From 01829933fdebe2e217eae0a8da9937f57b8010c8 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Mon, 8 May 2023 11:04:58 +0200
Subject: [PATCH] Update NORMs in tokenizer exceptions and related tests

---
 spacy/lang/sr/tokenizer_exceptions.py  |  3 +++
 spacy/tests/lang/sr/test_exceptions.py | 12 ++++++------
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/spacy/lang/sr/tokenizer_exceptions.py b/spacy/lang/sr/tokenizer_exceptions.py
index dcaa3e239..053306088 100755
--- a/spacy/lang/sr/tokenizer_exceptions.py
+++ b/spacy/lang/sr/tokenizer_exceptions.py
@@ -1,3 +1,4 @@
+from .lex_attrs import _cyr_to_latin_norm
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
 from ...symbols import ORTH, NORM
 from ...util import update_exc
@@ -89,5 +90,7 @@ _slang_exc = [
 for slang_desc in _slang_exc:
     _exc[slang_desc[ORTH]] = [slang_desc]
 
+for _exc_key in _exc:
+    _exc[_exc_key][0][NORM] = _cyr_to_latin_norm(_exc[_exc_key][0][NORM])
 
 TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
diff --git a/spacy/tests/lang/sr/test_exceptions.py b/spacy/tests/lang/sr/test_exceptions.py
index fa92e5e2d..e8819e628 100644
--- a/spacy/tests/lang/sr/test_exceptions.py
+++ b/spacy/tests/lang/sr/test_exceptions.py
@@ -2,15 +2,15 @@ import pytest
 
 
 @pytest.mark.parametrize(
-    "text,norms,lemmas",
+    "text,norms",
     [
-        ("о.г.", ["ове године"], ["ова година"]),
-        ("чет.", ["четвртак"], ["четвртак"]),
-        ("гђа", ["госпођа"], ["госпођа"]),
-        ("ил'", ["или"], ["или"]),
+        ("о.г.", ["ove godine"]),
+        ("чет.", ["četvrtak"]),
+        ("гђа", ["gospođa"]),
+        ("ил'", ["ili"]),
     ],
 )
-def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms, lemmas):
+def test_sr_tokenizer_abbrev_exceptions(sr_tokenizer, text, norms):
     tokens = sr_tokenizer(text)
     assert len(tokens) == 1
     assert [token.norm_ for token in tokens] == norms