bid-doctor/server/tests/test_check_units.py

"""查标的纯函数：检索、投标侧证据校验、问题级别（m3-plan §2）。"""

from __future__ import annotations

from uuid import uuid4

from bid_doctor.check import findings, match
from bid_doctor.check.retrieval import Index, tokens
from bid_doctor.document.pipeline.text_layer import Sentence


def sent(seq: int, text: str, page: int = 1) -> Sentence:
    return Sentence(key=f"doc:p{page}:s{seq}", page_no=page, seq=seq, text=text, quads=[[0, 0, 1, 1]])


def test_tokens_keep_number_unit_and_model_names() -> None:
    t = tokens("服务器内存不低于32GB，支持10GE和硬件BFD")
    assert "32gb" in t and "10ge" in t and "bfd" in t and "内存" in t


def test_bm25_ranks_the_responding_sentence_first() -> None:
    index = Index(
        [
            sent(1, "我公司提供7×24小时售后服务。"),
            sent(2, "服务器内存配置为64GB，并提供产品彩页。"),
            sent(3, "交换机支持硬件BFD，最小发送间隔3.3毫秒。"),
        ]
    )
    (top, *_) = index.search("交换机支持硬件BFD 最小报文发送间隔不大于50毫秒", 3)
    assert top.sentence.seq == 3
    assert index.search("完全无关的词语组合", 3) == []


def bid() -> tuple[match.BidDoc, dict[str, tuple[match.BidDoc, Sentence]]]:
    s = sent(9, "服务器内存不低于32GB的要求：我方服务器内存配置为64GB。")
    d = match.BidDoc(uuid4(), 1, "技术分册", [s])
    return d, {"d1p1s9": (d, s)}


def test_responded_needs_verified_evidence() -> None:
    """模型说已响应，但证据没通过：不能判已响应，记「未找到响应」并带原因码（C3）。"""
    _, allowed = bid()
    ok = match.judge(
        {"verdict": "responded", "evidence": [{"sid": "d1p1s9", "quote": "我方服务器内存配置为64GB。"}]}, allowed, []
    )
    assert ok.verdict == "responded" and ok.evidence_status == "verified" and len(ok.evidence) == 1

    no_ev = match.judge({"verdict": "responded", "evidence": []}, allowed, [])
    assert (no_ev.verdict, no_ev.evidence_status, no_ev.reason_code) == ("not_found", "unverified", "evidence_missing")

    rewritten = match.judge(
        {"verdict": "responded", "evidence": [{"sid": "d1p1s9", "quote": "内存为64GB，满足要求。"}]}, allowed, []
    )
    assert rewritten.reason_code == "quote_not_original" and rewritten.detail["claimed_pages"] == [1]

    other = match.judge({"verdict": "responded", "evidence": [{"sid": "d1p2s1", "quote": "x" * 10}]}, allowed, [])
    assert other.reason_code == "sid_unknown"

    missing = match.judge(None, allowed, ["技术分册"])
    assert (missing.verdict, missing.reason_code) == ("undetermined", "missing_answer")


def test_severity_comes_from_the_item_not_the_model() -> None:
    assert findings.severity({"importance": "substantive", "categories": ["tech_param", "invalidity"]}) == "fatal"
    assert findings.severity({"importance": "normal", "categories": ["qualification"]}) == "fatal"
    assert findings.severity({"importance": "important", "categories": ["tech_param"]}) == "important"
    assert findings.severity({"importance": "normal", "categories": ["scoring"]}) == "important"
    assert findings.severity({"importance": "normal", "categories": ["tech_param"]}) == "hint"


def test_no_value_is_a_hint_and_unverified_is_explained() -> None:
    item = {"title": "服务器内存", "importance": "substantive", "categories": ["tech_param"]}
    nv = findings.spec(match.Result("no_value", "model", "verified"), item)
    assert nv is not None and nv.severity == "hint" and nv.title.startswith("未给出具体值")
    uv = findings.spec(
        match.Result("not_found", "model", "unverified", "quote_not_original", detail={"claimed_pages": [3]}), item
    )
    assert uv is not None and uv.severity == "fatal" and "第 3 页" in uv.explanation and "没能核对" in uv.explanation
    assert findings.spec(match.Result("responded", "model", "verified"), item) is None


def test_response_mode_by_category() -> None:
    from bid_doctor.checklist import response_mode

    sents = [
        sent(1, "技术规格偏离表"),
        sent(2, "投标人应将所有偏离的条目列入上表，未列入上表的视作投标人完全接受。"),
        sent(3, "商务条款偏离表"),
        sent(4, "投标人须对商务要求逐条作出响应。"),
    ]
    m = response_mode.detect(sents)
    assert (m["technical"].mode, m["technical"].status) == ("implicit", "found")
    assert (m["commercial"].mode, m["commercial"].status) == ("explicit", "found")
    both = response_mode.detect([sent(1, "须逐项作出响应。"), sent(2, "否则将认为投标人接受招标文件的要求。")])
    assert (both["technical"].mode, both["technical"].status) == ("explicit", "conflict")  # 写法冲突按逐条（C12）
    none = response_mode.detect([sent(1, "本项目为货物采购。")])
    assert (none["commercial"].mode, none["commercial"].status) == ("explicit", "unknown")


def test_applicability_skips_items_that_need_no_response() -> None:
    from bid_doctor.check import applicability
    from bid_doctor.checklist import response_mode

    modes = response_mode.detect([sent(1, "未列入偏离表的技术要求视作投标人完全接受。")])
    decide = applicability.decide
    assert decide({"categories": ["invalidity"], "importance_basis": "tender_text"}, modes).skip == "condition"
    assert decide({"categories": ["invalidity"], "importance_basis": "marker"}, modes).match  # ★ 条款是要求
    assert decide({"categories": ["schedule"]}, modes).skip == "schedule"
    assert decide({"categories": ["scoring"]}, modes).skip == "scoring"
    assert decide({"categories": ["scoring"], "evidence_required": "业绩合同"}, modes).match
    assert decide({"categories": ["scoring"], "title": "业绩（2 分）：提供近三年类似项目合同复印件"}, modes).match
    assert (
        decide({"categories": ["scoring"], "title": "提供检测报告，中标后签订合同前提供原件"}, modes).skip == "scoring"
    )
    assert decide({"categories": ["tech_param"], "title": "支持硬件BFD，提供官网截图证明"}, modes).evidence
    assert decide({"categories": ["qualification"], "title": "未被列入信用中国失信名单"}, modes).skip == "no_proof"
    d = decide({"categories": ["tech_param"], "title": "内存"}, modes)
    assert d.match and d.mode == "implicit"


def test_implicit_not_found_is_accepted_but_substantive_gets_a_hint() -> None:
    from uuid import uuid4

    from bid_doctor.check import applicability

    a, b = uuid4(), uuid4()
    results = {a: match.Result("not_found", "model"), b: match.Result("not_found", "model")}
    items = {a: {"importance": "normal"}, b: {"importance": "substantive", "title": "★双电源"}}
    decisions = {a: applicability.Decision(True, mode="implicit"), b: applicability.Decision(True, mode="implicit")}
    match.apply_modes(results, items, decisions)
    assert results[a].verdict == "implicit_accepted" and findings.spec(results[a], items[a]) is None
    spec = findings.spec(results[b], items[b])
    assert results[b].verdict == "implicit_review" and spec is not None and spec.severity == "hint"


def test_presence_names_and_find() -> None:
    from bid_doctor.check import presence

    assert presence.names("须提供加盖公章的《法定代表人授权委托书》，否则投标无效") == ["法定代表人授权委托书"]
    assert presence.names("投标人须提交投标函及开标一览表") == ["投标函"]
    heading = sent(3, "4．法定代表人授权委托书")
    body = sent(4, "本授权委托书声明：我单位授权……（这是正文里顺带提到的，很长" + "，" * 60 + "）")
    assert presence.find("法定代表人授权委托书", [body, heading]) is heading
    assert presence.find("营业执照", [heading]) is None


def test_scanned_fallback_turns_missing_evidence_into_a_hint() -> None:
    from uuid import uuid4

    from bid_doctor.check import applicability

    a, b = uuid4(), uuid4()
    results = {a: match.Result("not_found", "model"), b: match.Result("not_found", "model")}
    items = {
        a: {"categories": ["qualification"], "title": "营业执照"},
        b: {"categories": ["tech_param"], "title": "内存"},
    }
    decisions = {a: applicability.Decision(True, evidence=True), b: applicability.Decision(True)}
    docs = [match.BidDoc(uuid4(), 1, "资格证明册", [], [12, 13])]
    match.scanned_fallback(results, items, decisions, docs)
    spec = findings.spec(results[a], items[a])
    assert (
        results[a].verdict == "scanned"
        and spec is not None
        and spec.severity == "hint"
        and "2 页扫描件" in spec.explanation
    )
    assert results[b].verdict == "not_found"  # 技术参数不是证明材料，照常报未找到