Merge #5062

5062: Fix bugs for v1.12 r=Kerollmops a=ManyTheFish

# Pull Request

## Related issue
Fixes #4984
Fixes https://github.com/meilisearch/meilisearch/issues/4974
Fixes [SDK test](https://github.com/meilisearch/meilisearch/actions/runs/11886701996/job/33118278794)
## What does this PR do?
- add 3 tests
- fix bugs

Co-authored-by: ManyTheFish <many@meilisearch.com>

crates/milli/src/search/new/matches/mod.rs

@@ -274,7 +274,7 @@ impl<'t, 'tokenizer> Matcher<'t, 'tokenizer, '_, '_> {
                     last_match_last_token_position_plus_one
                 } else {
                     // we have matched the end of possible tokens, there's nothing to advance
-                    tokens.len() - 1
+                    tokens.len()
                 }
             };
 

crates/milli/src/search/new/resolve_query_graph.rs

@@ -193,15 +193,23 @@ pub fn compute_phrase_docids(
     if words.is_empty() {
         return Ok(RoaringBitmap::new());
     }
-    let mut candidates = RoaringBitmap::new();
+    let mut candidates = None;
     for word in words.iter().flatten().copied() {
         if let Some(word_docids) = ctx.word_docids(None, Word::Original(word))? {
-            candidates |= word_docids;
+            if let Some(candidates) = candidates.as_mut() {
+                *candidates &= word_docids;
+            } else {
+                candidates = Some(word_docids);
+            }
         } else {
             return Ok(RoaringBitmap::new());
         }
     }
 
+    let Some(mut candidates) = candidates else {
+        return Ok(RoaringBitmap::new());
+    };
+
     let winsize = words.len().min(3);
 
     for win in words.windows(winsize) {

crates/milli/src/update/index_documents/extract/extract_docid_word_positions.rs

@@ -58,9 +58,9 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
         .map(|s| s.iter().map(String::as_str).collect());
     let old_dictionary: Option<Vec<_>> =
         settings_diff.old.dictionary.as_ref().map(|s| s.iter().map(String::as_str).collect());
-    let del_builder =
+    let mut del_builder =
         tokenizer_builder(old_stop_words, old_separators.as_deref(), old_dictionary.as_deref());
-    let del_tokenizer = del_builder.into_tokenizer();
+    let del_tokenizer = del_builder.build();
 
     let new_stop_words = settings_diff.new.stop_words.as_ref();
     let new_separators: Option<Vec<_>> = settings_diff
@@ -70,9 +70,9 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
         .map(|s| s.iter().map(String::as_str).collect());
     let new_dictionary: Option<Vec<_>> =
         settings_diff.new.dictionary.as_ref().map(|s| s.iter().map(String::as_str).collect());
-    let add_builder =
+    let mut add_builder =
         tokenizer_builder(new_stop_words, new_separators.as_deref(), new_dictionary.as_deref());
-    let add_tokenizer = add_builder.into_tokenizer();
+    let add_tokenizer = add_builder.build();
 
     // iterate over documents.
     let mut cursor = obkv_documents.into_cursor()?;