Tweak the date guesser to not allow dates prior to 1900 (#414)

This commit is contained in:
Daniel Quinn
2018-10-01 20:03:27 +01:00
parent f3ed677f4d
commit 0a4338143a
2 changed files with 31 additions and 7 deletions

View File

@@ -384,3 +384,16 @@ class TestDate(TestCase):
document.get_date(),
datetime.datetime(2017, 12, 31, 0, 0, tzinfo=tz.tzutc())
)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
return_value="01-07-0590 00:00:00"
)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SCRATCH
)
def test_crazy_date(self, *args):
document = RasterisedDocumentParser("/dev/null")
document.get_text()
self.assertIsNone(document.get_date())