paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-10-28 03:46:06 -05:00
Code Issues Packages Projects Releases Wiki Activity

Extends the regex to find dates in documents as reported by @isaacsando

Browse Source
This commit is contained in:
Wolf-Bastian Pöttner
2018-02-08 09:01:55 +01:00
parent 3a4626a3e2
commit 3899763261
4 changed files with 31 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/paperless_tesseract/parsers.py
View File

@@ -208,11 +208,13 @@ class RasterisedDocumentParser(DocumentParser):
# - XX/YY/ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits # - XX/YY/ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX-YY-ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits # - XX-YY-ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
# - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits # - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
# - MONTH ZZZZ # - MONTH ZZZZ, with ZZZZ being 4 digits
# - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
m = re.search( m = re.search(
r'\b([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})\b|' + r'\b([0-9]{1,2})[\.\/-]([0-9]{1,2})[\.\/-]([0-9]{4}|[0-9]{2})\b|' +
r'\b([0-9]{1,2}\. [^ ]{3,9} ([0-9]{4}|[0-9]{2}))\b|' + r'\b([0-9]{1,2}[\. ]+[^ ]{3,9} ([0-9]{4}|[0-9]{2}))\b|' +
r'\b([^ ]{3,9} [0-9]{4})\b', text) r'\b([\w]{3,9} [0-9]{1,2}, ([0-9]{4}))\b|' +
r'\b([\w]{3,9} [0-9]{4})\b', text)
if m is None: if m is None:
return None return None

BIN
src/paperless_tesseract/tests/samples/tests_date_8.pdf Normal file
View File

Binary file not shown.

BIN
src/paperless_tesseract/tests/samples/tests_date_9.pdf Normal file
View File

Binary file not shown.

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

@@ -204,3 +204,29 @@ class TestDate(TestCase):
self.assertEqual(document.get_date(), self.assertEqual(document.get_date(),
datetime.datetime(2018, 4, 1, 0, 0, datetime.datetime(2018, 4, 1, 0, 0,
tzinfo=tz.tzutc())) tzinfo=tz.tzutc()))
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_get_text_8_pdf(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_8.pdf")
document = RasterisedDocumentParser(input_file)
document.get_text()
self.assertEqual(document._is_ocred(), True)
self.assertEqual(document.get_date(),
datetime.datetime(2017, 12, 31, 0, 0,
tzinfo=tz.tzutc()))
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_get_text_9_pdf(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_9.pdf")
document = RasterisedDocumentParser(input_file)
document.get_text()
self.assertEqual(document._is_ocred(), True)
self.assertEqual(document.get_date(),
datetime.datetime(2017, 12, 31, 0, 0,
tzinfo=tz.tzutc()))