paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-08-20 00:56:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Merge pull request #2732 from bdr99/skip_neverarchive"

Browse Source 
This reverts commit 77b23d3acb, reversing
changes made to 5d8aa27831.
This commit is contained in:
Brandon Rothweiler
2023-02-23 21:26:53 -05:00
parent dbea2acc8f
commit 8a89f5ae27
4 changed files with 5 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
src/paperless_tesseract/tests/test_parser.py
View File

@@ -438,52 +438,6 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
self.assertIsNotNone(parser.archive_path)
@override_settings(OCR_MODE="skip_neverarchive")
def test_skip_neverarchive_withtext(self):
"""
GIVEN:
- File with existing text layer
- OCR mode set to skip_neverarchive
WHEN:
- Document is parsed
THEN:
- Text from images is extracted
- No archive file is created
"""
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_neverarchive")
def test_skip_neverarchive_notext(self):
"""
GIVEN:
- File with text contained in images but no text layer
- OCR mode set to skip_neverarchive
WHEN:
- Document is parsed
THEN:
- Text from images is extracted
- No archive file is created
"""
parser = RasterisedDocumentParser(None)
parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images.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")
def test_multi_page_mixed(self):
"""