cb0c2fcafe
- checklist/response_mode.py：按类别（技术 / 商务）识别招标文件的响应方式（逐条响应 / 默认接受），规则优先； 两种写法冲突按逐条，认不出按逐条并写进覆盖范围。 - check/applicability.py：无效情形（★ / 斜体下划线标注的条款除外）、日期与递交、没要求附材料的评分标准、 无需提供证明或由采购人查询的资格，不逐条找响应，写进覆盖范围；要求附证明材料按原文判断，中标后才交的不算。 - 默认接受的要求没找到响应：一般要求记 implicit_accepted、不出问题；实质性要求记 implicit_review、提示级 人工核对；要附证明材料的不免（迁移 0006）。 - match.py：修同一行单元格又是别的条目候选句时的 KeyError（每条清单项单独记候选句，句子从总表里查）。 - 评测集：注入器同一要求的所有表格行一起改；散文、附件、格式文件里也响应了的要求不挂漏响应类问题； 错位响应必须是另一个参数；复核判不成立的单元不再挂；regen.py 按固定种子重新生成。 开发集 17 份：规矩投标文件报出的问题 639 → 229，误报 21.3 → 12.4 / 100，召回 68% → 65%，致命级 20 → 21 / 32 （docs/architecture/check-eval.md §4）。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
134 lines
7.1 KiB
Python
134 lines
7.1 KiB
Python
"""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"
|