paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-09 09:58:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

Fixes the creation of an archive file, even if noarchive was specified

Browse Source
This commit is contained in:
Trenton Holmes 2022-08-20 13:47:56 -07:00
parent 0878a199f4
commit b3b2519bf0
2 changed files with 37 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/paperless_tesseract/parsers.py
View File

@ -276,7 +276,10 @@ class RasterisedDocumentParser(DocumentParser):
self.log("debug", f"Calling OCRmyPDF with args: {args}") self.log("debug", f"Calling OCRmyPDF with args: {args}")
ocrmypdf.ocr(**args) ocrmypdf.ocr(**args)
self.archive_path = archive_path # Only create archive file if archiving isn't being skipped
if settings.OCR_MODE != "skip_noarchive":
self.archive_path = archive_path
self.text = self.extract_text(sidecar_file, archive_path) self.text = self.extract_text(sidecar_file, archive_path)
if not self.text: if not self.text:

34
src/paperless_tesseract/tests/test_parser.py
View File

@ -364,6 +364,16 @@ class TestParser(DirectoriesMixin, TestCase):
@override_settings(OCR_MODE="skip_noarchive") @override_settings(OCR_MODE="skip_noarchive")
def test_skip_noarchive_withtext(self): def test_skip_noarchive_withtext(self):
"""
GIVEN:
- File with existing text layer
- OCR mode set to skip_noarchive
WHEN:
- Document is parsed
THEN:
- Text from images is extracted
- No archive file is created
"""
parser = RasterisedDocumentParser(None) parser = RasterisedDocumentParser(None)
parser.parse( parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-digital.pdf"), os.path.join(self.SAMPLE_FILES, "multi-page-digital.pdf"),
@ -377,17 +387,29 @@ class TestParser(DirectoriesMixin, TestCase):
@override_settings(OCR_MODE="skip_noarchive") @override_settings(OCR_MODE="skip_noarchive")
def test_skip_noarchive_notext(self): def test_skip_noarchive_notext(self):
"""
GIVEN:
- File with text contained in images but no text layer
- OCR mode set to skip_noarchive
WHEN:
- Document is parsed
THEN:
- Text from images is extracted
- No archive file is created
"""
parser = RasterisedDocumentParser(None) parser = RasterisedDocumentParser(None)
parser.parse( parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"), os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"),
"application/pdf", "application/pdf",
) )
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings( self.assertContainsStrings(
parser.get_text().lower(), parser.get_text().lower(),
["page 1", "page 2", "page 3"], ["page 1", "page 2", "page 3"],
) )
self.assertIsNone(parser.archive_path)
@override_settings(OCR_MODE="skip") @override_settings(OCR_MODE="skip")
def test_multi_page_mixed(self): def test_multi_page_mixed(self):
parser = RasterisedDocumentParser(None) parser = RasterisedDocumentParser(None)
@ -408,6 +430,16 @@ class TestParser(DirectoriesMixin, TestCase):
@override_settings(OCR_MODE="skip_noarchive") @override_settings(OCR_MODE="skip_noarchive")
def test_multi_page_mixed_no_archive(self): def test_multi_page_mixed_no_archive(self):
"""
GIVEN:
- File with some text contained in images and some in text layer
- OCR mode set to skip_noarchive
WHEN:
- Document is parsed
THEN:
- Text from images is extracted
- No archive file is created
"""
parser = RasterisedDocumentParser(None) parser = RasterisedDocumentParser(None)
parser.parse( parser.parse(
os.path.join(self.SAMPLE_FILES, "multi-page-mixed.pdf"), os.path.join(self.SAMPLE_FILES, "multi-page-mixed.pdf"),