63 lines
2.7 KiB
Python
63 lines
2.7 KiB
Python
from pathlib import Path
|
|
from didactopus.document_adapters import adapt_document
|
|
from didactopus.topic_ingest import document_to_course, build_topic_bundle, merge_courses_into_topic_course, extract_concept_candidates
|
|
|
|
|
|
def test_cross_course_merge(tmp_path: Path) -> None:
|
|
a = tmp_path / "a.md"
|
|
b = tmp_path / "b.docx"
|
|
a.write_text("# T\n\n## M\n### L1\nBody A", encoding="utf-8")
|
|
b.write_text("# T\n\n## M\n### L1\nBody B", encoding="utf-8")
|
|
|
|
docs = [adapt_document(a), adapt_document(b)]
|
|
courses = [document_to_course(doc, "Topic") for doc in docs]
|
|
topic = build_topic_bundle("Topic", courses)
|
|
merged = merge_courses_into_topic_course(topic)
|
|
assert len(merged.modules) >= 1
|
|
assert len(merged.modules[0].lessons) == 1
|
|
|
|
|
|
def test_extract_concepts(tmp_path: Path) -> None:
|
|
a = tmp_path / "a.md"
|
|
a.write_text("# T\n\n## M\n### Lesson A\nObjective: Explain Topic A.\nBody.", encoding="utf-8")
|
|
doc = adapt_document(a)
|
|
course = document_to_course(doc, "Topic")
|
|
concepts = extract_concept_candidates(course)
|
|
assert len(concepts) >= 1
|
|
|
|
|
|
def test_document_to_course_skips_empty_sections(tmp_path: Path) -> None:
|
|
a = tmp_path / "a.md"
|
|
a.write_text("# T\n\n## Empty\n\n### Filled\nBody.", encoding="utf-8")
|
|
doc = adapt_document(a)
|
|
course = document_to_course(doc, "Topic")
|
|
assert [lesson.title for lesson in course.modules[0].lessons] == ["Filled"]
|
|
|
|
|
|
def test_document_to_course_parses_bulleted_objectives_and_exercises(tmp_path: Path) -> None:
|
|
a = tmp_path / "a.md"
|
|
a.write_text(
|
|
"# T\n\n## M\n### Shannon Entropy\n- Objective: Explain uncertainty.\n- Exercise: Compute entropy.\nBody.",
|
|
encoding="utf-8",
|
|
)
|
|
doc = adapt_document(a)
|
|
course = document_to_course(doc, "Topic")
|
|
lesson = course.modules[0].lessons[0]
|
|
assert lesson.objectives == ["Explain uncertainty."]
|
|
assert lesson.exercises == ["Compute entropy."]
|
|
|
|
|
|
def test_extract_concepts_retains_lessons_but_filters_generic_terms(tmp_path: Path) -> None:
|
|
a = tmp_path / "a.md"
|
|
a.write_text(
|
|
"# T\n\n## M\n### MIT OCW 6.050J Information and Entropy: Syllabus\n- Objective: Explain the course.\nBody.\n\n### Channel Capacity\n- Objective: Explain noisy channels.\n- Exercise: State a capacity limit.\nChannel Capacity links reliable communication to noise and coding.",
|
|
encoding="utf-8",
|
|
)
|
|
doc = adapt_document(a)
|
|
course = document_to_course(doc, "Topic")
|
|
concepts = extract_concept_candidates(course)
|
|
titles = {concept.title for concept in concepts}
|
|
assert "MIT OCW 6.050J Information and Entropy: Syllabus" in titles
|
|
assert "Explain" not in titles
|
|
assert "Channel Capacity" in titles
|