paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

Add tests and improve whitespace handling

Browse Source
This commit is contained in:
ishirav 2017-12-23 06:37:00 +02:00
parent 6a36a4ec97
commit 83746a9aeb
2 changed files with 32 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/documents/models.py
View File

@ -128,11 +128,11 @@ class MatchingModel(models.Model):
Example:
' some random words "with quotes " and spaces'
==>
['some', 'random', 'words', 'with quotes', 'and', 'spaces']
['some', 'random', 'words', 'with\s+quotes', 'and', 'spaces']
'''
findterms = re.compile(r'"([^"]+)"|(\S+)').findall
normspace = re.compile(r'\s{2,}').sub
return [normspace(' ', (t[0] or t[1]).strip()) for t in findterms(self.match)]
normspace = re.compile(r'\s+').sub
return [normspace(r'\s+', (t[0] or t[1]).strip()) for t in findterms(self.match)]
def save(self, *args, **kwargs):

31
src/documents/tests/test_matchables.py
View File

@ -16,9 +16,9 @@ class TestMatching(TestCase):
matching_algorithm=getattr(klass, algorithm)
)
for string in true:
self.assertTrue(instance.matches(string))
self.assertTrue(instance.matches(string), '"%s" should match "%s" but it does not' % (text, string))
for string in false:
self.assertFalse(instance.matches(string))
self.assertFalse(instance.matches(string), '"%s" should not match "%s" but it does' % (text, string))
def test_match_all(self):
@ -54,6 +54,21 @@ class TestMatching(TestCase):
)
)
self._test_matching(
'brown fox "lazy dogs"',
"MATCH_ALL",
(
"the quick brown fox jumped over the lazy dogs",
"the quick brown fox jumped over the lazy dogs",
),
(
"the quick fox jumped over the lazy dogs",
"the quick brown wolf jumped over the lazy dogs",
"the quick brown fox jumped over the fat dogs",
"the quick brown fox jumped over the lazy... dogs",
)
)
def test_match_any(self):
self._test_matching(
@ -89,6 +104,18 @@ class TestMatching(TestCase):
)
)
self._test_matching(
'"brown fox" " lazy dogs "',
"MATCH_ANY",
(
"the quick brown fox",
"jumped over the lazy dogs.",
),
(
"the lazy fox jumped over the brown dogs",
)
)
def test_match_literal(self):
self._test_matching(