paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-08-07 19:08:32 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #302 from BastianPoe/bugfix/extend_regex_to_find_more_dates

Browse Source 
Extends the regex to find dates in documents as reported by @isaacsando
This commit is contained in:
Daniel Quinn
2018-02-18 17:23:49 +01:00
committed by GitHub
parent 9a47dba494 96c7222269
commit 5d01410dc0
4 changed files with 153 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

117
src/paperless_tesseract/tests/test_date.py
View File

@@ -25,6 +25,97 @@ class TestDate(TestCase):
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SCRATCH
)
def test_date_format_1(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = "lorem ipsum 130218 lorem ipsum"
self.assertEqual(document.get_date(),
None)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_date_format_2(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = "lorem ipsum 2018 lorem ipsum"
self.assertEqual(document.get_date(),
None)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_date_format_3(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = "lorem ipsum 20180213 lorem ipsum"
self.assertEqual(document.get_date(),
None)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_date_format_4(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = "lorem ipsum 13.02.2018 lorem ipsum"
self.assertEqual(document.get_date(),
datetime.datetime(2018, 2, 13, 0, 0,
tzinfo=tz.tzutc()))
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_date_format_5(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = ("lorem ipsum 130218, 2018, 20180213 and "
"13.02.2018 lorem ipsum")
self.assertEqual(document.get_date(),
datetime.datetime(2018, 2, 13, 0, 0,
tzinfo=tz.tzutc()))
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_date_format_6(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = ("lorem ipsum\n"
"Wohnort\n"
"3100\n"
"IBAN\n"
"AT87 4534\n"
"1234\n"
"1234 5678\n"
"BIC\n"
"lorem ipsum")
self.assertEqual(document.get_date(),
None)
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_date_format_7(self):
input_file = os.path.join(self.SAMPLE_FILES, "")
document = RasterisedDocumentParser(input_file)
document.TEXT_CACHE = ("lorem ipsum\n"
"März 2019\n"
"lorem ipsum")
self.assertEqual(document.get_date(),
datetime.datetime(2019, 3, 1, 0, 0,
tzinfo=tz.tzutc()))
@mock.patch(
"paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
SAMPLE_FILES
)
def test_get_text_1_pdf(self):
input_file = os.path.join(self.SAMPLE_FILES, "tests_date_1.pdf")
document = RasterisedDocumentParser(input_file)
@@ -213,3 +304,29 @@ class TestDate(TestCase):
self.assertEqual(document.get_date(),
datetime.datetime(2018, 4, 1, 0, 0,
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()))