paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Adding more test coverage, in particular around Tika and its parser

Browse Source
This commit is contained in:
Trenton H
2023-02-02 12:46:49 -08:00
parent 8154c7b53a
commit bdcba570cb
8 changed files with 164 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/paperless_tesseract/parsers.py
View File

@@ -161,7 +161,7 @@ class RasterisedDocumentParser(DocumentParser):
except Exception:
# TODO catch all for various issues with PDFminer.six.
# If PDFminer fails, fall back to OCR.
# If pdftotext fails, fall back to OCR.
self.log(
"warning",
"Error while getting text from PDF document with " "pdfminer.six",

15
src/paperless_tesseract/tests/test_parser.py
View File

@@ -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: