explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add more matcher operator tests

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-16 13:38:01 +02:00
parent 0433181658
commit 748d525801
1 changed files with 37 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
spacy/tests/test_matcher.py
View File

@ -107,6 +107,7 @@ def test_matcher_empty_dict(en_vocab):
matches = matcher(doc)
assert len(matches) == 1
assert matches[0][1:] == (0, 3)
matcher = Matcher(en_vocab)
matcher.add('A.', None, [{'ORTH': 'a'}, {}])
matches = matcher(doc)
assert matches[0][1:] == (0, 2)
@ -175,3 +176,39 @@ def test_matcher_match_one_plus(matcher):
{'ORTH': 'Philippe', 'OP': '+'}])
m = matcher(doc)
assert len(m) == 1
def test_operator_combos(matcher):
cases = [
('aaab', 'a a a b', True),
('aaab', 'a+ b', True),
('aaab', 'a+ a+ b', True),
('aaab', 'a+ a+ a b', True),
('aaab', 'a+ a+ a+ b', True),
('aaab', 'a+ a a b', True),
('aaab', 'a+ a a', True),
('aaab', 'a+', True),
('aaa', 'a+ b', False),
('aaa', 'a+ a+ b', False),
('aaa', 'a+ a+ a+ b', False),
('aaa', 'a+ a b', False),
('aaa', 'a+ a a b', False),
('aaab', 'a+ a a', True),
('aaab', 'a+', True),
('aaab', 'a+ a b', False), # <-- This is the weird semantics
]
for string, pattern_str, result in cases:
matcher = Matcher(matcher.vocab)
doc = get_doc(matcher.vocab, words=list(string))
pattern = []
for part in pattern_str.split():
if part.endswith('+'):
pattern.append({'ORTH': part[0], 'op': '+'})
else:
pattern.append({'ORTH': part})
matcher.add('PATTERN', None, pattern)
matches = matcher(doc)
if result:
assert matches, (string, pattern_str)
else:
assert not matches, (string, pattern_str)