mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-08-20 00:56:26 +00:00
Adding more test coverage, in particular around Tika and its parser
This commit is contained in:
@@ -364,7 +364,7 @@ class TestParser(DirectoriesMixin, TestCase):
|
||||
)
|
||||
self.assertTrue(os.path.isfile(parser.archive_path))
|
||||
self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2"])
|
||||
self.assertFalse("page 3" in parser.get_text().lower())
|
||||
self.assertNotIn("page 3", parser.get_text().lower())
|
||||
|
||||
@override_settings(OCR_PAGES=1, OCR_MODE="force")
|
||||
def test_multi_page_analog_pages_force(self):
|
||||
@@ -386,8 +386,8 @@ class TestParser(DirectoriesMixin, TestCase):
|
||||
)
|
||||
self.assertTrue(os.path.isfile(parser.archive_path))
|
||||
self.assertContainsStrings(parser.get_text().lower(), ["page 1"])
|
||||
self.assertFalse("page 2" in parser.get_text().lower())
|
||||
self.assertFalse("page 3" in parser.get_text().lower())
|
||||
self.assertNotIn("page 2", parser.get_text().lower())
|
||||
self.assertNotIn("page 3", parser.get_text().lower())
|
||||
|
||||
@override_settings(OCR_MODE="skip_noarchive")
|
||||
def test_skip_noarchive_withtext(self):
|
||||
@@ -660,6 +660,15 @@ class TestParser(DirectoriesMixin, TestCase):
|
||||
params = parser.construct_ocrmypdf_parameters("", "", "", "")
|
||||
self.assertNotIn("deskew", params)
|
||||
|
||||
with override_settings(OCR_MAX_IMAGE_PIXELS=1_000_001.0):
|
||||
params = parser.construct_ocrmypdf_parameters("", "", "", "")
|
||||
self.assertIn("max_image_mpixels", params)
|
||||
self.assertAlmostEqual(params["max_image_mpixels"], 1, places=4)
|
||||
|
||||
with override_settings(OCR_MAX_IMAGE_PIXELS=-1_000_001.0):
|
||||
params = parser.construct_ocrmypdf_parameters("", "", "", "")
|
||||
self.assertNotIn("max_image_mpixels", params)
|
||||
|
||||
def test_rtl_language_detection(self):
|
||||
"""
|
||||
GIVEN:
|
||||
|
Reference in New Issue
Block a user