paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-30 18:27:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

fixes #631

Browse Source
This commit is contained in:
jonaswinkler
2021-03-14 14:42:48 +01:00
parent 0ad2b05455
commit 40ce38254b
6 changed files with 63 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/paperless_tesseract/parsers.py
View File

@@ -291,6 +291,7 @@ class RasterisedDocumentParser(DocumentParser):
f"No text was found in {document_path}, the content will "
f"be empty."
)
self.text = ""
def strip_excess_whitespace(text):

BIN
src/paperless_tesseract/tests/samples/encrypted.pdf
View File

Binary file not shown.

BIN
src/paperless_tesseract/tests/samples/signed.pdf Normal file
View File

Binary file not shown.

25
src/paperless_tesseract/tests/test_parser.py
View File

@@ -81,8 +81,8 @@ class TestParser(DirectoriesMixin, TestCase):
def test_thumbnail(self):
parser = RasterisedDocumentParser(uuid.uuid4())
parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'), "application/pdf")
# dont really know how to test it, just call it and assert that it does not raise anything.
thumb = parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'), "application/pdf")
self.assertTrue(os.path.isfile(thumb))
@mock.patch("documents.parsers.run_convert")
def test_thumbnail_fallback(self, m):
@@ -96,8 +96,13 @@ class TestParser(DirectoriesMixin, TestCase):
m.side_effect = call_convert
parser = RasterisedDocumentParser(uuid.uuid4())
parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'), "application/pdf")
# dont really know how to test it, just call it and assert that it does not raise anything.
thumb = parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'), "application/pdf")
self.assertTrue(os.path.isfile(thumb))
def test_thumbnail_encrypted(self):
parser = RasterisedDocumentParser(uuid.uuid4())
thumb = parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'encrypted.pdf'), "application/pdf")
self.assertTrue(os.path.isfile(thumb))
def test_get_dpi(self):
parser = RasterisedDocumentParser(None)
@@ -135,6 +140,15 @@ class TestParser(DirectoriesMixin, TestCase):
self.assertIsNone(parser.archive_path)
self.assertContainsStrings(parser.get_text(), ["Please enter your name in here:", "This is a PDF document with a form."])
@override_settings(OCR_MODE="skip")
def test_signed(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "signed.pdf"), "application/pdf")
self.assertIsNone(parser.archive_path)
self.assertContainsStrings(parser.get_text(), ["This is a digitally signed PDF, created with Acrobat Pro for the Paperless project to enable", "automated testing of signed/encrypted PDFs"])
@override_settings(OCR_MODE="skip")
def test_encrypted(self):
parser = RasterisedDocumentParser(None)
@@ -142,7 +156,8 @@ class TestParser(DirectoriesMixin, TestCase):
parser.parse(os.path.join(self.SAMPLE_FILES, "encrypted.pdf"), "application/pdf")
self.assertIsNone(parser.archive_path)
self.assertContainsStrings(parser.get_text(), ["This is a digitally signed PDF, created with Acrobat Pro for the Paperless project to enable", "automated testing of signed/encrypted PDFs"])
self.assertEqual(parser.get_text(), "")
@override_settings(OCR_MODE="redo")
def test_with_form_error_notext(self):