From c61c53d9ec7decbb1cfec0e2c29eae01cb97d3f3 Mon Sep 17 00:00:00 2001
From: Adam Janovsky
Date: Tue, 23 Nov 2021 18:29:13 +0100
Subject: fix string sanitization during cpe matching

---
 sec_certs/model/cpe_matching.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sec_certs/model/cpe_matching.py b/sec_certs/model/cpe_matching.py
index b8c28bcf..ac96d1de 100644
--- a/sec_certs/model/cpe_matching.py
+++ b/sec_certs/model/cpe_matching.py
@@ -131,8 +131,7 @@ class CPEClassifier(BaseEstimator):
 
     @staticmethod
     def _replace_special_chars_with_space(string: str) -> str:
-        replace_non_letter_non_numbers_with_space = re.compile(r"(?ui)\W")
-        return replace_non_letter_non_numbers_with_space.sub(' ', string)
+        return re.sub(r'[^a-zA-Z0-9 \n\.]', ' ', string)
 
     @staticmethod
     def _discard_trademark_symbols(string: str) -> str:
-- 
cgit v1.3.1