Files
paperless-ngx/src/paperless_tesseract/tests/test_ocr.py
2020-11-25 14:51:32 +01:00

35 lines
939 B
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import os
from unittest import mock, skipIf
from django.test import TestCase
from ..parsers import strip_excess_whitespace
class TestOCR(TestCase):
text_cases = [
("simple string", "simple string"),
(
"simple newline\n testing string",
"simple newline\ntesting string"
),
(
"utf-8 строка с пробелами в конце ",
"utf-8 строка с пробелами в конце"
)
]
def test_strip_excess_whitespace(self):
for source, result in self.text_cases:
actual_result = strip_excess_whitespace(source)
self.assertEqual(
result,
actual_result,
"strip_exceess_whitespace({}) != '{}', but '{}'".format(
source,
result,
actual_result
)
)