smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-07 15:25:41 +01:00
Code Issues Projects Releases Packages Wiki Activity

updated the classifier. Its now much faster and does not retrain when data hasnt changed.

Browse source
This commit is contained in:
Jonas Winkler 2020-11-06 14:46:06 +01:00
parent 9fa5eac9b9
commit 296c113b16
4 changed files with 109 additions and 75 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/documents/consumer.py
View file

@ -10,7 +10,7 @@ from django.db import transaction
from django.utils import timezone
from paperless.db import GnuPG
from .classifier import DocumentClassifier
from .classifier import DocumentClassifier, IncompatibleClassifierVersionError
from .models import Document, FileInfo
from .parsers import ParseError, get_parser_class
from .signals import (
@ -133,11 +133,8 @@ class Consumer:
try:
self.classifier.reload()
classifier = self.classifier
except FileNotFoundError:
self.log("warning", "Cannot classify documents, classifier "
"model file was not found. Consider "
"running python manage.py "
"document_create_classifier.")
except (FileNotFoundError, IncompatibleClassifierVersionError) as e:
logging.getLogger(__name__).warning("Cannot classify documents: {}.".format(e))
document_consumption_finished.send(
sender=self.__class__,