smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-20 05:26:53 +01:00
Code Issues Projects Releases Packages Wiki Activity

Fixes the download and usage of the downloaded data

Browse source
This commit is contained in:
Trenton Holmes 2022-09-16 06:55:42 -07:00 • committed by Trenton H
parent 1262c121f0
commit 6523cf0c4b
4 changed files with 25 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/documents/classifier.py
View file

@ -306,6 +306,12 @@ class DocumentClassifier:
from nltk.corpus import stopwords
from nltk.stem import SnowballStemmer
import nltk
# Not really hacky, since it isn't private and is documented, but
# set the search path for NLTK data to the single location it should be in
nltk.data.path = [settings.NLTK_DIR]
if self.stemmer is None:
self.stemmer = SnowballStemmer("english")