mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-10-18 22:08:14 +00:00
Trenton H
03ac4aed7e
Test modules in paperless, paperless_mail and documents imported filesystem assertions, the migration test base, the retry helper and the streaming-response reader out of documents/tests/utils.py, which kept each app's tests coupled to another app's test package. They now live in paperless_testing, and the progress manager fake is renamed FakeProgressManager and now subclasses the real ProgressManager, overriding only the transport, so the payload it records is built by the production code. The twenty places that patched documents.tasks.ProgressManager by hand now use a fake_progress_manager fixture.
271 lines
9.5 KiB
Python
271 lines
9.5 KiB
Python
import json
|
|
|
|
from django.test import TestCase
|
|
from django.test import override_settings
|
|
|
|
from paperless.models import ApplicationConfiguration
|
|
from paperless.models import CleanChoices
|
|
from paperless.models import ColorConvertChoices
|
|
from paperless.models import ModeChoices
|
|
from paperless.models import OutputTypeChoices
|
|
from paperless.parsers.tesseract import RasterisedDocumentParser
|
|
from paperless_testing.assertions import FileSystemAssertsMixin
|
|
from paperless_testing.dirs import DirectoriesMixin
|
|
|
|
|
|
class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
|
|
@classmethod
|
|
def setUpTestData(cls) -> None:
|
|
super().setUpTestData()
|
|
ApplicationConfiguration.objects.get_or_create()
|
|
|
|
@staticmethod
|
|
def get_params():
|
|
"""
|
|
Helper to get just the OCRMyPDF parameters from the parser
|
|
"""
|
|
return RasterisedDocumentParser(None).construct_ocrmypdf_parameters(
|
|
input_file="input.pdf",
|
|
output_file="output.pdf",
|
|
sidecar_file="sidecar.txt",
|
|
mime_type="application/pdf",
|
|
safe_fallback=False,
|
|
)
|
|
|
|
def test_db_settings_ocr_pages(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_PAGES than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_PAGES=10):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.pages = 5
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertEqual(params["pages"], "1-5")
|
|
|
|
def test_db_settings_ocr_language(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_LANGUAGE than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_LANGUAGE="eng+deu"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.language = "fra+ita"
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertEqual(params["language"], "fra+ita")
|
|
|
|
def test_db_settings_ocr_output_type(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_OUTPUT_TYPE than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_OUTPUT_TYPE="pdfa-3"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.output_type = OutputTypeChoices.PDF_A
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertEqual(params["output_type"], "pdfa")
|
|
|
|
def test_db_settings_ocr_mode(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_MODE than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized (AUTO mode with skip_text=True
|
|
triggers skip_text; AUTO mode alone does not add any extra flag)
|
|
"""
|
|
# AUTO mode with skip_text=True explicitly passed: skip_text is set
|
|
with override_settings(OCR_MODE="redo"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.mode = ModeChoices.AUTO
|
|
instance.save()
|
|
|
|
params = RasterisedDocumentParser(None).construct_ocrmypdf_parameters(
|
|
input_file="input.pdf",
|
|
output_file="output.pdf",
|
|
sidecar_file="sidecar.txt",
|
|
mime_type="application/pdf",
|
|
safe_fallback=False,
|
|
skip_text=True,
|
|
)
|
|
self.assertTrue(params["skip_text"])
|
|
self.assertNotIn("redo_ocr", params)
|
|
self.assertNotIn("force_ocr", params)
|
|
|
|
# AUTO mode alone (no skip_text): no extra OCR flag is set
|
|
with override_settings(OCR_MODE="redo"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.mode = ModeChoices.AUTO
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertNotIn("skip_text", params)
|
|
self.assertNotIn("redo_ocr", params)
|
|
self.assertNotIn("force_ocr", params)
|
|
|
|
def test_db_settings_ocr_clean(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_CLEAN than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_CLEAN="clean-final"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.unpaper_clean = CleanChoices.CLEAN
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertTrue(params["clean"])
|
|
self.assertNotIn("clean_final", params)
|
|
|
|
with override_settings(OCR_CLEAN="clean-final"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.unpaper_clean = CleanChoices.FINAL
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertTrue(params["clean_final"])
|
|
self.assertNotIn("clean", params)
|
|
|
|
def test_db_settings_ocr_deskew(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_DESKEW than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_DESKEW=False):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.deskew = True
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertTrue(params["deskew"])
|
|
|
|
def test_db_settings_ocr_rotate(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_ROTATE_PAGES
|
|
and OCR_ROTATE_PAGES_THRESHOLD than configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_ROTATE_PAGES=False, OCR_ROTATE_PAGES_THRESHOLD=30.0):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
assert instance is not None
|
|
instance.rotate_pages = True
|
|
instance.rotate_pages_threshold = 15.0
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertTrue(params["rotate_pages"])
|
|
self.assertAlmostEqual(params["rotate_pages_threshold"], 15.0)
|
|
|
|
def test_db_settings_ocr_max_pixels(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_MAX_IMAGE_PIXELS than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_MAX_IMAGE_PIXELS=2_000_000.0):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.max_image_pixels = 1_000_000.0
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertAlmostEqual(params["max_image_mpixels"], 1.0)
|
|
|
|
def test_db_settings_ocr_color_convert(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_COLOR_CONVERSION_STRATEGY than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(OCR_COLOR_CONVERSION_STRATEGY="LeaveColorUnchanged"):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.color_conversion_strategy = ColorConvertChoices.INDEPENDENT
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
self.assertEqual(
|
|
params["color_conversion_strategy"],
|
|
"UseDeviceIndependentColor",
|
|
)
|
|
|
|
def test_ocr_user_args(self) -> None:
|
|
"""
|
|
GIVEN:
|
|
- Django settings defines different value for OCR_USER_ARGS than
|
|
configuration object
|
|
WHEN:
|
|
- OCR parameters are constructed
|
|
THEN:
|
|
- Configuration from database is utilized
|
|
"""
|
|
with override_settings(
|
|
OCR_USER_ARGS=json.dumps({"continue_on_soft_render_error": True}),
|
|
):
|
|
instance = ApplicationConfiguration.objects.all().first()
|
|
assert instance is not None
|
|
instance.user_args = {"unpaper_args": "--pre-rotate 90"}
|
|
instance.save()
|
|
|
|
params = self.get_params()
|
|
|
|
self.assertIn("unpaper_args", params)
|
|
self.assertEqual(
|
|
params["unpaper_args"],
|
|
"--pre-rotate 90",
|
|
)
|