From 2421f559be12cbc575e0eada8d61576fceb12e5a Mon Sep 17 00:00:00 2001 From: Daniel Quinn <code@danielquinn.org> Date: Fri, 12 Feb 2016 08:27:09 +0000 Subject: [PATCH] Simpler regex --- src/documents/consumer.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/documents/consumer.py b/src/documents/consumer.py index 643ac4f66..777047b03 100644 --- a/src/documents/consumer.py +++ b/src/documents/consumer.py @@ -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(