smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-11 09:07:18 +01:00
Code Issues Projects Releases Packages Wiki Activity

optimize regex

Browse source
This commit is contained in:
phail 2022-11-20 12:48:03 +01:00
parent 073c3c8fed
commit d132eba143
2 changed files with 3 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/paperless_mail/parsers.py
View file

@ -105,9 +105,8 @@ class MailDocumentParser(DocumentParser):
def parse(self, document_path, mime_type, file_name=None):
def strip_text(text: str):
text = re.sub("\t", " ", text)
text = re.sub(" +", " ", text)
text = re.sub("(\n *)+", "\n", text)
text = re.sub(r"\s+", " ", text)
text = re.sub(r"(\n *)+", "\n", text)
return text.strip()
mail = self.get_parsed(document_path)