Rooba
/
RapidFuzz
mirror of https://github.com/maxbachmann/RapidFuzz.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

cleanup exceptions

This commit is contained in:
Max Bachmann 2024-04-11 02:02:33 +02:00
parent d14bb6819f
commit a53c125d95
4 changed files with 21 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.rst
View File

@ -5,14 +5,14 @@ Changelog
^^^^^^^^^^^^^^^^^^^^
Fixed
~~~~~
* use the correct version of `rapidfuzz-cpp` when building against a system installed version
* use the correct version of ``rapidfuzz-cpp`` when building against a system installed version
[3.8.0] - 2024-04-06
^^^^^^^^^^^^^^^^^^^^
Added
~~~~~
* added ``process.cpdist`` which allows pairwise comparision of two collection of inputs
* added ``process.cpdist`` which allows pairwise comparison of two collection of inputs
Fixed
~~~~~

3
src/rapidfuzz/distance/JaroWinkler_py.py
View File

@ -60,7 +60,8 @@ def similarity(
score_cutoff = 0
if prefix_weight > 1.0 or prefix_weight < 0.0:
raise ValueError("prefix_weight has to be in the range 0.0 - 1.0")
msg = "prefix_weight has to be in the range 0.0 - 1.0"
raise ValueError(msg)
s1, s2 = conv_sequences(s1, s2)
P_len = len(s1)

15
src/rapidfuzz/distance/metrics_cpp.pyx
View File

@ -948,7 +948,8 @@ def jaro_winkler_distance(s1, s2, *, double prefix_weight=0.1, processor=None, s
return 1.0
if prefix_weight > 1.0 or prefix_weight < 0.0:
raise ValueError("prefix_weight has to be in the range 0.0 - 1.0")
msg = "prefix_weight has to be in the range 0.0 - 1.0"
raise ValueError(msg)
cdef double c_score_cutoff = get_score_cutoff_f64(score_cutoff, 1.0, 0.0)
preprocess_strings(s1, s2, processor, &s1_proc, &s2_proc)
@ -961,7 +962,8 @@ def jaro_winkler_similarity(s1, s2, *, double prefix_weight=0.1, processor=None,
return 0.0
if prefix_weight > 1.0 or prefix_weight < 0.0:
raise ValueError("prefix_weight has to be in the range 0.0 - 1.0")
msg = "prefix_weight has to be in the range 0.0 - 1.0"
raise ValueError(msg)
cdef double c_score_cutoff = get_score_cutoff_f64(score_cutoff, 0.0, 1.0)
preprocess_strings(s1, s2, processor, &s1_proc, &s2_proc)
@ -974,7 +976,8 @@ def jaro_winkler_normalized_distance(s1, s2, *, double prefix_weight=0.1, proces
return 1.0
if prefix_weight > 1.0 or prefix_weight < 0.0:
raise ValueError("prefix_weight has to be in the range 0.0 - 1.0")
msg = "prefix_weight has to be in the range 0.0 - 1.0"
raise ValueError(msg)
cdef double c_score_cutoff = get_score_cutoff_f64(score_cutoff, 1.0, 0.0)
preprocess_strings(s1, s2, processor, &s1_proc, &s2_proc)
@ -987,7 +990,8 @@ def jaro_winkler_normalized_similarity(s1, s2, *, double prefix_weight=0.1, proc
return 0.0
if prefix_weight > 1.0 or prefix_weight < 0.0:
raise ValueError("prefix_weight has to be in the range 0.0 - 1.0")
msg = "prefix_weight has to be in the range 0.0 - 1.0"
raise ValueError(msg)
cdef double c_score_cutoff = get_score_cutoff_f64(score_cutoff, 0.0, 1.0)
preprocess_strings(s1, s2, processor, &s1_proc, &s2_proc)
@ -1002,7 +1006,8 @@ cdef bool JaroWinklerKwargsInit(RF_Kwargs * self, dict kwargs) except False:
prefix_weight[0] = kwargs.get("prefix_weight", 0.1)
if prefix_weight[0] > 1.0 or prefix_weight[0] < 0.0:
free(prefix_weight)
raise ValueError("prefix_weight has to be in the range 0.0 - 1.0")
msg = "prefix_weight has to be in the range 0.0 - 1.0"
raise ValueError(msg)
self.context = prefix_weight
self.dtor = KwargsDeinit

11
tests/distance/test_JaroWinkler.py
View File

@ -9,16 +9,19 @@ from tests.distance.common import JaroWinkler
def test_hash_special_case():
assert pytest.approx(JaroWinkler.similarity([0, -1], [0, -2])) == 0.666666
def test_large_prefix_weight():
assert pytest.approx(JaroWinkler.similarity('milyarder', 'milyarderlik',prefix_weight=0.5)) == 1.0
assert pytest.approx(JaroWinkler.similarity('milyarder', 'milyarderlik',prefix_weight=1.0)) == 1.0
assert pytest.approx(JaroWinkler.similarity("milyarder", "milyarderlik", prefix_weight=0.5)) == 1.0
assert pytest.approx(JaroWinkler.similarity("milyarder", "milyarderlik", prefix_weight=1.0)) == 1.0
def test_invalid_prefix_weight():
with pytest.raises(ValueError, match="prefix_weight has to be in the range 0.0 - 1.0"):
JaroWinkler.similarity('milyarder', 'milyarderlik',prefix_weight=-0.1)
JaroWinkler.similarity("milyarder", "milyarderlik", prefix_weight=-0.1)
with pytest.raises(ValueError, match="prefix_weight has to be in the range 0.0 - 1.0"):
JaroWinkler.similarity('milyarder', 'milyarderlik',prefix_weight=1.1)
JaroWinkler.similarity("milyarder", "milyarderlik", prefix_weight=1.1)
def test_edge_case_lengths():
"""