paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-05-01 11:19:32 -05:00
Code Issues Packages Projects Releases Wiki Activity

Handle dateparser ValueErrors

Browse Source 
When parsing dates from the document text or filenames, correctly handle values
errors indicating broken dates. Newly added tests ensure that this handling
works properly.
This commit is contained in:
Johannes Wienke 2020-03-08 18:35:28 +01:00
parent 6531a67940
commit ebcfcea05b
2 changed files with 28 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/documents/parsers.py
View File

@ -108,7 +108,7 @@ class DocumentParser:
try:
date = __parser(date_string, self.FILENAME_DATE_ORDER)
except TypeError:
except (TypeError, ValueError):
# Skip all matches that do not parse to a proper date
continue
@ -134,7 +134,7 @@ class DocumentParser:
try:
date = __parser(date_string, self.DATE_ORDER)
except TypeError:
except (TypeError, ValueError):
# Skip all matches that do not parse to a proper date
continue

26
src/paperless_tesseract/tests/test_date.py
View File

@ -172,3 +172,29 @@ class TestDate(TestCase):
document = RasterisedDocumentParser("/dev/null")
document.get_text()
self.assertIsNone(document.get_date())
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
return_value="20 408000l 2475"
)
@mock.patch(MOCK_SCRATCH, SCRATCH)
def test_crazy_date_with_spaces(self, *args):
document = RasterisedDocumentParser("/dev/null")
document.get_text()
self.assertIsNone(document.get_date())
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.get_text",
return_value="No date in here"
)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser."
"FILENAME_DATE_ORDER",
new_callable=mock.PropertyMock,
return_value="YMD"
)
@mock.patch(MOCK_SCRATCH, SCRATCH)
def test_filename_date_parse_invalid(self, *args):
document = RasterisedDocumentParser("/tmp/20 408000l 2475 - test.pdf")
document.get_text()
self.assertIsNone(document.get_date())