snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-26 20:15:07 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

remove old matcher

Browse Source
This commit is contained in:
ManyTheFish 2023-04-06 14:00:21 +02:00
parent 9c5f64769a
commit a1148c09c2
3 changed files with 0 additions and 1323 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

457
milli/src/search/matches/matching_words.rs
View File

@ -1,457 +0,0 @@
use std::cmp::{min, Reverse};
use std::collections::BTreeMap;
use std::fmt;
use std::ops::{Index, IndexMut};
use std::rc::Rc;
use charabia::Token;
use levenshtein_automata::{Distance, DFA};
use crate::error::InternalError;
use crate::search::build_dfa;
use crate::MAX_WORD_LENGTH;
type IsPrefix = bool;
/// Structure created from a query tree
/// referencing words that match the given query tree.
#[derive(Default)]
pub struct MatchingWords {
inner: Vec<(Vec<Rc<MatchingWord>>, Vec<PrimitiveWordId>)>,
}
impl fmt::Debug for MatchingWords {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(f, "[")?;
for (matching_words, primitive_word_id) in self.inner.iter() {
writeln!(f, "({matching_words:?}, {primitive_word_id:?})")?;
}
writeln!(f, "]")?;
Ok(())
}
}
impl MatchingWords {
pub fn new(
mut matching_words: Vec<(Vec<Rc<MatchingWord>>, Vec<PrimitiveWordId>)>,
) -> crate::Result<Self> {
// if one of the matching_words vec doesn't contain a word.
if matching_words.iter().any(|(mw, _)| mw.is_empty()) {
return Err(InternalError::InvalidMatchingWords.into());
}
// Sort word by len in DESC order prioritizing the longuest matches,
// in order to highlight the longuest part of the matched word.
matching_words.sort_unstable_by_key(|(mw, _)| Reverse((mw.len(), mw[0].word.len())));
Ok(Self { inner: matching_words })
}
/// Returns an iterator over terms that match or partially match the given token.
pub fn match_token<'a, 'b>(&'a self, token: &'b Token<'b>) -> MatchesIter<'a, 'b> {
MatchesIter { inner: Box::new(self.inner.iter()), token }
}
}
/// Iterator over terms that match the given token,
/// This allow to lazily evaluate matches.
pub struct MatchesIter<'a, 'b> {
#[allow(clippy::type_complexity)]
inner: Box<dyn Iterator<Item = &'a (Vec<Rc<MatchingWord>>, Vec<PrimitiveWordId>)> + 'a>,
token: &'b Token<'b>,
}
impl<'a> Iterator for MatchesIter<'a, '_> {
type Item = MatchType<'a>;
fn next(&mut self) -> Option<Self::Item> {
match self.inner.next() {
Some((matching_words, ids)) => match matching_words[0].match_token(self.token) {
Some(char_len) => {
if matching_words.len() > 1 {
Some(MatchType::Partial(PartialMatch {
matching_words: &matching_words[1..],
ids,
char_len,
}))
} else {
Some(MatchType::Full { char_len, ids })
}
}
None => self.next(),
},
None => None,
}
}
}
/// Id of a matching term corespounding to a word written by the end user.
pub type PrimitiveWordId = u8;
/// Structure used to match a specific term.
pub struct MatchingWord {
pub dfa: DFA,
pub word: String,
pub typo: u8,
pub prefix: IsPrefix,
}
impl fmt::Debug for MatchingWord {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.debug_struct("MatchingWord")
.field("word", &self.word)
.field("typo", &self.typo)
.field("prefix", &self.prefix)
.finish()
}
}
impl PartialEq for MatchingWord {
fn eq(&self, other: &Self) -> bool {
self.prefix == other.prefix && self.typo == other.typo && self.word == other.word
}
}
impl MatchingWord {
pub fn new(word: String, typo: u8, prefix: IsPrefix) -> Option<Self> {
if word.len() > MAX_WORD_LENGTH {
return None;
}
let dfa = build_dfa(&word, typo, prefix);
Some(Self { dfa, word, typo, prefix })
}
/// Returns the lenght in chars of the match in case of the token matches the term.
pub fn match_token(&self, token: &Token) -> Option<usize> {
match self.dfa.eval(token.lemma()) {
Distance::Exact(t) if t <= self.typo => {
if self.prefix {
let len = bytes_to_highlight(token.lemma(), &self.word);
Some(token.original_lengths(len).0)
} else {
Some(token.original_lengths(token.lemma().len()).0)
}
}
_otherwise => None,
}
}
}
/// A given token can partially match a query word for several reasons:
/// - split words
/// - multi-word synonyms
/// In these cases we need to match consecutively several tokens to consider that the match is full.
#[derive(Debug, PartialEq)]
pub enum MatchType<'a> {
Full { char_len: usize, ids: &'a [PrimitiveWordId] },
Partial(PartialMatch<'a>),
}
/// Structure helper to match several tokens in a row in order to complete a partial match.
#[derive(Debug, PartialEq)]
pub struct PartialMatch<'a> {
matching_words: &'a [Rc<MatchingWord>],
ids: &'a [PrimitiveWordId],
char_len: usize,
}
impl<'a> PartialMatch<'a> {
/// Returns:
/// - None if the given token breaks the partial match
/// - Partial if the given token matches the partial match but doesn't complete it
/// - Full if the given token completes the partial match
pub fn match_token(self, token: &Token) -> Option<MatchType<'a>> {
self.matching_words[0].match_token(token).map(|char_len| {
if self.matching_words.len() > 1 {
MatchType::Partial(PartialMatch {
matching_words: &self.matching_words[1..],
ids: self.ids,
char_len,
})
} else {
MatchType::Full { char_len, ids: self.ids }
}
})
}
pub fn char_len(&self) -> usize {
self.char_len
}
}
// A simple wrapper around vec so we can get contiguous but index it like it's 2D array.
struct N2Array<T> {
y_size: usize,
buf: Vec<T>,
}
impl<T: Clone> N2Array<T> {
fn new(x: usize, y: usize, value: T) -> N2Array<T> {
N2Array { y_size: y, buf: vec![value; x * y] }
}
}
impl<T> Index<(usize, usize)> for N2Array<T> {
type Output = T;
#[inline]
fn index(&self, (x, y): (usize, usize)) -> &T {
&self.buf[(x * self.y_size) + y]
}
}
impl<T> IndexMut<(usize, usize)> for N2Array<T> {
#[inline]
fn index_mut(&mut self, (x, y): (usize, usize)) -> &mut T {
&mut self.buf[(x * self.y_size) + y]
}
}
/// Returns the number of **bytes** we want to highlight in the `source` word.
/// Basically we want to highlight as much characters as possible in the source until it has too much
/// typos (= 2)
/// The algorithm is a modified
/// [Damerau-Levenshtein](https://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance)
fn bytes_to_highlight(source: &str, target: &str) -> usize {
let n = source.chars().count();
let m = target.chars().count();
if n == 0 {
return 0;
}
// since we allow two typos we can send two characters even if it's completely wrong
if m < 3 {
return source.chars().take(m).map(|c| c.len_utf8()).sum();
}
if n == m && source == target {
return source.len();
}
let inf = n + m;
let mut matrix = N2Array::new(n + 2, m + 2, 0);
matrix[(0, 0)] = inf;
for i in 0..=n {
matrix[(i + 1, 0)] = inf;
matrix[(i + 1, 1)] = i;
}
for j in 0..=m {
matrix[(0, j + 1)] = inf;
matrix[(1, j + 1)] = j;
}
let mut last_row = BTreeMap::new();
for (row, char_s) in source.chars().enumerate() {
let mut last_match_col = 0;
let row = row + 1;
for (col, char_t) in target.chars().enumerate() {
let col = col + 1;
let last_match_row = *last_row.get(&char_t).unwrap_or(&0);
let cost = usize::from(char_s != char_t);
let dist_add = matrix[(row, col + 1)] + 1;
let dist_del = matrix[(row + 1, col)] + 1;
let dist_sub = matrix[(row, col)] + cost;
let dist_trans = matrix[(last_match_row, last_match_col)]
+ (row - last_match_row - 1)
+ 1
+ (col - last_match_col - 1);
let dist = min(min(dist_add, dist_del), min(dist_sub, dist_trans));
matrix[(row + 1, col + 1)] = dist;
if cost == 0 {
last_match_col = col;
}
}
last_row.insert(char_s, row);
}
let mut minimum = (u32::max_value(), 0);
for x in 0..=m {
let dist = matrix[(n + 1, x + 1)] as u32;
if dist < minimum.0 {
minimum = (dist, x);
}
}
// everything was done characters wise and now we want to returns a number of bytes
source.chars().take(minimum.1).map(|c| c.len_utf8()).sum()
}
#[cfg(test)]
mod tests {
use std::borrow::Cow;
use std::str::from_utf8;
use charabia::TokenKind;
use super::{MatchingWords, *};
#[test]
fn test_bytes_to_highlight() {
struct TestBytesToHighlight {
query: &'static str,
text: &'static str,
length: usize,
}
let tests = [
TestBytesToHighlight { query: "bip", text: "bip", length: "bip".len() },
TestBytesToHighlight { query: "bip", text: "boup", length: "bip".len() },
TestBytesToHighlight {
query: "Levenshtein",
text: "Levenshtein",
length: "Levenshtein".len(),
},
// we get to the end of our word with only one typo
TestBytesToHighlight {
query: "Levenste",
text: "Levenshtein",
length: "Levenste".len(),
},
// we get our third and last authorized typo right on the last character
TestBytesToHighlight {
query: "Levenstein",
text: "Levenshte",
length: "Levenste".len(),
},
// we get to the end of our word with only two typos at the beginning
TestBytesToHighlight {
query: "Bavenshtein",
text: "Levenshtein",
length: "Bavenshtein".len(),
},
TestBytesToHighlight {
query: "Альфа", text: "Альфой", length: "Альф".len()
},
TestBytesToHighlight {
query: "Go💼", text: "Go💼od luck.", length: "Go💼".len()
},
TestBytesToHighlight {
query: "Go💼od", text: "Go💼od luck.", length: "Go💼od".len()
},
TestBytesToHighlight {
query: "chäräcters",
text: "chäräcters",
length: "chäräcters".len(),
},
TestBytesToHighlight { query: "ch", text: "chäräcters", length: "ch".len() },
TestBytesToHighlight { query: "chär", text: "chäräcters", length: "chär".len() },
];
for test in &tests {
let length = bytes_to_highlight(test.text, test.query);
assert_eq!(length, test.length, r#"lenght between: "{}" "{}""#, test.query, test.text);
assert!(
from_utf8(&test.query.as_bytes()[..length]).is_ok(),
r#"converting {}[..{}] to an utf8 str failed"#,
test.query,
length
);
}
}
#[test]
fn matching_words() {
let all = vec![
Rc::new(MatchingWord::new("split".to_string(), 1, true).unwrap()),
Rc::new(MatchingWord::new("this".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("world".to_string(), 1, true).unwrap()),
];
let matching_words = vec![
(vec![all[0].clone()], vec![0]),
(vec![all[1].clone()], vec![1]),
(vec![all[2].clone()], vec![2]),
];
let matching_words = MatchingWords::new(matching_words).unwrap();
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("word"),
char_end: "word".chars().count(),
byte_end: "word".len(),
..Default::default()
})
.next(),
Some(MatchType::Full { char_len: 3, ids: &[2] })
);
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("nyc"),
char_end: "nyc".chars().count(),
byte_end: "nyc".len(),
..Default::default()
})
.next(),
None
);
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("world"),
char_end: "world".chars().count(),
byte_end: "world".len(),
..Default::default()
})
.next(),
Some(MatchType::Full { char_len: 5, ids: &[2] })
);
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("splitted"),
char_end: "splitted".chars().count(),
byte_end: "splitted".len(),
..Default::default()
})
.next(),
Some(MatchType::Full { char_len: 5, ids: &[0] })
);
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("thisnew"),
char_end: "thisnew".chars().count(),
byte_end: "thisnew".len(),
..Default::default()
})
.next(),
None
);
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("borld"),
char_end: "borld".chars().count(),
byte_end: "borld".len(),
..Default::default()
})
.next(),
Some(MatchType::Full { char_len: 5, ids: &[2] })
);
assert_eq!(
matching_words
.match_token(&Token {
kind: TokenKind::Word,
lemma: Cow::Borrowed("wordsplit"),
char_end: "wordsplit".chars().count(),
byte_end: "wordsplit".len(),
..Default::default()
})
.next(),
Some(MatchType::Full { char_len: 4, ids: &[2] })
);
}
}

865
milli/src/search/matches/mod.rs
View File

@ -1,865 +0,0 @@
use std::borrow::Cow;
use charabia::{SeparatorKind, Token, Tokenizer};
use matching_words::{MatchType, PartialMatch, PrimitiveWordId};
pub use matching_words::{MatchingWord, MatchingWords};
use serde::Serialize;
pub mod matching_words;
const DEFAULT_CROP_MARKER: &str = "…";
const DEFAULT_HIGHLIGHT_PREFIX: &str = "<em>";
const DEFAULT_HIGHLIGHT_SUFFIX: &str = "</em>";
/// Structure used to build a Matcher allowing to customize formating tags.
pub struct MatcherBuilder<'a, A> {
matching_words: MatchingWords,
tokenizer: Tokenizer<'a, 'a, A>,
crop_marker: Option<String>,
highlight_prefix: Option<String>,
highlight_suffix: Option<String>,
}
impl<'a, A> MatcherBuilder<'a, A> {
pub fn new(matching_words: MatchingWords, tokenizer: Tokenizer<'a, 'a, A>) -> Self {
Self {
matching_words,
tokenizer,
crop_marker: None,
highlight_prefix: None,
highlight_suffix: None,
}
}
pub fn crop_marker(&mut self, marker: String) -> &Self {
self.crop_marker = Some(marker);
self
}
pub fn highlight_prefix(&mut self, prefix: String) -> &Self {
self.highlight_prefix = Some(prefix);
self
}
pub fn highlight_suffix(&mut self, suffix: String) -> &Self {
self.highlight_suffix = Some(suffix);
self
}
pub fn build<'t, 'm>(&'m self, text: &'t str) -> Matcher<'t, 'm, A> {
let crop_marker = match &self.crop_marker {
Some(marker) => marker.as_str(),
None => DEFAULT_CROP_MARKER,
};
let highlight_prefix = match &self.highlight_prefix {
Some(marker) => marker.as_str(),
None => DEFAULT_HIGHLIGHT_PREFIX,
};
let highlight_suffix = match &self.highlight_suffix {
Some(marker) => marker.as_str(),
None => DEFAULT_HIGHLIGHT_SUFFIX,
};
Matcher {
text,
matching_words: &self.matching_words,
tokenizer: &self.tokenizer,
crop_marker,
highlight_prefix,
highlight_suffix,
matches: None,
}
}
}
#[derive(Copy, Clone, Default)]
pub struct FormatOptions {
pub highlight: bool,
pub crop: Option<usize>,
}
impl FormatOptions {
pub fn merge(self, other: Self) -> Self {
Self { highlight: self.highlight || other.highlight, crop: self.crop.or(other.crop) }
}
}
#[derive(Clone, Debug)]
pub struct Match {
match_len: usize,
// ids of the query words that matches.
ids: Vec<PrimitiveWordId>,
// position of the word in the whole text.
word_position: usize,
// position of the token in the whole text.
token_position: usize,
}
#[derive(Serialize, Debug, Clone, PartialEq, Eq)]
pub struct MatchBounds {
pub start: usize,
pub length: usize,
}
/// Structure used to analize a string, compute words that match,
/// and format the source string, returning a highlighted and cropped sub-string.
pub struct Matcher<'t, 'm, A> {
text: &'t str,
matching_words: &'m MatchingWords,
tokenizer: &'m Tokenizer<'m, 'm, A>,
crop_marker: &'m str,
highlight_prefix: &'m str,
highlight_suffix: &'m str,
matches: Option<(Vec<Token<'t>>, Vec<Match>)>,
}
impl<'t, A: AsRef<[u8]>> Matcher<'t, '_, A> {
/// Iterates over tokens and save any of them that matches the query.
fn compute_matches(&mut self) -> &mut Self {
/// some words are counted as matches only if they are close together and in the good order,
/// compute_partial_match peek into next words to validate if the match is complete.
fn compute_partial_match<'a>(
mut partial: PartialMatch,
token_position: usize,
word_position: usize,
words_positions: &mut impl Iterator<Item = (usize, usize, &'a Token<'a>)>,
matches: &mut Vec<Match>,
) -> bool {
let mut potential_matches = vec![(token_position, word_position, partial.char_len())];
for (token_position, word_position, word) in words_positions {
partial = match partial.match_token(word) {
// token matches the partial match, but the match is not full,
// we temporarly save the current token then we try to match the next one.
Some(MatchType::Partial(partial)) => {
potential_matches.push((token_position, word_position, partial.char_len()));
partial
}
// partial match is now full, we keep this matches and we advance positions
Some(MatchType::Full { char_len, ids }) => {
// save previously matched tokens as matches.
let iter = potential_matches.into_iter().map(
|(token_position, word_position, match_len)| Match {
match_len,
ids: ids.to_vec(),
word_position,
token_position,
},
);
matches.extend(iter);
// save the token that closes the partial match as a match.
matches.push(Match {
match_len: char_len,
ids: ids.to_vec(),
word_position,
token_position,
});
// the match is complete, we return true.
return true;
}
// no match, continue to next match.
None => break,
};
}
// the match is not complete, we return false.
false
}
let tokens: Vec<_> = self.tokenizer.tokenize(self.text).collect();
let mut matches = Vec::new();
let mut words_positions = tokens
.iter()
.scan((0, 0), |(token_position, word_position), token| {
let current_token_position = *token_position;
let current_word_position = *word_position;
*token_position += 1;
if !token.is_separator() {
*word_position += 1;
}
Some((current_token_position, current_word_position, token))
})
.filter(|(_, _, token)| !token.is_separator());
while let Some((token_position, word_position, word)) = words_positions.next() {
for match_type in self.matching_words.match_token(word) {
match match_type {
// we match, we save the current token as a match,
// then we continue the rest of the tokens.
MatchType::Full { char_len, ids } => {
matches.push(Match {
match_len: char_len,
ids: ids.to_vec(),
word_position,
token_position,
});
break;
}
// we match partially, iterate over next tokens to check if we can complete the match.
MatchType::Partial(partial) => {
// if match is completed, we break the matching loop over the current token,
// then we continue the rest of the tokens.
let mut wp = words_positions.clone();
if compute_partial_match(
partial,
token_position,
word_position,
&mut wp,
&mut matches,
) {
words_positions = wp;
break;
}
}
}
}
}
self.matches = Some((tokens, matches));
self
}
/// Returns boundaries of the words that match the query.
pub fn matches(&mut self) -> Vec<MatchBounds> {
match &self.matches {
None => self.compute_matches().matches(),
Some((tokens, matches)) => matches
.iter()
.map(|m| MatchBounds {
start: tokens[m.token_position].byte_start,
length: m.match_len,
})
.collect(),
}
}
/// Returns the bounds in byte index of the crop window.
fn crop_bounds(&self, tokens: &[Token], matches: &[Match], crop_size: usize) -> (usize, usize) {
// if there is no match, we start from the beginning of the string by default.
let first_match_word_position = matches.first().map(|m| m.word_position).unwrap_or(0);
let first_match_token_position = matches.first().map(|m| m.token_position).unwrap_or(0);
let last_match_word_position = matches.last().map(|m| m.word_position).unwrap_or(0);
let last_match_token_position = matches.last().map(|m| m.token_position).unwrap_or(0);
// matches needs to be counted in the crop len.
let mut remaining_words = crop_size + first_match_word_position - last_match_word_position;
// create the initial state of the crop window: 2 iterators starting from the matches positions,
// a reverse iterator starting from the first match token position and going towards the beginning of the text,
let mut before_tokens = tokens[..first_match_token_position].iter().rev().peekable();
// an iterator starting from the last match token position and going towards the end of the text.
let mut after_tokens = tokens[last_match_token_position..].iter().peekable();
// grows the crop window peeking in both directions
// until the window contains the good number of words:
while remaining_words > 0 {
let before_token = before_tokens.peek().map(|t| t.separator_kind());
let after_token = after_tokens.peek().map(|t| t.separator_kind());
match (before_token, after_token) {
// we can expand both sides.
(Some(before_token), Some(after_token)) => {
match (before_token, after_token) {
// if they are both separators and are the same kind then advance both,
// or expand in the soft separator separator side.
(Some(before_token_kind), Some(after_token_kind)) => {
if before_token_kind == after_token_kind {
before_tokens.next();
// this avoid having an ending separator before crop marker.
if remaining_words > 1 {
after_tokens.next();
}
} else if before_token_kind == SeparatorKind::Hard {
after_tokens.next();
} else {
before_tokens.next();
}
}
// if one of the tokens is a word, we expend in the side of the word.
// left is a word, advance left.
(None, Some(_)) => {
before_tokens.next();
remaining_words -= 1;
}
// right is a word, advance right.
(Some(_), None) => {
after_tokens.next();
remaining_words -= 1;
}
// both are words, advance left then right if remaining_word > 0.
(None, None) => {
before_tokens.next();
remaining_words -= 1;
if remaining_words > 0 {
after_tokens.next();
remaining_words -= 1;
}
}
}
}
// the end of the text is reached, advance left.
(Some(before_token), None) => {
before_tokens.next();
if before_token.is_none() {
remaining_words -= 1;
}
}
// the start of the text is reached, advance right.
(None, Some(after_token)) => {
after_tokens.next();
if after_token.is_none() {
remaining_words -= 1;
}
}
// no more token to add.
(None, None) => break,
}
}
// finally, keep the byte index of each bound of the crop window.
let crop_byte_start = before_tokens.next().map_or(0, |t| t.byte_end);
let crop_byte_end = after_tokens.next().map_or(self.text.len(), |t| t.byte_start);
(crop_byte_start, crop_byte_end)
}
/// Compute the score of a match interval:
/// 1) count unique matches
/// 2) calculate distance between matches
/// 3) count ordered matches
fn match_interval_score(&self, matches: &[Match]) -> (i16, i16, i16) {
let mut ids: Vec<PrimitiveWordId> = Vec::with_capacity(matches.len());
let mut order_score = 0;
let mut distance_score = 0;
let mut iter = matches.iter().peekable();
while let Some(m) = iter.next() {
if let Some(next_match) = iter.peek() {
// if matches are ordered
if next_match.ids.iter().min() > m.ids.iter().min() {
order_score += 1;
}
// compute distance between matches
distance_score -= (next_match.word_position - m.word_position).min(7) as i16;
}
ids.extend(m.ids.iter());
}
ids.sort_unstable();
ids.dedup();
let uniq_score = ids.len() as i16;
// rank by unique match count, then by distance between matches, then by ordered match count.
(uniq_score, distance_score, order_score)
}
/// Returns the matches interval where the score computed by match_interval_score is the best.
fn find_best_match_interval<'a>(&self, matches: &'a [Match], crop_size: usize) -> &'a [Match] {
// we compute the matches interval if we have at least 2 matches.
if matches.len() > 1 {
// positions of the first and the last match of the best matches interval in `matches`.
let mut best_interval = (0, 0);
let mut best_interval_score = self.match_interval_score(&matches[0..=0]);
// current interval positions.
let mut interval_first = 0;
let mut interval_last = 0;
for (index, next_match) in matches.iter().enumerate().skip(1) {
// if next match would make interval gross more than crop_size,
// we compare the current interval with the best one,
// then we increase `interval_first` until next match can be added.
if next_match.word_position - matches[interval_first].word_position >= crop_size {
let interval_score =
self.match_interval_score(&matches[interval_first..=interval_last]);
// keep interval if it's the best
if interval_score > best_interval_score {
best_interval = (interval_first, interval_last);
best_interval_score = interval_score;
}
// advance start of the interval while interval is longer than crop_size.
while next_match.word_position - matches[interval_first].word_position
>= crop_size
{
interval_first += 1;
}
}
interval_last = index;
}
// compute the last interval score and compare it to the best one.
let interval_score =
self.match_interval_score(&matches[interval_first..=interval_last]);
if interval_score > best_interval_score {
best_interval = (interval_first, interval_last);
}
&matches[best_interval.0..=best_interval.1]
} else {
matches
}
}
// Returns the formatted version of the original text.
pub fn format(&mut self, format_options: FormatOptions) -> Cow<'t, str> {
if !format_options.highlight && format_options.crop.is_none() {
// compute matches is not needed if no highlight nor crop is requested.
Cow::Borrowed(self.text)
} else {
match &self.matches {
Some((tokens, matches)) => {
// If the text has to be cropped,
// compute the best interval to crop around.
let matches = match format_options.crop {
Some(crop_size) if crop_size > 0 => {
self.find_best_match_interval(matches, crop_size)
}
_ => matches,
};
// If the text has to be cropped,
// crop around the best interval.
let (byte_start, byte_end) = match format_options.crop {
Some(crop_size) if crop_size > 0 => {
self.crop_bounds(tokens, matches, crop_size)
}
_ => (0, self.text.len()),
};
let mut formatted = Vec::new();
// push crop marker if it's not the start of the text.
if byte_start > 0 && !self.crop_marker.is_empty() {
formatted.push(self.crop_marker);
}
let mut byte_index = byte_start;
if format_options.highlight {
// insert highlight markers around matches.
for m in matches {
let token = &tokens[m.token_position];
if byte_index < token.byte_start {
formatted.push(&self.text[byte_index..token.byte_start]);
}
let highlight_byte_index = self.text[token.byte_start..]
.char_indices()
.enumerate()
.find(|(i, _)| *i == m.match_len)
.map_or(token.byte_end, |(_, (i, _))| i + token.byte_start);
formatted.push(self.highlight_prefix);
formatted.push(&self.text[token.byte_start..highlight_byte_index]);
formatted.push(self.highlight_suffix);
// if it's a prefix highlight, we put the end of the word after the highlight marker.
if highlight_byte_index < token.byte_end {
formatted.push(&self.text[highlight_byte_index..token.byte_end]);
}
byte_index = token.byte_end;
}
}
// push the rest of the text between last match and the end of crop.
if byte_index < byte_end {
formatted.push(&self.text[byte_index..byte_end]);
}
// push crop marker if it's not the end of the text.
if byte_end < self.text.len() && !self.crop_marker.is_empty() {
formatted.push(self.crop_marker);
}
if formatted.len() == 1 {
// avoid concatenating if there is already 1 slice.
Cow::Borrowed(&self.text[byte_start..byte_end])
} else {
Cow::Owned(formatted.concat())
}
}
None => self.compute_matches().format(format_options),
}
}
}
}
#[cfg(test)]
mod tests {
use std::rc::Rc;
use charabia::TokenizerBuilder;
use super::*;
use crate::search::matches::matching_words::MatchingWord;
fn matching_words() -> MatchingWords {
let all = vec![
Rc::new(MatchingWord::new("split".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("the".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("world".to_string(), 1, true).unwrap()),
];
let matching_words = vec![
(vec![all[0].clone()], vec![0]),
(vec![all[1].clone()], vec![1]),
(vec![all[2].clone()], vec![2]),
];
MatchingWords::new(matching_words).unwrap()
}
impl MatcherBuilder<'_, Vec<u8>> {
pub fn from_matching_words(matching_words: MatchingWords) -> Self {
Self::new(matching_words, TokenizerBuilder::default().build())
}
}
#[test]
fn format_identity() {
let matching_words = matching_words();
let builder = MatcherBuilder::from_matching_words(matching_words);
let format_options = FormatOptions { highlight: false, crop: None };
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text);
// no crop and no highlight should return complete text.
assert_eq!(&matcher.format(format_options), &text);
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text);
// no crop and no highlight should return complete text.
assert_eq!(&matcher.format(format_options), &text);
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text);
// no crop and no highlight should return complete text.
assert_eq!(&matcher.format(format_options), &text);
}
#[test]
fn format_highlight() {
let matching_words = matching_words();
let builder = MatcherBuilder::from_matching_words(matching_words);
let format_options = FormatOptions { highlight: true, crop: None };
// empty text.
let text = "";
let mut matcher = builder.build(text);
assert_eq!(&matcher.format(format_options), "");
// text containing only separators.
let text = ":-)";
let mut matcher = builder.build(text);
assert_eq!(&matcher.format(format_options), ":-)");
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text);
// no crop should return complete text, because there is no matches.
assert_eq!(&matcher.format(format_options), &text);
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"Natalie risk her future to build a <em>world</em> with <em>the</em> boy she loves. Emily Henry: <em>The</em> Love That <em>Split</em> <em>The</em> <em>World</em>."
);
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"Natalie risk her future to build a <em>world</em> with <em>the</em> boy she loves."
);
}
#[test]
fn highlight_unicode() {
let all = vec![
Rc::new(MatchingWord::new("wessfali".to_string(), 1, true).unwrap()),
Rc::new(MatchingWord::new("world".to_string(), 1, true).unwrap()),
];
let matching_words = vec![(vec![all[0].clone()], vec![0]), (vec![all[1].clone()], vec![1])];
let matching_words = MatchingWords::new(matching_words).unwrap();
let builder = MatcherBuilder::from_matching_words(matching_words);
let format_options = FormatOptions { highlight: true, crop: None };
// Text containing prefix match.
let text = "Ŵôřlḑôle";
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"<em>Ŵôřlḑ</em>ôle"
);
// Text containing unicode match.
let text = "Ŵôřlḑ";
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"<em>Ŵôřlḑ</em>"
);
// Text containing unicode match.
let text = "Westfália";
let mut matcher = builder.build(text);
// no crop should return complete text with highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"<em>Westfáli</em>a"
);
}
#[test]
fn format_crop() {
let matching_words = matching_words();
let builder = MatcherBuilder::from_matching_words(matching_words);
let format_options = FormatOptions { highlight: false, crop: Some(10) };
// empty text.
let text = "";
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@""
);
// text containing only separators.
let text = ":-)";
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@":-)"
);
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text);
// no highlight should return 10 first words with a marker at the end.
insta::assert_snapshot!(
matcher.format(format_options),
@"A quick brown fox can not jump 32 feet, right…"
);
// Text without any match starting by a separator.
let text = "(A quick brown fox can not jump 32 feet, right? Brr, it is cold!)";
let mut matcher = builder.build(text);
// no highlight should return 10 first words with a marker at the end.
insta::assert_snapshot!(
matcher.format(format_options),
@"(A quick brown fox can not jump 32 feet, right…"
);
// Test phrase propagation
let text = "Natalie risk her future. Split The World is a book written by Emily Henry. I never read it.";
let mut matcher = builder.build(text);
// should crop the phrase instead of croping around the match.
insta::assert_snapshot!(
matcher.format(format_options),
@"… Split The World is a book written by Emily Henry…"
);
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text);
// no highlight should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@"…future to build a world with the boy she loves…"
);
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text);
// no highlight should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@"…she loves. Emily Henry: The Love That Split The World."
);
// Text containing a match unordered and a match ordered.
let text = "The world split void void void void void void void void void split the world void void";
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@"…void void void void void split the world void void"
);
// Text containing matches with diferent density.
let text = "split void the void void world void void void void void void void void void void split the world void void";
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@"…void void void void void split the world void void"
);
// Text containing matches with same word.
let text = "split split split split split split void void void void void void void void void void split the world void void";
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@"…void void void void void split the world void void"
);
}
#[test]
fn format_highlight_crop() {
let matching_words = matching_words();
let builder = MatcherBuilder::from_matching_words(matching_words);
let format_options = FormatOptions { highlight: true, crop: Some(10) };
// empty text.
let text = "";
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@""
);
// text containing only separators.
let text = ":-)";
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@":-)"
);
// Text without any match.
let text = "A quick brown fox can not jump 32 feet, right? Brr, it is cold!";
let mut matcher = builder.build(text);
// both should return 10 first words with a marker at the end.
insta::assert_snapshot!(
matcher.format(format_options),
@"A quick brown fox can not jump 32 feet, right…"
);
// Text containing some matches.
let text = "Natalie risk her future to build a world with the boy she loves.";
let mut matcher = builder.build(text);
// both should return 10 last words with a marker at the start and highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"…future to build a <em>world</em> with <em>the</em> boy she loves…"
);
// Text containing all matches.
let text = "Natalie risk her future to build a world with the boy she loves. Emily Henry: The Love That Split The World.";
let mut matcher = builder.build(text);
// both should return 10 last words with a marker at the start and highlighted matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"…she loves. Emily Henry: <em>The</em> Love That <em>Split</em> <em>The</em> <em>World</em>."
);
// Text containing a match unordered and a match ordered.
let text = "The world split void void void void void void void void void split the world void void";
let mut matcher = builder.build(text);
// crop should return 10 last words with a marker at the start.
insta::assert_snapshot!(
matcher.format(format_options),
@"…void void void void void <em>split</em> <em>the</em> <em>world</em> void void"
);
}
#[test]
fn smaller_crop_size() {
//! testing: https://github.com/meilisearch/specifications/pull/120#discussion_r836536295
let matching_words = matching_words();
let builder = MatcherBuilder::from_matching_words(matching_words);
let text = "void void split the world void void.";
// set a smaller crop size
let format_options = FormatOptions { highlight: false, crop: Some(2) };
let mut matcher = builder.build(text);
// because crop size < query size, partially format matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"…split the…"
);
// set a smaller crop size
let format_options = FormatOptions { highlight: false, crop: Some(1) };
let mut matcher = builder.build(text);
// because crop size < query size, partially format matches.
insta::assert_snapshot!(
matcher.format(format_options),
@"…split…"
);
// set crop size to 0
let format_options = FormatOptions { highlight: false, crop: Some(0) };
let mut matcher = builder.build(text);
// because crop size is 0, crop is ignored.
insta::assert_snapshot!(
matcher.format(format_options),
@"void void split the world void void."
);
}
#[test]
fn partial_matches() {
let all = vec![
Rc::new(MatchingWord::new("the".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("t".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("he".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("door".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("do".to_string(), 0, false).unwrap()),
Rc::new(MatchingWord::new("or".to_string(), 0, false).unwrap()),
];
let matching_words = vec![
(vec![all[0].clone()], vec![0]),
(vec![all[1].clone(), all[2].clone()], vec![0]),
(vec![all[3].clone()], vec![1]),
(vec![all[4].clone(), all[5].clone()], vec![1]),
(vec![all[4].clone()], vec![2]),
];
let matching_words = MatchingWords::new(matching_words).unwrap();
let mut builder = MatcherBuilder::from_matching_words(matching_words);
builder.highlight_prefix("_".to_string());
builder.highlight_suffix("_".to_string());
let format_options = FormatOptions { highlight: true, crop: None };
let text = "the do or die can't be he do and or isn't he";
let mut matcher = builder.build(text);
insta::assert_snapshot!(
matcher.format(format_options),
@"_the_ _do_ _or_ die can't be he _do_ and or isn'_t_ _he_"
);
}
}

1
milli/src/search/mod.rs
View File

@ -17,7 +17,6 @@ static LEVDIST2: Lazy<LevBuilder> = Lazy::new(|| LevBuilder::new(2, true));
pub mod facet;
mod fst_utils;
mod matches;
pub mod new;
pub struct Search<'a> {