import json
from pathlib import Path
from typing import Any

PROJECT_ROOT = Path(__file__).resolve().parents[3]
SAMPLE_ROOT = PROJECT_ROOT / "data" / "samples" / "public"


def load_jsonl(path: Path) -> list[dict[str, Any]]:
    return [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines()]


def test_demo_corpus_is_synthetic_pending_hash_bound_approval_and_unique() -> None:
    documents = load_jsonl(SAMPLE_ROOT / "demo_documents.jsonl")

    assert len(documents) == 20
    assert len({document["doc_id"] for document in documents}) == 20
    assert all(document["source_type"] == "synthetic" for document in documents)
    assert all(
        document["review_state"] == "LOCAL_PARSED_PENDING_CLOUD_REVIEW" for document in documents
    )
    assert all(document["cloud_policy_id"] == "synthetic-demo-v1" for document in documents)
    assert all("cloud_approved" not in document for document in documents)
    assert all(
        "虚构" in document["content"] or "演示" in document["content"] for document in documents
    )


def test_demo_queries_only_reference_existing_documents() -> None:
    documents = load_jsonl(SAMPLE_ROOT / "demo_documents.jsonl")
    queries = load_jsonl(SAMPLE_ROOT / "demo_queries.jsonl")
    document_ids = {document["doc_id"] for document in documents}

    assert len(queries) == 10
    assert len({query["qid"] for query in queries}) == 10
    assert all(set(query["expected_doc_ids"]) <= document_ids for query in queries)
    assert any(not query["answerable"] and not query["expected_doc_ids"] for query in queries)