smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-16 11:36:39 +01:00
Code Issues Projects Releases Packages Wiki Activity

Adds testing coverage of multipage TIFF with alpha, without and with alpha/sRGB

Browse source
This commit is contained in:
Trenton H 2023-01-03 08:21:23 -08:00
parent 59e0c1fe4e
commit 0fd51e35e1
4 changed files with 63 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

BIN
src/paperless_tesseract/tests/samples/multi-page-images-alpha-rgb.tiff Normal file
View file

Binary file not shown.

BIN
src/paperless_tesseract/tests/samples/multi-page-images-alpha.tiff Normal file
View file

Binary file not shown.

BIN
src/paperless_tesseract/tests/samples/multi-page-images.tiff Normal file
View file

Binary file not shown.

63
src/paperless_tesseract/tests/test_parser.py
View file

@ -542,6 +542,69 @@ class TestParser(DirectoriesMixin, TestCase):
],
)
def test_multi_page_tiff(self):
"""
GIVEN:
- Multi-page TIFF image
WHEN:
- Image is parsed
THEN:
- Text from all pages extracted
"""
parser = RasterisedDocumentParser(None)
parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images.tiff"),
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
)
def test_multi_page_tiff_alpha(self):
"""
GIVEN:
- Multi-page TIFF image
- Image include an alpha channel
WHEN:
- Image is parsed
THEN:
- Text from all pages extracted
"""
parser = RasterisedDocumentParser(None)
parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha.tiff"),
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
)
def test_multi_page_tiff_alpha_srgb(self):
"""
GIVEN:
- Multi-page TIFF image
- Image include an alpha channel
- Image is srgb colorspace
WHEN:
- Image is parsed
THEN:
- Text from all pages extracted
"""
parser = RasterisedDocumentParser(None)
parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images-alpha-rgb.tiff"),
"image/tiff",
)
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(
parser.get_text().lower(),
["page 1", "page 2", "page 3"],
)
def test_ocrmypdf_parameters(self):
parser = RasterisedDocumentParser(None)
params = parser.construct_ocrmypdf_parameters(