feat(v2): 新增 S1 契约层（材料集合导入与事实确认）
T02 首个子卡 = S1 契约层。新增 backend/contracts/prescreen.py（设计指定的 唯一 owner），定义 SourceLocator / ImportItem / ImportBatch / FactConflict 与共用约束、错误码与错误信封。 落实的规格条目： - BR-22 逐文件保留来源/定位/解析版本与状态 - BR-23 多来源冲突保留候选并要求显式处理（resolved 需说明+选择+人） - AC-23 反例：绝对路径(C:/、/、//share)、上级引用(..)、超限、空集合、 failed 缺 error_code、parsed 缺 document_id、parsed 带 error_code - AC-24 反例：候选值全同不构成冲突；未知用 null 而非 0/空串； candidates 必须与 candidate_evidence_ids 同序同集合 - 01 §5 错误码与既有 translate() 的 HTTP 语义对齐；E-17 为运行级、HTTP 200 - 03 §9.1 时间必须带时区；禁止未知字段（E-07） D3 定案（工程限制，非业务阈值）：单文件 ≤10 MiB 沿用既有 LIMIT；单批 ≤20 文件 / ≤20 MiB。依据 03 §1 末「管理员只能降低初期限制，放宽须重新验证」， 取保守方向即规格许可；放宽需另立验证。 依赖方向：contracts 不导入 services，标准字段白名单校验留在 service 层。 测试：新增 test_prescreen_contracts.py 38 项，全绿；scripts/verify.py 9/9 PASS。 Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
Claude Code
@@ -0,0 +1,309 @@
|
||||
"""兴邦预审 v2 · 首个实施切片（S1）契约：材料集合导入与事实确认。
|
||||
|
||||
唯一职责 owner：[docs/v2/03-detailed-design.md](../../../docs/v2/03-detailed-design.md) §1/§9.2 指定的
|
||||
`backend/contracts/prescreen.py`。本文件是该 owner 的**首版实现**，字段命名以本文件为准；
|
||||
`claude_use/T00/04-first-slice-contracts.md` 是提案记录，不是第二份契约定义。
|
||||
|
||||
S1 范围（T00/04 §4/§5）：
|
||||
SourceLocator · ImportItem · ImportBatch · FactConflict + 共用约束 + 错误信封
|
||||
|
||||
**不在本文件**（属后续任务包，不得在此提前定义）：CaseTimeline、DecisionEvent、
|
||||
ExperienceCard、KnowledgeCard、ReviewPlan、DimensionSpec、ScreeningRun、Judgment、
|
||||
Simulation、Evaluation、TrajectoryStep、ReviewOutcome、ImprovementCandidate、
|
||||
DatasetManifest、ProbabilityView。
|
||||
|
||||
依赖方向：本模块**不导入** `services/`。标准字段白名单（`assistant_materials.FIELDS`）
|
||||
的校验属 service 层，避免 contracts → services 的反向依赖。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from datetime import datetime
|
||||
from enum import StrEnum
|
||||
from typing import Annotated, Literal
|
||||
|
||||
from pydantic import AfterValidator, BaseModel, ConfigDict, Field, model_validator
|
||||
|
||||
# ---------------------------------------------------------------- 共用约束
|
||||
ID_MAX = 128
|
||||
PATH_MAX = 512
|
||||
NOTE_MAX = 2000
|
||||
EVIDENCE_MAX = 100
|
||||
DESC_MAX = 2000
|
||||
|
||||
# P0 初始工程限制（**非业务阈值**，见 docs/v2/03-detailed-design.md §1 末）。
|
||||
# 单文件上限沿用既有 assistant_materials.LIMIT = 10 MiB。
|
||||
# 单批总量取保守值：现有实现把整份文件 base64 存进 SQLite 单行，
|
||||
# 设计文档曾提 100 MiB/批 ≈ 133 MiB base64 入库，可直接造成演示故障
|
||||
# （claude_use/T00/04 §3.1）。**降低**无需重新验证；**放宽**须重新验证并更新规格。
|
||||
MAX_ITEM_BYTES = 10 * 1024 * 1024
|
||||
MAX_BATCH_BYTES = 20 * 1024 * 1024
|
||||
MAX_BATCH_FILES = 20
|
||||
|
||||
_SHA256 = re.compile(r"^[0-9a-f]{64}$")
|
||||
_WINDOWS_DRIVE = re.compile(r"^[A-Za-z]:")
|
||||
|
||||
|
||||
def _aware(value: datetime) -> datetime:
|
||||
"""时间必须带时区（docs/v2/03-detailed-design.md §9.1）。"""
|
||||
if value.tzinfo is None or value.utcoffset() is None:
|
||||
raise ValueError("时间必须带时区（ISO-8601）")
|
||||
return value
|
||||
|
||||
|
||||
AwareDatetime = Annotated[datetime, AfterValidator(_aware)]
|
||||
Identifier = Annotated[str, Field(min_length=1, max_length=ID_MAX)]
|
||||
|
||||
|
||||
class Contract(BaseModel):
|
||||
"""所有 S1 对象共用：禁止未知字段（对应 E-07 INVALID_REQUEST）。"""
|
||||
|
||||
model_config = ConfigDict(extra="forbid")
|
||||
|
||||
|
||||
class DataDomain(StrEnum):
|
||||
demo = "demo"
|
||||
production = "production"
|
||||
|
||||
|
||||
class Ref(Contract):
|
||||
"""通用版本引用（docs/v2/03-detailed-design.md §9.1）。"""
|
||||
|
||||
id: Identifier
|
||||
version: str = Field(min_length=1, max_length=ID_MAX)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- 错误契约
|
||||
class ErrorCode(StrEnum):
|
||||
"""S1 涉及的错误码。取值与 docs/v2/01-requirements.md §5 一一对应，不另造。"""
|
||||
|
||||
NOT_FOUND = "NOT_FOUND"
|
||||
ACCESS_DENIED = "ACCESS_DENIED"
|
||||
INVALID_REQUEST = "INVALID_REQUEST"
|
||||
INVALID_EVIDENCE = "INVALID_EVIDENCE"
|
||||
REVISION_CONFLICT = "REVISION_CONFLICT"
|
||||
IDEMPOTENCY_CONFLICT = "IDEMPOTENCY_CONFLICT"
|
||||
MATERIAL_PARSE_FAILED = "MATERIAL_PARSE_FAILED"
|
||||
IMPORT_BATCH_INVALID = "IMPORT_BATCH_INVALID"
|
||||
FACT_CONFLICT_UNRESOLVED = "FACT_CONFLICT_UNRESOLVED"
|
||||
|
||||
|
||||
# HTTP 语义沿用既有 translate()（backend/api/project_assistant.py:36-46），
|
||||
# 不另立一套。E-17 是**运行级结果标识**，不是 HTTP 错误（01 §5 末）。
|
||||
S1_ERROR_HTTP: dict[ErrorCode, int] = {
|
||||
ErrorCode.NOT_FOUND: 404,
|
||||
ErrorCode.ACCESS_DENIED: 403,
|
||||
ErrorCode.INVALID_REQUEST: 422,
|
||||
ErrorCode.INVALID_EVIDENCE: 422,
|
||||
ErrorCode.REVISION_CONFLICT: 409,
|
||||
ErrorCode.IDEMPOTENCY_CONFLICT: 409,
|
||||
ErrorCode.MATERIAL_PARSE_FAILED: 422,
|
||||
ErrorCode.IMPORT_BATCH_INVALID: 422,
|
||||
ErrorCode.FACT_CONFLICT_UNRESOLVED: 200,
|
||||
}
|
||||
|
||||
# 403/422 不自动重试；409 需客户端改载荷或刷新。见 03 §5。
|
||||
S1_ERROR_RETRYABLE: dict[ErrorCode, bool] = {code: False for code in ErrorCode}
|
||||
|
||||
|
||||
class ErrorBody(Contract):
|
||||
code: ErrorCode
|
||||
message: str = Field(min_length=1, max_length=DESC_MAX)
|
||||
retryable: bool
|
||||
request_id: str = Field(min_length=1, max_length=ID_MAX)
|
||||
|
||||
|
||||
class ErrorResponse(Contract):
|
||||
"""新 prescreen 路由的**独立**错误信封（T00/04 §2 决策 D2）。
|
||||
|
||||
既有路由仍是 FastAPI 默认 `{"detail": ...}`，本次不改，避免影响
|
||||
backend/api/project_assistant.py 的 translate() 及其全部消费方。
|
||||
"""
|
||||
|
||||
error: ErrorBody
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- 来源定位
|
||||
class SourceLocator(Contract):
|
||||
"""证据在原件中的定位。定位**不等于**真实性核验（01 §1）。
|
||||
|
||||
kind 决定必填字段，且三种寻址方式互斥：
|
||||
pdf → page
|
||||
table → sheet + cell_range
|
||||
manual → note
|
||||
"""
|
||||
|
||||
kind: Literal["pdf", "table", "manual"]
|
||||
document_id: Identifier
|
||||
document_version: int = Field(ge=1)
|
||||
page: int | None = Field(default=None, ge=1)
|
||||
sheet: str | None = Field(default=None, min_length=1, max_length=200)
|
||||
cell_range: str | None = Field(default=None, min_length=1, max_length=200)
|
||||
note: str | None = Field(default=None, min_length=1, max_length=PATH_MAX)
|
||||
excerpt: str | None = Field(default=None, max_length=4000)
|
||||
|
||||
_REQUIRED: dict[str, tuple[str, ...]] = {
|
||||
"pdf": ("page",),
|
||||
"table": ("sheet", "cell_range"),
|
||||
"manual": ("note",),
|
||||
}
|
||||
_ADDRESS_FIELDS = ("page", "sheet", "cell_range", "note")
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _check_kind_fields(self) -> SourceLocator:
|
||||
required = self._REQUIRED[self.kind]
|
||||
missing = [name for name in required if getattr(self, name) is None]
|
||||
if missing:
|
||||
raise ValueError(f"{self.kind} 定位缺少必填字段：{', '.join(missing)}")
|
||||
extra = [name for name in self._ADDRESS_FIELDS
|
||||
if name not in required and getattr(self, name) is not None]
|
||||
if extra:
|
||||
raise ValueError(f"{self.kind} 定位不允许字段：{', '.join(extra)}")
|
||||
return self
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- 导入清单
|
||||
class ImportItem(Contract):
|
||||
"""集合中的一个文件条目。`relative_path` 仅表达用户选择的文件集合，
|
||||
绝不作服务器写入路径（docs/v2/14-experience-loop.md §3）。
|
||||
"""
|
||||
|
||||
id: Identifier
|
||||
document_id: Identifier | None = None # 解析成功后由既有 upload 链回填
|
||||
relative_path: str = Field(min_length=1, max_length=PATH_MAX)
|
||||
sha256: str = Field(pattern=_SHA256.pattern)
|
||||
size_bytes: int = Field(ge=0, le=MAX_ITEM_BYTES)
|
||||
mime_type: str = Field(min_length=1, max_length=200)
|
||||
status: Literal["queued", "parsing", "parsed", "failed"]
|
||||
error_code: ErrorCode | None = None
|
||||
observed_at: AwareDatetime | None = None # 材料**发生**时间；未知为 null
|
||||
received_at: AwareDatetime
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _check_path_and_status(self) -> ImportItem:
|
||||
# 路径安全：不允许绝对路径、盘符或上级引用。校验用规范化副本，
|
||||
# 但**保留原值**，使客户端提交的内容与落库内容一致。
|
||||
normalized = self.relative_path.replace("\\", "/")
|
||||
if normalized.startswith("/") or _WINDOWS_DRIVE.match(normalized):
|
||||
raise ValueError("relative_path 不得为绝对路径")
|
||||
if any(part == ".." for part in normalized.split("/")):
|
||||
raise ValueError("relative_path 不得包含上级引用")
|
||||
|
||||
if self.status == "failed" and self.error_code is None:
|
||||
raise ValueError("failed 的条目必须有 error_code")
|
||||
if self.status == "parsed" and self.error_code is not None:
|
||||
raise ValueError("parsed 的条目不得带 error_code")
|
||||
if self.status == "parsed" and self.document_id is None:
|
||||
raise ValueError("parsed 的条目必须已关联 document_id")
|
||||
return self
|
||||
|
||||
|
||||
class ImportBatch(Contract):
|
||||
"""一次「文件集合」导入的容器对象。
|
||||
|
||||
状态机（T00/04 §6.1）：
|
||||
queued → parsing → ready | partial | failed
|
||||
queued | parsing → cancelled
|
||||
partial | failed → queued（retry，仅重置失败项，revision++）
|
||||
"""
|
||||
|
||||
id: Identifier
|
||||
project_id: Identifier
|
||||
data_domain: DataDomain
|
||||
revision: int = Field(ge=1)
|
||||
status: Literal["queued", "parsing", "ready", "partial", "failed", "cancelled"]
|
||||
created_at: AwareDatetime
|
||||
created_by: Identifier
|
||||
parser_version: str = Field(min_length=1, max_length=64)
|
||||
items: list[ImportItem] = Field(min_length=1, max_length=MAX_BATCH_FILES)
|
||||
# 不在此处加 le=MAX_BATCH_BYTES：字段级约束会先于模型级校验触发，
|
||||
# 使用户看到 pydantic 的英文默认文案而非下面的中文提示。
|
||||
total_bytes: int = Field(ge=0)
|
||||
warnings: list[str] = Field(default_factory=list, max_length=EVIDENCE_MAX)
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _check_consistency(self) -> ImportBatch:
|
||||
if len({item.id for item in self.items}) != len(self.items):
|
||||
raise ValueError("同一批次内 item id 必须唯一")
|
||||
# 单项上限已由 ImportItem.size_bytes 的 le 约束保证，此处不重复检查。
|
||||
total = sum(item.size_bytes for item in self.items)
|
||||
if total != self.total_bytes:
|
||||
raise ValueError("total_bytes 必须等于各 item size_bytes 之和")
|
||||
if total > MAX_BATCH_BYTES:
|
||||
raise ValueError(
|
||||
f"单批总量 {total} 超过上限 {MAX_BATCH_BYTES} 字节；请拆分后重试"
|
||||
)
|
||||
return self
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- 事实冲突
|
||||
class ConflictCandidate(Contract):
|
||||
"""并列展示的候选值之一。未知用 null，**不用 0 或空串代替**（03 §9.1）。"""
|
||||
|
||||
evidence_id: Identifier
|
||||
value: str | None = None
|
||||
source: str = Field(min_length=1, max_length=PATH_MAX)
|
||||
locator: str = Field(min_length=1, max_length=PATH_MAX)
|
||||
unit: str | None = Field(default=None, max_length=64)
|
||||
currency: str | None = Field(default=None, max_length=16)
|
||||
period: str | None = Field(default=None, max_length=64)
|
||||
|
||||
|
||||
class FactConflict(Contract):
|
||||
"""同一字段在多来源上给出不同值时的待处理对象（BR-23 / E-17 / AC-24）。
|
||||
|
||||
只允许 unresolved → resolved。再次冲突时**新建**对象并用 supersedes_id
|
||||
指向旧对象，不覆写历史。
|
||||
"""
|
||||
|
||||
id: Identifier
|
||||
project_id: Identifier
|
||||
data_domain: DataDomain
|
||||
revision: int = Field(ge=1)
|
||||
# 标准字段名（assistant_materials.FIELDS.values()）。白名单校验在 service 层，
|
||||
# 见本模块顶部「依赖方向」说明。
|
||||
field: str = Field(min_length=1, max_length=ID_MAX)
|
||||
candidate_evidence_ids: list[Identifier] = Field(min_length=2, max_length=EVIDENCE_MAX)
|
||||
candidates: list[ConflictCandidate] = Field(min_length=2, max_length=EVIDENCE_MAX)
|
||||
status: Literal["unresolved", "resolved"]
|
||||
resolution_note: str | None = Field(default=None, min_length=1, max_length=NOTE_MAX)
|
||||
selected_evidence_ids: list[Identifier] = Field(default_factory=list, max_length=EVIDENCE_MAX)
|
||||
resolved_by: Identifier | None = None
|
||||
resolved_at: AwareDatetime | None = None
|
||||
created_at: AwareDatetime
|
||||
supersedes_id: Identifier | None = None
|
||||
|
||||
@model_validator(mode="after")
|
||||
def _check_candidates_and_resolution(self) -> FactConflict:
|
||||
ids = self.candidate_evidence_ids
|
||||
if len(set(ids)) != len(ids):
|
||||
raise ValueError("candidate_evidence_ids 不得重复")
|
||||
if [c.evidence_id for c in self.candidates] != ids:
|
||||
raise ValueError("candidates 必须与 candidate_evidence_ids 同序同集合")
|
||||
# 「至少两个不同值」：全部候选值相同说明没有分歧，不应建冲突对象。
|
||||
if len({c.value for c in self.candidates}) < 2:
|
||||
raise ValueError("候选值全部相同，不构成事实冲突")
|
||||
|
||||
if self.status == "resolved":
|
||||
missing = [name for name, value in (
|
||||
("resolution_note", self.resolution_note),
|
||||
("resolved_by", self.resolved_by),
|
||||
("resolved_at", self.resolved_at),
|
||||
) if value is None]
|
||||
if missing:
|
||||
raise ValueError(f"resolved 必须提供：{', '.join(missing)}")
|
||||
if not self.selected_evidence_ids:
|
||||
raise ValueError("resolved 必须提供 selected_evidence_ids")
|
||||
unknown = set(self.selected_evidence_ids) - set(ids)
|
||||
if unknown:
|
||||
raise ValueError(f"选择的值不属于该冲突的候选：{sorted(unknown)}")
|
||||
else:
|
||||
stray = [name for name, value in (
|
||||
("resolution_note", self.resolution_note),
|
||||
("resolved_by", self.resolved_by),
|
||||
("resolved_at", self.resolved_at),
|
||||
) if value is not None]
|
||||
if stray or self.selected_evidence_ids:
|
||||
raise ValueError("unresolved 不得带解决字段")
|
||||
return self
|
||||
@@ -0,0 +1,321 @@
|
||||
"""S1 契约层测试：材料集合导入与事实确认。
|
||||
|
||||
覆盖 T00/04 §9 的 AC-23 / AC-24 可机械断言部分，以及契约自身的边界。
|
||||
每条规则都有反例——只测通过路径不能证明约束存在。
|
||||
"""
|
||||
|
||||
import unittest
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from pydantic import ValidationError
|
||||
|
||||
from contracts.prescreen import (
|
||||
MAX_BATCH_BYTES,
|
||||
MAX_BATCH_FILES,
|
||||
MAX_ITEM_BYTES,
|
||||
ConflictCandidate,
|
||||
DataDomain,
|
||||
ErrorCode,
|
||||
ErrorResponse,
|
||||
FactConflict,
|
||||
ImportBatch,
|
||||
ImportItem,
|
||||
Ref,
|
||||
S1_ERROR_HTTP,
|
||||
SourceLocator,
|
||||
)
|
||||
|
||||
NOW = datetime(2026, 9, 29, 12, 0, tzinfo=timezone.utc)
|
||||
|
||||
|
||||
def locator(**over):
|
||||
base = dict(kind="pdf", document_id="doc-1", document_version=1, page=3)
|
||||
base.update(over)
|
||||
return base
|
||||
|
||||
|
||||
def item(**over):
|
||||
base = dict(
|
||||
id="item-1", relative_path="materials/a.pdf", sha256="a" * 64,
|
||||
size_bytes=1024, mime_type="application/pdf", status="queued",
|
||||
received_at=NOW,
|
||||
)
|
||||
base.update(over)
|
||||
return base
|
||||
|
||||
|
||||
def batch(**over):
|
||||
base = dict(
|
||||
id="batch-1", project_id="DEMO-A", data_domain="demo", revision=1,
|
||||
status="queued", created_at=NOW, created_by="demo-manager",
|
||||
parser_version="assistant_materials@1", items=[item()], total_bytes=1024,
|
||||
)
|
||||
base.update(over)
|
||||
return base
|
||||
|
||||
|
||||
def conflict(**over):
|
||||
ids = ["ev-1", "ev-2"]
|
||||
base = dict(
|
||||
id="fc-1", project_id="DEMO-A", data_domain="demo", revision=1,
|
||||
field="facility.amount", candidate_evidence_ids=list(ids),
|
||||
candidates=[
|
||||
ConflictCandidate(evidence_id="ev-1", value="1000", source="a.csv", locator="第2行"),
|
||||
ConflictCandidate(evidence_id="ev-2", value="1200", source="b.csv", locator="第5行"),
|
||||
],
|
||||
status="unresolved", created_at=NOW,
|
||||
)
|
||||
base.update(over)
|
||||
return base
|
||||
|
||||
|
||||
class SharedConstraintTests(unittest.TestCase):
|
||||
def test_unknown_field_is_rejected(self):
|
||||
# E-07：所有输入禁止未知字段
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(), unexpected="x")
|
||||
|
||||
def test_naive_datetime_is_rejected(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(received_at=datetime(2026, 9, 29, 12, 0)))
|
||||
|
||||
def test_ref_requires_both_fields(self):
|
||||
self.assertEqual(Ref(id="r-1", version="v1").version, "v1")
|
||||
with self.assertRaises(ValidationError):
|
||||
Ref(id="r-1")
|
||||
|
||||
def test_data_domain_enum_values(self):
|
||||
self.assertEqual({d.value for d in DataDomain}, {"demo", "production"})
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(data_domain="staging"))
|
||||
|
||||
|
||||
class SourceLocatorTests(unittest.TestCase):
|
||||
def test_each_kind_accepts_its_own_fields(self):
|
||||
self.assertEqual(SourceLocator(**locator()).page, 3)
|
||||
self.assertEqual(
|
||||
SourceLocator(**locator(kind="table", page=None, sheet="Sheet1",
|
||||
cell_range="C4")).sheet, "Sheet1")
|
||||
self.assertEqual(
|
||||
SourceLocator(**locator(kind="manual", page=None, note="正文第2段")).note,
|
||||
"正文第2段")
|
||||
|
||||
def test_missing_required_field_per_kind(self):
|
||||
for over, missing in [
|
||||
(dict(page=None), "page"),
|
||||
(dict(kind="table", page=None), "sheet"),
|
||||
(dict(kind="table", page=None, sheet="S"), "cell_range"),
|
||||
(dict(kind="manual", page=None), "note"),
|
||||
]:
|
||||
with self.subTest(missing=missing):
|
||||
with self.assertRaises(ValidationError) as ctx:
|
||||
SourceLocator(**locator(**over))
|
||||
self.assertIn(missing, str(ctx.exception))
|
||||
|
||||
def test_cross_kind_fields_are_rejected(self):
|
||||
# 三种寻址方式互斥，不允许混填
|
||||
with self.assertRaises(ValidationError):
|
||||
SourceLocator(**locator(kind="table", sheet="S", cell_range="C4")) # page 也在
|
||||
with self.assertRaises(ValidationError):
|
||||
SourceLocator(**locator(note="顺带写个说明"))
|
||||
|
||||
def test_page_must_be_positive(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
SourceLocator(**locator(page=0))
|
||||
|
||||
|
||||
class ImportItemTests(unittest.TestCase):
|
||||
def test_valid_item(self):
|
||||
self.assertEqual(ImportItem(**item()).status, "queued")
|
||||
|
||||
def test_absolute_paths_rejected(self):
|
||||
for bad in ["/etc/passwd", "C:/Windows/x.pdf", "C:\\Windows\\x.pdf", "//share/x.pdf"]:
|
||||
with self.subTest(path=bad):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(relative_path=bad))
|
||||
|
||||
def test_parent_reference_rejected(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(relative_path="../../secret.pdf"))
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(relative_path="a/../../b.pdf"))
|
||||
|
||||
def test_backslash_relative_path_is_kept_verbatim(self):
|
||||
# 校验用规范化副本，但保留原值：落库内容须与客户端提交一致
|
||||
parsed = ImportItem(**item(relative_path="materials\\sub\\a.pdf"))
|
||||
self.assertEqual(parsed.relative_path, "materials\\sub\\a.pdf")
|
||||
|
||||
def test_sha256_shape(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(sha256="A" * 64)) # 大写不合法
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(sha256="a" * 63))
|
||||
|
||||
def test_single_file_over_limit_rejected(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(size_bytes=MAX_ITEM_BYTES + 1))
|
||||
|
||||
def test_failed_requires_error_code_and_parsed_forbids_it(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(status="failed"))
|
||||
self.assertEqual(
|
||||
ImportItem(**item(status="failed", error_code=ErrorCode.MATERIAL_PARSE_FAILED)).status,
|
||||
"failed")
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(status="parsed", document_id="doc-1",
|
||||
error_code=ErrorCode.MATERIAL_PARSE_FAILED))
|
||||
|
||||
def test_parsed_requires_document_id(self):
|
||||
# AC-23：解析成功必须能定位到既有 document
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportItem(**item(status="parsed"))
|
||||
self.assertEqual(
|
||||
ImportItem(**item(status="parsed", document_id="doc-9")).document_id, "doc-9")
|
||||
|
||||
def test_observed_at_may_be_null_and_is_not_faked(self):
|
||||
# BR-02：缺发生时间保留 null，不用导入时间冒充
|
||||
parsed = ImportItem(**item())
|
||||
self.assertIsNone(parsed.observed_at)
|
||||
self.assertIsNotNone(parsed.received_at)
|
||||
|
||||
|
||||
class ImportBatchTests(unittest.TestCase):
|
||||
def test_valid_batch(self):
|
||||
self.assertEqual(ImportBatch(**batch()).total_bytes, 1024)
|
||||
|
||||
def test_total_bytes_must_match_sum(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(total_bytes=999))
|
||||
|
||||
def test_duplicate_item_ids_rejected(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(
|
||||
items=[item(), item()], total_bytes=2048))
|
||||
|
||||
def test_empty_items_rejected(self):
|
||||
# E-16：空集合不合法
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(items=[], total_bytes=0))
|
||||
|
||||
def test_over_file_count_rejected(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(items=[], total_bytes=0)) # min_length=1 已拦截
|
||||
items = [item(id=f"i-{n}", size_bytes=1) for n in range(MAX_BATCH_FILES + 1)]
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(items=items, total_bytes=len(items)))
|
||||
|
||||
def test_batch_total_limit_enforced(self):
|
||||
# D3 决策：单批 ≤ 20 MiB。每个文件合法但合计超限必须拒绝。
|
||||
each = MAX_BATCH_BYTES // 3 + 1
|
||||
items = [item(id=f"i-{n}", size_bytes=each) for n in range(3)]
|
||||
self.assertLessEqual(each, MAX_ITEM_BYTES)
|
||||
with self.assertRaises(ValidationError) as ctx:
|
||||
ImportBatch(**batch(items=items, total_bytes=each * 3))
|
||||
self.assertIn("拆分", str(ctx.exception))
|
||||
|
||||
def test_status_enum_bounded(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
ImportBatch(**batch(status="done"))
|
||||
|
||||
|
||||
class FactConflictTests(unittest.TestCase):
|
||||
def test_valid_unresolved(self):
|
||||
parsed = FactConflict(**conflict())
|
||||
self.assertEqual(parsed.status, "unresolved")
|
||||
self.assertEqual(parsed.selected_evidence_ids, [])
|
||||
|
||||
def test_fewer_than_two_candidates_rejected(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
FactConflict(**conflict(candidate_evidence_ids=["ev-1"]))
|
||||
|
||||
def test_identical_values_are_not_a_conflict(self):
|
||||
# AC-24 反例：两个来源给出同一个值不应建冲突对象
|
||||
with self.assertRaises(ValidationError) as ctx:
|
||||
FactConflict(**conflict(candidates=[
|
||||
ConflictCandidate(evidence_id="ev-1", value="1000", source="a", locator="L1"),
|
||||
ConflictCandidate(evidence_id="ev-2", value="1000", source="b", locator="L2"),
|
||||
]))
|
||||
self.assertIn("不构成", str(ctx.exception))
|
||||
|
||||
def test_null_value_counts_as_distinct(self):
|
||||
# 未知用 null，且与已有数值构成分歧
|
||||
parsed = FactConflict(**conflict(candidates=[
|
||||
ConflictCandidate(evidence_id="ev-1", value="1000", source="a", locator="L1"),
|
||||
ConflictCandidate(evidence_id="ev-2", value=None, source="b", locator="L2"),
|
||||
]))
|
||||
self.assertIsNone(parsed.candidates[1].value)
|
||||
|
||||
def test_candidates_must_align_with_id_list(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
FactConflict(**conflict(candidates=[
|
||||
ConflictCandidate(evidence_id="ev-2", value="1000", source="a", locator="L1"),
|
||||
ConflictCandidate(evidence_id="ev-1", value="1200", source="b", locator="L2"),
|
||||
]))
|
||||
with self.assertRaises(ValidationError):
|
||||
FactConflict(**conflict(candidate_evidence_ids=["ev-1", "ev-1"], candidates=[
|
||||
ConflictCandidate(evidence_id="ev-1", value="1000", source="a", locator="L1"),
|
||||
ConflictCandidate(evidence_id="ev-1", value="1200", source="b", locator="L2"),
|
||||
]))
|
||||
|
||||
def test_resolved_requires_note_selection_and_actor(self):
|
||||
good = conflict(status="resolved", resolution_note="以合同为准",
|
||||
selected_evidence_ids=["ev-2"], resolved_by="demo-manager",
|
||||
resolved_at=NOW)
|
||||
self.assertEqual(FactConflict(**good).selected_evidence_ids, ["ev-2"])
|
||||
for drop in ("resolution_note", "resolved_by", "resolved_at", "selected_evidence_ids"):
|
||||
with self.subTest(drop=drop):
|
||||
broken = dict(good)
|
||||
broken.pop(drop)
|
||||
with self.assertRaises(ValidationError):
|
||||
FactConflict(**broken)
|
||||
|
||||
def test_selection_must_come_from_candidates(self):
|
||||
with self.assertRaises(ValidationError) as ctx:
|
||||
FactConflict(**conflict(status="resolved", resolution_note="n",
|
||||
selected_evidence_ids=["ev-999"],
|
||||
resolved_by="demo-manager", resolved_at=NOW))
|
||||
self.assertIn("不属于", str(ctx.exception))
|
||||
|
||||
def test_unresolved_must_not_carry_resolution(self):
|
||||
with self.assertRaises(ValidationError):
|
||||
FactConflict(**conflict(resolution_note="提前写了结论"))
|
||||
|
||||
def test_supersedes_chain_is_representable(self):
|
||||
# 再次冲突新建对象并指向旧对象，不覆写历史
|
||||
parsed = FactConflict(**conflict(id="fc-2", supersedes_id="fc-1"))
|
||||
self.assertEqual(parsed.supersedes_id, "fc-1")
|
||||
|
||||
|
||||
class ErrorContractTests(unittest.TestCase):
|
||||
def test_every_code_has_an_http_status(self):
|
||||
self.assertEqual(set(S1_ERROR_HTTP), set(ErrorCode))
|
||||
|
||||
def test_status_semantics_match_existing_translate(self):
|
||||
# 既有 translate() 的语义：KeyError→404, Conflict→409, PermissionError→403, ValueError→422
|
||||
self.assertEqual(S1_ERROR_HTTP[ErrorCode.NOT_FOUND], 404)
|
||||
self.assertEqual(S1_ERROR_HTTP[ErrorCode.ACCESS_DENIED], 403)
|
||||
self.assertEqual(S1_ERROR_HTTP[ErrorCode.REVISION_CONFLICT], 409)
|
||||
self.assertEqual(S1_ERROR_HTTP[ErrorCode.IDEMPOTENCY_CONFLICT], 409)
|
||||
self.assertEqual(S1_ERROR_HTTP[ErrorCode.IMPORT_BATCH_INVALID], 422)
|
||||
|
||||
def test_e17_is_not_an_http_error(self):
|
||||
# 01 §5 末：运行级错误 HTTP 200，只表示结果可读
|
||||
self.assertEqual(S1_ERROR_HTTP[ErrorCode.FACT_CONFLICT_UNRESOLVED], 200)
|
||||
|
||||
def test_envelope_shape(self):
|
||||
body = ErrorResponse.model_validate({"error": {
|
||||
"code": "IMPORT_BATCH_INVALID", "message": "材料集合不符合导入要求",
|
||||
"retryable": False, "request_id": "req-1"}})
|
||||
self.assertEqual(body.error.code, ErrorCode.IMPORT_BATCH_INVALID)
|
||||
|
||||
def test_no_credentials_in_contract_module(self):
|
||||
# 契约层不得出现凭据字段（E-10 / BR-16 的静态底线）
|
||||
import contracts.prescreen as module
|
||||
with open(module.__file__, encoding="utf-8") as handle:
|
||||
source = handle.read()
|
||||
for banned in ("api_key", "password", "token", "secret"):
|
||||
self.assertNotIn(banned, source.lower())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user