From 2852349e68b8b03a8567ba2cf2547f3626c03924 Mon Sep 17 00:00:00 2001
From: many <maxime@meilisearch.com>
Date: Thu, 17 Dec 2020 16:31:31 +0100
Subject: [PATCH] update tokenizer version

---
 Cargo.lock                          | 2 +-
 meilisearch-core/Cargo.toml         | 2 +-
 meilisearch-core/src/raw_indexer.rs | 4 ++--
 meilisearch-http/tests/search.rs    | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index a5f65b5fb..50bb4e9d6 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1699,7 +1699,7 @@ dependencies = [
 [[package]]
 name = "meilisearch-tokenizer"
 version = "0.1.1"
-source = "git+https://github.com/meilisearch/Tokenizer.git?tag=v0.1.1#dedea5df4b52d94216a65091f237ac64673bab09"
+source = "git+https://github.com/meilisearch/Tokenizer.git?tag=v0.1.2#8d91cd52f30aa4b651a085c15056938f7b599646"
 dependencies = [
  "character_converter",
  "cow-utils",
diff --git a/meilisearch-core/Cargo.toml b/meilisearch-core/Cargo.toml
index 8fbcba67b..dbf706e2c 100644
--- a/meilisearch-core/Cargo.toml
+++ b/meilisearch-core/Cargo.toml
@@ -26,7 +26,7 @@ levenshtein_automata = { version = "0.2.0", features = ["fst_automaton"] }
 log = "0.4.11"
 meilisearch-error = { path = "../meilisearch-error", version = "0.17.0" }
 meilisearch-schema = { path = "../meilisearch-schema", version = "0.17.0" }
-meilisearch-tokenizer = { git = "https://github.com/meilisearch/Tokenizer.git", tag = "v0.1.1" }
+meilisearch-tokenizer = { git = "https://github.com/meilisearch/Tokenizer.git", tag = "v0.1.2" }
 meilisearch-types = { path = "../meilisearch-types", version = "0.17.0" }
 once_cell = "1.5.2"
 ordered-float = { version = "2.0.1", features = ["serde"] }
diff --git a/meilisearch-core/src/raw_indexer.rs b/meilisearch-core/src/raw_indexer.rs
index c78d1f4ff..d83c02a28 100644
--- a/meilisearch-core/src/raw_indexer.rs
+++ b/meilisearch-core/src/raw_indexer.rs
@@ -140,7 +140,7 @@ fn process_tokens<'a>(tokens: impl Iterator<Item = Token<'a>>) -> impl Iterator<
     tokens
         .scan((0, None), |(offset, prev_kind), token| {
                 match token.kind {
-                    TokenKind::Word | TokenKind::StopWord | TokenKind::Any => {
+                    TokenKind::Word | TokenKind::StopWord | TokenKind::Unknown => {
                         *offset += match *prev_kind {
                             Some(TokenKind::Separator(SeparatorKind::Hard)) => 8,
                             Some(_) => 1,
@@ -227,7 +227,7 @@ mod tests {
         let analyzer = Analyzer::new(AnalyzerConfig::default_with_stopwords(&stopwords));
         let analyzer = analyzer.analyze(text);
         let tokens: Vec<_> = process_tokens(analyzer.tokens()).map(|(_, t)| t.text().to_string()).collect();
-        assert_eq!(tokens, ["为", "一", "包含", "一千多万", "目", "词", "的", "带", "标记", "平衡", "语料库"]);
+        assert_eq!(tokens, ["为", "一", "包含", "一千多万", "目词", "的", "带", "标记", "平衡", "语料库"]);
     }
 
     #[test]
diff --git a/meilisearch-http/tests/search.rs b/meilisearch-http/tests/search.rs
index 82804a019..cd1fae4bd 100644
--- a/meilisearch-http/tests/search.rs
+++ b/meilisearch-http/tests/search.rs
@@ -401,7 +401,7 @@ async fn search_with_attribute_to_highlight_wildcard_chinese() {
             "email": "SunTzu@chorizon.com",
             "phone": "+1 (810) 407-3258",
             "address": "吴国",
-            "about": "<em>孫武</em>（前544年－前470年或前496年），字長卿，春秋時期齊國人，著名軍事家、政治家，兵家代表人物。兵書《<em>孙子</em>兵法》的作者，後人尊稱為<em>孫子</em>、兵聖、東方兵聖，山東、蘇州等地尚有祀奉<em>孫武</em>的廟宇兵聖廟。其族人为乐安<em>孙</em>氏始祖，次<em>子孙</em>明为富春<em>孙</em>氏始祖。\r\n",
+            "about": "<em>孫武</em>（前544年－前470年或前496年），字長卿，春秋時期齊國人，著名軍事家、政治家，兵家代表人物。兵書《<em>孙子</em>兵法》的作者，後人尊稱為<em>孫子</em>、兵聖、東方兵聖，山東、蘇州等地尚有祀奉<em>孫武</em>的廟宇兵聖廟。其族人为乐安<em>孙氏</em>始祖，次<em>子孙</em>明为富春孙氏始祖。\r\n",
             "registered": "2014-10-20T10:13:32 -02:00",
             "latitude": 17.11935,
             "longitude": 65.38197,