smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-14 10:36:58 +01:00
Code Issues Projects Releases Packages Wiki Activity

Fix language guesses in tests

Browse source 
It turns out that the Lorem ipsum text in the sample files was confuing the language guesser, causing it to think the file was in Catalan and not English or German.
This commit is contained in:
Daniel Quinn 2018-12-01 15:55:02 +00:00
parent c5488dcb98
commit c1d18c1e83
6 changed files with 7 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/paperless_tesseract/tests/test_date.py
View file

@ -5,7 +5,7 @@ from unittest import mock
from uuid import uuid4
from dateutil import tz
from django.test import TestCase
from django.test import TestCase, override_settings
from ..parsers import RasterisedDocumentParser
@ -211,6 +211,7 @@ class TestDate(TestCase):
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SCRATCH
)
@override_settings(OCR_LANGUAGE="deu")
def test_get_text_3_pdf(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_3.pdf")
document = RasterisedDocumentParser(input_file)
@ -225,6 +226,7 @@ class TestDate(TestCase):
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SCRATCH
)
@override_settings(OCR_LANGUAGE="deu")
def test_get_text_3_png(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_3.png")
document = RasterisedDocumentParser(input_file)
@ -239,6 +241,7 @@ class TestDate(TestCase):
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SCRATCH
)
@override_settings(OCR_LANGUAGE="eng")
def test_get_text_4_pdf(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_4.pdf")
document = RasterisedDocumentParser(input_file)
@ -253,6 +256,7 @@ class TestDate(TestCase):
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SCRATCH
)
@override_settings(OCR_LANGUAGE="eng")
def test_get_text_4_png(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_4.png")
document = RasterisedDocumentParser(input_file)