snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-30 00:55:00 +08:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Prevent the exactness ranking rule from removing random words

Browse Source 
Make it strictly follow the term matching strategy
This commit is contained in:
Loïc Lecrenier 2023-04-25 17:52:42 +02:00
parent d3a94e8b25
commit 3421125a55
3 changed files with 61 additions and 145 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

87
milli/src/search/new/mod.rs
View File

@ -51,7 +51,6 @@ use resolve_query_graph::compute_query_graph_docids;
use sort::Sort; use sort::Sort;
use self::interner::Interned; use self::interner::Interned;
use self::query_term::ExactTerm;
/// A structure used throughout the execution of a search query. /// A structure used throughout the execution of a search query.
pub struct SearchContext<'ctx> { pub struct SearchContext<'ctx> {
@ -120,52 +119,13 @@ fn resolve_maximally_reduced_query_graph(
Ok(docids) Ok(docids)
} }
fn resolve_docids_containing_any_exact_word(
ctx: &mut SearchContext,
universe: &RoaringBitmap,
query_graph: &QueryGraph,
) -> Result<RoaringBitmap> {
let mut docids = RoaringBitmap::new();
for (_, node) in query_graph.nodes.iter() {
let term = match &node.data {
query_graph::QueryNodeData::Term(term) => term,
query_graph::QueryNodeData::Deleted
| query_graph::QueryNodeData::Start
| query_graph::QueryNodeData::End => {
continue;
}
};
if term.term_ids.len() != 1 {
continue;
}
let Some(exact_term) = term.term_subset.exact_term(ctx) else {
continue
};
let exact_term_docids = match exact_term {
ExactTerm::Phrase(phrase) => ctx.get_phrase_docids(phrase)? & universe,
ExactTerm::Word(word) => {
if let Some(word_docids) = ctx.word_docids(Word::Original(word))? {
word_docids & universe
} else {
continue;
}
}
};
docids |= exact_term_docids;
}
Ok(docids)
}
fn resolve_universe( fn resolve_universe(
ctx: &mut SearchContext, ctx: &mut SearchContext,
initial_universe: &RoaringBitmap, initial_universe: &RoaringBitmap,
query_graph: &QueryGraph, query_graph: &QueryGraph,
method: UniverseResolutionMethod,
matching_strategy: TermsMatchingStrategy, matching_strategy: TermsMatchingStrategy,
logger: &mut dyn SearchLogger<QueryGraph>, logger: &mut dyn SearchLogger<QueryGraph>,
) -> Result<RoaringBitmap> { ) -> Result<RoaringBitmap> {
match method {
UniverseResolutionMethod::TermMatchingStrategyOnly => {
resolve_maximally_reduced_query_graph( resolve_maximally_reduced_query_graph(
ctx, ctx,
initial_universe, initial_universe,
@ -173,20 +133,6 @@ fn resolve_universe(
matching_strategy, matching_strategy,
logger, logger,
) )
}
UniverseResolutionMethod::TermMatchingStrategyAndExactness => {
let mut resolved_universe = resolve_maximally_reduced_query_graph(
ctx,
initial_universe,
query_graph,
matching_strategy,
logger,
)?;
resolved_universe |=
resolve_docids_containing_any_exact_word(ctx, initial_universe, query_graph)?;
Ok(resolved_universe)
}
}
} }
/// Return the list of initialised ranking rules to be used for a placeholder search. /// Return the list of initialised ranking rules to be used for a placeholder search.
@ -233,17 +179,12 @@ fn get_ranking_rules_for_placeholder_search<'ctx>(
Ok(ranking_rules) Ok(ranking_rules)
} }
enum UniverseResolutionMethod {
TermMatchingStrategyOnly,
TermMatchingStrategyAndExactness,
}
/// Return the list of initialised ranking rules to be used for a query graph search. /// Return the list of initialised ranking rules to be used for a query graph search.
fn get_ranking_rules_for_query_graph_search<'ctx>( fn get_ranking_rules_for_query_graph_search<'ctx>(
ctx: &SearchContext<'ctx>, ctx: &SearchContext<'ctx>,
sort_criteria: &Option<Vec<AscDesc>>, sort_criteria: &Option<Vec<AscDesc>>,
terms_matching_strategy: TermsMatchingStrategy, terms_matching_strategy: TermsMatchingStrategy,
) -> Result<(Vec<BoxRankingRule<'ctx, QueryGraph>>, UniverseResolutionMethod)> { ) -> Result<Vec<BoxRankingRule<'ctx, QueryGraph>>> {
// query graph search // query graph search
let mut words = false; let mut words = false;
let mut typo = false; let mut typo = false;
@ -254,14 +195,15 @@ fn get_ranking_rules_for_query_graph_search<'ctx>(
let mut asc = HashSet::new(); let mut asc = HashSet::new();
let mut desc = HashSet::new(); let mut desc = HashSet::new();
let mut universe_resolution_method = UniverseResolutionMethod::TermMatchingStrategyOnly;
let mut ranking_rules: Vec<BoxRankingRule<QueryGraph>> = vec![]; let mut ranking_rules: Vec<BoxRankingRule<QueryGraph>> = vec![];
let settings_ranking_rules = ctx.index.criteria(ctx.txn)?; let settings_ranking_rules = ctx.index.criteria(ctx.txn)?;
for rr in settings_ranking_rules { for rr in settings_ranking_rules {
// Add Words before any of: typo, proximity, attribute // Add Words before any of: typo, proximity, attribute
match rr { match rr {
crate::Criterion::Typo | crate::Criterion::Attribute | crate::Criterion::Proximity => { crate::Criterion::Typo
| crate::Criterion::Attribute
| crate::Criterion::Proximity
| crate::Criterion::Exactness => {
if !words { if !words {
ranking_rules.push(Box::new(Words::new(terms_matching_strategy))); ranking_rules.push(Box::new(Words::new(terms_matching_strategy)));
words = true; words = true;
@ -313,11 +255,6 @@ fn get_ranking_rules_for_query_graph_search<'ctx>(
ranking_rules.push(Box::new(ExactAttribute::new())); ranking_rules.push(Box::new(ExactAttribute::new()));
ranking_rules.push(Box::new(Exactness::new())); ranking_rules.push(Box::new(Exactness::new()));
exactness = true; exactness = true;
if !words {
universe_resolution_method =
UniverseResolutionMethod::TermMatchingStrategyAndExactness;
}
} }
crate::Criterion::Asc(field_name) => { crate::Criterion::Asc(field_name) => {
if asc.contains(&field_name) { if asc.contains(&field_name) {
@ -335,7 +272,7 @@ fn get_ranking_rules_for_query_graph_search<'ctx>(
} }
} }
} }
Ok((ranking_rules, universe_resolution_method)) Ok(ranking_rules)
} }
fn resolve_sort_criteria<'ctx, Query: RankingRuleQueryTrait>( fn resolve_sort_criteria<'ctx, Query: RankingRuleQueryTrait>(
@ -417,17 +354,11 @@ pub fn execute_search(
check_sort_criteria(ctx, sort_criteria.as_ref())?; check_sort_criteria(ctx, sort_criteria.as_ref())?;
let (ranking_rules, universe_resolution_method) = let ranking_rules =
get_ranking_rules_for_query_graph_search(ctx, sort_criteria, terms_matching_strategy)?; get_ranking_rules_for_query_graph_search(ctx, sort_criteria, terms_matching_strategy)?;
universe = resolve_universe( universe =
ctx, resolve_universe(ctx, &universe, &graph, terms_matching_strategy, query_graph_logger)?;
&universe,
&graph,
universe_resolution_method,
terms_matching_strategy,
query_graph_logger,
)?;
bucket_sort(ctx, ranking_rules, &graph, &universe, from, length, query_graph_logger)? bucket_sort(ctx, ranking_rules, &graph, &universe, from, length, query_graph_logger)?
} else { } else {

11
milli/src/search/new/ranking_rule_graph/exactness/mod.rs
View File

@ -3,13 +3,14 @@ use roaring::RoaringBitmap;
use super::{ComputedCondition, RankingRuleGraphTrait}; use super::{ComputedCondition, RankingRuleGraphTrait};
use crate::search::new::interner::{DedupInterner, Interned}; use crate::search::new::interner::{DedupInterner, Interned};
use crate::search::new::query_term::{ExactTerm, LocatedQueryTermSubset}; use crate::search::new::query_term::{ExactTerm, LocatedQueryTermSubset};
use crate::search::new::resolve_query_graph::compute_query_term_subset_docids;
use crate::search::new::Word; use crate::search::new::Word;
use crate::{Result, SearchContext}; use crate::{Result, SearchContext};
#[derive(Clone, PartialEq, Eq, Hash)] #[derive(Clone, PartialEq, Eq, Hash)]
pub enum ExactnessCondition { pub enum ExactnessCondition {
ExactInAttribute(LocatedQueryTermSubset), ExactInAttribute(LocatedQueryTermSubset),
Skip(LocatedQueryTermSubset), Any(LocatedQueryTermSubset),
} }
pub enum ExactnessGraph {} pub enum ExactnessGraph {}
@ -54,7 +55,11 @@ impl RankingRuleGraphTrait for ExactnessGraph {
end_term_subset.term_subset.make_mandatory(); end_term_subset.term_subset.make_mandatory();
(compute_docids(ctx, dest_node, universe)?, end_term_subset) (compute_docids(ctx, dest_node, universe)?, end_term_subset)
} }
ExactnessCondition::Skip(dest_node) => (universe.clone(), dest_node.clone()), ExactnessCondition::Any(dest_node) => {
let docids =
universe & compute_query_term_subset_docids(ctx, &dest_node.term_subset)?;
(docids, dest_node.clone())
}
}; };
Ok(ComputedCondition { Ok(ComputedCondition {
@ -74,7 +79,7 @@ impl RankingRuleGraphTrait for ExactnessGraph {
let exact_condition = ExactnessCondition::ExactInAttribute(dest_node.clone()); let exact_condition = ExactnessCondition::ExactInAttribute(dest_node.clone());
let exact_condition = conditions_interner.insert(exact_condition); let exact_condition = conditions_interner.insert(exact_condition);
let skip_condition = ExactnessCondition::Skip(dest_node.clone()); let skip_condition = ExactnessCondition::Any(dest_node.clone());
let skip_condition = conditions_interner.insert(skip_condition); let skip_condition = conditions_interner.insert(skip_condition);
Ok(vec![(0, exact_condition), (dest_node.term_ids.len() as u32, skip_condition)]) Ok(vec![(0, exact_condition), (dest_node.term_ids.len() as u32, skip_condition)])

94
milli/src/search/new/tests/exactness.rs
View File

@ -6,19 +6,17 @@ This module tests the following properties about the exactness ranking rule:
2. documents which have an attribute which start with 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 3. documents which contain the most exact words from the query
- the set of all candidates when `exactness` precedes `word` is the union of: - the `exactness` ranking rule must be preceded by the `words` ranking rule
1. the same set of candidates that would be returned normally
2. the set of documents that contain at least one exact word from the query
- if it is placed after `word`, then it will only sort documents by: - 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" 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" 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 3. those that contain the most exact words from the remaining query
- if it is followed by other ranking rules, then: - if it is followed by other graph-based ranking rules (`typo`, `proximity`, `attribute`).
1. `word` will not remove the exact terms matched by `exactness` Then these rules will only work with
2. graph-based ranking rules (`typo`, `proximity`, `attribute`) will only work with 1. the exact terms selected by `exactness
(1) the exact terms selected by `exactness` or (2) the full query term otherwise 2. the full query term otherwise
*/ */
use crate::{ use crate::{
@ -440,14 +438,14 @@ fn test_exactness_simple_ordered() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("the quick brown fox jumps over the lazy dog"); s.query("the quick brown fox jumps over the lazy dog");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 8, 6, 7, 5, 4, 3, 2, 1]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 8, 7, 6, 5, 4, 3, 2, 1]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"the quick brown 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 lazy\"",
"\"the quick brown fox jumps over\"",
"\"the quick brown fox jumps over the\"", "\"the quick brown fox jumps over the\"",
"\"the quick brown fox jumps over\"",
"\"the quick brown fox jumps\"", "\"the quick brown fox jumps\"",
"\"the quick brown fox\"", "\"the quick brown fox\"",
"\"the quick brown\"", "\"the quick brown\"",
@ -467,19 +465,17 @@ fn test_exactness_simple_reversed() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("the quick brown fox jumps over the lazy dog"); s.query("the quick brown fox jumps over the lazy dog");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 8, 7, 6, 5, 4, 3, 2, 1]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 8, 3, 4, 5, 6, 7]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"the quick brown fox jumps over the lazy dog\"", "\"the quick brown fox jumps over the lazy dog\"",
"\"quick brown fox jumps over the lazy dog\"", "\"quick brown fox jumps over the lazy dog\"",
"\"brown fox jumps over the lazy dog\"",
"\"fox jumps over the lazy dog\"",
"\"jumps over the lazy dog\"",
"\"over the lazy dog\"",
"\"the lazy dog\"", "\"the lazy dog\"",
"\"lazy dog\"", "\"over the lazy dog\"",
"\"dog\"", "\"jumps over the lazy dog\"",
"\"fox jumps over the lazy dog\"",
"\"brown fox jumps over the lazy dog\"",
] ]
"###); "###);
@ -487,19 +483,17 @@ fn test_exactness_simple_reversed() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("the quick brown fox jumps over the lazy dog"); s.query("the quick brown fox jumps over the lazy dog");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 8, 7, 6, 5, 4, 3, 2, 1]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[9, 8, 3, 4, 5, 6, 7]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"the quick brown fox jumps over the lazy dog\"", "\"the quick brown fox jumps over the lazy dog\"",
"\"quick brown fox jumps over the lazy dog\"", "\"quick brown fox jumps over the lazy dog\"",
"\"brown fox jumps over the lazy dog\"",
"\"fox jumps over the lazy dog\"",
"\"jumps over the lazy dog\"",
"\"over the lazy dog\"",
"\"the lazy dog\"", "\"the lazy dog\"",
"\"lazy dog\"", "\"over the lazy dog\"",
"\"dog\"", "\"jumps over the lazy dog\"",
"\"fox jumps over the lazy dog\"",
"\"brown fox jumps over the lazy dog\"",
] ]
"###); "###);
} }
@ -514,18 +508,16 @@ fn test_exactness_simple_random() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("the quick brown fox jumps over the lazy dog"); s.query("the quick brown fox jumps over the lazy dog");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[8, 7, 5, 6, 3, 4, 1, 2]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[8, 7, 4, 6, 3, 5]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"the jumps dog quick over brown lazy fox\"", "\"the jumps dog quick over brown lazy fox\"",
"\"the dog brown over jumps quick lazy\"", "\"the dog brown over jumps quick lazy\"",
"\"fox the lazy dog brown\"", "\"jump dog quick the\"",
"\"jump fox quick lazy the dog\"", "\"jump fox quick lazy the dog\"",
"\"brown the lazy\"", "\"brown the lazy\"",
"\"jump dog quick the\"", "\"fox the lazy dog brown\"",
"\"over\"",
"\"jump dog\"",
] ]
"###); "###);
} }
@ -540,17 +532,13 @@ fn test_exactness_attribute_starts_with_simple() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("this balcony"); s.query("this balcony");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 1, 0, 3, 4, 5, 6]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 1, 0]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"this balcony\"", "\"this balcony\"",
"\"this balcony is overlooking the sea\"", "\"this balcony is overlooking the sea\"",
"\"what a lovely view from this balcony, I love it\"", "\"what a lovely view from this balcony, I love it\"",
"\"over looking the sea is a beautiful balcony\"",
"\"a beautiful balcony is overlooking the sea\"",
"\"overlooking the sea is a beautiful balcony, I love it\"",
"\"overlooking the sea is a beautiful balcony\"",
] ]
"###); "###);
} }
@ -565,17 +553,14 @@ fn test_exactness_attribute_starts_with_phrase() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("\"overlooking the sea\" is a beautiful balcony"); s.query("\"overlooking the sea\" is a beautiful balcony");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6, 5, 4, 3, 1, 0, 2]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6, 5, 4, 1]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"overlooking the sea is a beautiful balcony\"", "\"overlooking the sea is a beautiful balcony\"",
"\"overlooking the sea is a beautiful balcony, I love it\"", "\"overlooking the sea is a beautiful balcony, I love it\"",
"\"a beautiful balcony is overlooking the sea\"", "\"a beautiful balcony is overlooking the sea\"",
"\"over looking the sea is a beautiful balcony\"",
"\"this balcony is overlooking the sea\"", "\"this balcony is overlooking the sea\"",
"\"what a lovely view from this balcony, I love it\"",
"\"this balcony\"",
] ]
"###); "###);
@ -583,7 +568,7 @@ fn test_exactness_attribute_starts_with_phrase() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("overlooking the sea is a beautiful balcony"); s.query("overlooking the sea is a beautiful balcony");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6, 5, 4, 3, 1, 0, 2, 7]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[6, 5, 4, 3, 1, 7]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
@ -592,8 +577,6 @@ fn test_exactness_attribute_starts_with_phrase() {
"\"a beautiful balcony is overlooking the sea\"", "\"a beautiful balcony is overlooking the sea\"",
"\"over looking the sea is a beautiful balcony\"", "\"over looking the sea is a beautiful balcony\"",
"\"this balcony is overlooking the sea\"", "\"this balcony is overlooking the sea\"",
"\"what a lovely view from this balcony, I love it\"",
"\"this balcony\"",
"\"overlooking\"", "\"overlooking\"",
] ]
"###); "###);
@ -609,19 +592,16 @@ fn test_exactness_all_candidates_with_typo() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("overlocking the sea is a beautiful balcony"); s.query("overlocking the sea is a beautiful balcony");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[3, 4, 5, 6, 1, 0, 2, 7]"); insta::assert_snapshot!(format!("{documents_ids:?}"), @"[4, 5, 6, 1, 7]");
let texts = collect_field_values(&index, &txn, "text", &documents_ids); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
// "overlooking" is returned here because the term matching strategy allows it // "overlooking" is returned here because the term matching strategy allows it
// but it has the worst exactness score (0 exact words) // but it has the worst exactness score (0 exact words)
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"over looking the sea is a beautiful balcony\"",
"\"a beautiful balcony is overlooking the sea\"", "\"a beautiful balcony is overlooking the sea\"",
"\"overlooking the sea is a beautiful balcony, I love it\"", "\"overlooking the sea is a beautiful balcony, I love it\"",
"\"overlooking the sea is a beautiful balcony\"", "\"overlooking the sea is a beautiful balcony\"",
"\"this balcony is overlooking the sea\"", "\"this balcony is overlooking the sea\"",
"\"what a lovely view from this balcony, I love it\"",
"\"this balcony\"",
"\"overlooking\"", "\"overlooking\"",
] ]
"###); "###);
@ -686,26 +666,26 @@ fn test_words_after_exactness() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("the quick brown fox jumps over the lazy dog"); s.query("the quick brown fox jumps over the lazy dog");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[19, 18, 16, 17, 9, 15, 8, 14, 6, 7, 13, 5, 4, 12, 3, 2, 1, 11]"); 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); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
[ [
"\"the quick brown 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 quick brown fox jumps over the\"",
"\"the quack briwn fox jlmps over the lazy dog\"", "\"the quack briwn fox jlmps over the lazy dog\"",
"\"the quick brown fox jumps\"", "\"the quick brown fox jumps over the lazy\"",
"\"the quack briwn fox jlmps over the lazy\"", "\"the quack briwn fox jlmps over the lazy\"",
"\"the quick brown fox\"", "\"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 quack briwn fox jlmps over the\"", "\"the quack briwn fox jlmps over the\"",
"\"the quick brown\"", "\"the quick brown fox jumps\"",
"\"the quack briwn fox jlmps\"", "\"the quack briwn fox jlmps\"",
"\"the quick brown fox\"",
"\"the quack briwn fox\"", "\"the quack briwn fox\"",
"\"the quick\"", "\"the quick brown\"",
"\"the quack briwn\"", "\"the quack briwn\"",
"\"the quick\"",
"\"the quack\"", "\"the quack\"",
"\"the\"", "\"the\"",
"\"the\"", "\"the\"",
@ -729,7 +709,7 @@ fn test_proximity_after_exactness() {
s.terms_matching_strategy(TermsMatchingStrategy::Last); s.terms_matching_strategy(TermsMatchingStrategy::Last);
s.query("the quick brown fox jumps over the lazy dog"); s.query("the quick brown fox jumps over the lazy dog");
let SearchResult { documents_ids, .. } = s.execute().unwrap(); let SearchResult { documents_ids, .. } = s.execute().unwrap();
insta::assert_snapshot!(format!("{documents_ids:?}"), @"[2, 1, 0, 5, 4, 3, 8, 6, 7]"); 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); let texts = collect_field_values(&index, &txn, "text", &documents_ids);
insta::assert_debug_snapshot!(texts, @r###" insta::assert_debug_snapshot!(texts, @r###"
@ -737,12 +717,12 @@ fn test_proximity_after_exactness() {
"\"the quick brown fox jumps over the lazy dog\"", "\"the quick brown fox jumps over the lazy dog\"",
"\"the quick brown fox jumps over the very lazy dog\"", "\"the quick brown fox jumps over the very lazy dog\"",
"\"lazy jumps dog brown quick the over fox the\"", "\"lazy jumps dog brown quick the over fox the\"",
"\"the quick brown fox over the lazy dog\"",
"\"the quick brown fox over the very lazy dog\"", "\"the quick brown fox over the very lazy dog\"",
"\"dog brown quick the over fox the lazy\"", "\"the quick brown fox over the lazy dog\"",
"\"the quick brown fox over\"", "\"the quick brown fox over\"",
"\"brown quick the over fox\"",
"\"the very quick brown fox over\"", "\"the very quick brown fox over\"",
"\"dog brown quick the over fox the lazy\"",
"\"brown quick the over fox\"",
] ]
"###); "###);