps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quack briwn fox jlmps over\"",
|
||||
"\"the quack briwn fox jlmps over the\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quack briwn fox jlmps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quack briwn fox\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quack briwn\"",
|
||||
"\"the quick\"",
|
||||
"\"the quack\"",
|
||||
"\"the\"",
|
||||
"\"the\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_words_after_exactness() {
|
||||
let index = create_index_simple_ordered_with_typos();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Exactness, Criterion::Words]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[19, 9, 18, 8, 17, 16, 6, 7, 15, 5, 14, 4, 13, 3, 12, 2, 1, 11]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quack briwn fox jlmps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quack briwn fox jlmps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quack briwn fox jlmps over\"",
|
||||
"\"the quack briwn fox jlmps over the\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quack briwn fox jlmps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quack briwn fox\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quack briwn\"",
|
||||
"\"the quick\"",
|
||||
"\"the quack\"",
|
||||
"\"the\"",
|
||||
"\"the\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_proximity_after_exactness() {
|
||||
let index = create_index_with_varying_proximities();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Exactness, Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 1, 0, 4, 5, 8, 7, 3, 6]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the very lazy dog\"",
|
||||
"\"lazy jumps dog brown quick the over fox the\"",
|
||||
"\"the quick brown fox over the very lazy dog\"",
|
||||
"\"the quick brown fox over the lazy dog\"",
|
||||
"\"the quick brown fox over\"",
|
||||
"\"the very quick brown fox over\"",
|
||||
"\"dog brown quick the over fox the lazy\"",
|
||||
"\"brown quick the over fox\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let index = create_index_all_equal_except_proximity_between_ignored_terms();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Exactness, Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1, 2]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"lazy jumps dog brown quick the over fox the\"",
|
||||
"\"lazy jumps dog brown quick the over fox the. quack briwn jlmps\"",
|
||||
"\"lazy jumps dog brown quick the over fox the. quack briwn jlmps overt\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_exactness_followed_by_typo_prefer_no_typo_prefix() {
|
||||
let index = create_index_with_typo_and_prefix();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Exactness, Criterion::Words, Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("quick brown fox extra");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 1, 0, 4, 3]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"extra quick brown fox\"",
|
||||
"\"extraordinarily quick brown fox\"",
|
||||
"\"expraordinarily quick brown fox\"",
|
||||
"\"expraordinapily quick brown fox\"",
|
||||
"\"expraordinarily quack brown fox\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_typo_followed_by_exactness() {
|
||||
let index = create_index_with_typo_and_prefix();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Typo, Criterion::Exactness]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.query("extraordinarily quick brown fox");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
let document_ids_scores: Vec<_> = documents_ids.iter().zip(document_scores).collect();
|
||||
insta::assert_snapshot!(format!("{document_ids_scores:#?}"));
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 0, 4, 3]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"extraordinarily quick brown fox\"",
|
||||
"\"expraordinarily quick brown fox\"",
|
||||
"\"expraordinapily quick brown fox\"",
|
||||
"\"expraordinarily quack brown fox\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
309
crates/milli/src/search/new/tests/geo_sort.rs
Normal file
309
crates/milli/src/search/new/tests/geo_sort.rs
Normal file
@ -0,0 +1,309 @@
|
||||
/*!
|
||||
This module tests the `geo_sort` ranking rule
|
||||
*/
|
||||
|
||||
use big_s::S;
|
||||
use heed::RoTxn;
|
||||
use maplit::hashset;
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::score_details::ScoreDetails;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{AscDesc, Criterion, GeoSortStrategy, Member, Search, SearchResult};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_sortable_fields(hashset! { S("_geo") });
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Sort]);
|
||||
})
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[track_caller]
|
||||
fn execute_iterative_and_rtree_returns_the_same<'a>(
|
||||
rtxn: &RoTxn<'a>,
|
||||
index: &TempIndex,
|
||||
search: &mut Search<'a>,
|
||||
) -> (Vec<usize>, Vec<Vec<ScoreDetails>>) {
|
||||
search.geo_sort_strategy(GeoSortStrategy::AlwaysIterative(2));
|
||||
let SearchResult { documents_ids, document_scores: iterative_scores_bucketed, .. } =
|
||||
search.execute().unwrap();
|
||||
let iterative_ids_bucketed = collect_field_values(index, rtxn, "id", &documents_ids);
|
||||
|
||||
search.geo_sort_strategy(GeoSortStrategy::AlwaysIterative(1000));
|
||||
let SearchResult { documents_ids, document_scores: iterative_scores, .. } =
|
||||
search.execute().unwrap();
|
||||
let iterative_ids = collect_field_values(index, rtxn, "id", &documents_ids);
|
||||
|
||||
assert_eq!(iterative_ids_bucketed, iterative_ids, "iterative bucket");
|
||||
assert_eq!(iterative_scores_bucketed, iterative_scores, "iterative bucket score");
|
||||
|
||||
search.geo_sort_strategy(GeoSortStrategy::AlwaysRtree(2));
|
||||
let SearchResult { documents_ids, document_scores: rtree_scores_bucketed, .. } =
|
||||
search.execute().unwrap();
|
||||
let rtree_ids_bucketed = collect_field_values(index, rtxn, "id", &documents_ids);
|
||||
|
||||
search.geo_sort_strategy(GeoSortStrategy::AlwaysRtree(1000));
|
||||
let SearchResult { documents_ids, document_scores: rtree_scores, .. } =
|
||||
search.execute().unwrap();
|
||||
let rtree_ids = collect_field_values(index, rtxn, "id", &documents_ids);
|
||||
|
||||
assert_eq!(rtree_ids_bucketed, rtree_ids, "rtree bucket");
|
||||
assert_eq!(rtree_scores_bucketed, rtree_scores, "rtree bucket score");
|
||||
|
||||
assert_eq!(iterative_ids, rtree_ids, "iterative vs rtree");
|
||||
assert_eq!(iterative_scores, rtree_scores, "iterative vs rtree scores");
|
||||
|
||||
(iterative_ids.into_iter().map(|id| id.parse().unwrap()).collect(), iterative_scores)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_geo_sort() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{ "id": 2, "_geo": { "lat": 2, "lng": -1 } },
|
||||
{ "id": 3, "_geo": { "lat": -2, "lng": -2 } },
|
||||
{ "id": 5, "_geo": { "lat": 6, "lng": -5 } },
|
||||
{ "id": 4, "_geo": { "lat": 3, "lng": 5 } },
|
||||
{ "id": 0, "_geo": { "lat": 0, "lng": 0 } },
|
||||
{ "id": 1, "_geo": { "lat": 1, "lng": 1 } },
|
||||
{ "id": 6 }, { "id": 8 }, { "id": 7 }, { "id": 10 }, { "id": 9 },
|
||||
]))
|
||||
.unwrap();
|
||||
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&rtxn, &index);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([0., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[0, 1, 2, 3, 4, 5, 6, 8, 7, 10, 9]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Geo([0., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[5, 4, 3, 2, 1, 0, 6, 8, 7, 10, 9]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_geo_sort_around_the_edge_of_the_flat_earth() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{ "id": 0, "_geo": { "lat": 0, "lng": 0 } },
|
||||
{ "id": 1, "_geo": { "lat": 88, "lng": 0 } },
|
||||
{ "id": 2, "_geo": { "lat": -89, "lng": 0 } },
|
||||
|
||||
{ "id": 3, "_geo": { "lat": 0, "lng": 178 } },
|
||||
{ "id": 4, "_geo": { "lat": 0, "lng": -179 } },
|
||||
]))
|
||||
.unwrap();
|
||||
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&rtxn, &index);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
|
||||
// --- asc
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([0., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[0, 1, 2, 3, 4]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
// ensuring the lat doesn't wrap around
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([85., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[1, 0, 3, 4, 2]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([-85., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[2, 0, 3, 4, 1]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
// ensuring the lng does wrap around
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([0., 175.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[3, 4, 2, 1, 0]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([0., -175.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[4, 3, 2, 1, 0]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
// --- desc
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Geo([0., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[4, 3, 2, 1, 0]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
// ensuring the lat doesn't wrap around
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Geo([85., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[2, 4, 3, 0, 1]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Geo([-85., 0.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[1, 4, 3, 0, 2]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
// ensuring the lng does wrap around
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Geo([0., 175.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[0, 1, 2, 4, 3]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Geo([0., -175.]))]);
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[0, 1, 2, 3, 4]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn geo_sort_mixed_with_words() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{ "id": 0, "doggo": "jean", "_geo": { "lat": 0, "lng": 0 } },
|
||||
{ "id": 1, "doggo": "intel", "_geo": { "lat": 88, "lng": 0 } },
|
||||
{ "id": 2, "doggo": "jean bob", "_geo": { "lat": -89, "lng": 0 } },
|
||||
{ "id": 3, "doggo": "jean michel", "_geo": { "lat": 0, "lng": 178 } },
|
||||
{ "id": 4, "doggo": "bob marley", "_geo": { "lat": 0, "lng": -179 } },
|
||||
]))
|
||||
.unwrap();
|
||||
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&rtxn, &index);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([0., 0.]))]);
|
||||
|
||||
s.query("jean");
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[0, 2, 3]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
|
||||
s.query("bob");
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[2, 4]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
s.query("intel");
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[1]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn geo_sort_without_any_geo_faceted_documents() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{ "id": 0, "doggo": "jean" },
|
||||
{ "id": 1, "doggo": "intel" },
|
||||
{ "id": 2, "doggo": "jean bob" },
|
||||
{ "id": 3, "doggo": "jean michel" },
|
||||
{ "id": 4, "doggo": "bob marley" },
|
||||
]))
|
||||
.unwrap();
|
||||
|
||||
let rtxn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&rtxn, &index);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Geo([0., 0.]))]);
|
||||
|
||||
s.query("jean");
|
||||
let (ids, scores) = execute_iterative_and_rtree_returns_the_same(&rtxn, &index, &mut s);
|
||||
insta::assert_snapshot!(format!("{ids:?}"), @"[0, 2, 3]");
|
||||
insta::assert_snapshot!(format!("{scores:#?}"));
|
||||
}
|
||||
75
crates/milli/src/search/new/tests/integration.rs
Normal file
75
crates/milli/src/search/new/tests/integration.rs
Normal file
@ -0,0 +1,75 @@
|
||||
use std::io::Cursor;
|
||||
|
||||
use big_s::S;
|
||||
use heed::EnvOpenOptions;
|
||||
use maplit::{btreemap, hashset};
|
||||
|
||||
use crate::documents::{DocumentsBatchBuilder, DocumentsBatchReader};
|
||||
use crate::update::{IndexDocuments, IndexDocumentsConfig, IndexerConfig, Settings};
|
||||
use crate::{db_snap, Criterion, Index, Object};
|
||||
pub const CONTENT: &str = include_str!("../../../../tests/assets/test_set.ndjson");
|
||||
|
||||
pub fn setup_search_index_with_criteria(criteria: &[Criterion]) -> Index {
|
||||
let path = tempfile::tempdir().unwrap();
|
||||
let mut options = EnvOpenOptions::new();
|
||||
options.map_size(10 * 1024 * 1024); // 10 MB
|
||||
let index = Index::new(options, &path).unwrap();
|
||||
|
||||
let mut wtxn = index.write_txn().unwrap();
|
||||
let config = IndexerConfig::default();
|
||||
|
||||
let mut builder = Settings::new(&mut wtxn, &index, &config);
|
||||
|
||||
builder.set_criteria(criteria.to_vec());
|
||||
builder.set_filterable_fields(hashset! {
|
||||
S("tag"),
|
||||
S("asc_desc_rank"),
|
||||
S("_geo"),
|
||||
S("opt1"),
|
||||
S("opt1.opt2"),
|
||||
S("tag_in")
|
||||
});
|
||||
builder.set_sortable_fields(hashset! {
|
||||
S("tag"),
|
||||
S("asc_desc_rank"),
|
||||
});
|
||||
builder.set_synonyms(btreemap! {
|
||||
S("hello") => vec![S("good morning")],
|
||||
S("world") => vec![S("earth")],
|
||||
S("america") => vec![S("the united states")],
|
||||
});
|
||||
builder.set_searchable_fields(vec![S("title"), S("description")]);
|
||||
builder.execute(|_| (), || false).unwrap();
|
||||
|
||||
// index documents
|
||||
let config = IndexerConfig { max_memory: Some(10 * 1024 * 1024), ..Default::default() };
|
||||
let indexing_config = IndexDocumentsConfig::default();
|
||||
|
||||
let builder =
|
||||
IndexDocuments::new(&mut wtxn, &index, &config, indexing_config, |_| (), || false).unwrap();
|
||||
let mut documents_builder = DocumentsBatchBuilder::new(Vec::new());
|
||||
let reader = Cursor::new(CONTENT.as_bytes());
|
||||
|
||||
for result in serde_json::Deserializer::from_reader(reader).into_iter::<Object>() {
|
||||
let object = result.unwrap();
|
||||
documents_builder.append_json_object(&object).unwrap();
|
||||
}
|
||||
|
||||
let vector = documents_builder.into_inner().unwrap();
|
||||
|
||||
// index documents
|
||||
let content = DocumentsBatchReader::from_reader(Cursor::new(vector)).unwrap();
|
||||
let (builder, user_error) = builder.add_documents(content).unwrap();
|
||||
user_error.unwrap();
|
||||
builder.execute().unwrap();
|
||||
|
||||
wtxn.commit().unwrap();
|
||||
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn snapshot_integration_dataset() {
|
||||
let index = setup_search_index_with_criteria(&[Criterion::Attribute]);
|
||||
db_snap!(index, word_position_docids, @"3c9347a767bceef3beb31465f1e5f3ae");
|
||||
}
|
||||
23
crates/milli/src/search/new/tests/language.rs
Normal file
23
crates/milli/src/search/new/tests/language.rs
Normal file
@ -0,0 +1,23 @@
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::{Search, SearchResult};
|
||||
|
||||
#[test]
|
||||
fn test_kanji_language_detection() {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{ "id": 0, "title": "The quick (\"brown\") fox can't jump 32.3 feet, right? Brr, it's 29.3°F!" },
|
||||
{ "id": 1, "title": "東京のお寿司。" },
|
||||
{ "id": 2, "title": "הַשּׁוּעָל הַמָּהִיר (״הַחוּם״) לֹא יָכוֹל לִקְפֹּץ 9.94 מֶטְרִים, נָכוֹן? ברר, 1.5°C- בַּחוּץ!" }
|
||||
]))
|
||||
.unwrap();
|
||||
|
||||
let txn = index.write_txn().unwrap();
|
||||
let mut search = Search::new(&txn, &index);
|
||||
|
||||
search.query("東京");
|
||||
let SearchResult { documents_ids, .. } = search.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1]");
|
||||
}
|
||||
38
crates/milli/src/search/new/tests/mod.rs
Normal file
38
crates/milli/src/search/new/tests/mod.rs
Normal file
@ -0,0 +1,38 @@
|
||||
pub mod attribute_fid;
|
||||
pub mod attribute_position;
|
||||
pub mod cutoff;
|
||||
pub mod distinct;
|
||||
pub mod exactness;
|
||||
pub mod geo_sort;
|
||||
pub mod integration;
|
||||
#[cfg(feature = "all-tokenizations")]
|
||||
#[cfg(not(feature = "chinese-pinyin"))]
|
||||
pub mod language;
|
||||
pub mod ngram_split_words;
|
||||
pub mod proximity;
|
||||
pub mod proximity_typo;
|
||||
pub mod sort;
|
||||
pub mod stop_words;
|
||||
pub mod typo;
|
||||
pub mod typo_proximity;
|
||||
pub mod words_tms;
|
||||
|
||||
fn collect_field_values(
|
||||
index: &crate::Index,
|
||||
txn: &heed::RoTxn<'_>,
|
||||
fid: &str,
|
||||
docids: &[u32],
|
||||
) -> Vec<String> {
|
||||
let mut values = vec![];
|
||||
let fid = index.fields_ids_map(txn).unwrap().id(fid).unwrap();
|
||||
for doc in index.documents(txn, docids.iter().copied()).unwrap() {
|
||||
if let Some(v) = doc.1.get(fid) {
|
||||
let v: serde_json::Value = serde_json::from_slice(v).unwrap();
|
||||
let v = v.to_string();
|
||||
values.push(v);
|
||||
} else {
|
||||
values.push("__does_not_exist__".to_owned());
|
||||
}
|
||||
}
|
||||
values
|
||||
}
|
||||
428
crates/milli/src/search/new/tests/ngram_split_words.rs
Normal file
428
crates/milli/src/search/new/tests/ngram_split_words.rs
Normal file
@ -0,0 +1,428 @@
|
||||
/*!
|
||||
This module tests the following properties:
|
||||
|
||||
1. Two consecutive words from a query can be combined into a "2gram"
|
||||
2. Three consecutive words from a query can be combined into a "3gram"
|
||||
3. A word from the query can be split into two consecutive words (split words), no matter how short it is
|
||||
4. A 2gram can be split into two words
|
||||
5. A 3gram can be split into two words
|
||||
6. 2grams can contain up to 1 typo
|
||||
7. 3grams cannot have typos
|
||||
8. 2grams and 3grams can be prefix tolerant
|
||||
9. Disabling typo tolerance also disable the split words feature
|
||||
10. Disabling typo tolerance does not disable prefix tolerance
|
||||
11. Disabling typo tolerance does not disable ngram tolerance
|
||||
12. Prefix tolerance is disabled for the last word if a space follows it
|
||||
13. Ngrams cannot be formed by combining a phrase and a word or two phrases
|
||||
14. Split words are not disabled by the `disableOnAttribute` or `disableOnWords` typo settings
|
||||
*/
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "the sun flowers are pretty"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the sun flower is tall"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the sunflowers are pretty"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "the sunflower is tall"
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the sunflawer is tall"
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "sunflowering is not a verb"
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "xy z"
|
||||
}
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_2gram_simple() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("sun flower");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
// will also match documents with "sunflower" + prefix tolerance
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1, 2, 3, 5]");
|
||||
// scores are empty because the only rule is Words with All matching strategy
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[], [], [], [], []]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flowers are pretty\"",
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"sunflowering is not a verb\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
#[test]
|
||||
fn test_3gram_simple() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sun flower s are");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 2]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flowers are pretty\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_2gram_typo() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sun flawer");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1, 2, 3, 4, 5]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flowers are pretty\"",
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"the sunflawer is tall\"",
|
||||
"\"sunflowering is not a verb\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_no_disable_ngrams() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sun flower ");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
// documents containing `sunflower`
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 3]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflower is tall\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_2gram_prefix() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sun flow");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
// documents containing words beginning with `sunflow`
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1, 2, 3, 5]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flowers are pretty\"",
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"sunflowering is not a verb\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_3gram_prefix() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("su nf l");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
// documents containing a word beginning with sunfl
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 3, 4, 5]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"the sunflawer is tall\"",
|
||||
"\"sunflowering is not a verb\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_split_words() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sunflower ");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
// all the documents with either `sunflower` or `sun flower` + eventual typo
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 2, 3, 4]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"the sunflawer is tall\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_disable_split_words() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sunflower ");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
// no document containing `sun flower`
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 3]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflower is tall\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_2gram_split_words() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sunf lower");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
// all the documents with "sunflower", "sun flower", (sunflower + 1 typo), or (sunflower as prefix)
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 2, 3, 4, 5]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"the sunflawer is tall\"",
|
||||
"\"sunflowering is not a verb\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_3gram_no_split_words() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sunf lo wer");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
// no document with `sun flower`
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 2, 3, 5]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflowers are pretty\"",
|
||||
"\"the sunflower is tall\"",
|
||||
"\"sunflowering is not a verb\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_3gram_no_typos() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("sunf la wer");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[4]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sunflawer is tall\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_no_ngram_phrases() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("\"sun\" flower");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flowers are pretty\"",
|
||||
"\"the sun flower is tall\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("\"sun\" \"flower\"");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_short_split_words() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("xyz");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"xy z\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_split_words_never_disabled() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_exact_words(["sunflower"].iter().map(ToString::to_string).collect());
|
||||
s.set_exact_attributes(["text"].iter().map(ToString::to_string).collect());
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the sunflower is tall");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 3]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the sun flower is tall\"",
|
||||
"\"the sunflower is tall\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
490
crates/milli/src/search/new/tests/proximity.rs
Normal file
490
crates/milli/src/search/new/tests/proximity.rs
Normal file
@ -0,0 +1,490 @@
|
||||
/*!
|
||||
This module tests the Proximity ranking rule:
|
||||
|
||||
1. A proximity of >7 always has the same cost.
|
||||
|
||||
2. Phrase terms can be in sprximity to other terms via their start and end words,
|
||||
but we need to make sure that the phrase exists in the document that meets this
|
||||
proximity condition. This is especially relevant with split words and synonyms.
|
||||
|
||||
3. An ngram has the same sprximity cost as its component words being consecutive.
|
||||
e.g. `sunflower` equivalent to `sun flower`.
|
||||
|
||||
4. The prefix databases can be used to find the sprximity between two words, but
|
||||
they store fewer sprximities than the regular word sprximity DB.
|
||||
|
||||
*/
|
||||
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_simple_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "the very quick dark brown and smart fox did jump over the terribly lazy and small dog"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the. quick brown fox jumps over the lazy. dog"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quick brown fox jumps over the lazy. dog"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "dog the quick brown fox jumps over the lazy"
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the quickbrown fox jumps over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "brown quick fox jumps over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "the really quick brown fox jumps over the very lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the really quick brown fox jumps over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the quick brown fox jumps over the lazy"
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quack brown fox jumps over the lazy"
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quack brown fox jumps over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"text": "the quick brown fox jumps over the lazy dog"
|
||||
}
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
fn create_edge_cases_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index.add_documents(documents!([
|
||||
{
|
||||
// This document will insert "s" in the prefix database
|
||||
"id": 0,
|
||||
"text": "
|
||||
saa sab sac sae saf sag sah sai saj sak sal sam san sao sap saq sar sasa sat sau sav saw sax say saz
|
||||
sba sbb sbc sbe sbf sbg sbh sbi sbj sbk sbl sbm sbn sbo sbp sbq sbr sbsb sbt sbu sbv sbw sbx sby sbz
|
||||
sca scb scc sce scf scg sch sci scj sck scl scm scn sco scp scq scr scsc sct scu scv scw scx scy scz
|
||||
sda sdb sdc sde sdf sdg sdh sdi sdj sdk sdl sdm sdn sdo sdp sdq sdr sdsd sdt sdu sdv sdw sdx sdy sdz
|
||||
sea seb sec see sef seg seh sei sej sek sel sem sen seo sep seq ser sese set seu sev sew sex sey sez
|
||||
sfa sfb sfc sfe sff sfg sfh sfi sfj sfk sfl sfm sfn sfo sfp sfq sfr sfsf sft sfu sfv sfw sfx sfy sfz
|
||||
sga sgb sgc sge sgf sgg sgh sgi sgj sgk sgl sgm sgn sgo sgp sgq sgr sgsg sgt sgu sgv sgw sgx sgy sgz
|
||||
ska skb skc ske skf skg skh ski skj skk skl skm skn sko skp skq skr sksk skt sku skv skw skx sky skz
|
||||
sla slb slc sle slf slg slh sli slj slk sll slm sln slo slp slq slr slsl slt slu slv slw slx sly slz
|
||||
sma smb smc sme smf smg smh smi smj smk sml smm smn smo smp smq smr smsm smt smu smv smw smx smy smz
|
||||
sna snb snc sne snf sng snh sni snj snk snl snm snn sno snp snq snr snsn snt snu snv snw snx sny snz
|
||||
soa sob soc soe sof sog soh soi soj sok sol som son soo sop soq sor soso sot sou sov sow sox soy soz
|
||||
spa spb spc spe spf spg sph spi spj spk spl spm spn spo spp spq spr spsp spt spu spv spw spx spy spz
|
||||
sqa sqb sqc sqe sqf sqg sqh sqi sqj sqk sql sqm sqn sqo sqp sqq sqr sqsq sqt squ sqv sqw sqx sqy sqz
|
||||
sra srb src sre srf srg srh sri srj srk srl srm srn sro srp srq srr srsr srt sru srv srw srx sry srz
|
||||
ssa ssb ssc sse ssf ssg ssh ssi ssj ssk ssl ssm ssn sso ssp ssq ssr ssss sst ssu ssv ssw ssx ssy ssz
|
||||
sta stb stc ste stf stg sth sti stj stk stl stm stn sto stp stq str stst stt stu stv stw stx sty stz
|
||||
"
|
||||
},
|
||||
// The next 5 documents lay out a trap with the split word, phrase search, or synonym `sun flower`.
|
||||
// If the search query is "sunflower", the split word "Sun Flower" will match some documents.
|
||||
// The next 5 documents lay out a trap with the split word, phrase search, or synonym `sun flower`.
|
||||
// If the search query is "sunflower", the split word "Sun Flower" will match some documents.
|
||||
// If the query is `sunflower wilting`, then we should make sure that
|
||||
// the proximity condition `flower wilting: sprx N` also comes with the condition
|
||||
// `sun wilting: sprx N+1`, but this is not the exact condition we use for now.
|
||||
// We only check that the phrase `sun flower` exists and `flower wilting: sprx N`, which
|
||||
// is better than nothing but not the best.
|
||||
{
|
||||
"id": 1,
|
||||
"text": "Sun Flower sounds like the title of a painting, maybe about a plant wilting under the heat."
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "Sun Flower sounds like the title of a painting, maybe about a flower wilting under the heat."
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
// This document matches the query `sunflower wilting`, but the sprximity condition
|
||||
// This document matches the query `sunflower wilting`, but the sprximity condition
|
||||
// between `sunflower` and `wilting` cannot be through the split-word `Sun Flower`
|
||||
// which would reduce to only `flower` and `wilting` being in sprximity.
|
||||
"text": "A flower wilting under the sun, unlike a sunflower"
|
||||
},
|
||||
{
|
||||
// This should be the best document for `sunflower wilting`
|
||||
"id": 4,
|
||||
"text": "sun flower wilting under the heat"
|
||||
},
|
||||
{
|
||||
// This is also the best document for `sunflower wilting`
|
||||
"id": 5,
|
||||
"text": "sunflower wilting under the heat"
|
||||
},
|
||||
{
|
||||
// Prox MAX between `best` and `s` prefix
|
||||
"id": 6,
|
||||
"text": "this is the best meal I have ever had in such a beautiful summer day"
|
||||
},
|
||||
{
|
||||
// Prox 5 between `best` and `s` prefix
|
||||
"id": 7,
|
||||
"text": "this is the best cooked meal of the summer"
|
||||
},
|
||||
{
|
||||
// Prox 4 between `best` and `s` prefix
|
||||
"id": 8,
|
||||
"text": "this is the best meal of the summer"
|
||||
},
|
||||
{
|
||||
// Prox 3 between `best` and `s` prefix
|
||||
"id": 9,
|
||||
"text": "this is the best meal of summer"
|
||||
},
|
||||
{
|
||||
// Prox 1 between `best` and `s` prefix
|
||||
"id": 10,
|
||||
"text": "this is the best summer meal"
|
||||
},
|
||||
{
|
||||
// Reverse Prox 3 between `best` and `s` prefix
|
||||
"id": 11,
|
||||
"text": "summer x y best"
|
||||
},
|
||||
{
|
||||
// Reverse Prox 2 between `best` and `s` prefix
|
||||
"id": 12,
|
||||
"text": "summer x best"
|
||||
},
|
||||
{
|
||||
// Reverse Prox 1 between `best` and `s` prefix
|
||||
"id": 13,
|
||||
"text": "summer best"
|
||||
},
|
||||
{
|
||||
// This document will insert "win" in the prefix database
|
||||
"id": 14,
|
||||
"text": "
|
||||
winaa winab winac winae winaf winag winah winai winaj winak winal winam winan winao winap winaq winar winasa winat winau winav winaw winax winay winaz
|
||||
winba winbb winbc winbe winbf winbg winbh winbi winbj winbk winbl winbm winbn winbo winbp winbq winbr winbsb winbt winbu winbv winbw winbx winby winbz
|
||||
winca wincb wincc wince wincf wincg winch winci wincj winck wincl wincm wincn winco wincp wincq wincr wincsc winct wincu wincv wincw wincx wincy wincz
|
||||
winda windb windc winde windf windg windh windi windj windk windl windm windn windo windp windq windr windsd windt windu windv windw windx windy windz
|
||||
winea wineb winec winee winef wineg wineh winei winej winek winel winem winen wineo winep wineq winer winese winet wineu winev winew winex winey winez
|
||||
winfa winfb winfc winfe winff winfg winfh winfi winfj winfk winfl winfm winfn winfo winfp winfq winfr winfsf winft winfu winfv winfw winfx winfy winfz
|
||||
winga wingb wingc winge wingf wingg wingh wingi wingj wingk wingl wingm wingn wingo wingp wingq wingr wingsg wingt wingu wingv wingw wingx wingy wingz
|
||||
winka winkb winkc winke winkf winkg winkh winki winkj winkk winkl winkm winkn winko winkp winkq winkr winksk winkt winku winkv winkw winkx winky winkz
|
||||
winla winlb winlc winle winlf winlg winlh winli winlj winlk winll winlm winln winlo winlp winlq winlr winlsl winlt winlu winlv winlw winlx winly winlz
|
||||
winma winmb winmc winme winmf winmg winmh winmi winmj winmk winml winmm winmn winmo winmp winmq winmr winmsm winmt winmu winmv winmw winmx winmy winmz
|
||||
winna winnb winnc winne winnf winng winnh winni winnj winnk winnl winnm winnn winno winnp winnq winnr winnsn winnt winnu winnv winnw winnx winny winnz
|
||||
winoa winob winoc winoe winof winog winoh winoi winoj winok winol winom winon winoo winop winoq winor winoso winot winou winov winow winox winoy winoz
|
||||
winpa winpb winpc winpe winpf winpg winph winpi winpj winpk winpl winpm winpn winpo winpp winpq winpr winpsp winpt winpu winpv winpw winpx winpy winpz
|
||||
winqa winqb winqc winqe winqf winqg winqh winqi winqj winqk winql winqm winqn winqo winqp winqq winqr winqsq winqt winqu winqv winqw winqx winqy winqz
|
||||
winra winrb winrc winre winrf winrg winrh winri winrj winrk winrl winrm winrn winro winrp winrq winrr winrsr winrt winru winrv winrw winrx winry winrz
|
||||
winsa winsb winsc winse winsf winsg winsh winsi winsj winsk winsl winsm winsn winso winsp winsq winsr winsss winst winsu winsv winsw winsx winsy winsz
|
||||
winta wintb wintc winte wintf wintg winth winti wintj wintk wintl wintm wintn winto wintp wintq wintr wintst wintt wintu wintv wintw wintx winty wintz
|
||||
"
|
||||
},
|
||||
{
|
||||
// Prox MAX between `best` and `win` prefix
|
||||
"id": 15,
|
||||
"text": "this is the best meal I have ever had in such a beautiful winter day"
|
||||
},
|
||||
{
|
||||
// Prox 5 between `best` and `win` prefix
|
||||
"id": 16,
|
||||
"text": "this is the best cooked meal of the winter"
|
||||
},
|
||||
{
|
||||
// Prox 4 between `best` and `win` prefix
|
||||
"id": 17,
|
||||
"text": "this is the best meal of the winter"
|
||||
},
|
||||
{
|
||||
// Prox 3 between `best` and `win` prefix
|
||||
"id": 18,
|
||||
"text": "this is the best meal of winter"
|
||||
},
|
||||
{
|
||||
// Prox 1 between `best` and `win` prefix
|
||||
"id": 19,
|
||||
"text": "this is the best winter meal"
|
||||
},
|
||||
{
|
||||
// Reverse Prox 3 between `best` and `win` prefix
|
||||
"id": 20,
|
||||
"text": "winter x y best"
|
||||
},
|
||||
{
|
||||
// Reverse Prox 2 between `best` and `win` prefix
|
||||
"id": 21,
|
||||
"text": "winter x best"
|
||||
},
|
||||
{
|
||||
// Reverse Prox 1 between `best` and `win` prefix
|
||||
"id": 22,
|
||||
"text": "winter best"
|
||||
},
|
||||
])).unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_proximity_simple() {
|
||||
let index = create_simple_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 10, 4, 7, 6, 2, 3, 5, 1, 0]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quack brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quickbrown fox jumps over the lazy dog\"",
|
||||
"\"the really quick brown fox jumps over the lazy dog\"",
|
||||
"\"the really quick brown fox jumps over the very lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy. dog\"",
|
||||
"\"dog the quick brown fox jumps over the lazy\"",
|
||||
"\"brown quick fox jumps over the lazy dog\"",
|
||||
"\"the. quick brown fox jumps over the lazy. dog\"",
|
||||
"\"the very quick dark brown and smart fox did jump over the terribly lazy and small dog\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_proximity_split_word() {
|
||||
let index = create_edge_cases_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("sunflower wilting");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 4, 5, 1, 3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
// "2" and "4" should be swapped ideally
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"Sun Flower sounds like the title of a painting, maybe about a flower wilting under the heat.\"",
|
||||
"\"sun flower wilting under the heat\"",
|
||||
"\"sunflower wilting under the heat\"",
|
||||
"\"Sun Flower sounds like the title of a painting, maybe about a plant wilting under the heat.\"",
|
||||
"\"A flower wilting under the sun, unlike a sunflower\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("\"sun flower\" wilting");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 4, 1]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
// "2" and "4" should be swapped ideally
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"Sun Flower sounds like the title of a painting, maybe about a flower wilting under the heat.\"",
|
||||
"\"sun flower wilting under the heat\"",
|
||||
"\"Sun Flower sounds like the title of a painting, maybe about a plant wilting under the heat.\"",
|
||||
]
|
||||
"###);
|
||||
drop(txn);
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
let mut syns = BTreeMap::new();
|
||||
syns.insert("xyz".to_owned(), vec!["sun flower".to_owned()]);
|
||||
s.set_synonyms(syns);
|
||||
})
|
||||
.unwrap();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("xyz wilting");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 4, 1]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
// "2" and "4" should be swapped ideally
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"Sun Flower sounds like the title of a painting, maybe about a flower wilting under the heat.\"",
|
||||
"\"sun flower wilting under the heat\"",
|
||||
"\"Sun Flower sounds like the title of a painting, maybe about a plant wilting under the heat.\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_proximity_prefix_db() {
|
||||
let index = create_edge_cases_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("best s");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 9, 6, 7, 8, 11, 12, 13, 15]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
// This test illustrates the loss of precision from using the prefix DB
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"this is the best summer meal\"",
|
||||
"\"this is the best meal of summer\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful summer day\"",
|
||||
"\"this is the best cooked meal of the summer\"",
|
||||
"\"this is the best meal of the summer\"",
|
||||
"\"summer x y best\"",
|
||||
"\"summer x best\"",
|
||||
"\"summer best\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful winter day\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// Difference when using the `su` prefix, which is not in the prefix DB
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("best su");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 13, 9, 12, 6, 7, 8, 11, 15]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"this is the best summer meal\"",
|
||||
"\"summer best\"",
|
||||
"\"this is the best meal of summer\"",
|
||||
"\"summer x best\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful summer day\"",
|
||||
"\"this is the best cooked meal of the summer\"",
|
||||
"\"this is the best meal of the summer\"",
|
||||
"\"summer x y best\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful winter day\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// Note that there is a case where a prefix is in the prefix DB but not in the
|
||||
// **proximity** prefix DB. In that case, its sprximity score will always be
|
||||
// the maximum. This happens for prefixes that are larger than 2 bytes.
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("best win");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[19, 18, 15, 16, 17, 20, 21, 22]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"this is the best winter meal\"",
|
||||
"\"this is the best meal of winter\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful winter day\"",
|
||||
"\"this is the best cooked meal of the winter\"",
|
||||
"\"this is the best meal of the winter\"",
|
||||
"\"winter x y best\"",
|
||||
"\"winter x best\"",
|
||||
"\"winter best\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// Now using `wint`, which is not in the prefix DB:
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("best wint");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[19, 22, 18, 21, 15, 16, 17, 20]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"this is the best winter meal\"",
|
||||
"\"winter best\"",
|
||||
"\"this is the best meal of winter\"",
|
||||
"\"winter x best\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful winter day\"",
|
||||
"\"this is the best cooked meal of the winter\"",
|
||||
"\"this is the best meal of the winter\"",
|
||||
"\"winter x y best\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// and using `wi` which is in the prefix DB and proximity prefix DB
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("best wi");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[19, 18, 15, 16, 17, 20, 21, 22]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"this is the best winter meal\"",
|
||||
"\"this is the best meal of winter\"",
|
||||
"\"this is the best meal I have ever had in such a beautiful winter day\"",
|
||||
"\"this is the best cooked meal of the winter\"",
|
||||
"\"this is the best meal of the winter\"",
|
||||
"\"winter x y best\"",
|
||||
"\"winter x best\"",
|
||||
"\"winter best\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
106
crates/milli/src/search/new/tests/proximity_typo.rs
Normal file
106
crates/milli/src/search/new/tests/proximity_typo.rs
Normal file
@ -0,0 +1,106 @@
|
||||
/*!
|
||||
This module tests the interactions between the proximity and typo ranking rules.
|
||||
|
||||
The proximity ranking rule should transform the query graph such that it
|
||||
only contains the word pairs that it used to compute its bucket, but this is not currently
|
||||
implemented.
|
||||
*/
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Proximity, Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
// Basic trap.
|
||||
//
|
||||
// We have one document with the perfect word pair: `sommer - holiday`
|
||||
// and another with the perfect word pair: `sommer holidty`.
|
||||
//
|
||||
// The proximity ranking rule will put them both in the same bucket, and it
|
||||
// should minify the query graph to make it represent:
|
||||
// EITHER:
|
||||
// sommer + holiday
|
||||
// OR:
|
||||
// sommer + holidty
|
||||
//
|
||||
// Such that the child typo ranking rule does not find any match
|
||||
// for its zero-typo bucket `summer + holiday`, even though both documents
|
||||
// contain these two exact words.
|
||||
{
|
||||
"id": 0,
|
||||
"text": "summer. holiday. sommer holidty"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "summer. holiday. sommer holiday"
|
||||
},
|
||||
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_trap_basic() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("summer holiday");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
// This is incorrect, 1 should come before 0
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"summer. holiday. sommer holidty\"",
|
||||
"\"summer. holiday. sommer holiday\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/attribute_fid.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
2,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 91,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 81,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 14,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 79,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 77,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 12,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 83,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 75,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 79,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 73,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 77,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
10,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 6,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 81,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 6,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 81,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 6,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 78,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
14,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 75,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 91,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/attribute_fid.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
2,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 91,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 81,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 14,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 79,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 77,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 12,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 83,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 75,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 79,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 73,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 77,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
10,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 6,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 81,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 6,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 81,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 6,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 78,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
14,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 75,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 91,
|
||||
max_rank: 91,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/attribute_position.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
10,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/attribute_position.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
10,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/attribute_position.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
5,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 51,
|
||||
max_rank: 51,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 51,
|
||||
max_rank: 51,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 51,
|
||||
max_rank: 51,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 51,
|
||||
max_rank: 51,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 50,
|
||||
max_rank: 51,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/attribute_position.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
10,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 15,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 5,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,366 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
19,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 6,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
18,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 8,
|
||||
max_matching_words: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
17,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
16,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
15,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
14,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,106 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 6,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 6,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 6,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 0,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,126 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 6,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,86 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,66 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,136 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,186 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
9,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 8,
|
||||
max_matching_words: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,126 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,146 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
9,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,146 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
9,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,84 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
0,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,240 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 25,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 24,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,110 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
0,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,366 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/exactness.rs
|
||||
expression: "format!(\"{document_ids_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
(
|
||||
19,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
9,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 6,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
18,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 8,
|
||||
max_matching_words: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
8,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
17,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
16,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 7,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
6,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
7,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
15,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 5,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
5,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
14,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
4,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
13,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
3,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
12,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
2,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
1,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
(
|
||||
11,
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
ExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
),
|
||||
]
|
||||
@ -0,0 +1,168 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
1.0,
|
||||
1.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
2.0,
|
||||
-1.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-2.0,
|
||||
-2.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
3.0,
|
||||
5.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
6.0,
|
||||
-5.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,168 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
6.0,
|
||||
-5.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
3.0,
|
||||
5.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
-2.0,
|
||||
-2.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
2.0,
|
||||
-1.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
1.0,
|
||||
1.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
-175.0,
|
||||
],
|
||||
ascending: false,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
-85.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,91 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
-179.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
88.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
175.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,75 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
-89.0,
|
||||
0.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: Some(
|
||||
[
|
||||
0.0,
|
||||
178.0,
|
||||
],
|
||||
),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/geo_sort.rs
|
||||
expression: "format!(\"{scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
GeoSort(
|
||||
GeoSort {
|
||||
target_point: [
|
||||
0.0,
|
||||
0.0,
|
||||
],
|
||||
ascending: true,
|
||||
value: None,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,70 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 3,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,70 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,78 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,78 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 3,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,70 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,46 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,30 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,30 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,206 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/sort.rs
|
||||
expression: document_scores_json
|
||||
---
|
||||
[
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 0.0
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 1.0
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 1.0
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 1.0
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 1.1367
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 1.2367
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": 1.5673
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": "0"
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": "1"
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": "false"
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": "false"
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": "true"
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": "true"
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
},
|
||||
{
|
||||
"vague:asc": {
|
||||
"order": 0,
|
||||
"value": null
|
||||
},
|
||||
"<hidden-rule-1>": {
|
||||
"order": 1,
|
||||
"value": "<hidden>"
|
||||
}
|
||||
}
|
||||
]
|
||||
@ -0,0 +1,206 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/sort.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(2.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.5673),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.2367),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.1367),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("true"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("true"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("false"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("false"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("1"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("0"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,206 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/sort.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("i"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("i"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("i"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("h"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("g"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("g"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("f"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("f"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("f"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("e"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("e"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("e"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("e"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("e"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("e"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("d"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("c"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("c"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("c"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "letter",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: String("b"),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,206 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/sort.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(5.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(4.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(3.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(2.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(2.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(2.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(2.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(2.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "rank",
|
||||
ascending: false,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,206 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/sort.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(0.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(1.0),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(1.1367),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(1.2367),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Number(1.5673),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: String("0"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: String("1"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: String("false"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: String("false"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: String("true"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: String("true"),
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Sort(
|
||||
Sort {
|
||||
field_name: "vague",
|
||||
ascending: true,
|
||||
redacted: false,
|
||||
value: Null,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,129 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/stop_words.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 31,
|
||||
max_rank: 31,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 31,
|
||||
max_rank: 31,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 27,
|
||||
max_rank: 31,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,13 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/stop_words.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
]
|
||||
@ -0,0 +1,12 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
]
|
||||
@ -0,0 +1,54 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 5,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,54 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 6,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 6,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 6,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 6,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 3,
|
||||
max_typo_count: 6,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 4,
|
||||
max_typo_count: 6,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,9 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
]
|
||||
@ -0,0 +1,9 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[],
|
||||
[],
|
||||
[],
|
||||
]
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,244 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 8,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,30 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,30 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 2,
|
||||
max_typo_count: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,62 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo_proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 3,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 3,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,34 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/typo_proximity.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 1,
|
||||
max_typo_count: 5,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,216 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 17,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 16,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 16,
|
||||
max_rank: 16,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 16,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 4,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,160 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 17,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 14,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 16,
|
||||
max_rank: 16,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,286 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 25,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 25,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 24,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 24,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 23,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 16,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,286 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 25,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 24,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 23,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 18,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 22,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 16,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 13,
|
||||
max_rank: 19,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 10,
|
||||
max_rank: 13,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 7,
|
||||
max_rank: 10,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 5,
|
||||
max_rank: 7,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,102 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 25,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 25,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 24,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 24,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 23,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 22,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 21,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 20,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 19,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 25,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,86 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,54 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
@ -0,0 +1,166 @@
|
||||
---
|
||||
source: milli/src/search/new/tests/words_tms.rs
|
||||
expression: "format!(\"{document_scores:#?}\")"
|
||||
---
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 9,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 8,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 7,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 5,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 9,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
356
crates/milli/src/search/new/tests/sort.rs
Normal file
356
crates/milli/src/search/new/tests/sort.rs
Normal file
@ -0,0 +1,356 @@
|
||||
/*!
|
||||
This module tests the `sort` ranking rule:
|
||||
|
||||
1. an error is returned if the sort ranking rule exists but no fields-to-sort were given at search time
|
||||
2. an error is returned if the fields-to-sort are not sortable
|
||||
3. it is possible to add multiple fields-to-sort at search time
|
||||
4. custom sort ranking rules can be added to the settings, they interact with the generic `sort` ranking rule as expected
|
||||
5. numbers appear before strings
|
||||
6. documents with either: (1) no value, (2) null, or (3) an object for the field-to-sort appear at the end of the bucket
|
||||
7. boolean values are translated to strings
|
||||
8. if a field contains an array, it is sorted by the best value in the array according to the sort rule
|
||||
*/
|
||||
|
||||
use big_s::S;
|
||||
use maplit::hashset;
|
||||
use meili_snap::insta;
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{
|
||||
score_details, AscDesc, Criterion, Member, Search, SearchResult, TermsMatchingStrategy,
|
||||
};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_sortable_fields(hashset! { S("rank"), S("vague"), S("letter") });
|
||||
s.set_criteria(vec![Criterion::Sort]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"letter": "A",
|
||||
"rank": 0,
|
||||
"vague": 0,
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"letter": "A",
|
||||
"rank": 1,
|
||||
"vague": "0",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"letter": "B",
|
||||
"rank": 0,
|
||||
"vague": 1,
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"letter": "B",
|
||||
"rank": 1,
|
||||
"vague": "1",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"letter": "B",
|
||||
"rank": 2,
|
||||
"vague": [1, 2],
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"letter": "C",
|
||||
"rank": 0,
|
||||
"vague": [1, "2"],
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"letter": "C",
|
||||
"rank": 1,
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"letter": "C",
|
||||
"rank": 2,
|
||||
"vague": null,
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"letter": "D",
|
||||
"rank": 0,
|
||||
"vague": [null, null, ""]
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"letter": "E",
|
||||
"rank": 0,
|
||||
"vague": ""
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"letter": "E",
|
||||
"rank": 1,
|
||||
"vague": {
|
||||
"sub": 0,
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"letter": "E",
|
||||
"rank": 2,
|
||||
"vague": true,
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"letter": "E",
|
||||
"rank": 3,
|
||||
"vague": false,
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"letter": "E",
|
||||
"rank": 4,
|
||||
"vague": 1.5673,
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"letter": "E",
|
||||
"rank": 5,
|
||||
},
|
||||
{
|
||||
"id": 15,
|
||||
"letter": "F",
|
||||
"rank": 0,
|
||||
},
|
||||
{
|
||||
"id": 16,
|
||||
"letter": "F",
|
||||
"rank": 1,
|
||||
},
|
||||
{
|
||||
"id": 17,
|
||||
"letter": "F",
|
||||
"rank": 2,
|
||||
},
|
||||
{
|
||||
"id": 18,
|
||||
"letter": "G",
|
||||
"rank": 0,
|
||||
},
|
||||
{
|
||||
"id": 19,
|
||||
"letter": "G",
|
||||
"rank": 1,
|
||||
},
|
||||
{
|
||||
"id": 20,
|
||||
"letter": "H",
|
||||
"rank": 0,
|
||||
"vague": true,
|
||||
},
|
||||
{
|
||||
"id": 21,
|
||||
"letter": "I",
|
||||
"rank": 0,
|
||||
"vague": false,
|
||||
},
|
||||
{
|
||||
"id": 22,
|
||||
"letter": "I",
|
||||
"rank": 1,
|
||||
"vague": [1.1367, "help", null]
|
||||
},
|
||||
{
|
||||
"id": 23,
|
||||
"letter": "I",
|
||||
"rank": 2,
|
||||
"vague": [1.2367, "hello"]
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_sort() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("letter")))]);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[21, 22, 23, 20, 18, 19, 15, 16, 17, 9, 10, 11, 12, 13, 14, 8, 5, 6, 7, 2]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
let letter_values = collect_field_values(&index, &txn, "letter", &documents_ids);
|
||||
insta::assert_debug_snapshot!(letter_values, @r###"
|
||||
[
|
||||
"\"I\"",
|
||||
"\"I\"",
|
||||
"\"I\"",
|
||||
"\"H\"",
|
||||
"\"G\"",
|
||||
"\"G\"",
|
||||
"\"F\"",
|
||||
"\"F\"",
|
||||
"\"F\"",
|
||||
"\"E\"",
|
||||
"\"E\"",
|
||||
"\"E\"",
|
||||
"\"E\"",
|
||||
"\"E\"",
|
||||
"\"E\"",
|
||||
"\"D\"",
|
||||
"\"C\"",
|
||||
"\"C\"",
|
||||
"\"C\"",
|
||||
"\"B\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("rank")))]);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[14, 13, 12, 4, 7, 11, 17, 23, 1, 3, 6, 10, 16, 19, 22, 0, 2, 5, 8, 9]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
let rank_values = collect_field_values(&index, &txn, "rank", &documents_ids);
|
||||
insta::assert_debug_snapshot!(rank_values, @r###"
|
||||
[
|
||||
"5",
|
||||
"4",
|
||||
"3",
|
||||
"2",
|
||||
"2",
|
||||
"2",
|
||||
"2",
|
||||
"2",
|
||||
"1",
|
||||
"1",
|
||||
"1",
|
||||
"1",
|
||||
"1",
|
||||
"1",
|
||||
"1",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
"0",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![AscDesc::Asc(Member::Field(S("vague")))]);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 2, 4, 5, 22, 23, 13, 1, 3, 12, 21, 11, 20, 6, 7, 8, 9, 10, 14, 15]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
let vague_values = collect_field_values(&index, &txn, "vague", &documents_ids);
|
||||
insta::assert_debug_snapshot!(vague_values, @r###"
|
||||
[
|
||||
"0",
|
||||
"1",
|
||||
"[1,2]",
|
||||
"[1,\"2\"]",
|
||||
"[1.1367,\"help\",null]",
|
||||
"[1.2367,\"hello\"]",
|
||||
"1.5673",
|
||||
"\"0\"",
|
||||
"\"1\"",
|
||||
"false",
|
||||
"false",
|
||||
"true",
|
||||
"true",
|
||||
"__does_not_exist__",
|
||||
"null",
|
||||
"[null,null,\"\"]",
|
||||
"\"\"",
|
||||
"{\"sub\":0}",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![AscDesc::Desc(Member::Field(S("vague")))]);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[4, 13, 23, 22, 2, 5, 0, 11, 20, 12, 21, 3, 1, 6, 7, 8, 9, 10, 14, 15]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
let vague_values = collect_field_values(&index, &txn, "vague", &documents_ids);
|
||||
insta::assert_debug_snapshot!(vague_values, @r###"
|
||||
[
|
||||
"[1,2]",
|
||||
"1.5673",
|
||||
"[1.2367,\"hello\"]",
|
||||
"[1.1367,\"help\",null]",
|
||||
"1",
|
||||
"[1,\"2\"]",
|
||||
"0",
|
||||
"true",
|
||||
"true",
|
||||
"false",
|
||||
"false",
|
||||
"\"1\"",
|
||||
"\"0\"",
|
||||
"__does_not_exist__",
|
||||
"null",
|
||||
"[null,null,\"\"]",
|
||||
"\"\"",
|
||||
"{\"sub\":0}",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_redacted() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_displayed_fields(vec!["text".to_owned(), "vague".to_owned()]);
|
||||
s.set_sortable_fields(hashset! { S("rank"), S("vague"), S("letter") });
|
||||
s.set_criteria(vec![Criterion::Sort]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.sort_criteria(vec![
|
||||
AscDesc::Asc(Member::Field(S("vague"))),
|
||||
AscDesc::Asc(Member::Field(S("letter"))),
|
||||
]);
|
||||
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
let document_scores_json: Vec<_> = document_scores
|
||||
.iter()
|
||||
.map(|scores| score_details::ScoreDetails::to_json_map(scores.iter()))
|
||||
.collect();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 2, 4, 5, 22, 23, 13, 1, 3, 12, 21, 11, 20, 6, 7, 8, 9, 10, 14, 15]");
|
||||
insta::assert_json_snapshot!(document_scores_json);
|
||||
}
|
||||
461
crates/milli/src/search/new/tests/stop_words.rs
Normal file
461
crates/milli/src/search/new/tests/stop_words.rs
Normal file
@ -0,0 +1,461 @@
|
||||
/*!
|
||||
This module tests the following properties about stop words:
|
||||
- they are not indexed
|
||||
- they are not searchable
|
||||
- they are case sensitive
|
||||
- they are ignored in phrases
|
||||
- If a query consists only of stop words, a placeholder query is used instead
|
||||
- A prefix word is never ignored, even if the prefix is a stop word
|
||||
- Phrases consisting only of stop words are ignored
|
||||
*/
|
||||
|
||||
use std::collections::BTreeSet;
|
||||
use std::iter::FromIterator;
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::{Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["title".to_owned()]);
|
||||
s.set_stop_words(BTreeSet::from_iter([
|
||||
"to".to_owned(),
|
||||
"The".to_owned(),
|
||||
"xyz".to_owned(),
|
||||
]));
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"title": "Shazam!",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"title": "Captain Marvel",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"title": "Escape Room",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"title": "How to Train Your Dragon: The Hidden World",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"title": "Gläss",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"title": "How to Attempt to Train Your Dragon",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"title": "How to Train Your Dragon: the Hidden World",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[cfg(not(feature = "swedish-recomposition"))]
|
||||
fn test_stop_words_not_indexed() {
|
||||
let index = create_index();
|
||||
crate::db_snap!(index, word_docids, @"6288f9d7db3703b02c57025eb4a69264");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ignore_stop_words() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
// `the` is treated as a prefix here, so it's not ignored
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("xyz to the");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// `xyz` is treated as a prefix here, so it's not ignored
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("to the xyz");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
// `xyz` is not treated as a prefix anymore because of the trailing space, so it's ignored
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("to the xyz ");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 1,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 9,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("to the dragon xyz");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 2,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 3,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 17,
|
||||
max_rank: 21,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 2,
|
||||
max_matching_words: 2,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_stop_words_in_phrase() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("\"how to train your dragon\"");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3, 6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 0,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 4,
|
||||
max_matching_words: 4,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 0,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 11,
|
||||
max_rank: 11,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
MatchesStart,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 1,
|
||||
max_matching_words: 1,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("how \"to\" train \"the");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[
|
||||
Words(
|
||||
Words {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
Typo(
|
||||
Typo {
|
||||
typo_count: 0,
|
||||
max_typo_count: 2,
|
||||
},
|
||||
),
|
||||
Proximity(
|
||||
Rank {
|
||||
rank: 2,
|
||||
max_rank: 4,
|
||||
},
|
||||
),
|
||||
Fid(
|
||||
Rank {
|
||||
rank: 1,
|
||||
max_rank: 1,
|
||||
},
|
||||
),
|
||||
Position(
|
||||
Rank {
|
||||
rank: 29,
|
||||
max_rank: 31,
|
||||
},
|
||||
),
|
||||
ExactAttribute(
|
||||
NoExactMatch,
|
||||
),
|
||||
ExactWords(
|
||||
ExactWords {
|
||||
matching_words: 3,
|
||||
max_matching_words: 3,
|
||||
},
|
||||
),
|
||||
],
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("how \"to\" train \"The dragon");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3, 6, 5]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("\"to\"");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 1, 2, 3, 4, 5, 6]");
|
||||
// The search is handled as a placeholder search because it doesn't have any non-stop words in it.
|
||||
// As a result the scores are empty lists
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
}
|
||||
637
crates/milli/src/search/new/tests/typo.rs
Normal file
637
crates/milli/src/search/new/tests/typo.rs
Normal file
@ -0,0 +1,637 @@
|
||||
/*!
|
||||
This module tests the following properties:
|
||||
|
||||
1. The `words` ranking rule is typo-tolerant
|
||||
2. Typo-tolerance handles missing letters, extra letters, replaced letters, and swapped letters (at least)
|
||||
3. Words which are < `min_word_len_one_typo` are not typo tolerant
|
||||
4. Words which are >= `min_word_len_one_typo` but < `min_word_len_two_typos` can have one typo
|
||||
5. Words which are >= `min_word_len_two_typos` can have two typos
|
||||
6. A typo on the first letter of a word counts as two typos
|
||||
7. Phrases are not typo tolerant
|
||||
8. 2grams can have 1 typo if they are larger than `min_word_len_two_typos`
|
||||
9. 3grams are not typo tolerant (but they can be split into two words)
|
||||
10. The `typo` ranking rule assumes the role of the `words` ranking rule implicitly
|
||||
if `words` doesn't exist before it.
|
||||
11. The `typo` ranking rule places documents with the same number of typos in the same bucket
|
||||
12. Prefix tolerance costs nothing according to the typo ranking rule
|
||||
13. Split words cost 1 typo according to the typo ranking rule
|
||||
14. Synonyms cost nothing according to the typo ranking rule
|
||||
*/
|
||||
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "the quick brown fox jumps over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the quick brown foxes jump over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quick brown fax sends a letter to the dog"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "the quickest brownest fox jumps over the laziest dog"
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "a fox doesn't quack, that crown goes to the duck."
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "the quicker browner fox jumped over the lazier dog"
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "the extravagant fox skyrocketed over the languorous dog" // thanks thesaurus
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the quick brown fox jumps over the lazy"
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the quick brown fox jumps over the"
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quick brown fox jumps over"
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"text": "the quick brown fox jumps"
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"text": "the quick brown fox"
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"text": "the quick brown"
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"text": "the quick"
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"text": "netwolk interconections sunflawar"
|
||||
},
|
||||
{
|
||||
"id": 15,
|
||||
"text": "network interconnections sunflawer"
|
||||
},
|
||||
{
|
||||
"id": 16,
|
||||
"text": "network interconnection sunflower"
|
||||
},
|
||||
{
|
||||
"id": 17,
|
||||
"text": "network interconnection sun flower"
|
||||
},
|
||||
{
|
||||
"id": 18,
|
||||
"text": "network interconnection sunflowering"
|
||||
},
|
||||
{
|
||||
"id": 19,
|
||||
"text": "network interconnection sun flowering"
|
||||
},
|
||||
{
|
||||
"id": 20,
|
||||
"text": "network interconnection sunflowar"
|
||||
},
|
||||
{
|
||||
"id": 21,
|
||||
"text": "the fast brownish fox jumps over the lackadaisical dog"
|
||||
},
|
||||
{
|
||||
"id": 22,
|
||||
"text": "the quick brown fox jumps over the lackadaisical dog"
|
||||
},
|
||||
{
|
||||
"id": 23,
|
||||
"text": "the quivk brown fox jumps over the lazy dog"
|
||||
},
|
||||
{
|
||||
"id": 24,
|
||||
"tolerant_text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 25,
|
||||
"tolerant_text": "the quivk brown fox jumps over the lazy dog",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_no_typo() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_autorize_typos(false);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_default_typo() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let ot = index.min_word_len_one_typo(&txn).unwrap();
|
||||
let tt = index.min_word_len_two_typos(&txn).unwrap();
|
||||
insta::assert_debug_snapshot!(ot, @"5");
|
||||
insta::assert_debug_snapshot!(tt, @"9");
|
||||
|
||||
// 0 typo
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 23]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[],
|
||||
[],
|
||||
]
|
||||
"###);
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// 1 typo on one word, replaced letter
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quack brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// 1 typo on one word, missing letter, extra letter
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quicest brownest fox jummps over the laziest dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quickest brownest fox jumps over the laziest dog\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_phrase_no_typo_allowed() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the \"quick brewn\" fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @"[]");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_typo_exact_word() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_exact_words(
|
||||
["quick", "quack", "sunflower"].iter().map(ToString::to_string).collect(),
|
||||
)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let ot = index.min_word_len_one_typo(&txn).unwrap();
|
||||
let tt = index.min_word_len_two_typos(&txn).unwrap();
|
||||
insta::assert_debug_snapshot!(ot, @"5");
|
||||
insta::assert_debug_snapshot!(tt, @"9");
|
||||
|
||||
// don't match quivk
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// Don't match quick
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quack brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[]");
|
||||
|
||||
// words not in exact_words (quicest, jummps) have normal typo handling
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("the quicest brownest fox jummps over the laziest dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quickest brownest fox jumps over the laziest dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// exact words do not disable prefix (sunflowering OK, but no sunflowar)
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("network interconnection sunflower");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[16, 17, 18]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"network interconnection sunflower\"",
|
||||
"\"network interconnection sun flower\"",
|
||||
"\"network interconnection sunflowering\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_typo_exact_attribute() {
|
||||
let index = create_index();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_exact_attributes(["text"].iter().map(ToString::to_string).collect());
|
||||
s.set_searchable_fields(
|
||||
["text", "tolerant_text"].iter().map(ToString::to_string).collect(),
|
||||
);
|
||||
s.set_exact_words(["quivk"].iter().map(ToString::to_string).collect())
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let ot = index.min_word_len_one_typo(&txn).unwrap();
|
||||
let tt = index.min_word_len_two_typos(&txn).unwrap();
|
||||
insta::assert_debug_snapshot!(ot, @"5");
|
||||
insta::assert_debug_snapshot!(tt, @"9");
|
||||
|
||||
// Exact match returns both exact attributes and tolerant ones.
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 24, 25]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"__does_not_exist__",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
let texts = collect_field_values(&index, &txn, "tolerant_text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"__does_not_exist__",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// 1 typo only returns the tolerant attribute
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quidk brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[24, 25]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[],
|
||||
[],
|
||||
]
|
||||
"###);
|
||||
let texts = collect_field_values(&index, &txn, "tolerant_text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// combine with exact words
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quivk brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[23, 25]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @r###"
|
||||
[
|
||||
[],
|
||||
[],
|
||||
]
|
||||
"###);
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
"__does_not_exist__",
|
||||
]
|
||||
"###);
|
||||
let texts = collect_field_values(&index, &txn, "tolerant_text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"__does_not_exist__",
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// No result in tolerant attribute
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quicest brownest fox jummps over the laziest dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[]");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ngram_typos() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the extra lagant fox skyrocketed over the languorous dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the extravagant fox skyrocketed over the languorous dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the ex tra lagant fox skyrocketed over the languorous dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"), @"[]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @"[]");
|
||||
}
|
||||
#[test]
|
||||
fn test_typo_ranking_rule_not_preceded_by_words_ranking_rule() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids: ids_1, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{ids_1:?}"), @"[0, 23, 7, 8, 9, 22, 10, 11, 1, 2, 12, 13, 4, 3, 5, 6, 21]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &ids_1);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps over the lackadaisical dog\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown foxes jump over the lazy dog\"",
|
||||
"\"the quick brown fax sends a letter to the dog\"",
|
||||
"\"the quick brown\"",
|
||||
"\"the quick\"",
|
||||
"\"a fox doesn't quack, that crown goes to the duck.\"",
|
||||
"\"the quickest brownest fox jumps over the laziest dog\"",
|
||||
"\"the quicker browner fox jumped over the lazier dog\"",
|
||||
"\"the extravagant fox skyrocketed over the languorous dog\"",
|
||||
"\"the fast brownish fox jumps over the lackadaisical dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
let SearchResult { documents_ids: ids_2, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{ids_2:?}"), @"[0, 23, 7, 8, 9, 22, 10, 11, 1, 2, 12, 13, 4, 3, 5, 6, 21]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
|
||||
assert_eq!(ids_1, ids_2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_typo_bucketing() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
// First do the search with just the Words ranking rule
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("network interconnection sunflower");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[14, 15, 16, 17, 18, 20]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"netwolk interconections sunflawar\"",
|
||||
"\"network interconnections sunflawer\"",
|
||||
"\"network interconnection sunflower\"",
|
||||
"\"network interconnection sun flower\"",
|
||||
"\"network interconnection sunflowering\"",
|
||||
"\"network interconnection sunflowar\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
// Then with the typo ranking rule
|
||||
drop(txn);
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Typo]);
|
||||
})
|
||||
.unwrap();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("network interconnection sunflower");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[16, 18, 17, 20, 15, 14]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"network interconnection sunflower\"",
|
||||
"\"network interconnection sunflowering\"",
|
||||
"\"network interconnection sun flower\"",
|
||||
"\"network interconnection sunflowar\"",
|
||||
"\"network interconnections sunflawer\"",
|
||||
"\"netwolk interconections sunflawar\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("network interconnection sun flower");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[17, 19, 16, 18, 20, 15]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"network interconnection sun flower\"",
|
||||
"\"network interconnection sun flowering\"",
|
||||
"\"network interconnection sunflower\"",
|
||||
"\"network interconnection sunflowering\"",
|
||||
"\"network interconnection sunflowar\"",
|
||||
"\"network interconnections sunflawer\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_typo_synonyms() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Typo]);
|
||||
|
||||
let mut synonyms = BTreeMap::new();
|
||||
synonyms.insert("lackadaisical".to_owned(), vec!["lazy".to_owned()]);
|
||||
synonyms.insert("fast brownish".to_owned(), vec!["quick brown".to_owned()]);
|
||||
|
||||
s.set_synonyms(synonyms);
|
||||
})
|
||||
.unwrap();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the quick brown fox jumps over the lackadaisical dog");
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[0, 22, 23]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lackadaisical dog\"",
|
||||
"\"the quivk brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
s.query("the fast brownish fox jumps over the lackadaisical dog");
|
||||
|
||||
// The interaction of ngrams + synonyms means that the multi-word synonyms end up having a typo cost.
|
||||
// This is probably not what we want.
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[21, 0, 22]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the fast brownish fox jumps over the lackadaisical dog\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lackadaisical dog\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
127
crates/milli/src/search/new/tests/typo_proximity.rs
Normal file
127
crates/milli/src/search/new/tests/typo_proximity.rs
Normal file
@ -0,0 +1,127 @@
|
||||
/*!
|
||||
This module tests the interactions between the typo and proximity ranking rules.
|
||||
|
||||
The typo ranking rule should transform the query graph such that it only contains
|
||||
the combinations of word derivations that it used to compute its bucket.
|
||||
|
||||
The proximity ranking rule should then look for proximities only between those specific derivations.
|
||||
For example, given the search query `beautiful summer` and the dataset:
|
||||
```text
|
||||
{ "id": 0, "text": "beautigul summer...... beautiful day in the summer" }
|
||||
{ "id": 1, "text": "beautiful summer" }
|
||||
```
|
||||
Then the document with id `1` should be returned before `0`.
|
||||
The proximity ranking rule is not allowed to look for the proximity between `beautigul` and `summer`
|
||||
because the typo ranking rule before it only used the derivation `beautiful`.
|
||||
*/
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Typo, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
// trap explained in the module documentation
|
||||
{
|
||||
"id": 0,
|
||||
"text": "beautigul summer. beautiful x y z summer"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "beautiful summer"
|
||||
},
|
||||
// the next 2 documents set up a more complicated trap
|
||||
// with the query `beautiful summer`, we will have:
|
||||
// 1. documents with no typos, id 0 and 1
|
||||
// 2. documents with 1 typos: id 2 and 3, those are interpreted as EITHER
|
||||
// - id 2: "beautigul + summer" ; OR
|
||||
// - id 3: "beautiful + sommer"
|
||||
// To sort these two documents, the proximity ranking rule must use only the
|
||||
// word pairs: `beautigul -- summer` and `beautiful -- sommer` even though
|
||||
// all variations of `beautiful` and `sommer` were used by the typo ranking rule.
|
||||
{
|
||||
"id": 2,
|
||||
"text": "beautigul sommer. beautigul x summer"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "beautiful sommer"
|
||||
},
|
||||
// The next two documents lay out an even more complex trap.
|
||||
// With the user query `delicious sweet dessert`, the typo ranking rule will return one bucket of:
|
||||
// - id 4: delicitous + sweet + dessert
|
||||
// - id 5: beautiful + sweet + desgert
|
||||
// The word pairs that the proximity ranking rules is allowed to use are
|
||||
// EITHER:
|
||||
// delicitous -- sweet AND sweet -- dessert
|
||||
// OR
|
||||
// delicious -- sweet AND sweet -- desgert
|
||||
// So the word pair to use for the terms `summer` and `dessert` depend on the
|
||||
// word pairs explored before them.
|
||||
{
|
||||
"id": 4,
|
||||
"text": "delicitous. sweet. dessert. delicitous sweet desgert",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "delicious. sweet desgert. delicious sweet desgert",
|
||||
},
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_trap_basic_and_complex1() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("beautiful summer");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[1, 0, 3, 2]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"beautiful summer\"",
|
||||
"\"beautigul summer. beautiful x y z summer\"",
|
||||
"\"beautiful sommer\"",
|
||||
"\"beautigul sommer. beautigul x summer\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_trap_complex2() {
|
||||
let index = create_index();
|
||||
let txn = index.read_txn().unwrap();
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.query("delicious sweet dessert");
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[5, 4]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"delicious. sweet desgert. delicious sweet desgert\"",
|
||||
"\"delicitous. sweet. dessert. delicitous sweet desgert\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
460
crates/milli/src/search/new/tests/words_tms.rs
Normal file
460
crates/milli/src/search/new/tests/words_tms.rs
Normal file
@ -0,0 +1,460 @@
|
||||
/*!
|
||||
This module tests the following properties:
|
||||
|
||||
1. The `last` term matching strategy starts removing terms from the query
|
||||
starting from the end if no more results match it.
|
||||
2. Phrases are never deleted by the `last` term matching strategy
|
||||
3. Duplicate words don't affect the ranking of a document according to the `words` ranking rule
|
||||
4. The proximity of the first and last word of a phrase to its adjacent terms is taken into
|
||||
account by the proximity ranking rule.
|
||||
5. Unclosed double quotes still make a phrase
|
||||
6. The `all` term matching strategy does not remove any term from the query
|
||||
7. The search is capable of returning no results if no documents match the query
|
||||
*/
|
||||
|
||||
use crate::index::tests::TempIndex;
|
||||
use crate::search::new::tests::collect_field_values;
|
||||
use crate::{Criterion, Search, SearchResult, TermsMatchingStrategy};
|
||||
|
||||
fn create_index() -> TempIndex {
|
||||
let index = TempIndex::new();
|
||||
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_primary_key("id".to_owned());
|
||||
s.set_searchable_fields(vec!["text".to_owned()]);
|
||||
s.set_criteria(vec![Criterion::Words]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
index
|
||||
.add_documents(documents!([
|
||||
{
|
||||
"id": 0,
|
||||
"text": "",
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"text": "the",
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"text": "the quick",
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"text": "the quick brown",
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"text": "the quick brown fox",
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"text": "the quick brown fox jumps",
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"text": "the quick brown fox jumps over",
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"text": "the quick brown fox jumps over the",
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"text": "the quick brown fox jumps over the lazy",
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"text": "the quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"text": "the brown quick fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"text": "the quick brown fox talks to the lazy and slow dog",
|
||||
},
|
||||
{
|
||||
"id": 12,
|
||||
"text": "the quick brown fox talks to the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 13,
|
||||
"text": "the mighty and quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 14,
|
||||
"text": "the great quick brown fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 15,
|
||||
"text": "this quick brown and very scary fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 16,
|
||||
"text": "this quick brown and scary fox jumps over the lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 17,
|
||||
"text": "the quick brown fox jumps over the really lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 18,
|
||||
"text": "the brown quick fox jumps over the really lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 19,
|
||||
"text": "the brown quick fox immediately jumps over the really lazy dog",
|
||||
},
|
||||
{
|
||||
"id": 20,
|
||||
"text": "the brown quick fox immediately jumps over the really lazy blue dog",
|
||||
},
|
||||
{
|
||||
"id": 21,
|
||||
"text": "the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.",
|
||||
},
|
||||
{
|
||||
"id": 22,
|
||||
"text": "the, quick, brown, fox, jumps, over, the, lazy, dog",
|
||||
}
|
||||
]))
|
||||
.unwrap();
|
||||
index
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_words_tms_last_simple() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// 6 and 7 have the same score because "the" appears twice
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 10, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 8, 6, 7, 5, 4, 11, 12, 3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox jumps over the lazy dog\"",
|
||||
"\"the mighty and quick brown fox jumps over the lazy dog\"",
|
||||
"\"the great quick brown fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and very scary fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and scary fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the brown quick fox jumps over the really lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy blue dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the, quick, brown, fox, jumps, over, the, lazy, dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown fox talks to the lazy and slow dog\"",
|
||||
"\"the quick brown fox talks to the lazy dog\"",
|
||||
"\"the quick brown\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("extravagant the quick brown fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[]");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_words_tms_last_phrase() {
|
||||
let index = create_index();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("\"the quick brown fox\" jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// "The quick brown fox" is a phrase, not deleted by this term matching strategy
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 17, 21, 8, 6, 7, 5, 4, 11, 12]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown fox talks to the lazy and slow dog\"",
|
||||
"\"the quick brown fox talks to the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("\"the quick brown fox\" jumps over the \"lazy\" dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// "lazy" is a phrase, not deleted by this term matching strategy
|
||||
// but words before it can be deleted
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 17, 21, 8, 11, 12]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox talks to the lazy and slow dog\"",
|
||||
"\"the quick brown fox talks to the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("\"the quick brown fox jumps over the lazy dog\"");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// The whole query is a phrase, no terms are removed
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[Words(Words { matching_words: 9, max_matching_words: 9 })]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("\"the quick brown fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// The whole query is still a phrase, even without closing quotes, so no terms are removed
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[[Words(Words { matching_words: 9, max_matching_words: 9 })]]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_words_proximity_tms_last_simple() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// 7 is better than 6 because of the proximity between "the" and its surrounding terms
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 21, 14, 17, 13, 10, 18, 16, 19, 15, 20, 22, 8, 7, 6, 5, 4, 11, 12, 3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the great quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the mighty and quick brown fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox jumps over the really lazy dog\"",
|
||||
"\"this quick brown and scary fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy dog\"",
|
||||
"\"this quick brown and very scary fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy blue dog\"",
|
||||
"\"the, quick, brown, fox, jumps, over, the, lazy, dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown fox talks to the lazy and slow dog\"",
|
||||
"\"the quick brown fox talks to the lazy dog\"",
|
||||
"\"the quick brown\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the brown quick fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// 10 is better than 9 because of the proximity between "quick" and "brown"
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[10, 18, 19, 9, 20, 21, 14, 17, 13, 15, 16, 22, 8, 7, 6, 5, 4, 11, 12, 3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the brown quick fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox jumps over the really lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy blue dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the great quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the mighty and quick brown fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and very scary fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and scary fox jumps over the lazy dog\"",
|
||||
"\"the, quick, brown, fox, jumps, over, the, lazy, dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown fox talks to the lazy and slow dog\"",
|
||||
"\"the quick brown fox talks to the lazy dog\"",
|
||||
"\"the quick brown\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_words_proximity_tms_last_phrase() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the \"quick brown\" fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// "quick brown" is a phrase. The proximity of its first and last words
|
||||
// to their adjacent query words should be taken into account
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 21, 14, 17, 13, 16, 15, 8, 7, 6, 5, 4, 11, 12, 3]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the great quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the mighty and quick brown fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and scary fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and very scary fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
"\"the quick brown fox\"",
|
||||
"\"the quick brown fox talks to the lazy and slow dog\"",
|
||||
"\"the quick brown fox talks to the lazy dog\"",
|
||||
"\"the quick brown\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the \"quick brown\" \"fox jumps\" over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::Last);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
// "quick brown" is a phrase. The proximity of its first and last words
|
||||
// to their adjacent query words should be taken into account.
|
||||
// The same applies to `fox jumps`.
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 21, 14, 17, 13, 16, 15, 8, 7, 6, 5]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the great quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the mighty and quick brown fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and scary fox jumps over the lazy dog\"",
|
||||
"\"this quick brown and very scary fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the lazy\"",
|
||||
"\"the quick brown fox jumps over the\"",
|
||||
"\"the quick brown fox jumps over\"",
|
||||
"\"the quick brown fox jumps\"",
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_words_tms_all() {
|
||||
let index = create_index();
|
||||
index
|
||||
.update_settings(|s| {
|
||||
s.set_criteria(vec![Criterion::Words, Criterion::Proximity]);
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let txn = index.read_txn().unwrap();
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("the quick brown fox jumps over the lazy dog");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 21, 14, 17, 13, 10, 18, 16, 19, 15, 20, 22]");
|
||||
insta::assert_snapshot!(format!("{document_scores:#?}"));
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @r###"
|
||||
[
|
||||
"\"the quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown. quick brown fox. brown fox jumps. fox jumps over. over the lazy. the lazy dog.\"",
|
||||
"\"the great quick brown fox jumps over the lazy dog\"",
|
||||
"\"the quick brown fox jumps over the really lazy dog\"",
|
||||
"\"the mighty and quick brown fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox jumps over the really lazy dog\"",
|
||||
"\"this quick brown and scary fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy dog\"",
|
||||
"\"this quick brown and very scary fox jumps over the lazy dog\"",
|
||||
"\"the brown quick fox immediately jumps over the really lazy blue dog\"",
|
||||
"\"the, quick, brown, fox, jumps, over, the, lazy, dog\"",
|
||||
]
|
||||
"###);
|
||||
|
||||
let mut s = Search::new(&txn, &index);
|
||||
s.query("extravagant");
|
||||
s.terms_matching_strategy(TermsMatchingStrategy::All);
|
||||
s.scoring_strategy(crate::score_details::ScoringStrategy::Detailed);
|
||||
let SearchResult { documents_ids, document_scores, .. } = s.execute().unwrap();
|
||||
|
||||
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[]");
|
||||
insta::assert_snapshot!(format!("{document_scores:?}"), @"[]");
|
||||
let texts = collect_field_values(&index, &txn, "text", &documents_ids);
|
||||
insta::assert_debug_snapshot!(texts, @"[]");
|
||||
}
|
||||
Reference in New Issue
Block a user