22 lines
875 B
Python
22 lines
875 B
Python
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
from ont_platform.core.extractors.web_extractor import extract_web_content
|
||
|
|
from ont_platform.models.content_unit import PlatformContentUnit
|
||
|
|
|
||
|
|
FIXTURES = Path(__file__).resolve().parents[1] / "fixtures" / "korean"
|
||
|
|
|
||
|
|
|
||
|
|
def test_platform_content_unit_wraps_ontocast_unit_without_mutating_core() -> None:
|
||
|
|
html = (FIXTURES / "shop_coupang.html").read_text(encoding="utf-8")
|
||
|
|
extracted = extract_web_content(html=html, url="https://example.test/shop/data-quality-tool")
|
||
|
|
|
||
|
|
unit = PlatformContentUnit.from_extracted(extracted)
|
||
|
|
ontocast_unit = unit.as_ontocast()
|
||
|
|
|
||
|
|
assert unit.source_url == "https://example.test/shop/data-quality-tool"
|
||
|
|
assert unit.content_hash == extracted.content_hash
|
||
|
|
assert ontocast_unit.text == extracted.text
|
||
|
|
assert str(ontocast_unit.doc_iri).startswith("urn:source:doc_")
|