Make the matcher consume the search context

This commit is contained in:
ManyTheFish 2023-04-06 12:28:28 +02:00
parent 13b7c826c1
commit ebe23b04c9
2 changed files with 35 additions and 34 deletions

View File

@ -23,9 +23,9 @@ pub struct LocatedMatchingWords {
/// Structure created from a query tree /// Structure created from a query tree
/// referencing words that match the given query tree. /// referencing words that match the given query tree.
pub struct MatchingWords<'ctx> { pub struct MatchingWords {
word_interner: &'ctx DedupInterner<String>, word_interner: DedupInterner<String>,
phrase_interner: &'ctx DedupInterner<Phrase>, phrase_interner: DedupInterner<Phrase>,
phrases: Vec<LocatedMatchingPhrase>, phrases: Vec<LocatedMatchingPhrase>,
words: Vec<LocatedMatchingWords>, words: Vec<LocatedMatchingWords>,
} }
@ -82,8 +82,8 @@ fn extract_matching_terms(term: &QueryTerm) -> (Vec<Interned<Phrase>>, Vec<Inter
(matching_phrases, matching_words) (matching_phrases, matching_words)
} }
impl<'ctx> MatchingWords<'ctx> { impl MatchingWords {
pub fn new(ctx: &'ctx SearchContext, located_terms: Vec<LocatedQueryTerm>) -> Self { pub fn new(ctx: SearchContext, located_terms: Vec<LocatedQueryTerm>) -> Self {
let mut phrases = Vec::new(); let mut phrases = Vec::new();
let mut words = Vec::new(); let mut words = Vec::new();
@ -112,18 +112,18 @@ impl<'ctx> MatchingWords<'ctx> {
Self { Self {
phrases, phrases,
words, words,
word_interner: &ctx.word_interner, word_interner: ctx.word_interner,
phrase_interner: &ctx.phrase_interner, phrase_interner: ctx.phrase_interner,
} }
} }
/// Returns an iterator over terms that match or partially match the given token. /// Returns an iterator over terms that match or partially match the given token.
pub fn match_token<'b>(&'ctx self, token: &'b Token<'b>) -> MatchesIter<'ctx, 'b> { pub fn match_token<'a, 'b>(&'a self, token: &'b Token<'b>) -> MatchesIter<'a, 'b> {
MatchesIter { matching_words: self, phrases: Box::new(self.phrases.iter()), token } MatchesIter { matching_words: self, phrases: Box::new(self.phrases.iter()), token }
} }
/// Try to match the token with one of the located_words. /// Try to match the token with one of the located_words.
fn match_unique_words(&'ctx self, token: &Token) -> Option<MatchType<'ctx>> { fn match_unique_words<'a>(&'a self, token: &Token) -> Option<MatchType<'a>> {
for located_words in &self.words { for located_words in &self.words {
for word in &located_words.value { for word in &located_words.value {
let word = self.word_interner.get(*word); let word = self.word_interner.get(*word);
@ -148,7 +148,7 @@ impl<'ctx> MatchingWords<'ctx> {
/// Iterator over terms that match the given token, /// Iterator over terms that match the given token,
/// This allow to lazily evaluate matches. /// This allow to lazily evaluate matches.
pub struct MatchesIter<'a, 'b> { pub struct MatchesIter<'a, 'b> {
matching_words: &'a MatchingWords<'a>, matching_words: &'a MatchingWords,
phrases: Box<dyn Iterator<Item = &'a LocatedMatchingPhrase> + 'a>, phrases: Box<dyn Iterator<Item = &'a LocatedMatchingPhrase> + 'a>,
token: &'b Token<'b>, token: &'b Token<'b>,
} }
@ -268,7 +268,7 @@ pub(crate) mod tests {
let tokenizer = TokenizerBuilder::new().build(); let tokenizer = TokenizerBuilder::new().build();
let tokens = tokenizer.tokenize("split this world"); let tokens = tokenizer.tokenize("split this world");
let query_terms = located_query_terms_from_string(&mut ctx, tokens, None).unwrap(); let query_terms = located_query_terms_from_string(&mut ctx, tokens, None).unwrap();
let matching_words = MatchingWords::new(&ctx, query_terms); let matching_words = MatchingWords::new(ctx, query_terms);
assert_eq!( assert_eq!(
matching_words matching_words

View File

@ -14,17 +14,17 @@ const DEFAULT_HIGHLIGHT_PREFIX: &str = "<em>";
const DEFAULT_HIGHLIGHT_SUFFIX: &str = "</em>"; const DEFAULT_HIGHLIGHT_SUFFIX: &str = "</em>";
/// Structure used to build a Matcher allowing to customize formating tags. /// Structure used to build a Matcher allowing to customize formating tags.
pub struct MatcherBuilder<'a, 'ctx, A> { pub struct MatcherBuilder<'a, A> {
matching_words: MatchingWords<'ctx>, matching_words: MatchingWords,
tokenizer: Tokenizer<'a, 'a, A>, tokenizer: Tokenizer<'a, 'a, A>,
crop_marker: Option<String>, crop_marker: Option<String>,
highlight_prefix: Option<String>, highlight_prefix: Option<String>,
highlight_suffix: Option<String>, highlight_suffix: Option<String>,
} }
impl<'a, 'ctx, A> MatcherBuilder<'a, 'ctx, A> { impl<'a, A> MatcherBuilder<'a, A> {
pub fn new( pub fn new(
ctx: &'ctx SearchContext, ctx: SearchContext,
located_terms: Vec<LocatedQueryTerm>, located_terms: Vec<LocatedQueryTerm>,
tokenizer: Tokenizer<'a, 'a, A>, tokenizer: Tokenizer<'a, 'a, A>,
) -> Self { ) -> Self {
@ -112,7 +112,7 @@ pub struct MatchBounds {
/// and format the source string, returning a highlighted and cropped sub-string. /// and format the source string, returning a highlighted and cropped sub-string.
pub struct Matcher<'t, 'm, A> { pub struct Matcher<'t, 'm, A> {
text: &'t str, text: &'t str,
matching_words: &'m MatchingWords<'m>, matching_words: &'m MatchingWords,
tokenizer: &'m Tokenizer<'m, 'm, A>, tokenizer: &'m Tokenizer<'m, 'm, A>,
crop_marker: &'m str, crop_marker: &'m str,
highlight_prefix: &'m str, highlight_prefix: &'m str,
@ -509,11 +509,11 @@ mod tests {
use super::super::located_query_terms_from_string; use super::super::located_query_terms_from_string;
use super::*; use super::*;
impl<'a, 'ctx> MatcherBuilder<'a, 'ctx, &[u8]> { impl<'a, 'ctx> MatcherBuilder<'a, &[u8]> {
pub fn new_test(ctx: &'ctx mut SearchContext, query: &'a str) -> Self { pub fn new_test(mut ctx: SearchContext, query: &'a str) -> Self {
let tokenizer = TokenizerBuilder::new().build(); let tokenizer = TokenizerBuilder::new().build();
let tokens = tokenizer.tokenize(query); let tokens = tokenizer.tokenize(query);
let query_terms = located_query_terms_from_string(ctx, tokens, None).unwrap(); let query_terms = located_query_terms_from_string(&mut ctx, tokens, None).unwrap();
Self::new(ctx, query_terms, TokenizerBuilder::new().build()) Self::new(ctx, query_terms, TokenizerBuilder::new().build())
} }
} }
@ -522,8 +522,8 @@ mod tests {
fn format_identity() { fn format_identity() {
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(&mut ctx, "split the world"); let builder = MatcherBuilder::new_test(ctx, "split the world");
let format_options = FormatOptions { highlight: false, crop: None }; let format_options = FormatOptions { highlight: false, crop: None };
@ -550,8 +550,8 @@ mod tests {
fn format_highlight() { fn format_highlight() {
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(&mut ctx, "split the world"); let builder = MatcherBuilder::new_test(ctx, "split the world");
let format_options = FormatOptions { highlight: true, crop: None }; let format_options = FormatOptions { highlight: true, crop: None };
@ -594,8 +594,8 @@ mod tests {
fn highlight_unicode() { fn highlight_unicode() {
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(&mut ctx, "world"); let builder = MatcherBuilder::new_test(ctx, "world");
let format_options = FormatOptions { highlight: true, crop: None }; let format_options = FormatOptions { highlight: true, crop: None };
// Text containing prefix match. // Text containing prefix match.
@ -616,7 +616,8 @@ mod tests {
@"<em>Ŵôřlḑ</em>" @"<em>Ŵôřlḑ</em>"
); );
let builder = MatcherBuilder::new_test(&mut ctx, "westfali"); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(ctx, "westfali");
let format_options = FormatOptions { highlight: true, crop: None }; let format_options = FormatOptions { highlight: true, crop: None };
// Text containing unicode match. // Text containing unicode match.
@ -633,8 +634,8 @@ mod tests {
fn format_crop() { fn format_crop() {
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(&mut ctx, "split the world"); let builder = MatcherBuilder::new_test(ctx, "split the world");
let format_options = FormatOptions { highlight: false, crop: Some(10) }; let format_options = FormatOptions { highlight: false, crop: Some(10) };
@ -731,8 +732,8 @@ mod tests {
fn format_highlight_crop() { fn format_highlight_crop() {
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(&mut ctx, "split the world"); let builder = MatcherBuilder::new_test(ctx, "split the world");
let format_options = FormatOptions { highlight: true, crop: Some(10) }; let format_options = FormatOptions { highlight: true, crop: Some(10) };
@ -794,8 +795,8 @@ mod tests {
//! testing: https://github.com/meilisearch/specifications/pull/120#discussion_r836536295 //! testing: https://github.com/meilisearch/specifications/pull/120#discussion_r836536295
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let builder = MatcherBuilder::new_test(&mut ctx, "split the world"); let builder = MatcherBuilder::new_test(ctx, "split the world");
let text = "void void split the world void void."; let text = "void void split the world void void.";
@ -831,8 +832,8 @@ mod tests {
fn partial_matches() { fn partial_matches() {
let temp_index = temp_index_with_documents(); let temp_index = temp_index_with_documents();
let rtxn = temp_index.read_txn().unwrap(); let rtxn = temp_index.read_txn().unwrap();
let mut ctx = SearchContext::new(&temp_index, &rtxn); let ctx = SearchContext::new(&temp_index, &rtxn);
let mut builder = MatcherBuilder::new_test(&mut ctx, "the \"t he\" door \"do or\""); let mut builder = MatcherBuilder::new_test(ctx, "the \"t he\" door \"do or\"");
builder.highlight_prefix("_".to_string()); builder.highlight_prefix("_".to_string());
builder.highlight_suffix("_".to_string()); builder.highlight_suffix("_".to_string());