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

Chores: Enhance smart-crop code comments

Browse Source
This commit is contained in:
ManyTheFish 2022-07-07 16:28:09 +02:00
parent ce90fc628a
commit 5d79617a56
1 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
milli/src/search/matches/mod.rs
View File

@ -11,6 +11,7 @@ const DEFAULT_CROP_MARKER: &'static str = "…";
const DEFAULT_HIGHLIGHT_PREFIX: &'static str = "<em>";
const DEFAULT_HIGHLIGHT_SUFFIX: &'static 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>,
@ -100,6 +101,8 @@ pub struct MatchBounds {
pub length: usize,
}
/// Structure used to analize a string, compute words that match,
/// and format the source string returning an highlighted and croped sub-string.
pub struct Matcher<'t, 'm, A> {
text: &'t str,
matching_words: &'m MatchingWords,
@ -113,6 +116,8 @@ pub struct Matcher<'t, 'm, A> {
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 word are counted as matches only if there 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,
@ -246,9 +251,14 @@ impl<'t, A: AsRef<[u8]>> Matcher<'t, '_, A> {
// 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 trew 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 trew the end of the text.
let mut after_tokens = tokens[last_match_token_position..].iter().peekable();
// gross the crop window peeking in both drections
// 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());
@ -315,6 +325,7 @@ impl<'t, A: AsRef<[u8]>> Matcher<'t, '_, A> {
}
}
// finally, keep the byte index of each bounds 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);
@ -353,7 +364,7 @@ impl<'t, A: AsRef<[u8]>> Matcher<'t, '_, A> {
(uniq_score, distance_score, order_score)
}
/// Returns the matches interval where the score computed by match_interval_score is maximal.
/// 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 {
@ -408,6 +419,8 @@ impl<'t, A: AsRef<[u8]>> Matcher<'t, '_, A> {
} else {
match &self.matches {
Some((tokens, matches)) => {
// If the text have to be croped,
// 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)
@ -415,6 +428,8 @@ impl<'t, A: AsRef<[u8]>> Matcher<'t, '_, A> {
_ => matches,
};
// If the text have to be croped,
// 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)