smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-13 18:17:02 +01:00
Code Issues Projects Releases Packages Wiki Activity

Mock out the nltk portions so the data doesn't need to be downloaded

Browse source
This commit is contained in:
Trenton Holmes 2022-09-15 19:40:21 -07:00 • committed by Trenton H
parent a7e1ba82d6
commit f7cd6974c5
2 changed files with 13 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

14
src/documents/tests/test_classifier.py
View file

@ -1,9 +1,9 @@
import os
import re
import tempfile
from pathlib import Path
from unittest import mock
import documents
import pytest
from django.conf import settings
from django.test import override_settings
@ -20,10 +20,19 @@ from documents.models import Tag
from documents.tests.utils import DirectoriesMixin
def dummy_preprocess(content: str):
content = content.lower().strip()
content = re.sub(r"\s+", " ", content)
return content
class TestClassifier(DirectoriesMixin, TestCase):
def setUp(self):
super().setUp()
self.classifier = DocumentClassifier()
self.classifier.preprocess_content = mock.MagicMock(
side_effect=dummy_preprocess,
)
def generate_test_data(self):
self.c1 = Correspondent.objects.create(
@ -192,6 +201,8 @@ class TestClassifier(DirectoriesMixin, TestCase):
new_classifier = DocumentClassifier()
new_classifier.load()
new_classifier.preprocess_content = mock.MagicMock(side_effect=dummy_preprocess)
self.assertFalse(new_classifier.train())
# @override_settings(
@ -215,6 +226,7 @@ class TestClassifier(DirectoriesMixin, TestCase):
new_classifier = DocumentClassifier()
new_classifier.load()
new_classifier.preprocess_content = mock.MagicMock(side_effect=dummy_preprocess)
self.assertCountEqual(new_classifier.predict_tags(self.doc2.content), [45, 12])