explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-05 04:40:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Parameterize test over greedy

Browse Source 
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
This commit is contained in:
Adriane Boyd 2023-01-09 13:08:17 +01:00 committed by GitHub
parent 213fb85d12
commit 8ee6551348
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/tests/matcher/test_matcher_api.py
View File

@ -225,18 +225,24 @@ def test_matcher_match_fuzzyn_various_edits(en_vocab, fuzzyn):
assert len(matcher(doc)) == fuzzyn + 1 assert len(matcher(doc)) == fuzzyn + 1
@pytest.mark.parametrize("greedy", ["FIRST", "LONGEST"])
@pytest.mark.parametrize("set_op", ["IN", "NOT_IN"]) @pytest.mark.parametrize("set_op", ["IN", "NOT_IN"])
def test_matcher_match_fuzzyn_set_op_longest(en_vocab, set_op): def test_matcher_match_fuzzyn_set_op_longest(en_vocab, greedy, set_op):
rules = { rules = {
"GoogleNow": [[{"ORTH": {"FUZZY2": {set_op: ["Google", "Now"]}}, "OP": "+"}]] "GoogleNow": [[{"ORTH": {"FUZZY2": {set_op: ["Google", "Now"]}}, "OP": "+"}]]
} }
matcher = Matcher(en_vocab) matcher = Matcher(en_vocab)
for key, patterns in rules.items(): for key, patterns in rules.items():
matcher.add(key, patterns, greedy="LONGEST") matcher.add(key, patterns, greedy=greedy)
words = ["They", "like", "Goggle", "Noo"] words = ["They", "like", "Goggle", "Noo"]
doc = Doc(matcher.vocab, words=words) doc = Doc(matcher.vocab, words=words)
assert len(matcher(doc)) == 1 spans = matcher(doc, as_spans=True)
assert len(spans) == 1
if set_op == "IN":
assert spans[0].text == "Goggle Noo"
else:
assert spans[0].text == "They like"
def test_matcher_match_fuzzyn_set_multiple(en_vocab): def test_matcher_match_fuzzyn_set_multiple(en_vocab):