From 98c1db81cd98ff301f0b0ee10ffc3be5d4c90b58 Mon Sep 17 00:00:00 2001
From: Narek <narek.hakobyan.07@gmail.com>
Date: Wed, 12 Feb 2025 14:52:33 +0400
Subject: [PATCH] add test for Armenian

---
 charabia/src/normalizer/lowercase.rs | 106 ++++++++++++++++-----------
 1 file changed, 63 insertions(+), 43 deletions(-)

diff --git a/charabia/src/normalizer/lowercase.rs b/charabia/src/normalizer/lowercase.rs
index dc543fc..5b013ca 100644
--- a/charabia/src/normalizer/lowercase.rs
+++ b/charabia/src/normalizer/lowercase.rs
@@ -44,57 +44,77 @@ mod test {
 
     fn tokens() -> Vec<Token<'static>> {
         vec![Token {
-            lemma: Owned("PascalCase".to_string()),
-            char_end: 10,
-            byte_end: 10,
-            script: Script::Latin,
-            ..Default::default()
-        }]
+                lemma: Owned("PascalCase".to_string()),
+                char_end: 10,
+                byte_end: 10,
+                script: Script::Latin,
+                ..Default::default()
+            }, Token {
+                lemma: Owned("ֆիզիկոսը".to_string()),
+                char_end: 8,
+                byte_end: 16,
+                script: Script::Armenian,
+                ..Default::default()
+            }]
     }
 
     fn normalizer_result() -> Vec<Token<'static>> {
         vec![Token {
-            lemma: Owned("pascalcase".to_string()),
-            char_end: 10,
-            byte_end: 10,
-            script: Script::Latin,
-            char_map: Some(vec![
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-            ]),
-            ..Default::default()
-        }]
+                lemma: Owned("pascalcase".to_string()),
+                char_end: 10,
+                byte_end: 10,
+                script: Script::Latin,
+                char_map: Some(vec![
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                ]),
+                ..Default::default()
+            }, Token {
+                lemma: Owned("ֆիզիկոսը".to_string()),
+                char_end: 8,
+                byte_end: 16,
+                script: Script::Armenian,
+                ..Default::default()
+            }]
     }
 
     fn normalized_tokens() -> Vec<Token<'static>> {
         vec![Token {
-            lemma: Owned("pascalcase".to_string()),
-            char_end: 10,
-            byte_end: 10,
-            script: Script::Latin,
-            kind: TokenKind::Word,
-            char_map: Some(vec![
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-                (1, 1),
-            ]),
-            ..Default::default()
-        }]
+                lemma: Owned("pascalcase".to_string()),
+                char_end: 10,
+                byte_end: 10,
+                script: Script::Latin,
+                kind: TokenKind::Word,
+                char_map: Some(vec![
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                    (1, 1),
+                ]),
+                ..Default::default()
+            },
+            Token {
+                lemma: Owned("ֆիզիկոսը".to_string()),
+                char_end: 8,
+                byte_end: 16,
+                script: Script::Armenian,
+                kind: TokenKind::Word,
+                ..Default::default()
+            }]
     }
 
     test_normalizer!(LowercaseNormalizer, tokens(), normalizer_result(), normalized_tokens());