diff --git a/milli/src/search/new/matches/mod.rs b/milli/src/search/new/matches/mod.rs index 72e155b3e..5d61de0f4 100644 --- a/milli/src/search/new/matches/mod.rs +++ b/milli/src/search/new/matches/mod.rs @@ -418,19 +418,11 @@ impl<'t> Matcher<'t, '_> { } 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 => { + let matches = self.find_best_match_interval(matches, crop_size); self.crop_bounds(tokens, matches, crop_size) } _ => (0, self.text.len()), @@ -450,6 +442,11 @@ impl<'t> Matcher<'t, '_> { for m in matches { let token = &tokens[m.token_position]; + // skip matches out of the crop window. + if token.byte_start < byte_start || token.byte_end > byte_end { + continue; + } + if byte_index < token.byte_start { formatted.push(&self.text[byte_index..token.byte_start]); } @@ -800,6 +797,37 @@ mod tests { ); } + #[test] + fn format_highlight_crop_phrase_query() { + //! testing: https://github.com/meilisearch/meilisearch/issues/3975 + let temp_index = TempIndex::new(); + temp_index + .add_documents(documents!([ + { "id": 1, "text": "The groundbreaking invention had the power to split the world between those who embraced progress and those who resisted change!" } + ])) + .unwrap(); + let rtxn = temp_index.read_txn().unwrap(); + + let format_options = FormatOptions { highlight: true, crop: Some(10) }; + let text = "The groundbreaking invention had the power to split the world between those who embraced progress and those who resisted change!"; + + let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "\"the world\""); + let mut matcher = builder.build(text); + // should return 10 words with a marker at the start as well the end, and the highlighted matches. + insta::assert_snapshot!( + matcher.format(format_options), + @"…had the power to split the world between those who…" + ); + + let builder = MatcherBuilder::new_test(&rtxn, &temp_index, "those \"and those\""); + let mut matcher = builder.build(text); + // should highlight "those" and the phrase "and those". + insta::assert_snapshot!( + matcher.format(format_options), + @"…world between those who embraced progress and those who resisted…" + ); + } + #[test] fn smaller_crop_size() { //! testing: https://github.com/meilisearch/specifications/pull/120#discussion_r836536295