From 54dacb362d9f60b8b9c60b962cceae8b3a3c477e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20Renault?= <clement@meilisearch.com>
Date: Tue, 14 Jan 2020 17:10:35 +0100
Subject: [PATCH] Use different algorithms for different documents ratios

---
 meilisearch-core/src/bucket_sort.rs | 68 ++++++++++++++++++++---------
 1 file changed, 48 insertions(+), 20 deletions(-)

diff --git a/meilisearch-core/src/bucket_sort.rs b/meilisearch-core/src/bucket_sort.rs
index 1ff05086b..bebfa5a5f 100644
--- a/meilisearch-core/src/bucket_sort.rs
+++ b/meilisearch-core/src/bucket_sort.rs
@@ -94,37 +94,65 @@ where
 
     let before = Instant::now();
 
+    let docidslen = docids.len() as f32;
     let mut bare_matches = Vec::new();
     mk_arena!(arena);
 
     for ((query, input, distance), matches) in queries {
 
         let postings_list_view = PostingsListView::original(Rc::from(input), Rc::new(matches));
-        let mut offset = 0;
-        for id in docids.as_slice() {
-            let di = DocIndex { document_id: *id, ..DocIndex::default() };
-            let pos = exponential_search(&postings_list_view[offset..], &di).unwrap_or_else(|x| x);
+        let pllen = postings_list_view.len() as f32;
 
-            let group = postings_list_view[offset + pos..]
-                .linear_group_by_key(|m| m.document_id)
-                .next()
-                .filter(|matches| matches[0].document_id == *id);
+        if docidslen / pllen >= 0.8 {
+            let mut offset = 0;
+            for matches in postings_list_view.linear_group_by_key(|m| m.document_id) {
+                let document_id = matches[0].document_id;
+                if docids.contains(&document_id) {
+                    let range = postings_list_view.range(offset, matches.len());
+                    let posting_list_index = arena.add(range);
 
-            offset += pos;
+                    let bare_match = BareMatch {
+                        document_id,
+                        query_index: query.id,
+                        distance,
+                        is_exact: true, // TODO where can I find this info?
+                        postings_list: posting_list_index,
+                    };
 
-            if let Some(matches) = group {
-                let range = postings_list_view.range(pos, matches.len());
-                let posting_list_index = arena.add(range);
+                    bare_matches.push(bare_match);
+                }
 
-                let bare_match = BareMatch {
-                    document_id: *id,
-                    query_index: query.id,
-                    distance: distance,
-                    is_exact: true, // TODO where can I find this info?
-                    postings_list: posting_list_index,
-                };
+                offset += matches.len();
+            }
 
-                bare_matches.push(bare_match);
+        } else {
+
+            let mut offset = 0;
+            for id in docids.as_slice() {
+                let di = DocIndex { document_id: *id, ..DocIndex::default() };
+                let pos = exponential_search(&postings_list_view[offset..], &di).unwrap_or_else(|x| x);
+
+                offset += pos;
+
+                let group = postings_list_view[offset..]
+                    .linear_group_by_key(|m| m.document_id)
+                    .next()
+                    .filter(|matches| matches[0].document_id == *id);
+
+                if let Some(matches) = group {
+                    let range = postings_list_view.range(offset, matches.len());
+                    let posting_list_index = arena.add(range);
+
+                    let bare_match = BareMatch {
+                        document_id: *id,
+                        query_index: query.id,
+                        distance,
+                        is_exact: true, // TODO where can I find this info?
+                        postings_list: posting_list_index,
+                    };
+
+                    bare_matches.push(bare_match);
+                }
             }
         }
     }