1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
|
import csv
import pytest
open_kwargs = {"encoding": "utf8"}
def assertAlmostEqual(a, b, places=3):
assert abs(a - b) < (0.1**places)
implementations = ["python", "rust"]
@pytest.fixture(params=implementations)
def jf(request):
if request.param == "python":
import jellyfish._jellyfish as jf
elif request.param == "rust":
from jellyfish import _rustyfish as jf
return jf
def _load_data(name):
with open("testdata/{}.csv".format(name), **open_kwargs) as f:
yield from csv.reader(f)
@pytest.mark.parametrize("s1,s2,value", _load_data("jaro_winkler"), ids=str)
def test_jaro_winkler_similarity(jf, s1, s2, value):
value = float(value)
assertAlmostEqual(jf.jaro_winkler_similarity(s1, s2), value, places=3)
@pytest.mark.parametrize("s1,s2,value", _load_data("jaro_winkler_longtol"), ids=str)
def test_jaro_winkler_similarity_longtol(jf, s1, s2, value):
value = float(value)
assertAlmostEqual(jf.jaro_winkler_similarity(s1, s2, True), value, places=3)
@pytest.mark.parametrize("s1,s2,value", _load_data("jaro_distance"), ids=str)
def test_jaro_similarity(jf, s1, s2, value):
value = float(value)
assertAlmostEqual(jf.jaro_similarity(s1, s2), value, places=3)
@pytest.mark.parametrize("s1,s2,value", _load_data("hamming"), ids=str)
def test_hamming_distance(jf, s1, s2, value):
value = int(value)
assert jf.hamming_distance(s1, s2) == value
@pytest.mark.parametrize("s1,s2,value", _load_data("levenshtein"), ids=str)
def test_levenshtein_distance(jf, s1, s2, value):
value = int(value)
assert jf.levenshtein_distance(s1, s2) == value
@pytest.mark.parametrize("s1,s2,value", _load_data("damerau_levenshtein"), ids=str)
def test_damerau_levenshtein_distance(jf, s1, s2, value):
value = int(value)
assert jf.damerau_levenshtein_distance(s1, s2) == value
@pytest.mark.parametrize("s1,code", _load_data("soundex"), ids=str)
def test_soundex(jf, s1, code):
assert jf.soundex(s1) == code
@pytest.mark.parametrize("s1,code", _load_data("metaphone"), ids=str)
def test_metaphone(jf, s1, code):
assert jf.metaphone(s1) == code
@pytest.mark.parametrize("s1,s2", _load_data("nysiis"), ids=str)
def test_nysiis(jf, s1, s2):
assert jf.nysiis(s1) == s2
@pytest.mark.parametrize("s1,s2", _load_data("match_rating_codex"), ids=str)
def test_match_rating_codex(jf, s1, s2):
assert jf.match_rating_codex(s1) == s2
@pytest.mark.parametrize("s1,s2,value", _load_data("match_rating_comparison"), ids=str)
def test_match_rating_comparison(jf, s1, s2, value):
value = {"True": True, "False": False, "None": None}[value]
assert jf.match_rating_comparison(s1, s2) is value
def test_jaro_winkler_long_tolerance(jf):
no_lt = jf.jaro_winkler_similarity(
"two long strings", "two long stringz", long_tolerance=False
)
with_lt = jf.jaro_winkler_similarity(
"two long strings", "two long stringz", long_tolerance=True
)
# make sure long_tolerance does something
assertAlmostEqual(no_lt, 0.975)
assertAlmostEqual(with_lt, 0.984)
def test_damerau_levenshtein_distance_type(jf):
jf.damerau_levenshtein_distance("abc", "abc")
with pytest.raises(TypeError) as exc:
jf.damerau_levenshtein_distance(b"abc", b"abc")
def test_levenshtein_distance_type(jf):
assert jf.levenshtein_distance("abc", "abc") == 0
with pytest.raises(TypeError) as exc:
jf.levenshtein_distance(b"abc", b"abc")
def test_jaro_similarity_type(jf):
assert jf.jaro_similarity("abc", "abc") == 1
with pytest.raises(TypeError) as exc:
jf.jaro_similarity(b"abc", b"abc")
def test_jaro_winkler_type(jf):
assert jf.jaro_winkler_similarity("abc", "abc") == 1
with pytest.raises(TypeError) as exc:
jf.jaro_winkler_similarity(b"abc", b"abc")
def test_mra_comparison_type(jf):
assert jf.match_rating_comparison("abc", "abc") is True
with pytest.raises(TypeError) as exc:
jf.match_rating_comparison(b"abc", b"abc")
def test_hamming_type(jf):
assert jf.hamming_distance("abc", "abc") == 0
with pytest.raises(TypeError) as exc:
jf.hamming_distance(b"abc", b"abc")
def test_soundex_type(jf):
assert jf.soundex("ABC") == "A120"
with pytest.raises(TypeError) as exc:
jf.soundex(b"ABC")
def test_metaphone_type(jf):
assert jf.metaphone("abc") == "ABK"
with pytest.raises(TypeError) as exc:
jf.metaphone(b"abc")
def test_nysiis_type(jf):
assert jf.nysiis("abc") == "ABC"
with pytest.raises(TypeError) as exc:
jf.nysiis(b"abc")
def test_mr_codex_type(jf):
assert jf.match_rating_codex("abc") == "ABC"
with pytest.raises(TypeError) as exc:
jf.match_rating_codex(b"abc")
def test_mr_codex_bad_string(jf):
with pytest.raises(ValueError) as exc:
res = jf.match_rating_codex("i’m")
print(res)
|
