qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-11 11:29:57 +02:00
Code Issues Releases Wiki Activity

Merge branch 'master' of https://github.com/qurator-spk/sbb_textline_detector

Browse source
This commit is contained in:
b-vr103 2019-12-09 11:57:16 +01:00
parent 41e00eb900
commit 1303a7d92f
73 changed files with 1686 additions and 64834 deletions
Download patch file Download diff file Expand all files Collapse all files

48
qurator/dinglehopper/tests/test_editops.py
View file

@ -1,48 +0,0 @@
import unicodedata
from .. import seq_editops, editops
def test_trivial():
assert seq_editops('abc', 'abc') == []
assert seq_editops('', '') == []
def test_insert():
assert seq_editops('bc', 'abc') == [('insert', 0, 0)]
assert seq_editops('ac', 'abc') == [('insert', 1, 1)]
assert seq_editops('ab', 'abc') == [('insert', 2, 2)]
assert seq_editops('', 'a') == [('insert', 0, 0)]
def test_multiple():
assert seq_editops('bcd', 'abce') == [('insert', 0, 0), ('replace', 2, 3)]
def test_delete():
assert seq_editops('abcdef', 'cdef') == [('delete', 0, 0), ('delete', 1, 0)]
assert seq_editops('Xabcdef', 'Xcdef') == [('delete', 1, 1), ('delete', 2, 1)]
assert seq_editops('abcdefg', 'acdefX') == [('delete', 1, 1), ('replace', 6, 5)]
assert seq_editops('abcde', 'aabcd') == [('insert', 1, 1), ('delete', 4, 5)]
assert seq_editops('Foo', '') == [('delete', 0, 0), ('delete', 1, 0), ('delete', 2, 0)]
assert seq_editops('Foolish', 'Foo') == [('delete', 3, 3), ('delete', 4, 3), ('delete', 5, 3), ('delete', 6, 3)]
def test_ambiguous():
assert seq_editops('bcd', 'abcef') == [('insert', 0, 0), ('replace', 2, 3), ('insert', 3, 4)]
def test_editops():
"""Test editops() in cases where dealing with grapheme clusters matters"""
# 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) == []