def test_image_calc_a4_dpi(self):
parser = RasterisedDocumentParser(None)
dpi = parser.calculate_a4_dpi(
os.path.join(self.SAMPLE_FILES, "simple-no-dpi.png"))
self.assertEqual(dpi, 62)
def test_parse_text_simple_language_match(self):
parser = RasterisedDocumentParser(self.get_input_file(1), uuid.uuid4())
text = parser.get_text()
self.assertEqual(text, "line 0")
self.assertListEqual([args[1] for args in image_to_string_calls],
["eng"])
def test_encrypted(self):
parser = RasterisedDocumentParser(None)
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"])
def test_parse_text_lang_mismatch(self):
parser = RasterisedDocumentParser(self.get_input_file(3), uuid.uuid4())
text = parser.get_text()
self.assertEqual(text, "line 0 line 1 line 2")
self.assertListEqual([args[1] for args in image_to_string_calls],
["eng", "deu", "deu", "deu"])
def test_multi_page_mixed_no_archive(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-mixed.pdf"),
"application/pdf")
self.assertIsNone(parser.archive_path)
self.assertContainsStrings(parser.get_text().lower(),
["page 4", "page 5", "page 6"])
def test_parse_text_lang_not_installed(self):
parser = RasterisedDocumentParser(self.get_input_file(4), uuid.uuid4())
text = parser.get_text()
self.assertEqual(text, "line 0 line 1 line 2 line 3")
self.assertListEqual([args[1] for args in image_to_string_calls],
["eng", "eng", "eng", "eng"])
def test_skip_noarchive_notext(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"),
"application/pdf")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(parser.get_text().lower(),
["page 1", "page 2", "page 3"])
def test_with_form_error(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "with-form.pdf"), "application/pdf")
self.assertIsNone(parser.archive_path)
self.assertContainsStrings(parser.get_text(), ["Please enter your name in here:", "This is a PDF document with a form."])
def test_is_ocred(self, m2, m):
parser = RasterisedDocumentParser("", uuid.uuid4())
m.return_value = "lots of text lots of text lots of text lots of text lots of text lots of text " \
"lots of text lots of text lots of text lots of text lots of text lots of text " \
"lots of text lots of text lots of text lots of text lots of text lots of text "
parser.get_text()
self.assertEqual(m.call_count, 2)
self.assertEqual(m2.call_count, 0)
def test_parse_empty_doc(self):
parser = RasterisedDocumentParser(self.get_input_file(0), uuid.uuid4())
try:
parser.get_text()
except ParseError as e:
self.assertEqual("Empty document, nothing to do.", str(e))
else:
self.fail("Should raise exception")
def test_encrypted(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "encrypted.pdf"),
"application/pdf")
self.assertIsNone(parser.archive_path)
self.assertEqual(parser.get_text(), "")
def test_get_dpi(self):
parser = RasterisedDocumentParser(None)
dpi = parser.get_dpi(os.path.join(self.SAMPLE_FILES, "simple-no-dpi.png"))
self.assertEqual(dpi, None)
dpi = parser.get_dpi(os.path.join(self.SAMPLE_FILES, "simple.png"))
self.assertEqual(dpi, 72)
def test_simple_digital(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-digital.pdf"), "application/pdf")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(parser.get_text(), ["This is a test document."])
def test_image_no_dpi_default(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-no-dpi.png"), "image/png")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(parser.get_text().lower(), ["this is a test document."])
def test_rotate(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "rotated.pdf"), "application/pdf")
self.assertContainsStrings(parser.get_text(), [
"This is the text that appears on the first page. It’s a lot of text.",
"Even if the pages are rotated, OCRmyPDF still gets the job done.",
"This is a really weird file with lots of nonsense text.",
"If you read this, it’s your own fault. Also check your screen orientation."
])
def test_image_calc_a4_dpi(self, m):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-no-dpi.png"), "image/png")
m.assert_called_once()
args, kwargs = m.call_args
self.assertEqual(kwargs['image_dpi'], 62)
def test_multi_page_mixed(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-mixed.pdf"), "application/pdf")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2", "page 3", "page 4", "page 5", "page 6"])
with open(os.path.join(parser.tempdir, "sidecar.txt")) as f:
sidecar = f.read()
self.assertIn("[OCR skipped on page(s) 4-6]", sidecar)
def test_thumbnail_fallback(self, m):
def call_convert(input_file, output_file, **kwargs):
if ".pdf" in input_file:
raise ParseError("Does not compute.")
else:
run_convert(input_file=input_file, output_file=output_file, **kwargs)
m.side_effect = call_convert
parser = RasterisedDocumentParser(uuid.uuid4())
parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'), "application/pdf")
def test_with_form_error_notext(self):
parser = RasterisedDocumentParser(None)
def f():
parser.parse(os.path.join(self.SAMPLE_FILES, "with-form.pdf"), "application/pdf")
self.assertRaises(ParseError, f)
def test_image_simple_alpha_fail(self):
parser = RasterisedDocumentParser(None)
def f():
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-alpha.png"), "image/png")
self.assertRaises(ParseError, f)
def test_image_dpi_fail(self, m):
m.return_value = None
parser = RasterisedDocumentParser(None)
def f():
parser.parse(os.path.join(self.SAMPLE_FILES, "simple-no-dpi.png"), "image/png")
self.assertRaises(ParseError, f)
def test_ocrmypdf_parameters(self):
parser = RasterisedDocumentParser(None)
params = parser.construct_ocrmypdf_parameters(
input_file="input.pdf",
output_file="output.pdf",
sidecar_file="sidecar.txt",
mime_type="application/pdf",
safe_fallback=False)
self.assertEqual(params['input_file'], "input.pdf")
self.assertEqual(params['output_file'], "output.pdf")
self.assertEqual(params['sidecar'], "sidecar.txt")
with override_settings(OCR_CLEAN="none"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertNotIn("clean", params)
self.assertNotIn("clean_final", params)
with override_settings(OCR_CLEAN="clean"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertTrue(params['clean'])
self.assertNotIn("clean_final", params)
with override_settings(OCR_CLEAN="clean-final", OCR_MODE="skip"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertTrue(params['clean_final'])
self.assertNotIn("clean", params)
with override_settings(OCR_CLEAN="clean-final", OCR_MODE="redo"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertTrue(params['clean'])
self.assertNotIn("clean_final", params)
with override_settings(OCR_DESKEW=True, OCR_MODE="skip"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertTrue(params['deskew'])
with override_settings(OCR_DESKEW=True, OCR_MODE="redo"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertNotIn('deskew', params)
with override_settings(OCR_DESKEW=False, OCR_MODE="skip"):
params = parser.construct_ocrmypdf_parameters("", "", "", "")
self.assertNotIn('deskew', params)
def test_multi_page_analog_pages_force(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"), "application/pdf")
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())
def test_thumbnail(self):
parser = RasterisedDocumentParser(uuid.uuid4())
parser.get_thumbnail(os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'), "application/pdf")
def test_get_text_from_pdf(self):
parser = RasterisedDocumentParser(uuid.uuid4())
text = parser.extract_text(None, os.path.join(self.SAMPLE_FILES, 'simple-digital.pdf'))
self.assertContainsStrings(text.strip(), ["This is a test document."])
def test_tiff(self):
parser = RasterisedDocumentParser(None)
parser.parse(os.path.join(self.SAMPLE_FILES, "simple.tif"), "image/tiff")
self.assertTrue(os.path.isfile(parser.archive_path))
self.assertTrue("this is a test document" in parser.get_text().lower())
def test_thumbnail(self):
parser = RasterisedDocumentParser(
os.path.join(self.SAMPLE_FILES, 'simple.pdf'), uuid.uuid4())
parser.get_thumbnail()
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))
