1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-10 19:09:58 +02:00
dinglehopper/src/dinglehopper/tests/test_edit_distance.py
Robert Sachunsky a33b713f36 adapt tests
2025-03-20 19:35:19 +01:00

24 lines
700 B
Python

from __future__ import division, print_function
import unicodedata
from .. import distance
def test_distance():
assert distance("Fnord", "Food") == 2 / 5
assert distance("Müll", "Mull") == 1 / 4
word1 = unicodedata.normalize("NFC", "Schlyñ")
word2 = unicodedata.normalize("NFD", "Schlyñ") # Different, decomposed!
assert distance(word1, word2) == 0
word1 = "Schlyñ"
assert (
len(word1) == 6
) # This ends with LATIN SMALL LETTER N WITH TILDE, so 6 code points
word2 = "Schlym̃"
assert (
len(word2) == 7
) # This, OTOH, ends with LATIN SMALL LETTER M + COMBINING TILDE, 7 code points
assert distance(word1, word2) == 1 / 6