explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-06 05:10:21 +03:00
Code Issues Packages Projects Releases Wiki Activity

Parametrize and merge fuzzy+set tests

Browse Source
This commit is contained in:
Adriane Boyd 2022-11-11 13:32:16 +01:00
parent 070cbf2be0
commit d677335199
1 changed files with 35 additions and 87 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

122
spacy/tests/matcher/test_matcher_api.py
View File

@ -118,91 +118,56 @@ def test_matcher_match_multi(matcher):
] ]
# fuzzy matches on specific tokens @pytest.mark.parametrize(
"rules,match_locs",
[
(
{
"GoogleNow": [[{"ORTH": {"FUZZY": "Google"}}, {"ORTH": "Now"}]],
},
[(2, 4)],
),
(
{
"Java": [[{"LOWER": {"FUZZY": "java"}}]],
},
[(5, 6)],
),
(
{
"JS": [[{"ORTH": {"FUZZY": "JavaScript"}}]],
"GoogleNow": [[{"ORTH": {"FUZZY": "Google"}}, {"ORTH": "Now"}]],
"Java": [[{"LOWER": {"FUZZY": "java"}}]],
},
[(2, 4), (5, 6), (8, 9)],
),
],
)
def test_matcher_match_fuzzy(en_vocab, rules, match_locs):
words = ["They", "like", "Goggle", "Now", "and", "Jav", "but", "not", "JvvaScrpt"]
doc = Doc(en_vocab, words=words)
def test_matcher_match_fuzzy1(en_vocab):
rules = {
"JS": [[{"ORTH": "JavaScript"}]],
"GoogleNow": [[{"ORTH": {"FUZZY": "Google"}}, {"ORTH": "Now"}]],
"Java": [[{"LOWER": "java"}]],
}
matcher = Matcher(en_vocab) matcher = Matcher(en_vocab)
for key, patterns in rules.items(): for key, patterns in rules.items():
matcher.add(key, patterns) matcher.add(key, patterns)
assert match_locs == [(start, end) for m_id, start, end in matcher(doc)]
words = ["They", "like", "Goggle", "Now", "and", "Jav", "but", "not", "JvvaScrpt"]
doc = Doc(matcher.vocab, words=words)
assert matcher(doc) == [
(doc.vocab.strings["GoogleNow"], 2, 4),
]
def test_matcher_match_fuzzy2(en_vocab): @pytest.mark.parametrize("set_op", ["IN", "NOT_IN"])
def test_matcher_match_fuzzy_set_op_longest(en_vocab, set_op):
rules = { rules = {
"JS": [[{"ORTH": "JavaScript"}]], "GoogleNow": [[{"ORTH": {"FUZZY": {set_op: ["Google", "Now"]}}, "OP": "+"}]]
"GoogleNow": [[{"ORTH": "Google"}, {"ORTH": "Now"}]],
"Java": [[{"LOWER": {"FUZZY": "java"}}]],
}
matcher = Matcher(en_vocab)
for key, patterns in rules.items():
matcher.add(key, patterns)
words = ["They", "like", "Goggle", "Now", "and", "Jav", "but", "not", "JvvaScrpt"]
doc = Doc(matcher.vocab, words=words)
assert matcher(doc) == [
(doc.vocab.strings["Java"], 5, 6),
]
def test_matcher_match_fuzzy3(en_vocab):
rules = {
"JS": [[{"ORTH": {"FUZZY": "JavaScript"}}]],
"GoogleNow": [[{"ORTH": {"FUZZY": "Google"}}, {"ORTH": "Now"}]],
"Java": [[{"LOWER": {"FUZZY": "java"}}]],
}
matcher = Matcher(en_vocab)
for key, patterns in rules.items():
matcher.add(key, patterns)
words = ["They", "like", "Goggle", "Now", "and", "Jav", "but", "not", "JvvaScrpt"]
doc = Doc(matcher.vocab, words=words)
assert matcher(doc) == [
(doc.vocab.strings["GoogleNow"], 2, 4),
(doc.vocab.strings["Java"], 5, 6),
(doc.vocab.strings["JS"], 8, 9),
]
def test_matcher_match_fuzzy_set1(en_vocab):
rules = {"GoogleNow": [[{"ORTH": {"FUZZY": {"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"], 2, 4),
]
def test_matcher_match_fuzzy_set2(en_vocab):
rules = {
"GoogleNow": [[{"ORTH": {"FUZZY": {"NOT_IN": ["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="LONGEST")
words = ["They", "like", "Goggle", "Noo"] words = ["They", "like", "Goggle", "Noo"]
doc = Doc(matcher.vocab, words=words) doc = Doc(en_vocab, words=words)
assert matcher(doc) == [ assert len(matcher(doc)) == 1
(doc.vocab.strings["GoogleNow"], 0, 2),
]
def test_matcher_match_fuzzy_set3(en_vocab): def test_matcher_match_fuzzy_set_multiple(en_vocab):
rules = { rules = {
"GoogleNow": [ "GoogleNow": [
[ [
@ -224,23 +189,6 @@ def test_matcher_match_fuzzy_set3(en_vocab):
] ]
def test_matcher_match_fuzzy_set4(en_vocab):
rules = {
"QUESTION": [
[{"ORTH": {"FUZZY": {"IN": ["what"]}, "NOT_IN": ["that"]}}, {"ORTH": "do"}]
]
}
matcher = Matcher(en_vocab)
for key, patterns in rules.items():
matcher.add(key, patterns, greedy="LONGEST")
words = ["what", "do", "you", "want"]
doc = Doc(matcher.vocab, words=words)
assert matcher(doc) == [
(doc.vocab.strings["QUESTION"], 0, 2),
]
@pytest.mark.parametrize("fuzzyn", range(1, 6)) @pytest.mark.parametrize("fuzzyn", range(1, 6))
def test_matcher_match_fuzzyn(en_vocab, fuzzyn): def test_matcher_match_fuzzyn(en_vocab, fuzzyn):
matcher = Matcher(en_vocab) matcher = Matcher(en_vocab)