paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-25 10:49:30 -05:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Modify one of date regexes (#5540)

Browse Source
This commit is contained in:
shamoon 2024-01-25 13:29:22 -08:00 committed by GitHub
parent 6fb4daf03e
commit ba0f4718e5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/documents/parsers.py
View File

@ -38,7 +38,7 @@ from documents.utils import copy_file_with_basic_stats
DATE_REGEX = re.compile(
r"(\b|(?!=([_-])))([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{4}|[0-9]{2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{1,2})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{1,2}[\. ]+[a-zA-Z]{3,9} ([0-9]{4}|[0-9]{2}))(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{1,2}[\. ]+[a-zA-Z]{3,9} [0-9]{4}|[a-zA-Z]{3,9} [0-9]{1,2}, [0-9]{4})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([^\W\d_]{3,9} [0-9]{1,2}, ([0-9]{4}))(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([^\W\d_]{3,9} [0-9]{4})(\b|(?=([_-])))|"
r"(\b|(?!=([_-])))([0-9]{1,2}[^ ]{2}[\. ]+[^ ]{3,9}[ \.\/-][0-9]{4})(\b|(?=([_-])))|"

7
src/documents/tests/test_date_parsing.py
View File

@ -201,6 +201,13 @@ class TestDate(TestCase):
datetime.datetime(2022, 3, 25, 0, 0, tzinfo=tz.gettz(settings.TIME_ZONE)),
)
def test_date_format_26(self):
text = "CHASE 0 September 25, 2019 JPMorgan Chase Bank, NA. P0 Box 182051"
self.assertEqual(
parse_date("", text),
datetime.datetime(2019, 9, 25, 0, 0, tzinfo=tz.gettz(settings.TIME_ZONE)),
)
def test_crazy_date_past(self, *args):
self.assertIsNone(parse_date("", "01-07-0590 00:00:00"))