64 lines
2.0 KiB
Python
64 lines
2.0 KiB
Python
import random, string
|
|
from levenshtein import edit_distance, ops
|
|
|
|
|
|
def brute(a, b):
|
|
n, m = len(a), len(b)
|
|
dp = [[0]*(m+1) for _ in range(n+1)]
|
|
for i in range(n+1): dp[i][0]=i
|
|
for j in range(m+1): dp[0][j]=j
|
|
for i in range(1,n+1):
|
|
for j in range(1,m+1):
|
|
c = 0 if a[i-1]==b[j-1] else 1
|
|
dp[i][j]=min(dp[i-1][j]+1, dp[i][j-1]+1, dp[i-1][j-1]+c)
|
|
return dp[n][m]
|
|
|
|
|
|
def test_known():
|
|
cases = [("kitten","sitting",3),("","abc",3),("abc","",3),
|
|
("flaw","lawn",2),("same","same",0),("a","b",1),
|
|
("","",-0 if False else 0)]
|
|
for a,b,e in cases:
|
|
assert edit_distance(a,b)==e, (a,b,edit_distance(a,b),e)
|
|
|
|
|
|
def test_random_vs_brute():
|
|
rng = random.Random(42)
|
|
alpha = "ab"
|
|
for _ in range(2000):
|
|
la = rng.randint(0,8); lb = rng.randint(0,8)
|
|
a = "".join(rng.choice(alpha) for _ in range(la))
|
|
b = "".join(rng.choice(alpha) for _ in range(lb))
|
|
assert edit_distance(a,b)==brute(a,b), (a,b)
|
|
|
|
|
|
def test_ops_roundtrip():
|
|
rng = random.Random(7)
|
|
for _ in range(500):
|
|
a = "".join(rng.choice("ab") for _ in range(rng.randint(0,6)))
|
|
b = "".join(rng.choice("ab") for _ in range(rng.randint(0,6)))
|
|
o = ops(a,b)
|
|
# apply ops to a -> should yield b
|
|
out = []
|
|
i = 0 # index into a
|
|
j = 0 # index into b
|
|
for tag in o:
|
|
if tag == "=":
|
|
assert a[i] == b[j]
|
|
out.append(a[i]); i += 1; j += 1
|
|
elif tag == "S":
|
|
out.append(b[j]); i += 1; j += 1
|
|
elif tag == "D":
|
|
i += 1
|
|
elif tag == "I":
|
|
# need current b char; find next unconsumed b
|
|
out.append(b[j]); j += 1
|
|
assert "".join(out) == b, (a,b,o,"".join(out))
|
|
edits = sum(1 for t in o if t in ("S","D","I"))
|
|
assert edits == edit_distance(a,b), (a,b,edits,edit_distance(a,b))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_known(); test_random_vs_brute(); test_ops_roundtrip()
|
|
print("ALL OK")
|