paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

Simpler regex

Browse Source
This commit is contained in:
Daniel Quinn 2016-02-12 08:27:09 +00:00
parent a022fcb8f1
commit 2421f559be
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/documents/consumer.py
View File

@ -47,11 +47,11 @@ class Consumer(Renderable):
DEFAULT_OCR_LANGUAGE = settings.OCR_LANGUAGE
REGEX_TITLE = re.compile(
r"^.*/([^/]*)\.(pdf|jpe?g|png|gif|tiff)$",
r"^.*/(.*)\.(pdf|jpe?g|png|gif|tiff)$",
flags=re.IGNORECASE
)
REGEX_SENDER_TITLE = re.compile(
r"^.*/(.+) - ([^/]+)\.(pdf|jpe?g|png|gif|tiff)$",
r"^.*/(.+) - (.*)\.(pdf|jpe?g|png|gif|tiff)$",
flags=re.IGNORECASE
)
REGEX_SENDER_TITLE_TAGS = re.compile(
@ -233,6 +233,7 @@ class Consumer(Renderable):
def _store(self, text, doc):
sender, title, tags, file_type = self._guess_attributes_from_name(doc)
tags = list(tags)
lower_text = text.lower()
relevant_tags = set(