"""评测指标纯函数单元测试（不依赖 Qdrant / Ollama）"""

import pytest

from scripts.eval.metrics import (
    aggregate,
    entity_recall,
    precision_at_k,
    pruning_loss,
    recall_at_k,
    routing_f1,
)


class TestEntityRecall:
    def test_all_entities_kept(self) -> None:
        source = "使用 Qdrant 存储 1536 维向量，模型 bge-m3，见《部署手册》第三条。"
        summary = "基于 Qdrant 与 bge-m3 的 1536 维向量检索，详见《部署手册》第三条。"
        assert entity_recall(source, summary) == pytest.approx(1.0)

    def test_partial_entities_kept(self) -> None:
        source = "支持 text-embedding-3-small 和 bge-m3 两个模型。"
        summary = "支持 bge-m3 模型。"
        score = entity_recall(source, summary)
        assert 0.0 < score < 1.0

    def test_no_entities_returns_full_score(self) -> None:
        assert entity_recall("这是一段没有任何实体的中文普通句子。", "很短") == 1.0

    def test_empty_summary_drops_all(self) -> None:
        source = "版本 v1.2.0 修复了 3 个问题。"
        assert entity_recall(source, "") == pytest.approx(0.0)


class TestRoutingF1:
    def test_perfect_routing(self) -> None:
        golden = [{"d1"}, {"d2"}]
        routed = [{"d1"}, {"d2"}]
        result = routing_f1(golden, routed)
        assert result == {"precision": 1.0, "recall": 1.0, "f1": 1.0}

    def test_micro_average(self) -> None:
        # query1: tp=1 fp=1；query2: tp=0 fn=1 → micro p=1/2 r=1/2 f1=1/2
        golden = [{"d1"}, {"d2"}]
        routed = [{"d1", "d3"}, set()]
        result = routing_f1(golden, routed)
        assert result["precision"] == pytest.approx(0.5)
        assert result["recall"] == pytest.approx(0.5)
        assert result["f1"] == pytest.approx(0.5)

    def test_empty_routed(self) -> None:
        result = routing_f1([{"d1"}], [set()])
        assert result["precision"] == 0.0
        assert result["recall"] == 0.0


class TestPruningLoss:
    def test_mixed_cases(self) -> None:
        assert pruning_loss([False, True, False, False]) == pytest.approx(0.25)

    def test_empty(self) -> None:
        assert pruning_loss([]) == 0.0


class TestPrecisionRecallAtK:
    def test_precision_at_k(self) -> None:
        hits = ["d1", "d2", "d3", "d4", "d5"]
        assert precision_at_k(hits, {"d1", "d3"}, 5) == pytest.approx(0.4)

    def test_precision_at_k_empty_hits(self) -> None:
        assert precision_at_k([], {"d1"}, 5) == 0.0

    def test_recall_at_k_dedup(self) -> None:
        hits = ["d1", "d1", "d2"]
        assert recall_at_k(hits, {"d1", "d2", "d3"}, 3) == pytest.approx(2 / 3)

    def test_recall_at_k_empty_golden(self) -> None:
        assert recall_at_k(["d1"], set(), 5) == 0.0


class TestAggregate:
    def test_mean_per_key(self) -> None:
        records = [{"a": 1.0, "b": 0.5}, {"a": 0.0, "b": 1.0}]
        result = aggregate(records)
        assert result["a"] == pytest.approx(0.5)
        assert result["b"] == pytest.approx(0.75)

    def test_partial_keys(self) -> None:
        result = aggregate([{"a": 1.0}, {"a": 0.0, "b": 1.0}])
        assert result["a"] == pytest.approx(0.5)
        assert result["b"] == pytest.approx(1.0)

    def test_empty(self) -> None:
        assert aggregate([]) == {}