From 98a479c48d8056a1263d404ee7abf2b5eececb35 Mon Sep 17 00:00:00 2001 From: Narek Date: Mon, 17 Feb 2025 13:44:53 +0400 Subject: [PATCH] change Armenian word for test --- charabia/src/normalizer/lowercase.rs | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/charabia/src/normalizer/lowercase.rs b/charabia/src/normalizer/lowercase.rs index f80e232..bf58be7 100644 --- a/charabia/src/normalizer/lowercase.rs +++ b/charabia/src/normalizer/lowercase.rs @@ -52,7 +52,7 @@ mod test { ..Default::default() }, Token { - lemma: Owned("ֆիզիկոսը".to_string()), + lemma: Owned("ՀայասՏան".to_string()), char_end: 8, byte_end: 16, script: Script::Armenian, @@ -83,10 +83,20 @@ mod test { ..Default::default() }, Token { - lemma: Owned("ֆիզիկոսը".to_string()), + lemma: Owned("հայաստան".to_string()), char_end: 8, byte_end: 16, script: Script::Armenian, + char_map: Some(vec![ + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + ]), ..Default::default() }, ] @@ -115,11 +125,21 @@ mod test { ..Default::default() }, Token { - lemma: Owned("ֆիզիկոսը".to_string()), + lemma: Owned("հայաստան".to_string()), char_end: 8, byte_end: 16, script: Script::Armenian, kind: TokenKind::Word, + char_map: Some(vec![ + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + (2, 2), + ]), ..Default::default() }, ]