diff options
| author | Adam Janovsky | 2021-11-23 18:29:13 +0100 |
|---|---|---|
| committer | Adam Janovsky | 2021-11-23 18:29:13 +0100 |
| commit | c61c53d9ec7decbb1cfec0e2c29eae01cb97d3f3 (patch) | |
| tree | e44cdf680b07c392e4bc48ac93cf385cd89b0f2e | |
| parent | 399ba59eaef0e785c239b3c4c257696e34a4b440 (diff) | |
| download | sec-certs-c61c53d9ec7decbb1cfec0e2c29eae01cb97d3f3.tar.gz sec-certs-c61c53d9ec7decbb1cfec0e2c29eae01cb97d3f3.tar.zst sec-certs-c61c53d9ec7decbb1cfec0e2c29eae01cb97d3f3.zip | |
fix string sanitization during cpe matching
| -rw-r--r-- | sec_certs/model/cpe_matching.py | 3 |
1 files changed, 1 insertions, 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: |