1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
|
import pytest
from lunr import lunr
from lunr.languages import LANGUAGE_SUPPORT, SUPPORTED_LANGUAGES
from lunr.pipeline import Pipeline
documents = [
{
"id": "a",
"text": (
"Este es un ejemplo inventado de lo que sería un documento en el "
"idioma que se más se habla en España."
),
"title": "Ejemplo de documento en español",
},
{
"id": "b",
"text": (
"Según un estudio que me acabo de inventar porque soy un experto en"
"idiomas que se hablan en España."
),
"title": "Español es el tercer idioma más hablado del mundo",
},
]
class TestLanguageSupport:
@classmethod
def setup_class(cls):
assert (
LANGUAGE_SUPPORT is True
), "NLTK not found, please run `pip install -e .[languages]`"
def test_lunr_function_raises_if_unsupported_language(self):
with pytest.raises(RuntimeError):
lunr("id", ["title", "text"], documents, "foo")
def test_lunr_function_raises_if_any_unsupported_language_is_passed(self):
with pytest.raises(RuntimeError):
lunr("id", ["title", "text"], documents, ["es", "foo"])
def test_register_languages_in_pipeline_class(self):
for lang in set(SUPPORTED_LANGUAGES) - {"en"}:
assert "stemmer-{}".format(lang) in Pipeline.registered_functions
def test_lunr_function_registers_nltk_stemmers_in_pipeline(self):
idx = lunr("id", ["title", "text"], documents, ["es", "it"])
assert "stemmer-es" in repr(idx.pipeline)
assert "stemmer-it" in repr(idx.pipeline)
def test_lunr_registers_lun_stemmers_in_pipeline_if_language_is_en(self):
idx = lunr("id", ["title", "text"], documents, ["en", "es"])
assert "stemmer,stemmer-es" in repr(idx.pipeline)
def test_search_stems_search_terms(self):
idx = lunr("id", ["title", "text"], documents, "es")
results = idx.search("inventando") # stemmed to "invent"
assert len(results) == 2
def test_search_stems_search_terms_for_both_languages(self):
italian_document = {
"id": "c",
"text": (
"Secondo uno studio che ho appena inventato perché sono un "
"esperto di lingue parlate in Spagna."
),
"title": "Lo spagnolo è la terza lingua più parlata al mondo",
}
idx = lunr(
ref="id",
fields=["title", "text"],
documents=(documents + [italian_document]),
languages=["es", "it"],
)
results = idx.search("spagna")
assert len(results) == 1
results = idx.search("inventando")
assert len(results) == 2
|
