33 lines
1.0 KiB
Python
33 lines
1.0 KiB
Python
from tools.graphrag.graphrag import extract_works
|
|
from .test_graphrag import make_document, make_chunk
|
|
|
|
|
|
def test_scientific_project_heading_has_research_project_semantics():
|
|
works = extract_works(
|
|
make_document(categories=["vp2024"]),
|
|
[
|
|
make_chunk(
|
|
0,
|
|
["Vedecký projekt 2024"],
|
|
"Sekcia: Vedecký projekt 2024\nNázov: Overovanie jazykových modelov\n",
|
|
)
|
|
],
|
|
)
|
|
assert len(works) == 1
|
|
assert works[0]["work_type"] == "research_project"
|
|
assert works[0]["year"] == 2024
|
|
|
|
|
|
def test_bachelor_project_is_separate_from_thesis_category_year():
|
|
works = extract_works(
|
|
make_document(categories=["bp2025"]),
|
|
[
|
|
make_chunk(
|
|
0,
|
|
["Bakalársky projekt 2024"],
|
|
"Sekcia: Bakalársky projekt 2024\nNázov: Overovanie automatických odpovedí\n",
|
|
)
|
|
],
|
|
)
|
|
assert [(w["work_type"], w["year"]) for w in works] == [("bachelor_project", 2024)]
|