explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-06 21:30:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Parametrize fuzzyn+set tests

Browse Source
This commit is contained in:
Adriane Boyd 2022-11-12 11:26:04 +01:00
parent ae0bb75d70
commit 6a9fec7ea8
1 changed files with 5 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
spacy/tests/matcher/test_matcher_api.py
View File

@ -211,9 +211,10 @@ def test_matcher_match_fuzzyn(en_vocab, fuzzyn):
assert len(matcher(doc)) == fuzzyn + 1 assert len(matcher(doc)) == fuzzyn + 1
def test_matcher_match_fuzzyn_set1(en_vocab): @pytest.mark.parametrize("set_op", ["IN", "NOT_IN"])
def test_matcher_match_fuzzyn_set_op_longest(en_vocab, set_op):
rules = { rules = {
"GoogleNow": [[{"ORTH": {"FUZZY2": {"IN": ["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():
@ -221,27 +222,10 @@ def test_matcher_match_fuzzyn_set1(en_vocab):
words = ["They", "like", "Goggle", "Noo"] words = ["They", "like", "Goggle", "Noo"]
doc = Doc(matcher.vocab, words=words) doc = Doc(matcher.vocab, words=words)
assert matcher(doc) == [ assert len(matcher(doc)) == 1
(doc.vocab.strings["GoogleNow"], 2, 4),
]
def test_matcher_match_fuzzyn_set2(en_vocab): def test_matcher_match_fuzzyn_set_multiple(en_vocab):
rules = {
"GoogleNow": [[{"ORTH": {"FUZZY2": {"NOT_IN": ["Google", "Now"]}}, "OP": "+"}]],
}
matcher = Matcher(en_vocab)
for key, patterns in rules.items():
matcher.add(key, patterns, greedy="LONGEST")
words = ["They", "like", "Goggle", "Noo"]
doc = Doc(matcher.vocab, words=words)
assert matcher(doc) == [
(doc.vocab.strings["GoogleNow"], 0, 2),
]
def test_matcher_match_fuzzyn_set3(en_vocab):
rules = { rules = {
"GoogleNow": [ "GoogleNow": [
[ [