Add option to ignore certain dates in parse_date

PAPERLESS_IGNORE_DATES allows to specify a comma separated list of dates
to ignore during date parsing (from filename and content). This can be
used so specify dates that do appear often in documents but are usually
not the documents creation date (like your date of birth).
This commit is contained in:
jayme-github
2021-01-02 14:40:56 +01:00
parent 3550c677b6
commit cd15490e91
3 changed files with 34 additions and 4 deletions

View File

@@ -138,3 +138,18 @@ class TestDate(TestCase):
@override_settings(FILENAME_DATE_ORDER="YMD")
def test_filename_date_parse_invalid(self, *args):
self.assertIsNone(parse_date("/tmp/20 408000l 2475 - test.pdf", "No date in here"))
@override_settings(IGNORE_DATES=(datetime.date(2019, 11, 3), datetime.date(2020, 1, 17)))
def test_ignored_dates(self, *args):
text = (
"lorem ipsum 110319, 20200117 and lorem 13.02.2018 lorem "
"ipsum"
)
date = parse_date("", text)
self.assertEqual(
date,
datetime.datetime(
2018, 2, 13, 0, 0,
tzinfo=tz.gettz(settings.TIME_ZONE)
)
)