123 lines
4.1 KiB
Python
123 lines
4.1 KiB
Python
"""GeneratedQuestion.sub_pattern 字段 + _to_generated_question 透传。"""
|
|
|
|
from app.question_gen.generator_v2 import CandidateQuestion
|
|
from app.question_gen.pipeline_v2 import _to_generated_question
|
|
from core.types import GeneratedQuestion
|
|
|
|
|
|
def _candidate() -> CandidateQuestion:
|
|
return CandidateQuestion(
|
|
question_id="v1_Action Recognition_0001",
|
|
video_id="v1",
|
|
task_type="Action Recognition",
|
|
skill_target="M1_AR",
|
|
question="厨师最终采用了哪种烹饪方式？",
|
|
options=("A. 蒸", "B. 炒", "C. 煮", "D. 炸"),
|
|
answer="A",
|
|
source_nodes=("n1", "n2"),
|
|
difficulty="hard",
|
|
)
|
|
|
|
|
|
def test_generated_question_has_sub_pattern_default_none():
|
|
q = GeneratedQuestion(
|
|
question_id="q1",
|
|
video_id="v1",
|
|
task_type="Action Recognition",
|
|
question="?",
|
|
options=("A. x",),
|
|
answer="A",
|
|
source_nodes=("n1",),
|
|
difficulty="easy",
|
|
)
|
|
assert q.sub_pattern is None
|
|
|
|
|
|
def test_to_generated_question_threads_sub_pattern():
|
|
q = _to_generated_question(
|
|
_candidate(),
|
|
family="ACTION_RECOGNITION",
|
|
sub_pattern="premature_evidence_anchoring",
|
|
)
|
|
assert q.sub_pattern == "premature_evidence_anchoring"
|
|
|
|
|
|
def test_to_generated_question_sub_pattern_defaults_none():
|
|
q = _to_generated_question(_candidate(), family="RETRIEVAL")
|
|
assert q.sub_pattern is None
|
|
|
|
|
|
def test_question_to_entry_includes_sub_pattern():
|
|
from tools.generate_questions import _question_to_entry
|
|
|
|
q = GeneratedQuestion(
|
|
question_id="v1_Action Recognition_0001",
|
|
video_id="v1",
|
|
task_type="Action Recognition",
|
|
question="?",
|
|
options=("A. 蒸", "B. 炒", "C. 煮", "D. 炸"),
|
|
answer="A",
|
|
source_nodes=("n1",),
|
|
difficulty="hard",
|
|
family="ACTION_RECOGNITION",
|
|
skill_target="M1_AR",
|
|
sub_pattern="temporal_reasoning_failure",
|
|
)
|
|
entry = _question_to_entry(q)
|
|
assert entry["sub_pattern"] == "temporal_reasoning_failure"
|
|
assert entry["question_id"] == "v1_Action Recognition_0001"
|
|
assert entry["options"] == ["A. 蒸", "B. 炒", "C. 煮", "D. 炸"]
|
|
|
|
|
|
def test_append_to_json_writes_sub_pattern(tmp_path):
|
|
from tools.generate_questions import _append_to_json
|
|
|
|
q = GeneratedQuestion(
|
|
question_id="v1_Action Recognition_0001",
|
|
video_id="v1",
|
|
task_type="Action Recognition",
|
|
question="?",
|
|
options=("A. 蒸", "B. 炒", "C. 煮", "D. 炸"),
|
|
answer="A",
|
|
source_nodes=("n1",),
|
|
difficulty="hard",
|
|
family="ACTION_RECOGNITION",
|
|
skill_target="M1_AR",
|
|
sub_pattern="temporal_reasoning_failure",
|
|
)
|
|
_append_to_json(tmp_path, q)
|
|
import json
|
|
|
|
data = json.loads((tmp_path / "v1.json").read_text(encoding="utf-8"))
|
|
assert data[0]["sub_pattern"] == "temporal_reasoning_failure"
|
|
|
|
|
|
def test_load_benchmark_restores_sub_pattern(tmp_path):
|
|
from app.question_gen.loader import load_benchmark
|
|
import json
|
|
entry = {
|
|
"question_id": "v1_Action Recognition_0001", "video_id": "v1",
|
|
"task_type": "Action Recognition", "question": "?",
|
|
"options": ["A. 蒸", "B. 炒", "C. 煮", "D. 炸"], "answer": "A",
|
|
"source_nodes": ["n1"], "difficulty": "hard",
|
|
"family": "ACTION_RECOGNITION", "skill_target": "M1_AR",
|
|
"sub_pattern": "temporal_reasoning_failure",
|
|
}
|
|
(tmp_path / "v1.json").write_text(json.dumps([entry]), encoding="utf-8")
|
|
loaded = load_benchmark(tmp_path)
|
|
assert loaded[0].sub_pattern == "temporal_reasoning_failure"
|
|
|
|
|
|
def test_load_benchmark_sub_pattern_defaults_none_when_absent(tmp_path):
|
|
from app.question_gen.loader import load_benchmark
|
|
import json
|
|
entry = {
|
|
"question_id": "v1_Object Recognition_0001", "video_id": "v1",
|
|
"task_type": "Object Recognition", "question": "?",
|
|
"options": ["A. a", "B. b", "C. c", "D. d"], "answer": "A",
|
|
"source_nodes": ["n1"], "difficulty": "medium",
|
|
}
|
|
(tmp_path / "v1.json").write_text(json.dumps([entry]), encoding="utf-8")
|
|
loaded = load_benchmark(tmp_path)
|
|
assert loaded[0].sub_pattern is None
|