def test_infer():
assert Alignment.infer('test', 'test') == Alignment.identity(4)
assert Alignment.infer('asdf', 'jkl;') == Alignment.identity(4)
assert Alignment.infer('color', 'colour') == Alignment([
(0, 0),
(1, 1),
(2, 2),
(3, 3),
(4, 4),
(4, 5),
(5, 6),
])
assert Alignment.infer('color',
'colour') == Alignment.infer('colour',
'color').inverse()
assert Alignment.infer("ab---", "ab") == Alignment([
(0, 0),
(1, 1),
(2, 2),
(3, 2),
(4, 2),
(5, 2),
])
def test_append():
builder = BistrBuilder('hello WORLD')
builder.append(bistr(builder.peek(5)).upper('en_US'))
builder.skip(1)
builder.append(bistr(builder.peek(5)).lower('en_US'))
bs = builder.build()
assert bs[1:4] == bistr('ell', 'ELL', Alignment.identity(3))
assert bs[7:10] == bistr('ORL', 'orl', Alignment.identity(3))
def test_canonicalization():
assert Alignment([(0, 0), (1, 2), (1, 2), (2, 4)]) == Alignment([(0, 0),
(1, 2),
(2, 4)])
assert Alignment([(0, 0),
(1, 2)]) + Alignment([(1, 2),
(2, 4)]) == Alignment([(0, 0),
(1, 2),
(2, 4)])
def test_identity():
alignment = Alignment.identity(1, 16)
assert alignment == Alignment((i, i) for i in range(1, 17))
assert list(alignment) == [(i, i) for i in range(1, 17)]
assert alignment.original_bounds() == (1, 16)
assert alignment.modified_bounds() == (1, 16)
assert alignment.original_bounds(4, 7) == (4, 7)
assert alignment.modified_bounds(4, 7) == (4, 7)
def test_compose_identity():
alignment = Alignment([
(0, 2),
(2, 2),
(4, 4),
(6, 6),
(8, 6),
])
# Modified sequence is smaller
_test_identity_composition(alignment)
# Original sequence is smaller
_test_identity_composition(alignment.inverse())
def test_capitalize():
bs = bistr('hello WORLD').capitalize('en_US')
assert bs.original == 'hello WORLD'
assert bs.modified == 'Hello world'
assert bs.alignment == Alignment.identity(11)
bs = bistr('τελικός').capitalize('el_GR')
assert bs.original == 'τελικός'
assert bs.modified == 'Τελικός'
assert bs.alignment == Alignment.identity(7)
bs = bistr('ἴΣ').capitalize('el_GR')
assert bs.original == 'ἴΣ'
assert bs.modified == 'Ἴς'
assert bs.alignment == Alignment.identity(2)
def test_swapcase():
bs = bistr('hello WORLD').swapcase('en_US')
assert bs.original == 'hello WORLD'
assert bs.modified == 'HELLO world'
assert bs.alignment == Alignment.identity(11)
# Ligatures/digraphs in title case don't have a swapped form
bs = bistr('Ljepòta').swapcase('hr_HR')
assert bs.original == 'Ljepòta'
assert bs.modified == 'LjEPÒTA'
assert bs.alignment == Alignment.identity(6)
bs = bistr('Ljepòta').normalize('NFKC').swapcase('hr_HR')
assert bs.original == 'Ljepòta'
assert bs.modified == 'lJEPÒTA'
assert bs[0:2] == bistr('Lj', 'lJ')
def test_infer():
bs = bistr.infer('test', 'test')
assert bs == bistr('test', 'test', Alignment.identity(4))
bs = bistr.infer('color', 'colour')
assert bs[3:5].original == 'o'
assert bs.inverse() == bistr.infer('colour', 'color')
def test_infer():
bs = bistr.infer('test', 'test')
assert bs == bistr('test', 'test', Alignment.identity(4))
bs = bistr.infer('color', 'colour')
assert bs[3:5].original == 'o'
assert bs.inverse() == bistr.infer('colour', 'color')
bs = bistr.infer("--Hello, world!--", "hello world")
assert bs[:5] == bistr("Hello", "hello", Alignment.identity(5))
assert bs[6:] == bistr("world")
bs = bistr.infer(
'🅃🄷🄴 🅀🅄🄸🄲🄺, 🄱🅁🄾🅆🄽 🦊 🄹🅄🄼🄿🅂 🄾🅅🄴🅁 🅃🄷🄴 🄻🄰🅉🅈 🐶',
'the quick brown fox jumps over the lazy dog',
)
assert bs[0:3] == bistr('🅃🄷🄴', 'the', Alignment.identity(3))
assert bs[4:9] == bistr('🅀🅄🄸🄲🄺', 'quick', Alignment.identity(5))
assert bs[10:15] == bistr('🄱🅁🄾🅆🄽', 'brown', Alignment.identity(5))
assert bs[16:19].original == '🦊'
assert bs[16:19].modified == 'fox'
assert bs[20:25] == bistr('🄹🅄🄼🄿🅂', 'jumps', Alignment.identity(5))
assert bs[40:43].original == '🐶'
assert bs[40:43].modified == 'dog'
bs = bistr.infer(
'Ṫḧë qüïċḳ, ḅṛöẅṅ 🦊 jüṁṗṡ öṿëṛ ẗḧë ḷäżÿ 🐶',
'the quick brown fox jumps over the lazy dog',
)
assert bs[0:3] == bistr('Ṫḧë', 'the', Alignment.identity(3))
assert bs[4:9] == bistr('qüïċḳ', 'quick', Alignment.identity(5))
assert bs[10:15] == bistr('ḅṛöẅṅ', 'brown', Alignment.identity(5))
assert bs[16:19].original == '🦊'
assert bs[16:19].modified == 'fox'
assert bs[20:25] == bistr('jüṁṗṡ', 'jumps', Alignment.identity(5))
assert bs[40:43].original == '🐶'
assert bs[40:43].modified == 'dog'
bs = bistr.infer(
'Z̴̡̪̫̖̥̔̿̃̈̏̎͠͝á̸̪̠̖̻̬̖̪̞͙͇̮̠͎̆͋́̐͌̒͆̓l̶͉̭̳̤̬̮̩͎̟̯̜͇̥̠̘͑͐̌͂̄́̀̂̌̈͛̊̄̚͜ģ̸̬̼̞̙͇͕͎̌̾̒̐̿̎̆̿̌̃̏̌́̾̈͘͜o̶̢̭͕͔̩͐ ̴̡̡̜̥̗͔̘̦͉̣̲͚͙̐̈́t̵͈̰̉̀͒̎̈̿̔̄̽͑͝͠ẹ̵̫̲̫̄͜͜x̵͕̳͈̝̤̭̼̼̻͓̿̌̽̂̆̀̀̍̒͐́̈̀̚͝t̸̡̨̥̺̣̟͎̝̬̘̪͔͆́̄̅̚',
'Zalgo text')
for i, c in enumerate(bs):
assert bs[i:i + 1].original.startswith(c)
def test_empty():
pytest.raises(ValueError, Alignment, [])
alignment = Alignment.identity(0)
assert list(alignment) == [(0, 0)]
assert alignment.original_bounds() == (0, 0)
assert alignment.modified_bounds() == (0, 0)
assert alignment.original_bounds(0, 0) == (0, 0)
assert alignment.modified_bounds(0, 0) == (0, 0)
def test_new():
pytest.raises(TypeError, bistr, 42)
pytest.raises(TypeError, bistr, 'fourty-two', 42)
pytest.raises(TypeError, bistr, 'fourty-two', '42', 42)
pytest.raises(ValueError, bistr, 'fourty-two', '42', Alignment([
(0, 0),
(9, 2),
]))
pytest.raises(ValueError, bistr, 'fourty-two', '42', Alignment([
(0, 0),
(10, 1),
]))
bistr('42')
bistr('fourty-two', '42')
bistr('fourty-two', '42', Alignment([
(0, 0),
(6, 1),
(7, 1),
(10, 2),
]))
def test_indexing():
data = [
(0, 1),
(1, 2),
(2, 4),
(3, 8),
(4, 16),
]
length = len(data)
alignment = Alignment(data)
assert len(alignment) == length
for i in range(length):
assert alignment[i] == data[i]
assert alignment[i - length] == data[i - length]
for j in range(i + 1, length + 1):
assert list(alignment[i:j]) == data[i:j]
def test_equality():
bs1 = bistr(' Hello world ').strip().casefold()
bs2 = bistr(' Hello world ', 'hello world', Alignment([
(0, 0),
(2, 0),
(3, 1),
(4, 2),
(5, 3),
(6, 4),
(7, 5),
(8, 6),
(9, 7),
(10, 8),
(11, 9),
(12, 10),
(13, 11),
(15, 11),
]))
assert bs1 == bs2
def _test_identity_composition(alignment):
_test_composition(alignment, Alignment.identity(alignment.modified_range()))
_test_composition(Alignment.identity(alignment.original_range()), alignment)
def test_compose():
first = Alignment((i, 2 * i) for i in range(4))
second = Alignment((i, 2 * i) for i in range(7))
_test_composition(first, second)
def test_aligning():
alignment = Alignment([(0, 0), (1, 2), (2, 4), (3, 6)])
assert alignment.original_bounds() == (0, 3)
assert alignment.modified_bounds() == (0, 6)
assert alignment.original_bounds(0, 0) == (0, 0)
assert alignment.original_bounds(0, 1) == (0, 1)
assert alignment.original_bounds(0, 2) == (0, 1)
assert alignment.original_bounds(0, 3) == (0, 2)
assert alignment.original_bounds(1, 1) == (0, 1)
assert alignment.original_bounds(1, 3) == (0, 2)
assert alignment.original_bounds(1, 4) == (0, 2)
assert alignment.original_bounds(2, 2) == (1, 1)
assert alignment.original_bounds(2, 4) == (1, 2)
assert alignment.original_bounds(2, 5) == (1, 3)
assert alignment.original_bounds(3, 3) == (1, 2)
assert alignment.modified_bounds(0, 0) == (0, 0)
assert alignment.modified_bounds(0, 1) == (0, 2)
assert alignment.modified_bounds(0, 2) == (0, 4)
assert alignment.modified_bounds(0, 3) == (0, 6)
assert alignment.modified_bounds(1, 1) == (2, 2)
assert alignment.modified_bounds(2, 2) == (4, 4)