From c83c3cd7967c2833d0b4fab63b8c7528532c7421 Mon Sep 17 00:00:00 2001
From: Kerollmops <clement@meilisearch.com>
Date: Wed, 7 Sep 2022 14:11:44 +0200
Subject: [PATCH] Add a test to make sure that long words are correctly skipped

---
 milli/src/update/index_documents/mod.rs | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/milli/src/update/index_documents/mod.rs b/milli/src/update/index_documents/mod.rs
index 23618b478..365b0d024 100644
--- a/milli/src/update/index_documents/mod.rs
+++ b/milli/src/update/index_documents/mod.rs
@@ -1741,4 +1741,22 @@ mod tests {
         index.add_documents(doc3).unwrap_err();
         index.add_documents(doc4).unwrap_err();
     }
+
+    #[test]
+    fn long_words_must_be_skipped() {
+        let index = TempIndex::new();
+
+        // this is obviousy too long
+        let long_word = "lol".repeat(1000);
+        let doc1 = documents! {[{
+            "id": "1",
+            "title": long_word.clone(),
+        }]};
+
+        index.add_documents(doc1).unwrap();
+
+        let rtxn = index.read_txn().unwrap();
+        let words_fst = index.words_fst(&rtxn).unwrap();
+        assert!(!words_fst.contains(&long_word));
+    }
 }