1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-09 11:50:00 +02:00

🐛 dinglehopper: Work on NFC'ed grapheme clusters when aligning text

This commit is contained in:
Gerber, Mike 2019-09-30 18:17:13 +02:00
parent 534958be1d
commit 8d055e7b6e
3 changed files with 23 additions and 4 deletions

View file

@ -1,3 +1,5 @@
import unicodedata
from .. import seq_editops, editops
@ -36,3 +38,11 @@ def test_editops():
# In these cases, one of the words has a composed form, the other one does not.
assert editops('Schlyñ', 'Schlym̃') == [('replace', 5, 5)]
assert editops('oͤde', 'öde') == [('replace', 0, 0)]
def test_editops_canonically_equivalent():
left = unicodedata.lookup('LATIN SMALL LETTER N') + unicodedata.lookup('COMBINING TILDE')
right = unicodedata.lookup('LATIN SMALL LETTER N WITH TILDE')
assert left != right
assert unicodedata.normalize('NFC', left) == unicodedata.normalize('NFC', right)
assert editops(left, right) == []