slovnet

1

2
import pytest
3

4
from slovnet.shape import (
5
    X, x, xx, XX, Xx, Xx_Xx, OTHER,
6
    RU, EN, NUM, PUNCT,
7

8
    word_shape,
9
    format_shape as s
10
)
11
from slovnet.token import tokenize
12

13

14
TESTS = [
15
    [
16
        'В',
17
        [s(RU, X)],
18
    ],
19
    [
20
        'ИЛ-2',
21
        [s(RU, XX)],
22
    ],
23
    [
24
        '105г.',
25
        [NUM, s(RU, x), s(PUNCT, '.')]
26
    ],
27
    [
28
        'Pal-Yz',
29
        [s(EN, Xx_Xx)]
30
    ],
31
    [
32
        'и Я-ДаА',
33
        [s(RU, x), s(RU, OTHER)]
34
    ],
35
    [
36
        'Прибыл на I@',
37
        [s(RU, Xx), s(RU, xx), s(EN, X), s(PUNCT, '@')]
38
    ],
39
    [
40
        'и -‐',
41
        [s(RU, x), s(PUNCT, OTHER)]
42
    ]
43
]
44

45

46
@pytest.mark.parametrize('test', TESTS)
47
def test_shape(test):
48
    text, etalon = test
49
    tokens = tokenize(text)
50
    guess = [word_shape(_.text) for _ in tokens]
51
    assert guess == etalon
52