"""失败安全与词边界单元测试（T-R3，采纳 llmrouter 设计）。"""
from router_system.classifier import RuleClassifier, build_classifier
from router_system.difficulty import estimate_difficulty


def test_word_boundary_stops_substring_false_positive():
    """英文标记整词命中：'int' 不再被 'print'/'point' 误触发 hard。"""
    diff, score = estimate_difficulty("如何用 print 函数打印结果")
    # 旧实现 'int' 误命中 print 叠加 如何 -> hard；现在应为 medium 以下
    assert diff in ("easy", "medium")

    diff2, _ = estimate_difficulty("请总结这段逻辑代码的思路")
    # 'sum' 不被 'summary/总结' 类场景误判：'逻辑' 含 'log' 也不再整词误命中
    assert diff2 in ("easy", "medium")


def test_word_boundary_still_counts_whole_words():
    """整词出现照常计数：int/log 作为真词仍触发 hard 信号。"""
    diff, _ = estimate_difficulty("explain how to implement int overflow and log parsing in depth")
    assert diff in ("medium", "hard")


def test_chinese_markers_keep_substring_semantics():
    """中文标记保持子串语义：'证明' 命中 '证明费马大定理'。"""
    diff, _ = estimate_difficulty("证明费马大定理并推导其推论，给出详细步骤")
    assert diff in ("medium", "hard")


def test_build_hf_falls_back_when_unavailable(monkeypatch):
    """HF 分类器构造失败（依赖缺失/模型加载失败）安全回落规则分类器。"""
    def _boom(self, *a, **k):
        raise RuntimeError("HuggingFaceClassifier 需要安装 ML 依赖")
    import router_system.classifier as C
    monkeypatch.setattr(C.HuggingFaceClassifier, "__init__", _boom)
    clf = build_classifier({"type": "hf", "model": "whatever"})
    assert isinstance(clf, RuleClassifier)
    assert clf.classify("用 Python 写一个快速排序函数").domain == "code"


def test_hf_runtime_failure_falls_back_to_rules():
    """推理期异常（torch 缺失/tokenizer 损坏）回落内置规则分类器。"""
    from router_system.classifier import HuggingFaceClassifier
    hf = HuggingFaceClassifier.__new__(HuggingFaceClassifier)
    hf.labels = ["code", "math", "legal", "medical", "general"]
    hf.confidence_floor = 0.55
    hf._rule_fallback = RuleClassifier(confidence_floor=0.55)
    r = hf.classify("用 Python 写一个快速排序函数")  # 本环境无 torch/tokenizer -> 必走回落
    assert r.domain == "code"