from __future__ import annotations

from app.fact_coverage import (
    classify_fact_requirements,
    hard_fact_is_preserved,
    missing_hard_facts,
    missing_semantic_fact_ids,
    semantic_coverage_is_low,
)


def _facts(description: str) -> list[dict[str, str]]:
    return [{"id": "entry_description", "source": "user_form", "field": "description", "text": description}]


def test_fact_requirements_extract_atomic_objective_anchors() -> None:
    hard, coverage = classify_fact_requirements(
        _facts("This was an internal learning project.\nBuilt the import API with FastAPI for 300 users.")
    )

    assert {(fact["kind"], fact["text"]) for fact in hard} == {
        ("quantity", "300 users"),
        ("named_term", "fastapi"),
    }
    assert [fact["id"] for fact in coverage] == [
        "entry_description_part_1",
        "entry_description_part_2",
    ]


def test_card_metadata_is_not_a_narrative_requirement() -> None:
    facts = _facts("Built the reporting API with Python.")
    facts.extend([
        {"id": "entry_company", "field": "company", "text": "Example Co"},
        {"id": "entry_position", "field": "position", "text": "Intern"},
    ])

    hard, coverage = classify_fact_requirements(facts)

    assert {fact["id"] for fact in coverage} == {"entry_description"}
    assert {fact["text"] for fact in hard} == {"python"}


def test_repeated_named_terms_create_one_hard_anchor() -> None:
    hard, _coverage = classify_fact_requirements(
        _facts("Built a FastAPI service and documented the FastAPI deployment.")
    )

    assert [(fact["kind"], fact["text"]) for fact in hard] == [("named_term", "fastapi")]


def test_ordinary_uppercase_word_is_not_a_hard_anchor() -> None:
    hard, _coverage = classify_fact_requirements(_facts("Improved the API workflow for Client teams."))


    assert hard == []

def test_quantity_requires_its_bound_object() -> None:
    fact = {"id": "fact_1", "text": "300 users", "kind": "quantity"}

    assert hard_fact_is_preserved(fact, "Supported 300 users.")
    assert not hard_fact_is_preserved(fact, "Processed 300 requests.")
    assert not hard_fact_is_preserved(fact, "Supported 200 users.")


def test_literal_and_named_terms_are_checked_without_sentence_matching() -> None:
    ratio = {"id": "ratio", "text": "GPA: 4.3/5.0", "kind": "literal"}
    tool = {"id": "tool", "text": "fastapi", "kind": "named_term"}

    assert hard_fact_is_preserved(ratio, "GPA 4.3 / 5.0")
    assert not hard_fact_is_preserved(ratio, "GPA 4.0 / 5.0")
    assert hard_fact_is_preserved(tool, "Built the service with FastAPI.")
    assert not hard_fact_is_preserved(tool, "Built the service framework.")


def test_responsibility_downgrade_is_a_hard_omission() -> None:
    fact = {"id": "responsibility", "text": "lead", "kind": "responsibility"}

    assert hard_fact_is_preserved(fact, "\u4e3b\u5bfc\u7528\u6237\u6743\u9650\u6a21\u5757\u5f00\u53d1")
    assert not hard_fact_is_preserved(fact, "\u53c2\u4e0e\u7528\u6237\u6743\u9650\u6a21\u5757\u5f00\u53d1")
    assert missing_hard_facts([fact], "\u53c2\u4e0e\u7528\u6237\u6743\u9650\u6a21\u5757\u5f00\u53d1") == ["lead"]


def test_semantic_coverage_is_model_declared_and_thresholded() -> None:
    targets = [{"id": f"fact_{index}", "text": f"fact {index}"} for index in range(1, 5)]

    assert not semantic_coverage_is_low(targets, None)
    assert semantic_coverage_is_low(targets, ["fact_1", "fact_2"])
    assert not semantic_coverage_is_low(targets, ["fact_1", "fact_2", "fact_3"])
    assert missing_semantic_fact_ids(targets, ["fact_1", "fact_3"]) == ["fact_2", "fact_4"]


def test_small_semantic_target_sets_never_trigger_repair() -> None:
    targets = [{"id": "fact_1", "text": "one"}, {"id": "fact_2", "text": "two"}]

    assert not semantic_coverage_is_low(targets, [])