paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-19 10:19:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

testing the new noarchive option.

Browse Source
This commit is contained in:
jonaswinkler 2020-12-01 14:30:13 +01:00
parent fd3df1ec58
commit 12fa844c7f
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
src/paperless_tesseract/tests/test_parser.py
View File

@ -233,3 +233,17 @@ class TestParser(DirectoriesMixin, TestCase):
self.assertContainsStrings(parser.get_text().lower(), ["page 1"]) self.assertContainsStrings(parser.get_text().lower(), ["page 1"])
self.assertFalse("page 2" in parser.get_text().lower()) self.assertFalse("page 2" in parser.get_text().lower())
self.assertFalse("page 3" in parser.get_text().lower()) self.assertFalse("page 3" in parser.get_text().lower())
@override_settings(OCR_MODE="skip_noarchive")
def test_skip_noarchive_withtext(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-digital.pdf"), "application/pdf")
self.assertIsNone(parser.archive_path)
self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2", "page 3"])
@override_settings(OCR_MODE="skip_noarchive")
def test_skip_noarchive_notext(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"), "application/pdf")
self.assertTrue(os.path.join(parser.archive_path))
self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2", "page 3"])